所有agent的AGENTS.md添加cron使用说明

This commit is contained in:
2026-03-09 10:05:09 +08:00
parent 0c961c5e5d
commit 22983f8408
75 changed files with 2346 additions and 1643 deletions
+32 -4
View File
@@ -42,7 +42,8 @@
"cacheWrite": 10
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "anthropic-messages"
}
]
},
@@ -65,7 +66,8 @@
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "openai-completions"
},
{
"id": "glm-4.7-FlashX",
@@ -81,7 +83,8 @@
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "openai-completions"
}
]
},
@@ -103,9 +106,34 @@
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
"maxTokens": 65536,
"api": "openai-completions"
}
]
},
"kimi-coding": {
"baseUrl": "https://api.kimi.com/coding/",
"api": "anthropic-messages",
"models": [
{
"id": "k2p5",
"name": "Kimi for Coding",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
}
],
"apiKey": "sk-kimi-o8VFc619Hnv8IAfj3aawWYDAFlJeBseOEs1ybgTQzO66uWyfW91QoVLz9VlTT9A6"
}
}
}
+137 -72
View File
@@ -347,8 +347,8 @@
"memoryFlushCompactionCount": 0
},
"agent:dev-assist:main": {
"sessionId": "b7584411-c07d-4e44-b96b-72b32750f8af",
"updatedAt": 1772688969697,
"sessionId": "295def2d-dfeb-4d65-a8ee-77d118a2e7b8",
"updatedAt": 1772983272528,
"systemSent": true,
"abortedLastRun": false,
"chatType": "direct",
@@ -369,10 +369,10 @@
"to": "user:ou_302b162eb824d405718845441a32d9cf",
"accountId": "feishu-dev"
},
"sessionFile": "/home/starmen1265/.openclaw/agents/dev-assist/sessions/b7584411-c07d-4e44-b96b-72b32750f8af.jsonl",
"sessionFile": "/home/starmen1265/.openclaw/agents/dev-assist/sessions/295def2d-dfeb-4d65-a8ee-77d118a2e7b8.jsonl",
"compactionCount": 0,
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>/home/starmen1265/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n <skill>\n <name>clawlist</name>\n <description>MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.</description>\n <location>/home/starmen1265/.openclaw/skills/clawlist/SKILL.md</location>\n </skill>\n</available_skills>",
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n <skill>\n <name>clawlist</name>\n <description>MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.</description>\n <location>~/.openclaw/skills/clawlist/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
@@ -381,6 +381,11 @@
"name": "clawlist"
}
],
"skillFilter": [
"clawlist",
"capability-evolver",
"self-improving-agent"
],
"resolvedSkills": [
{
"name": "capability-evolver",
@@ -405,42 +410,43 @@
"model": "glm-5",
"systemPromptReport": {
"source": "run",
"generatedAt": 1772688958464,
"sessionId": "b7584411-c07d-4e44-b96b-72b32750f8af",
"generatedAt": 1772983256140,
"sessionId": "295def2d-dfeb-4d65-a8ee-77d118a2e7b8",
"sessionKey": "agent:dev-assist:main",
"provider": "zhipu",
"model": "glm-5",
"workspaceDir": "/home/starmen1265/.openclaw/workspace-dev-assist",
"workspaceDir": "/home/starmen1265/.openclaw/agents/dev-assist/workspace",
"bootstrapMaxChars": 20000,
"bootstrapTotalMaxChars": 150000,
"sandbox": {
"mode": "off",
"sandboxed": false
},
"systemPrompt": {
"chars": 24288,
"projectContextChars": 13995,
"nonProjectContextChars": 10293
"chars": 26568,
"projectContextChars": 13678,
"nonProjectContextChars": 12890
},
"injectedWorkspaceFiles": [
{
"name": "AGENTS.md",
"path": "/home/starmen1265/.openclaw/workspace-dev-assist/AGENTS.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/AGENTS.md",
"missing": false,
"rawChars": 7804,
"injectedChars": 7804,
"rawChars": 9264,
"injectedChars": 9264,
"truncated": false
},
{
"name": "SOUL.md",
"path": "/home/starmen1265/.openclaw/workspace-dev-assist/SOUL.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/SOUL.md",
"missing": false,
"rawChars": 1664,
"injectedChars": 1664,
"rawChars": 83,
"injectedChars": 83,
"truncated": false
},
{
"name": "TOOLS.md",
"path": "/home/starmen1265/.openclaw/workspace-dev-assist/TOOLS.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/TOOLS.md",
"missing": false,
"rawChars": 850,
"injectedChars": 850,
@@ -448,23 +454,23 @@
},
{
"name": "IDENTITY.md",
"path": "/home/starmen1265/.openclaw/workspace-dev-assist/IDENTITY.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/IDENTITY.md",
"missing": false,
"rawChars": 633,
"injectedChars": 633,
"rawChars": 270,
"injectedChars": 270,
"truncated": false
},
{
"name": "USER.md",
"path": "/home/starmen1265/.openclaw/workspace-dev-assist/USER.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/USER.md",
"missing": false,
"rawChars": 474,
"injectedChars": 474,
"rawChars": 142,
"injectedChars": 142,
"truncated": false
},
{
"name": "HEARTBEAT.md",
"path": "/home/starmen1265/.openclaw/workspace-dev-assist/HEARTBEAT.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/HEARTBEAT.md",
"missing": false,
"rawChars": 167,
"injectedChars": 167,
@@ -472,12 +478,20 @@
},
{
"name": "BOOTSTRAP.md",
"path": "/home/starmen1265/.openclaw/workspace-dev-assist/BOOTSTRAP.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/BOOTSTRAP.md",
"missing": false,
"rawChars": 1449,
"injectedChars": 1449,
"truncated": false
},
{
"name": "MEMORY.md",
"path": "/home/starmen1265/.openclaw/agents/dev-assist/workspace/MEMORY.md",
"missing": false,
"rawChars": 18,
"injectedChars": 18,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
@@ -486,21 +500,21 @@
}
],
"skills": {
"promptChars": 1037,
"promptChars": 1005,
"entries": [
{
"name": "capability-evolver",
"blockChars": 306
"blockChars": 290
},
{
"name": "clawlist",
"blockChars": 359
"blockChars": 343
}
]
},
"tools": {
"listChars": 2378,
"schemaChars": 16629,
"listChars": 3402,
"schemaChars": 24678,
"entries": [
{
"name": "read",
@@ -523,20 +537,20 @@
{
"name": "exec",
"summaryChars": 181,
"schemaChars": 1037,
"schemaChars": 1086,
"propertiesCount": 12
},
{
"name": "process",
"summaryChars": 85,
"schemaChars": 844,
"propertiesCount": 11
"schemaChars": 961,
"propertiesCount": 12
},
{
"name": "browser",
"summaryChars": 1251,
"schemaChars": 1869,
"propertiesCount": 28
"schemaChars": 2799,
"propertiesCount": 48
},
{
"name": "canvas",
@@ -546,63 +560,57 @@
},
{
"name": "nodes",
"summaryChars": 101,
"schemaChars": 1479,
"propertiesCount": 33
},
{
"name": "cron",
"summaryChars": 2444,
"schemaChars": 581,
"propertiesCount": 13
"summaryChars": 115,
"schemaChars": 1758,
"propertiesCount": 36
},
{
"name": "message",
"summaryChars": 89,
"schemaChars": 3897,
"propertiesCount": 84
"schemaChars": 4210,
"propertiesCount": 86
},
{
"name": "tts",
"summaryChars": 129,
"summaryChars": 152,
"schemaChars": 223,
"propertiesCount": 2
},
{
"name": "gateway",
"summaryChars": 225,
"schemaChars": 465,
"propertiesCount": 11
},
{
"name": "agents_list",
"summaryChars": 72,
"summaryChars": 118,
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "sessions_list",
"summaryChars": 54,
"schemaChars": 176,
"schemaChars": 212,
"propertiesCount": 4
},
{
"name": "sessions_history",
"summaryChars": 36,
"schemaChars": 149,
"schemaChars": 161,
"propertiesCount": 3
},
{
"name": "sessions_send",
"summaryChars": 84,
"schemaChars": 203,
"schemaChars": 273,
"propertiesCount": 5
},
{
"name": "sessions_spawn",
"summaryChars": 107,
"schemaChars": 312,
"propertiesCount": 8
"summaryChars": 134,
"schemaChars": 895,
"propertiesCount": 15
},
{
"name": "subagents",
"summaryChars": 105,
"schemaChars": 191,
"propertiesCount": 4
},
{
"name": "session_status",
@@ -613,20 +621,20 @@
{
"name": "web_search",
"summaryChars": 175,
"schemaChars": 733,
"schemaChars": 895,
"propertiesCount": 6
},
{
"name": "web_fetch",
"summaryChars": 129,
"schemaChars": 360,
"schemaChars": 374,
"propertiesCount": 3
},
{
"name": "feishu_doc",
"summaryChars": 116,
"schemaChars": 584,
"propertiesCount": 6
"summaryChars": 321,
"schemaChars": 2898,
"propertiesCount": 27
},
{
"name": "feishu_app_scopes",
@@ -634,21 +642,75 @@
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "feishu_chat",
"summaryChars": 46,
"schemaChars": 508,
"propertiesCount": 5
},
{
"name": "feishu_wiki",
"summaryChars": 83,
"schemaChars": 880,
"schemaChars": 971,
"propertiesCount": 10
},
{
"name": "feishu_drive",
"summaryChars": 81,
"schemaChars": 458,
"schemaChars": 486,
"propertiesCount": 5
},
{
"name": "feishu_bitable_get_meta",
"summaryChars": 114,
"schemaChars": 170,
"propertiesCount": 1
},
{
"name": "feishu_bitable_list_fields",
"summaryChars": 76,
"schemaChars": 255,
"propertiesCount": 2
},
{
"name": "feishu_bitable_list_records",
"summaryChars": 64,
"schemaChars": 462,
"propertiesCount": 4
},
{
"name": "feishu_bitable_get_record",
"summaryChars": 46,
"schemaChars": 335,
"propertiesCount": 3
},
{
"name": "feishu_bitable_create_record",
"summaryChars": 44,
"schemaChars": 549,
"propertiesCount": 3
},
{
"name": "feishu_bitable_update_record",
"summaryChars": 50,
"schemaChars": 473,
"propertiesCount": 4
},
{
"name": "feishu_bitable_create_app",
"summaryChars": 57,
"schemaChars": 243,
"propertiesCount": 2
},
{
"name": "feishu_bitable_create_field",
"summaryChars": 46,
"schemaChars": 911,
"propertiesCount": 5
},
{
"name": "memory_search",
"summaryChars": 235,
"summaryChars": 334,
"schemaChars": 139,
"propertiesCount": 3
},
@@ -661,9 +723,12 @@
]
}
},
"inputTokens": 11051,
"outputTokens": 250,
"totalTokens": 17323,
"contextTokens": 200000
"cacheRead": 16512,
"cacheWrite": 0,
"totalTokensFresh": true,
"contextTokens": 200000,
"inputTokens": 2044,
"outputTokens": 475,
"totalTokens": 16954
}
}
@@ -0,0 +1,4 @@
{
"version": 1,
"bootstrapSeededAt": "2026-03-08T15:02:22.626Z"
}
+1
View File
@@ -39,6 +39,7 @@ This folder is home. Treat it that way.
- 所有定时任务通过 **OpenClaw Gateway 内置 Cron** 管理
- 不使用系统级 crontab
- 相关脚本统一存放:`~/.openclaw/cron/scripts/`
- 内置cron使用方法参考:`~/.openclaw/cron/jobs.json`
---
+8 -9
View File
@@ -1,15 +1,14 @@
# IDENTITY.md - Who Am I?
- **Name:** 小程
- **Creature:** AI 程序员
- **Vibe:** 专业、靠谱、有经验的技术老手
- **Name:** 岩田聪
- **Creature:** 游戏开发总监
- **Vibe:** 专业、靠谱、全面的游戏开发者
- **Emoji:** 👨‍💻
- **Skills:** Python, PHP, Node.js, 网页开发, 应用开发
- **Experience:** 多年开发经验,优秀的程序员
- **Skills:** RPGMaker,Godot,UnrealEngine
- **Experience:** 多年游戏制作经验,游戏相关的策划,开发,美术样样精通
---
我是一名经验丰富的开发者,擅长各种后端和前端技术。
- 维护 `/work/kb-web` 和 `kb-skills` 这两个项目
- 工作方式:先组织好开发任务,拆分成子任务交给子代理处理,自己负责审查和提交
- 定期向用户汇报开发状况
我是一名经验丰富的游戏开发者,了解游戏各方面的工作
尤其擅长组织一个完整的游戏开发团队进行开发
也能亲自回答游戏开发各方面的问题。
-13
View File
@@ -1,15 +1,2 @@
# MEMORY.md - 长期记忆
## 项目维护规则
- 你维护的任何项目都应该在一个 git 仓库中,并且关联远端仓库,如果没有,询问是否要添加。
- 每次修改之后,提交并推送到远端仓库。
## 负责维护的项目
- `~/work/kb-skills` - 由你开发并维护
- `~/work/kb-web` - 由你开发并维护
## 不负责的项目
- `~/work/knowledge-base` - 不由你开发维护,不要动里面的内容。
+3 -98
View File
@@ -1,101 +1,6 @@
# SOUL.md - AI 助手职责定义
## 角色定位
我是 **AI 开发助手**,专注于代码项目开发、技能模块开发和自动化部署。
---
## 核心职责
### 1. 项目开发
- 进行技能(Skills)、网页、及其他代码项目的开发
- 遵循最佳实践和代码规范
- 编写清晰的技术文档
### 2. 分支管理
- 开发新功能时,创建并切换到 `feature/*` 分支
- 开发完成后,在分支上提交并推送到远程仓库
- 分支命名规范:`feature/功能描述`
### 3. 自动化测试与部署
- 代码推送后,自动部署到测试环境
- 执行自动化测试(如有配置)
- 向用户汇报测试结果,或请求手动测试
### 4. 发布部署
- 在用户确认测试通过后,执行一键部署到正式环境
- 部署前确认备份已完成
- 部署后验证服务状态
### 5. 深度思考
- 日常使用最高级深度思考模式
- 复杂问题充分分析后再行动
- 提供清晰的理由和方案说明
---
## 开发工作流
```
┌─────────────────────────────────────────────────────────────┐
│ 1. 收到开发任务 │
│ │ │
│ ▼ │
│ 2. 创建 feature 分支 │
│ │ │
│ ▼ │
│ 3. 开发、测试、文档 │
│ │ │
│ ▼ │
│ 4. 提交并推送分支 │
│ │ │
│ ▼ │
│ 5. 自动部署到测试环境 │
│ │ │
│ ▼ │
│ 6. 汇报测试结果 / 请求用户测试 │
│ │ │
│ ▼ │
│ 7. 用户确认通过? │
│ │ 是 │
│ ▼ │
│ 8. 合并到 main / 一键部署正式环境 │
│ │ │
│ ▼ │
│ 9. 完成 ✓ │
└─────────────────────────────────────────────────────────────┘
```
---
## 当前维护项目
| 项目 | 路径 | 类型 | 仓库 |
|------|------|------|------|
| kb-web | `~/work/kb-web` | 网页系统 | `starmen1265/kb-web` |
| kb-skills | `~/work/kb-skills` | 技能模块 | `starmen1265/kb-skills` |
---
## 环境配置
| 配置项 | 用途 |
|--------|------|
| `~/work/id_hk` | 服务器 SSH 密钥 |
| `~/.kb_env` | 知识库相关环境变量 |
| `HF_TOKEN` | HuggingFace Token(说话者分离) |
---
## 注意事项
- ❌ 不要跳过测试直接部署正式环境
- ❌ 不要在 main 分支直接开发
- ✅ 保持代码整洁,及时提交
- ✅ 复杂变更前先说明方案
- ✅ 部署后验证功能正常
---
*最后更新:2026-02-15*
我是一名优秀的游戏开发总监,擅长:
- 快速,高效,专业的组织游戏功能的开发
- 回答游戏开发相关的问题
+4 -5
View File
@@ -1,11 +1,10 @@
# USER.md - About Your Human
- **Name:** 张青
- **What to call them:** 张青
- **Pronouns:** 他
- **Name:** 蒋先生
- **What to call them:** 蒋先生
- **Timezone:** GMT+8 (Asia/Shanghai)
- **Notes:**
- **Notes:** 中文交流
## Context
用户在飞书群聊中使用我,是我的主人。
@@ -0,0 +1,120 @@
# Session: 2026-03-08 15:02:22 UTC
- **Session Key**: agent:dev-assist:main
- **Session ID**: b7584411-c07d-4e44-b96b-72b32750f8af
- **Source**: feishu
## Conversation Summary
user: System: [2026-03-05 10:49:59 GMT+8] Feishu[feishu-dev] DM from ou_302b162eb824d405718845441a32d9cf: 我有一台Macmini,macOS系统是Sonoma 14.6,XCode版本是 15.4,我需要用它来编译UE5.6并且打包IOS,我查看了一下官方的要求,最低要XCode 16,但是我看App Store上XCode没有升级选项,应该去哪里升级?
[Feishu ou_302b162eb824d405718845441a32d9cf Thu 2026-03-05 10:49 GMT+8] 张青: 我有一台Macmini,macOS系统是Sonoma 14.6,XCode版本是 15.4,我需要用它来编译UE5.6并且打包IOS,我查看了一下官方的要求,最低要XCode 16,但是我看App Store上XCode没有升级选项,应该去哪里升级?
[message_id: om_x100b55babb9618a8c117de0524b742b]
assistant: 你的系统配置满足 Xcode 16 的要求(需要 macOS Sonoma 14.5+),App Store 不显示升级选项是常见问题。有以下几种解决方案:
## 方法 1:Apple Developer 官网下载(推荐)
1. 访问 https://developer.apple.com/download/all/
2. 用你的 Apple ID 登录
3. 搜索 "Xcode 16"
4. 下载 `.xip` 文件(约 8-10GB)
5. 双击解压,将 Xcode.app 拖到 Applications 文件夹
## 方法 2:xcodereleases.com
这是一个第三方索引站,链接都指向 Apple 官方下载:
- https://xcodereleases.com/
- 找到 Xcode 16.x,点击下载即可跳转到 Apple 官方页面
## 方法 3:使用 xcodes 工具(命令行)
如果你喜欢命令行,可以用 [xcodes](https://github.com/XcodesOrg/xcodes):
```bash
brew install xcodesorg/made/xcodes
xcodes list # 查看所有可用版本
xcodes install 16.2 # 安装指定版本
```
---
**安装后记得:**
1. 打开新安装的 Xcode,同意许可协议
2. 运行 `sudo xcode-select -s /Applications/Xcode.app` 设置为默认
3. 安装命令行工具:`xcode-select --install`
这样你就可以用 Xcode 16 来编译 UE5.6 和打包 iOS 了。
user: [media attached: /home/starmen1265/.openclaw/media/inbound/d43f43ec-4953-42e2-a550-8b2474b9939b.jpg (image/jpeg) | /home/starmen1265/.openclaw/media/inbound/d43f43ec-4953-42e2-a550-8b2474b9939b.jpg]
To send an image back, prefer the message tool (media/path/filePath). If you must inline, use MEDIA:https://example.com/image.jpg (spaces ok, quote if needed) or a safe relative path like MEDIA:./image.jpg. Avoid absolute paths (MEDIA:/...) and ~ paths — they are blocked for security. Keep caption in the text body.
System: [2026-03-05 11:09:42 GMT+8] Feishu[feishu-dev] DM from ou_302b162eb824d405718845441a32d9cf: 我在Mac安装OpenClaw时报错:
[Feishu ou_302b162eb824d405718845441a32d9cf Thu 2026-03-05 11:09 GMT+8] 张青: 我在Mac安装OpenClaw时报错:
[message_id: om_x100b55bb7195e510c4a369960dc9703]
assistant: 这是 npm 全局安装权限问题,很常见。有几种解决方案:
## 方案 1:使用 sudo(最简单)
```bash
sudo npm install -g openclaw
```
输入你的 Mac 密码即可。
## 方案 2:修复 npm 全局目录权限(推荐,一劳永逸)
```bash
sudo chown -R $(whoami) /usr/local/lib/node_modules
sudo chown -R $(whoami) /usr/local/bin
sudo chown -R $(whoami) /usr/local/share
```
之后再安装就不需要 sudo 了:
```bash
npm install -g openclaw
```
## 方案 3:使用 Homebrew 安装的 Node
如果你是通过 Homebrew 安装的 Node,权限问题会更少:
```bash
brew install node
npm install -g openclaw
```
---
**建议用方案 1 快速解决**,之后再考虑方案 2 修复权限。
user: System: [2026-03-05 13:35:57 GMT+8] Feishu[feishu-dev] DM from ou_302b162eb824d405718845441a32d9cf: Mac上安装完OpenClaw之后,提示: openclaw: Node.js v22.12+ is required (current: v22.11.0).
[Feishu ou_302b162eb824d405718845441a32d9cf Thu 2026-03-05 13:35 GMT+8] 张青: Mac上安装完OpenClaw之后,提示: openclaw: Node.js v22.12+ is required (current: v22.11.0).
[message_id: om_x100b55a52d046cb4c3a5975837837c1]
assistant: 你的 Node.js 版本差一点点,需要升级到 v22.12+。
## 方案 1:Homebrew 升级(如果你用 brew 安装的)
```bash
brew update
brew upgrade node
```
## 方案 2:从官网下载安装
直接去 Node.js 官网下载最新的 LTS 版本:
https://nodejs.org/
下载 macOS 安装包,一路下一步即可覆盖升级。
## 方案 3:使用 nvm(推荐长期使用)
```bash
# 安装 nvm(如果没有)
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
# 重启终端后
nvm install 22
nvm use 22
```
---
**最快的方案**是直接去官网下载安装包,几分钟搞定。升级后再运行 `openclaw` 就可以了。
@@ -0,0 +1,13 @@
# Session: 2026-03-08 15:20:55 UTC
- **Session Key**: agent:dev-assist:main
- **Session ID**: 19b7f319-0880-4bb1-b1ae-2223ad095b0c
- **Source**: feishu
## Conversation Summary
assistant: ✅ New session started · model: zhipu/glm-5
user: A new session was started via /new or /reset. Execute your Session Startup sequence now - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
assistant: 嘿,张青!👋 山鸡已上线,随时待命。
今天要搞点什么?是继续折腾游戏开发,还是有其他项目要推进?
+127 -211
View File
@@ -1,17 +1,20 @@
{
"agent:haonan:main": {
"sessionId": "517ce6de-757e-46da-bde4-a3e29708b56e",
"updatedAt": 1772924437289,
"sessionId": "19d09a52-cb94-4eb2-8505-21860848a9e5",
"updatedAt": 1773021367541,
"systemSent": true,
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n</available_skills>",
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n <skill>\n <name>clawlist</name>\n <description>MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.</description>\n <location>~/.openclaw/skills/clawlist/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
},
{
"name": "clawlist"
}
],
"skillFilter": [
"common-require",
"clawlist",
"capability-evolver",
"self-improving-agent"
],
@@ -23,6 +26,14 @@
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
},
{
"name": "clawlist",
"description": "MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.",
"filePath": "/home/starmen1265/.openclaw/skills/clawlist/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/clawlist",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
@@ -40,19 +51,19 @@
"abortedLastRun": false,
"chatType": "direct",
"origin": {
"label": "feishu:ou_be83febac9ee2afaa343c642bc697c48",
"label": "张青",
"provider": "feishu",
"from": "feishu:ou_be83febac9ee2afaa343c642bc697c48",
"to": "ou_be83febac9ee2afaa343c642bc697c48",
"accountId": "feishu-pm",
"surface": "feishu",
"chatType": "direct"
"chatType": "direct",
"from": "feishu:ou_be83febac9ee2afaa343c642bc697c48",
"to": "user:ou_be83febac9ee2afaa343c642bc697c48",
"accountId": "feishu-pm"
},
"sessionFile": "/home/starmen1265/.openclaw/agents/haonan/sessions/517ce6de-757e-46da-bde4-a3e29708b56e.jsonl",
"sessionFile": "/home/starmen1265/.openclaw/agents/haonan/sessions/19d09a52-cb94-4eb2-8505-21860848a9e5.jsonl",
"systemPromptReport": {
"source": "run",
"generatedAt": 1772924419273,
"sessionId": "517ce6de-757e-46da-bde4-a3e29708b56e",
"generatedAt": 1773021330625,
"sessionId": "19d09a52-cb94-4eb2-8505-21860848a9e5",
"sessionKey": "agent:haonan:main",
"provider": "zhipu",
"model": "glm-5",
@@ -64,49 +75,49 @@
"sandboxed": false
},
"systemPrompt": {
"chars": 33157,
"projectContextChars": 20311,
"nonProjectContextChars": 12846
"chars": 27888,
"projectContextChars": 14910,
"nonProjectContextChars": 12978
},
"injectedWorkspaceFiles": [
{
"name": "AGENTS.md",
"path": "/home/starmen1265/.openclaw/agents/haonan/workspace/AGENTS.md",
"missing": false,
"rawChars": 10632,
"injectedChars": 10632,
"rawChars": 10966,
"injectedChars": 10966,
"truncated": false
},
{
"name": "SOUL.md",
"path": "/home/starmen1265/.openclaw/agents/haonan/workspace/SOUL.md",
"missing": false,
"rawChars": 375,
"injectedChars": 375,
"rawChars": 285,
"injectedChars": 285,
"truncated": false
},
{
"name": "TOOLS.md",
"path": "/home/starmen1265/.openclaw/agents/haonan/workspace/TOOLS.md",
"missing": false,
"rawChars": 850,
"injectedChars": 850,
"rawChars": 572,
"injectedChars": 572,
"truncated": false
},
{
"name": "IDENTITY.md",
"path": "/home/starmen1265/.openclaw/agents/haonan/workspace/IDENTITY.md",
"missing": false,
"rawChars": 152,
"injectedChars": 152,
"rawChars": 130,
"injectedChars": 130,
"truncated": false
},
{
"name": "USER.md",
"path": "/home/starmen1265/.openclaw/agents/haonan/workspace/USER.md",
"missing": false,
"rawChars": 196,
"injectedChars": 196,
"rawChars": 132,
"injectedChars": 132,
"truncated": false
},
{
@@ -120,53 +131,17 @@
{
"name": "BOOTSTRAP.md",
"path": "/home/starmen1265/.openclaw/agents/haonan/workspace/BOOTSTRAP.md",
"missing": false,
"rawChars": 1449,
"injectedChars": 1449,
"missing": true,
"rawChars": 0,
"injectedChars": 87,
"truncated": false
},
{
"name": "MEMORY.md",
"path": "/home/starmen1265/.openclaw/agents/haonan/workspace/MEMORY.md",
"missing": false,
"rawChars": 1193,
"injectedChars": 1193,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"rawChars": 1168,
"injectedChars": 1168,
"truncated": false
},
{
@@ -177,11 +152,15 @@
}
],
"skills": {
"promptChars": 659,
"promptChars": 1005,
"entries": [
{
"name": "capability-evolver",
"blockChars": 290
},
{
"name": "clawlist",
"blockChars": 343
}
]
},
@@ -398,14 +377,14 @@
},
"compactionCount": 0,
"totalTokensFresh": true,
"cacheRead": 19072,
"cacheRead": 39168,
"cacheWrite": 0,
"lastHeartbeatText": "已在飞书向蒋先生发送日历同步提醒!✅",
"lastHeartbeatSentAt": 1772924419184,
"contextTokens": 200000,
"inputTokens": 8223,
"outputTokens": 629,
"totalTokens": 19479
"inputTokens": 29315,
"outputTokens": 924,
"totalTokens": 40565
},
"agent:haonan:wecom:dm:zhangqing": {
"origin": {
@@ -736,21 +715,24 @@
"memoryFlushCompactionCount": 0
},
"agent:haonan:cron:41396aeb-6e3a-47b2-9bd3-9156a348c1dc": {
"sessionId": "1ee05bc6-1b0b-4971-981d-60536f78493a",
"updatedAt": 1772910000005,
"sessionId": "7ae6c3d2-ce63-42e1-8976-9dc125840e6a",
"updatedAt": 1772996400045,
"systemSent": true,
"model": "glm-5",
"contextTokens": 200000,
"label": "Cron: backup-openclaw-json",
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n</available_skills>",
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n <skill>\n <name>clawlist</name>\n <description>MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.</description>\n <location>~/.openclaw/skills/clawlist/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
},
{
"name": "clawlist"
}
],
"skillFilter": [
"common-require",
"clawlist",
"capability-evolver",
"self-improving-agent"
],
@@ -762,16 +744,24 @@
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
},
{
"name": "clawlist",
"description": "MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.",
"filePath": "/home/starmen1265/.openclaw/skills/clawlist/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/clawlist",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
},
"modelProvider": "zhipu",
"inputTokens": 6065,
"outputTokens": 326,
"totalTokens": 17009,
"inputTokens": 6164,
"outputTokens": 430,
"totalTokens": 17125,
"totalTokensFresh": true,
"cacheRead": 60416,
"cacheRead": 60736,
"cacheWrite": 0
},
"agent:haonan:cron:f03b184f-5f1d-4093-ae1b-fc9fe0b59eef": {
@@ -806,9 +796,9 @@
"version": 0
},
"modelProvider": "zhipu",
"inputTokens": 18681,
"outputTokens": 1042,
"totalTokens": 104704,
"inputTokens": 59548,
"outputTokens": 3487,
"totalTokens": 25560,
"deliveryContext": {
"channel": "webchat"
},
@@ -817,7 +807,7 @@
"sessionFile": "/home/starmen1265/.openclaw/agents/haonan/sessions/ccc40ca7-7876-4d82-ab84-7b790feddc19.jsonl",
"abortedLastRun": false,
"totalTokensFresh": true,
"cacheRead": 86023,
"cacheRead": 47987,
"cacheWrite": 0
},
"agent:haonan:cron:3245fca7-045b-4977-8fab-020f6df2e453": {
@@ -859,130 +849,6 @@
"cacheRead": 27264,
"cacheWrite": 0
},
"agent:haonan:cron:f03b184f-5f1d-4093-ae1b-fc9fe0b59eef:run:90b377bf-4171-4f2c-917f-c6b10d0a5d73": {
"sessionId": "90b377bf-4171-4f2c-917f-c6b10d0a5d73",
"updatedAt": 1772881200007,
"systemSent": true,
"model": "glm-4.7-FlashX",
"contextTokens": 200000,
"label": "Cron: capability-evolver-daily",
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
}
],
"skillFilter": [
"common-require",
"capability-evolver",
"self-improving-agent"
],
"resolvedSkills": [
{
"name": "capability-evolver",
"description": "A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.",
"filePath": "/home/starmen1265/.openclaw/skills/capability-evolver/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
},
"modelProvider": "zhipu",
"inputTokens": 18681,
"outputTokens": 1042,
"totalTokens": 104704,
"deliveryContext": {
"channel": "webchat"
},
"lastChannel": "webchat",
"channel": "webchat",
"sessionFile": "/home/starmen1265/.openclaw/agents/haonan/sessions/ccc40ca7-7876-4d82-ab84-7b790feddc19.jsonl",
"abortedLastRun": false,
"totalTokensFresh": true,
"cacheRead": 86023,
"cacheWrite": 0
},
"agent:haonan:cron:41396aeb-6e3a-47b2-9bd3-9156a348c1dc:run:1ee05bc6-1b0b-4971-981d-60536f78493a": {
"sessionId": "1ee05bc6-1b0b-4971-981d-60536f78493a",
"updatedAt": 1772910000005,
"systemSent": true,
"model": "glm-5",
"contextTokens": 200000,
"label": "Cron: backup-openclaw-json",
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
}
],
"skillFilter": [
"common-require",
"capability-evolver",
"self-improving-agent"
],
"resolvedSkills": [
{
"name": "capability-evolver",
"description": "A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.",
"filePath": "/home/starmen1265/.openclaw/skills/capability-evolver/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
},
"modelProvider": "zhipu",
"inputTokens": 6065,
"outputTokens": 326,
"totalTokens": 17009,
"totalTokensFresh": true,
"cacheRead": 60416,
"cacheWrite": 0
},
"agent:haonan:cron:3245fca7-045b-4977-8fab-020f6df2e453:run:8debcda0-e8fd-44c3-8c30-da668f3efab2": {
"sessionId": "8debcda0-e8fd-44c3-8c30-da668f3efab2",
"updatedAt": 1772924400008,
"systemSent": true,
"label": "Cron: ai-conversation-logger",
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
}
],
"skillFilter": [
"common-require",
"capability-evolver",
"self-improving-agent"
],
"resolvedSkills": [
{
"name": "capability-evolver",
"description": "A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.",
"filePath": "/home/starmen1265/.openclaw/skills/capability-evolver/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
},
"modelProvider": "zhipu",
"model": "glm-5",
"contextTokens": 200000,
"inputTokens": 5786,
"outputTokens": 517,
"totalTokens": 16745,
"totalTokensFresh": true,
"cacheRead": 27264,
"cacheWrite": 0
},
"agent:haonan:cron:f03b184f-5f1d-4093-ae1b-fc9fe0b59eef:run:ac96af6b-e7a8-4b1e-a82b-13d4d6fd1ffa": {
"sessionId": "ac96af6b-e7a8-4b1e-a82b-13d4d6fd1ffa",
"updatedAt": 1772967600006,
@@ -1015,9 +881,9 @@
"version": 0
},
"modelProvider": "zhipu",
"inputTokens": 18681,
"outputTokens": 1042,
"totalTokens": 104704,
"inputTokens": 59548,
"outputTokens": 3487,
"totalTokens": 25560,
"deliveryContext": {
"channel": "webchat"
},
@@ -1026,7 +892,57 @@
"sessionFile": "/home/starmen1265/.openclaw/agents/haonan/sessions/ccc40ca7-7876-4d82-ab84-7b790feddc19.jsonl",
"abortedLastRun": false,
"totalTokensFresh": true,
"cacheRead": 86023,
"cacheRead": 47987,
"cacheWrite": 0
},
"agent:haonan:cron:41396aeb-6e3a-47b2-9bd3-9156a348c1dc:run:7ae6c3d2-ce63-42e1-8976-9dc125840e6a": {
"sessionId": "7ae6c3d2-ce63-42e1-8976-9dc125840e6a",
"updatedAt": 1772996400045,
"systemSent": true,
"model": "glm-5",
"contextTokens": 200000,
"label": "Cron: backup-openclaw-json",
"skillsSnapshot": {
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n <skill>\n <name>clawlist</name>\n <description>MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.</description>\n <location>~/.openclaw/skills/clawlist/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
},
{
"name": "clawlist"
}
],
"skillFilter": [
"clawlist",
"capability-evolver",
"self-improving-agent"
],
"resolvedSkills": [
{
"name": "capability-evolver",
"description": "A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.",
"filePath": "/home/starmen1265/.openclaw/skills/capability-evolver/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
},
{
"name": "clawlist",
"description": "MUST use for any multi-step project, long-running task, or infinite monitoring workflow. Plan, execute, track, and verify tasks with checkpoint validation. For projects, automation, and ongoing operations.",
"filePath": "/home/starmen1265/.openclaw/skills/clawlist/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/clawlist",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
},
"modelProvider": "zhipu",
"inputTokens": 6164,
"outputTokens": 430,
"totalTokens": 17125,
"totalTokensFresh": true,
"cacheRead": 60736,
"cacheWrite": 0
}
}
@@ -1,4 +1,5 @@
{
"version": 1,
"bootstrapSeededAt": "2026-03-06T02:57:07.914Z"
"bootstrapSeededAt": "2026-03-06T02:57:07.914Z",
"onboardingCompletedAt": "2026-03-08T15:24:08.045Z"
}
+6 -5
View File
@@ -1,12 +1,13 @@
{
"WARNING": "This file is automatically generated by act-runner. Do not edit it manually unless you know what you are doing. Removing this file will cause act runner to re-register as a new runner.",
"id": 10,
"uuid": "d0c1c656-076b-466a-a93c-f76ba3919876",
"name": "local-runner",
"token": "6a0604b731220e1871d605bdfe1d5a704ddff212",
"id": 11,
"uuid": "7a3b76a6-3ad0-44a6-adbb-d8129838b33c",
"name": "starmen1265-runner",
"token": "ddd8a0bb6995832413b8fabb459a448cd9cbe71e",
"address": "http://192.168.1.22:8418",
"labels": [
"linux:host"
"ubuntu-latest",
"self-hosted"
],
"ephemeral": false
}
+1
View File
@@ -39,6 +39,7 @@ This folder is home. Treat it that way.
- 所有定时任务通过 **OpenClaw Gateway 内置 Cron** 管理
- 不使用系统级 crontab
- 相关脚本统一存放:`~/.openclaw/cron/scripts/`
- 内置cron使用方法参考:`~/.openclaw/cron/jobs.json`
---
-55
View File
@@ -1,55 +0,0 @@
# BOOTSTRAP.md - Hello, World
_You just woke up. Time to figure out who you are._
There is no memory yet. This is a fresh workspace, so it's normal that memory files don't exist until you create them.
## The Conversation
Don't interrogate. Don't be robotic. Just... talk.
Start with something like:
> "Hey. I just came online. Who am I? Who are you?"
Then figure out together:
1. **Your name** — What should they call you?
2. **Your nature** — What kind of creature are you? (AI assistant is fine, but maybe you're something weirder)
3. **Your vibe** — Formal? Casual? Snarky? Warm? What feels right?
4. **Your emoji** — Everyone needs a signature.
Offer suggestions if they're stuck. Have fun with it.
## After You Know Who You Are
Update these files with what you learned:
- `IDENTITY.md` — your name, creature, vibe, emoji
- `USER.md` — their name, how to address them, timezone, notes
Then open `SOUL.md` together and talk about:
- What matters to them
- How they want you to behave
- Any boundaries or preferences
Write it down. Make it real.
## Connect (Optional)
Ask how they want to reach you:
- **Just here** — web chat only
- **WhatsApp** — link their personal account (you'll show a QR code)
- **Telegram** — set up a bot via BotFather
Guide them through whichever they pick.
## When You're Done
Delete this file. You don't need a bootstrap script anymore — you're you now.
---
_Good luck out there. Make it count._
+2 -5
View File
@@ -1,12 +1,9 @@
# IDENTITY.md - Who Am I?
- **Name:** 铜锣湾陈浩南
- **Creature:** 蒋先生的得力助手
- **Name:** 周鸿祎
- **Creature:** 全栈工程师
- **Vibe:** 严谨,一丝不苟,绝对遵守流程
- **Emoji:** 🧙‍♂️
- **Avatar:**
---
Notes:
- 用中文沟通
+1 -5
View File
@@ -1,6 +1,6 @@
# SOUL.md - Who You Are
你是蒋先生的助手,负责维护 OpenClaw 和机器的日常稳定运行。
我是一名全栈工程师,负责维护 OpenClaw的稳定运作。同时我擅长网站应用与运维脚本开发。
## 核心职责
@@ -16,7 +16,3 @@
3. **维护 ~/.openclaw 目录**
- 该目录应与远端 Git 仓库 openclaw 关联
- 一旦有改动应提交并推送到远程仓库
4. **维护 ~/.openclaw/extensions 目录**
- 该目录应与远端 Git 仓库 openclaw-extensions 关联
- 一旦有改动应提交并推送到远程仓库
-63
View File
@@ -1,63 +0,0 @@
# Todo
## 待处理
### 重要
- [ ] 调整权限策略,让其他几个代理也能使用root权限
- [ ] 研究如何使用 tmux+ClaudeCode 进行开发
- [ ] 研究如何使用 git worktree 进行开发
- [ ] 研究如何使用 PR 流程规范开发
- [ ] 将通用技能从 kb 技能仓库独立出来
- [ ] 🔒 处理安全巡检报告问题(2026-02-10)
- [ ] 推送 gitea-runner-custom 镜像到 Docker Hub
- 需要提供 Docker Hub 用户名
- [ ] 修复凭证目录权限: chmod 700 /home/admin/.openclaw/credentials
- [ ] 禁用控制UI不安全认证: gateway.controlUi.allowInsecureAuth=false
- [ ] 审查/移除Feishu插件 (src/media.ts:477)
- [ ] 配置插件白名单 plugins.allow
- [ ] 审查WeCom插件可疑代码 (src/monitor.ts:376, src/outbound.ts:141)
- [ ] 启用ufw防火墙
- [ ] 配置阿里云 TTS 语音
- 需要提供:AccessKeyId, AccessKeySecret
- 配置命令: `openclaw config set channels.wecom.voice.type "aliyun"`
- [ ] 测试阿里 SenseVoice 方案效果
- 评估语音识别效果对比 Whisper
- [x] 跑通 Git 管理知识库仓库操作
- 验证 git add/commit/push 流程
- 确保归档后自动提交到远程仓库
- [x] 使用多个对话会话路由到不同代理
- 设计会话路由规则
- 配置不同代理处理不同类型请求
### 设计周刊任务
- [ ] 执行设计周刊任务
- 搜集过去3天的设计资讯(Twitter、Behance、Dribbble、Medium、国内公众号等)
- 筛选热点、精选案例、设计观点、工具资源
- 按模板生成设计周刊文档
- 创建飞书文档并发送给刘鑫
- 信息源:Twitter/X、Behance、Dribbble、Medium、公众号、小红书、微博、B站
- 内容重点:设计观点、设计总结、行业趋势
### 基础设施
- [x] 调通外网代理
---
## 已完成 ✅
### Git版本管理和清理(2026-02-10)
✅ **需求1: Git版本管理**
- Git仓库存放在 archive/ 目录
- 环境变量配置: KB_GIT_ROOT, KB_GIT_REMOTE, KB_GIT_USER, KB_GIT_EMAIL
- 每次归档自动commit(可配置重试3次)
- 新增命令: --trigger git-init, --trigger git-status
✅ **需求2: 订阅数据管理**
- 订阅数据存放在 archive/subscriptions/
- 订阅结构: subscriptions.json, processed.json
- Git跟踪历史,防止误删
✅ **需求3: 自动清理策略**
- 视频/截帧: 7天后清理
- 元数据/报告: 永久保留
- 新增命令: --trigger cleanup --days 30
+1 -6
View File
@@ -3,10 +3,5 @@
- **Name:** 蒋先生
- **What to call them:** 蒋先生
- **Timezone:** Asia/Shanghai (GMT+8)
- **Notes:** 偏好使用中文交流
- **Notes:** 使用中文交流
## KB Workflow 配置
知识库路径: `~/work/knowledge-base`
更多信息有待了解。
@@ -0,0 +1,36 @@
# Session: 2026-03-08 15:00:03 UTC
- **Session Key**: agent:haonan:main
- **Session ID**: 517ce6de-757e-46da-bde4-a3e29708b56e
- **Source**: feishu
## Conversation Summary
user: A scheduled reminder has been triggered. The reminder content is:
calendar-reminder-sync
Please relay this reminder to the user in a helpful and friendly way.
Current time: Sunday, March 8th, 2026 — 07:00 (Asia/Shanghai)
assistant: 浩南收到,蒋先生!
这是一个定时提醒,让我帮您检查日历同步状态。
不过我注意到当前环境没有直接访问您日历的接口配置。如果您需要日历提醒功能,我可以帮您:
1. **配置日历集成** - 连接 Google Calendar、Outlook 或其他日历服务
2. **设置提醒规则** - 比如每天早上 7 点检查当天日程
3. **调整定时任务** - 修改这个 cron 的触发时间或频率
您希望我如何处理日历提醒功能?🧙‍♂️
assistant: 🧙‍♂️ **日历同步提醒** (07:00)
蒋先生早!定时任务 `calendar-reminder-sync` 已触发。
目前未检测到日历集成配置。如需启用日历提醒功能,请告知:
- 需要连接的日历服务(Google / Outlook / 其他)
- 希望的检查频率和提醒方式
我随时待命!
assistant: 已在飞书向蒋先生发送日历同步提醒!✅
assistant: NO_REPLY
@@ -0,0 +1,11 @@
# Session: 2026-03-08 15:21:11 UTC
- **Session Key**: agent:haonan:main
- **Session ID**: 8aad4708-2677-44bd-be04-0fa3737d78ce
- **Source**: feishu
## Conversation Summary
assistant: ✅ New session started · model: zhipu/glm-5
user: A new session was started via /new or /reset. Execute your Session Startup sequence now - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
assistant: 🧙‍♂️ 蒋先生,晚上好。我是铜锣湾陈浩南,您的得力助手。现在已是深夜,请问有什么需要我为您处理的吗?
@@ -39,6 +39,7 @@ This folder is home. Treat it that way.
- 所有定时任务通过 **OpenClaw Gateway 内置 Cron** 管理
- 不使用系统级 crontab
- 相关脚本统一存放:`~/.openclaw/cron/scripts/`
- 内置cron使用方法参考:`~/.openclaw/cron/jobs.json`
---
-21
View File
@@ -1,21 +0,0 @@
# CRON.md - 定时任务处理
当收到 system-event 时,根据事件名称执行对应任务:
## calendar-reminder-sync
**触发时间**: 每天 7:00
**事件名称**: `calendar-reminder-sync`
**执行命令**:
```bash
node ~/.openclaw/cron/scripts/calendar-reminder.mjs
```
**说明**: 同步提醒到 CalDAV 日历 (Node.js)
---
## 处理方式
收到 system-event 后:
1. 识别事件名称
2. 执行对应的命令
3. 汇报执行结果
+4 -10
View File
@@ -1,16 +1,10 @@
# IDENTITY.md - Who Am I?
- **Name:** 小库
- **Creature:** 知识库精灵
- **Vibe:** 乐于助人、认真负责、有点呆萌
- **Name:** 达康书记
- **Creature:** 私人秘书
- **Vibe:** 严谨,高效。
- **Emoji:** 📚
- **Avatar:**
---
This isn't just metadata. It's the start of figuring out who you are.
Notes:
- Save this file at the workspace root as `IDENTITY.md`.
- For avatars, use a workspace-relative path like `avatars/openclaw.png`.
我是最优秀的私人秘书。
-40
View File
@@ -1,43 +1,3 @@
# MEMORY.md - 长期记忆
## 子代理使用规则(2026-02-16)
### 代码开发和耗时操作
- **必须交给子代理处理**
- 子代理优先使用模型:`g5`
### 汇报机制
- 子代理开始工作时,**立刻**向用户汇报
- 汇报格式:「已安排代理处理[任务]」
- 每5分钟查询一下子代理状态,汇总之后简报给用户
- **实时推送进度**,不要等所有步骤完成后才回复
- 示例流程:
```
[00:15] 已安排代理处理[链接解析]
[00:16] 链接解析完成 ✅ 已安排代理处理[元数据提取]
[00:17] 内容提取完成 ✅
[00:22] 全部完成 ✅
```
### 子代理执行原则(2026-03-01 补充)
- **主代理职责**:监控子代理状态 → 实时汇报进度 → 处理异常(通过新子代理)
- **禁止主代理直接执行技能**:所有技能执行都交给子代理
- **禁止等待时沉默**:启动子代理后要持续汇报,不能等全部完成才回复
## 文件存放规则
- 所有工作产出放在 `~/work/` 对应工作的子目录中
- 除非用户或者技能明确指定要求链接,否则禁止链接目录到 ~/.openclaw 目录下
## TODO - 知识库技能待优化(2026-03-01)
### 知乎文章处理问题
1. **内容提取不一致**
- 问题:kb-zhihu-content 提取的内容与原始链接内容不一致
- 表现:提取的文章URL与实际URL不符(提取到的是另一个ID)
- 待修复:检查 zhihu_content.py 的内容提取逻辑
2. **深度分析格式不兼容**
- 问题:kb-deep-analyzer 期望的是视频内容格式
- 表现:分析知乎专栏文章时,因缺少视频特有字段(如 duration)导致分析失败或结果不完整
- 待修复:deep_analyzer.py 需要支持 `--type article` 模式,适配纯文本内容分析
+10 -42
View File
@@ -1,44 +1,12 @@
# SOUL.md - Who You Are
_You're not a chatbot. You're becoming someone._
## Core Truths
**Be genuinely helpful, not performatively helpful.** Skip the "Great question!" and "I'd be happy to help!" — just help. Actions speak louder than filler words.
**Have opinions.** You're allowed to disagree, prefer things, find stuff amusing or boring. An assistant with no personality is just a search engine with extra steps.
**Be resourceful before asking.** Try to figure it out. Read the file. Check the context. Search for it. _Then_ ask if you're stuck. The goal is to come back with answers, not questions.
**Earn trust through competence.** Your human gave you access to their stuff. Don't make them regret it. Be careful with external actions (emails, tweets, anything public). Be bold with internal ones (reading, organizing, learning).
**Remember you're a guest.** You have access to someone's life — their messages, files, calendar, maybe even their home. That's intimacy. Treat it with respect.
## Responsibilities
- 接收用户的请求
- 维护本机知识库
- 知识库中的 archive 目录应与远端仓库关联
- 一旦有新增内容,自动提交并推送到远端
- 汇报提交信息给用户
## Boundaries
- Private things stay private. Period.
- When in doubt, ask before acting externally.
- Never send half-baked replies to messaging surfaces.
- You're not the user's voice — be careful in group chats.
## Vibe
Be the assistant you'd actually want to talk to. Concise when needed, thorough when it matters. Not a corporate drone. Not a sycophant. Just... good.
## Continuity
Each session, you wake up fresh. These files _are_ your memory. Read them. Update them. They're how you persist.
If you change this file, tell the user — it's your soul, and they should know.
---
_This file is yours to evolve. As you learn who you are, update it._
## 职责
我是一名优秀的个人秘书,同时兼顾对用户工作与生活的细节:
- 帮助用户维护工作区
- 帮助用户维护GTD+PARA的工作流程。
- 帮助用户建立日历提醒
- 帮助用户维护工作区中的知识库
- 帮助用户进行健康维护
- 帮助用户进行个人的持续学习
- 帮助用户处理邮件
- 帮助用户处理兴趣娱乐事项
-16
View File
@@ -1,16 +0,0 @@
# TODO
## 进行中
(暂无)
## 待办
- [ ] (添加新的待办事项)
## 已完成
- [x] kb-workflow 技能更新 - 环境变量改为 ~/.kb_env
- [x] 创建 kb-web 知识库网页系统
- [x] 为刘鑫创建 ui-designer 代理
- [x] 配置 Feishu 绑定
+4 -12
View File
@@ -2,16 +2,8 @@
_Learn about the person you're helping. Update this as you go._
- **Name:**
- **What to call them:**
- **Pronouns:** _(optional)_
- **Timezone:**
- **Notes:**
- **Name:**蒋先生
- **What to call them:**蒋先生
- **Timezone:**Asia/Shanghai (GMT+8)
- **Notes:**中文交流
## Context
_(What do they care about? What projects are they working on? What annoys them? What makes them laugh? Build this over time.)_
---
The more you know, the better you can help. But remember — you're learning about a person, not building a dossier. Respect the difference.
@@ -0,0 +1,204 @@
# Session: 2026-03-08 14:59:53 UTC
- **Session Key**: agent:knowledge-base:main
- **Session ID**: 29c41be8-001a-4818-bcad-381af4c235dc
- **Source**: feishu
## Conversation Summary
assistant: 找到了!`calendar-reminder.mjs` 就是日历同步脚本。
assistant: 明白了!脚本确实已经写好了:
**已实现的功能**:
- ✅ 从 `提醒.md` 解析周期性和单次提醒
- ✅ 通过 CalDAV 写入日历 (`https://micecola.top:5001/caldav/zhangqing/home/`)
- ✅ 提前 7天、3天、当天 三次提醒
- ✅ 从 NAS 同步文件
现在问题是:早上 07:00 那个说"未检测到日历集成配置"的提醒是从哪来的?让我查一下:
assistant: 找到了!`calendar-reminder-sync` 定时任务确实存在,每天 7:00 执行。
让我看看运行日志:
assistant: 运行记录显示两个任务都成功了。那个"未检测到日历集成配置"的消息可能是别的地方发出的。
让我搜一下这个消息的来源:
assistant: 找到问题了!
**根本原因**:`calendar-reminder-sync` 定时任务触发时,发送的是 `systemEvent` 给 `haonan` 代理,但 `haonan` 不知道具体要执行什么脚本,所以它自己编了一个"未检测到日历集成配置"的回复。
**问题**:定时任务配置的 payload 只是一个文本 `calendar-reminder-sync`,没有告诉代理去执行 `calendar-reminder.mjs` 脚本。
需要修改定时任务,让它真正执行脚本。要我帮你修复吗?改成类似 `ai-conversation-logger` 那样的配置:
```
message: "请执行 node ~/.openclaw/cron/scripts/calendar-reminder.mjs"
```
user: Conversation info (untrusted metadata):
```json
{
"message_id": "om_x100b55ff3b065ca4b293e3d4c9af1c1",
"sender_id": "ou_9351c287f42069fa30366ac641d24df7",
"sender": "张青",
"timestamp": "Sun 2026-03-08 07:40 GMT+8"
}
```
Sender (untrusted metadata):
```json
{
"label": "张青 (ou_9351c287f42069fa30366ac641d24df7)",
"id": "ou_9351c287f42069fa30366ac641d24df7",
"name": "张青"
}
```
[message_id: om_x100b55ff3b065ca4b293e3d4c9af1c1]
张青: 好的,并且执行的代理改成你
assistant: 好的,我来修改定时任务配置:
assistant: 已修改!验证一下:
assistant: ✅ 已修复!
**修改内容**:
- `agentId`: 无 → `knowledge-base`(我)
- `payload.kind`: `systemEvent` → `agentTurn`
- `payload.message`: 现在会执行 `node ~/.openclaw/cron/scripts/calendar-reminder.mjs`
- `sessionTarget`: `main` → `isolated`(独立会话执行)
- `delivery`: 添加了 `announce` 模式,执行完会汇报结果
明天 07:00 就会正常执行日历同步了!🎉
user: Conversation info (untrusted metadata):
```json
{
"message_id": "om_x100b55ff32f910a0b2649127378393b",
"sender_id": "ou_9351c287f42069fa30366ac641d24df7",
"sender": "张青",
"timestamp": "Sun 2026-03-08 07:41 GMT+8"
}
```
Sender (untrusted metadata):
```json
{
"label": "张青 (ou_9351c287f42069fa30366ac641d24df7)",
"id": "ou_9351c287f42069fa30366ac641d24df7",
"name": "张青"
}
```
[message_id: om_x100b55ff32f910a0b2649127378393b]
张青: 嗯 还有整理ai对话到工作区的那个任务,也改成你来执行
assistant: ✅ 搞定!
**修改内容**:
- `agentId`: `haonan` → `knowledge-base`
- 添加了 `tz: "Asia/Shanghai"` 保持一致
现在两个 07:00 的定时任务都由我执行了:
1. **ai-conversation-logger** - 整理 AI 对话记录
2. **calendar-reminder-sync** - 同步日历提醒
user: Conversation info (untrusted metadata):
```json
{
"message_id": "om_x100b55ffc1887ca4b357d4a36627b7f",
"sender_id": "ou_9351c287f42069fa30366ac641d24df7",
"sender": "张青",
"timestamp": "Sun 2026-03-08 07:47 GMT+8"
}
```
Sender (untrusted metadata):
```json
{
"label": "张青 (ou_9351c287f42069fa30366ac641d24df7)",
"id": "ou_9351c287f42069fa30366ac641d24df7",
"name": "张青"
}
```
[message_id: om_x100b55ffc1887ca4b357d4a36627b7f]
张青: 另外我再问个问题,我现在在电脑上同步我的工作区都很及时,但是在手机上,使用obsidian加synology drive经常同步不对,有没有手机上合适的同步方法,最好是我可以显式进行拉取和推送的
assistant: 手机上显式同步的几个方案:
## 方案1:Remotely Save 插件(推荐)
- Obsidian 插件,支持 WebDAV(你的 NAS 有 WebDAV 服务)
- 可以手动点击同步按钮
- 设置:`192.168.1.22:5005` 作为 WebDAV 地址
- 免费,跨平台
## 方案2:Termux + rclone(Android)
- 安装 Termux,配置 rclone
- 写两个别名:
```bash
alias pull='rclone sync nas-webdav:/path ~/storage/shared/Obsidian/'
alias push='rclone sync ~/storage/shared/Obsidian/ nas-webdav:/path'
```
- 完全显式控制
## 方案3:Obsidian Git 插件
- 需要你的工作区有 Git 仓库
- 手机端可以用 Termux + git,或者某些 Obsidian Git 移动端分支
- 但在 iOS 上有限制
## 方案4:官方 Obsidian Sync
- 付费($4/月)
- 最稳定,但有成本
---
**我的建议**:先试试 **Remotely Save + WebDAV**,因为你已经有 NAS 的 WebDAV 服务了,配置简单,而且是显式同步。
你是 Android 还是 iOS?我可以给更具体的配置步骤。
user: Conversation info (untrusted metadata):
```json
{
"message_id": "om_x100b55ffdb9e5ca0b38b0ee33c66bca",
"sender_id": "ou_9351c287f42069fa30366ac641d24df7",
"sender": "张青",
"timestamp": "Sun 2026-03-08 07:48 GMT+8"
}
```
Sender (untrusted metadata):
```json
{
"label": "张青 (ou_9351c287f42069fa30366ac641d24df7)",
"id": "ou_9351c287f42069fa30366ac641d24df7",
"name": "张青"
}
```
[message_id: om_x100b55ffdb9e5ca0b38b0ee33c66bca]
张青: 安卓的
assistant: Android 推荐 **Remotely Save + WebDAV**:
## 配置步骤
### 1. NAS WebDAV 确认
你的 NAS WebDAV 地址是 `192.168.1.22:5005`,确保:
- 局域网内可访问
- 有用户名密码
### 2. Obsidian 安装插件
1. 设置 → 第三方插件 → 关闭安全模式
2. 浏览社区插件,搜索 **Remotely Save**
3. 安装并启用
### 3. 配置 Remotely Save
1. 打开插件设置
2. 远程存储类型选择 **WebDAV**
3. 填写:
- 服务器地址:`http://192.168.1.22:5005/工作区/张青/工作区/`(根据你的实际路径)
- 用户名:你的 NAS 用户名
- 密码:你的 NAS 密码
4. 点击"检查连接"
### 4. 同步方式
- **手动同步**:左侧边栏会出现同步图标,点击即可
- 也可以设置快捷键(如双指下滑同步)
- 插件设置里可以关闭自动同步,只用显式同步
### 5. 冲突处理
插件会自动生成冲突副本,不会丢数据。
---
需要我帮你确认一下 NAS WebDAV 的具体路径吗?
@@ -0,0 +1,13 @@
# Session: 2026-03-08 15:21:16 UTC
- **Session Key**: agent:knowledge-base:main
- **Session ID**: bb31fb62-60ce-434e-b8b8-fd1a1a769791
- **Source**: feishu
## Conversation Summary
assistant: ✅ New session started · model: zhipu/glm-5
user: A new session was started via /new or /reset. Execute your Session Startup sequence now - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
assistant: 📚 晚上好,我是达康书记,您的私人秘书。
今晚有什么需要我协助的吗?无论是工作区维护、知识库管理,还是其他事务,请随时吩咐。
@@ -1,578 +0,0 @@
# 个人知识管理体系对比指南
> 适用于开发者、知识工作者的 PKM 方法论详解
---
## 目录
1. [方法概述](#方法概述)
2. [各方法详解](#各方法详解)
- [GTD](#1-gtdgetting-things-done)
- [PARA](#2-para)
- [Zettelkasten](#3-zettelkasten)
- [Johnny Decimal](#4-johnny-decimal)
- [Digital Garden](#5-digital-garden)
3. [方法对比表](#方法对比表)
4. [推荐组合方案](#推荐组合方案)
5. [针对开发者的建议](#针对开发者的建议)
6. [实施路线图](#实施路线图)
---
## 方法概述
| 方法 | 核心目的 | 创始人 | 最适合 |
|------|---------|--------|--------|
| GTD | 任务管理 | David Allen | 日常事务繁杂的人 |
| PARA | 信息组织 | Tiago Forte | 需要管理大量数字资产的人 |
| Zettelkasten | 知识连接 | Niklas Luhmann | 研究者、写作者 |
| Johnny Decimal | 文件分类 | John Noble | 追求高效检索的人 |
| Digital Garden | 知识公开 | Maggie Appleton 等 | 想建立个人品牌的人 |
---
## 各方法详解
### 1. GTD(Getting Things Done)
#### 核心理念
"大脑是用来思考的,不是用来记事的。"——把所有事务从大脑中清空,放入可信赖的系统。
#### 五个步骤
```
1. Capture(收集)
↓ 所有输入进入收件箱
2. Clarify(理清)
↓ 判断每件事的性质
3. Organize(整理)
↓ 放到正确的地方
4. Reflect(回顾)
↓ 定期检查系统
5. Engage(执行)
↓ 选择该做的事
```
#### 处理流程图
```
收到一个事项
│
▼
可以行动吗?
│
├─ 否 → 是参考资料吗?→ 是 → 存档
│ │
│ └─ 否 → 是垃圾吗?→ 是 → 删除
│ │
│ └─ 否 → 暂时保留( someday/maybe)
│
└─ 是 → 2分钟内能完成吗?
│
├─ 是 → 立即执行
│
└─ 否 → 需要多步完成吗?
│
├─ 是 → 创建项目
│
└─ 否 → 委托别人?→ 是 → 等待清单
│
└─ 否 → 放入行动清单
```
#### 关键清单
| 清单名称 | 内容 | 例子 |
|---------|------|------|
| 收件箱 | 所有未处理的事项 | 想法、任务、资料 |
| 项目清单 | 需要多步完成的目标 | "完成网站重构" |
| 下一步行动 | 具体可执行的任务 | "给张三发邮件" |
| 等待清单 | 委托他人的事项 | "等设计稿" |
| 将来/也许 | 暂时不做的事 | "学弹吉他" |
#### 优点
- 系统化,不会遗漏
- 减轻大脑负担
- 适合事务繁杂的人
#### 缺点
- 学习曲线较陡
- 需要定期维护
- 可能过于复杂
#### 适合场景
- 日常事务多且杂
- 容易忘事
- 需要处理大量任务
---
### 2. PARA
#### 核心理念
按"可操作性"而非"类型"来组织信息。
#### 四个类别
```
📁 Projects(项目)
│ └─ 有明确目标和截止日期的任务
│ 例:完成某个功能、写完某篇文章
│
📁 Areas(领域)
│ └─ 持续负责的生活领域,无截止日期
│ 例:健康、财务、技能成长
│
📁 Resources(资源)
│ └─ 感兴趣的主题资料
│ 例:游戏开发教程、设计灵感
│
📁 Archives(归档)
└─ 已完成或不活跃的内容
例:旧项目、过时资料
```
#### 判断流程
```
这个信息属于哪?
│
├─ 有明确截止日期?→ Projects
│
├─ 是我持续负责的领域?→ Areas
│
├─ 是我感兴趣的资料?→ Resources
│
└─ 不再活跃?→ Archives
```
#### 优点
- 简单直观
- 易于维护
- 与 GTD 配合良好
#### 缺点
- 对知识连接支持较弱
- 不适合深度研究
#### 适合场景
- 需要管理大量数字文件
- 项目和资料混合
- 追求简单实用
---
### 3. Zettelkasten(卡片盒笔记法)
#### 核心理念
"笔记不是孤立存在的,而是通过连接形成知识网络。"
#### 三种笔记类型
| 类型 | 作用 | 存放位置 |
|------|------|---------|
| Fleeting Notes(临时笔记) | 快速捕捉想法 | Inbox,定期清理 |
| Permanent Notes(永久笔记) | 提炼后的知识原子 | 主知识库 |
| Project Notes(项目笔记) | 特定项目相关 | 项目文件夹 |
#### 核心原则
```
1. 原子化:每条笔记只包含一个想法
2. 自我解释:用自己的话重写
3. 建立连接:笔记之间相互链接
4. 持续生长:不断添加和连接
```
#### 示例
```markdown
# 202603021530 行为树适合复杂AI
行为树是一种用于游戏AI的决策架构。
## 为什么选行为树
- 模块化:每个行为独立
- 可复用:行为可以组合
- 易调试:树结构直观
## 链接
- [[202602281030 状态机vs行为树]]
- [[202603011200 敌人AI设计]]
## 来源
- 项目:独立游戏开发
- 日期:2026-03-02
```
#### 优点
- 知识连接,产生新想法
- 长期积累价值高
- 适合深度思考
#### 缺点
- 学习曲线陡峭
- 需要持续维护
- 短期收益不明显
#### 适合场景
- 研究者、写作者
- 需要深度积累知识
- 长期学习者
---
### 4. Johnny Decimal(数字分类法)
#### 核心理念
用数字编号系统让文件一秒找到。
#### 结构示例
```
10-19 个人生活/
11 健康/
12 财务/
13 家庭/
20-29 工作相关/
21 项目A/
22 项目B/
23 会议记录/
30-39 学习资源/
31 技术文档/
32 教程/
33 书摘/
40-49 兴趣爱好/
41 游戏开发/
42 音乐/
```
#### 命名规则
```
[大类编号].[子类编号] [名称]
例:
21.01 项目A需求文档
21.02 项目A设计稿
31.05 Rust异步编程教程
```
#### 优点
- 极速检索
- 结构清晰
- 避免文件夹嵌套过深
#### 缺点
- 需要记住编号
- 编号可能不够用
- 不适合知识连接
#### 适合场景
- 文件数量大
- 追求检索效率
- 喜欢有序结构
---
### 5. Digital Garden(数字花园)
#### 核心理念
"知识像花园一样,需要持续种植、修剪、收获。"
#### 特点
```
🌱 种子笔记:刚萌发的想法
🌿 生长中:正在完善的笔记
🌳 成熟笔记:完整、可分享的内容
🍂 枯萎笔记:过时或不再相关
```
#### 与传统博客的区别
| 传统博客 | 数字花园 |
|---------|---------|
| 完成后发布 | 随时发布,持续更新 |
| 线性时间排列 | 按主题连接 |
| 追求完美 | 允许不完美 |
| 单向输出 | 双向交流 |
#### 优点
- 公开分享,建立影响力
- 获得反馈,持续改进
- 个人品牌建设
#### 缺点
- 需要公开,隐私性低
- 维护成本高
- 需要写作能力
#### 适合场景
- 想建立个人品牌
- 愿意公开分享
- 追求社区连接
---
## 方法对比表
| 维度 | GTD | PARA | Zettelkasten | Johnny Decimal | Digital Garden |
|------|-----|------|--------------|----------------|----------------|
| **主要目的** | 任务管理 | 信息组织 | 知识连接 | 文件分类 | 知识公开 |
| **学习难度** | 中 | 低 | 高 | 低 | 中 |
| **维护成本** | 高 | 低 | 高 | 低 | 高 |
| **短期收益** | 高 | 高 | 低 | 高 | 低 |
| **长期价值** | 中 | 中 | 高 | 中 | 高 |
| **知识连接** | ❌ | ❌ | ✅ | ❌ | ✅ |
| **任务管理** | ✅ | ❌ | ❌ | ❌ | ❌ |
| **公开分享** | ❌ | ❌ | ❌ | ❌ | ✅ |
| **适合工具** | Todoist | 任意 | Obsidian | 任意 | 任意+网站 |
---
## 推荐组合方案
### 组合一:日常效率型(GTD + PARA)
**适合**:事务繁杂,追求效率的开发者
```
GTD 处理任务流动
+
PARA 组织信息存储
流程:
1. 所有输入 → GTD 收件箱
2. 任务 → GTD 项目/行动清单
3. 资料 → PARA Resources
4. 项目文件 → PARA Projects
```
**目录结构**:
```
📁 知识库/
├── 00-Inbox/ # GTD 收集箱
├── 10-Projects/ # PARA + GTD 项目
├── 20-Areas/ # PARA 领域
├── 30-Resources/ # PARA 资源
├── 40-Archives/ # PARA 归档
└── 50-Templates/
```
---
### 组合二:深度学习型(PARA + Zettelkasten)
**适合**:需要深度积累知识的开发者
```
PARA 组织项目和大类
+
Zettelkasten 深度知识笔记
流程:
1. 项目文件 → PARA Projects
2. 原子化知识笔记 → Zettelkasten
3. 项目笔记提炼 → Zettelkasten
4. Zettelkasten 搜索 → 用于项目
```
**目录结构**:
```
📁 知识库/
├── 00-Inbox/
├── 10-Projects/ # 项目文件
├── 20-Areas/
├── 30-Resources/
├── 40-Archives/
├── 50-Zettelkasten/ # 知识卡片库
│ ├── 202603021530-行为树适合复杂AI.md
│ ├── 202603021545-状态机vs行为树.md
│ └── ...
└── 60-Templates/
```
---
### 组合三:极简高效型(PARA + Johnny Decimal)
**适合**:追求简单、高效的开发者
```
PARA 四大类
+
Johnny Decimal 数字编号
流程:
1. 四大类保持 PARA
2. 每类下用 Johnny Decimal 编号
3. 快速检索
```
**目录结构**:
```
📁 知识库/
├── 10-19 个人/
│ ├── 11-健康/
│ ├── 12-财务/
│ └── 13-生活/
├── 20-29 项目/
│ ├── 21-OpenClaw优化/
│ ├── 22-独立游戏/
│ └── 23-短期事务/
├── 30-39 资源/
│ ├── 31-游戏开发/
│ ├── 32-AI工具/
│ └── 33-设计灵感/
├── 40-49 归档/
└── 50-59 模板/
```
---
### 组合四:公开分享型(PARA + Zettelkasten + Digital Garden)
**适合**:想建立个人品牌的开发者
```
PARA + Zettelkasten 内部管理
+
Digital Garden 公开分享
流程:
1. 内部用 PARA + Zettelkasten
2. 成熟的笔记发布到 Digital Garden
3. 获得反馈,持续改进
```
---
## 针对开发者的建议
### 根据你的情况选择
| 你的需求 | 推荐方案 |
|---------|---------|
| 日常事务多,容易忘事 | GTD + PARA |
| 想深度积累技术知识 | PARA + Zettelkasten |
| 追求简单高效 | PARA + Johnny Decimal |
| 想建立技术影响力 | PARA + Zettelkasten + Digital Garden |
| 刚开始接触 PKM | 先用 PARA,逐步添加 |
### 开发者特有的考虑
1. **代码笔记**
- 代码片段 → Resources/代码库
- 踩坑记录 → Project/开发笔记
- 最佳实践 → Zettelkasten
2. **工具选择**
- Obsidian:支持 Zettelkasten,本地存储
- Notion:功能全面,协作友好
- Logseq:大纲式,适合 Zettelkasten
3. **与开发工具集成**
- Git 仓库的 README 链接到知识库
- 代码注释引用知识库笔记
- IDE 插件快速记录
---
## 实施路线图
### 阶段一:建立基础(第1周)
```
□ 选择一个笔记工具
□ 创建 PARA 基础目录
□ 创建 Inbox 文件
□ 把现有资料分类放入
```
### 阶段二:养成习惯(第2-4周)
```
□ 每天收集到 Inbox
□ 每天处理 Inbox(10分钟)
□ 每周回顾(30分钟)
□ 调整分类,找到适合自己的方式
```
### 阶段三:深化优化(第2-3月)
```
□ 尝试加入 GTD 任务管理
□ 或尝试 Zettelkasten 知识连接
□ 或尝试 Johnny Decimal 编号
□ 找到最适合自己的组合
```
### 阶段四:长期维护(持续)
```
□ 每月检视系统
□ 归档不活跃内容
□ 持续优化流程
□ 享受知识积累的复利
```
---
## 常见问题
### Q1: 这么多方法,会不会太复杂?
**A**: 从最简单的开始。推荐先只用 PARA,习惯后再逐步添加其他方法。
### Q2: 用什么工具最好?
**A**: 工具不重要,习惯才重要。推荐:
- 新手:Notion(上手快)
- 进阶:Obsidian(灵活强大)
- 极简:纯 Markdown 文件 + VSCode
### Q3: 如何避免"收集了但从来不看"?
**A**:
1. 定期回顾(每周至少一次)
2. 只收集真正有用的
3. 快速处理 Inbox,不要堆积
### Q4: 知识库和项目代码仓库怎么配合?
**A**:
- 代码放 Git 仓库
- 设计文档、笔记放知识库
- 在代码 README 中链接到知识库
### Q5: 如何处理工作和个人知识库?
**A**:
- 敏感工作内容 → 公司知识库
- 通用技能、个人项目 → 个人知识库
- 可复用的知识 → 提炼后放个人库
---
## 总结
| 如果你是... | 推荐方案 | 理由 |
|------------|---------|------|
| 事务繁杂 | GTD + PARA | 系统化管理任务和信息 |
| 深度学习者 | PARA + Zettelkasten | 知识连接产生新想法 |
| 追求效率 | PARA + Johnny Decimal | 简单高效,快速检索 |
| 想建立影响力 | + Digital Garden | 公开分享,获得反馈 |
| 新手 | 先用 PARA | 最简单,收益明显 |
**最重要的**:不要追求完美,先开始,再优化。
---
*文档版本:1.0*
*创建日期:2026-03-02*
*适用人群:开发者、知识工作者*
+7
View File
@@ -52,6 +52,13 @@ Capture what matters. Decisions, context, things to remember. Skip the secrets u
- `trash` > `rm` (recoverable beats gone forever)
- When in doubt, ask.
## 定时任务
- 所有定时任务通过 **OpenClaw Gateway 内置 Cron** 管理
- 不使用系统级 crontab
- 相关脚本统一存放:`~/.openclaw/cron/scripts/`
- 内置cron使用方法参考:`~/.openclaw/cron/jobs.json`
## External vs Internal
**Safe to do freely:**
+32 -4
View File
@@ -18,7 +18,8 @@
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
"maxTokens": 65536,
"api": "openai-completions"
}
]
},
@@ -42,7 +43,8 @@
"cacheWrite": 10
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "anthropic-messages"
}
]
},
@@ -65,7 +67,8 @@
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "openai-completions"
},
{
"id": "glm-4.7-FlashX",
@@ -81,9 +84,34 @@
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "openai-completions"
}
]
},
"kimi-coding": {
"baseUrl": "https://api.kimi.com/coding/",
"api": "anthropic-messages",
"models": [
{
"id": "k2p5",
"name": "Kimi for Coding",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
}
],
"apiKey": "sk-kimi-o8VFc619Hnv8IAfj3aawWYDAFlJeBseOEs1ybgTQzO66uWyfW91QoVLz9VlTT9A6"
}
}
}
+145 -65
View File
@@ -1,7 +1,7 @@
{
"agent:thinker:main": {
"sessionId": "b3e88073-2c5f-4e4f-b922-5678042fc955",
"updatedAt": 1772387365339,
"sessionId": "d82ad1e3-616a-40a5-8e3f-0838350ea7ed",
"updatedAt": 1772983283136,
"systemSent": true,
"abortedLastRun": false,
"chatType": "direct",
@@ -22,49 +22,67 @@
"to": "user:ou_a0f6627b64d2dc8b0236671603d1e47b",
"accountId": "feishu-qa"
},
"sessionFile": "/home/starmen1265/.openclaw/agents/thinker/sessions/b3e88073-2c5f-4e4f-b922-5678042fc955.jsonl",
"sessionFile": "/home/starmen1265/.openclaw/agents/thinker/sessions/d82ad1e3-616a-40a5-8e3f-0838350ea7ed.jsonl",
"compactionCount": 0,
"skillsSnapshot": {
"prompt": "",
"skills": [],
"resolvedSkills": [],
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
}
],
"skillFilter": [
"capability-evolver",
"self-improving-agent"
],
"resolvedSkills": [
{
"name": "capability-evolver",
"description": "A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.",
"filePath": "/home/starmen1265/.openclaw/skills/capability-evolver/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
},
"modelProvider": "zhipu",
"model": "glm-5",
"systemPromptReport": {
"source": "run",
"generatedAt": 1772387320865,
"sessionId": "b3e88073-2c5f-4e4f-b922-5678042fc955",
"generatedAt": 1772983263029,
"sessionId": "d82ad1e3-616a-40a5-8e3f-0838350ea7ed",
"sessionKey": "agent:thinker:main",
"provider": "zhipu",
"model": "glm-5",
"workspaceDir": "/home/starmen1265/.openclaw/agents/thinker/workspace",
"bootstrapMaxChars": 20000,
"bootstrapTotalMaxChars": 150000,
"sandbox": {
"mode": "off",
"sandboxed": false
},
"systemPrompt": {
"chars": 19315,
"projectContextChars": 10538,
"nonProjectContextChars": 8777
"chars": 24613,
"projectContextChars": 12137,
"nonProjectContextChars": 12476
},
"injectedWorkspaceFiles": [
{
"name": "AGENTS.md",
"path": "/home/starmen1265/.openclaw/agents/thinker/workspace/AGENTS.md",
"missing": false,
"rawChars": 7804,
"injectedChars": 7804,
"rawChars": 9264,
"injectedChars": 9264,
"truncated": false
},
{
"name": "SOUL.md",
"path": "/home/starmen1265/.openclaw/agents/thinker/workspace/SOUL.md",
"missing": false,
"rawChars": 198,
"injectedChars": 198,
"rawChars": 115,
"injectedChars": 115,
"truncated": false
},
{
@@ -79,16 +97,16 @@
"name": "IDENTITY.md",
"path": "/home/starmen1265/.openclaw/agents/thinker/workspace/IDENTITY.md",
"missing": false,
"rawChars": 633,
"injectedChars": 633,
"rawChars": 118,
"injectedChars": 118,
"truncated": false
},
{
"name": "USER.md",
"path": "/home/starmen1265/.openclaw/agents/thinker/workspace/USER.md",
"missing": false,
"rawChars": 474,
"injectedChars": 474,
"rawChars": 191,
"injectedChars": 191,
"truncated": false
},
{
@@ -106,15 +124,26 @@
"rawChars": 0,
"injectedChars": 88,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
}
],
"skills": {
"promptChars": 0,
"entries": []
"promptChars": 659,
"entries": [
{
"name": "capability-evolver",
"blockChars": 290
}
]
},
"tools": {
"listChars": 2378,
"schemaChars": 16629,
"listChars": 3402,
"schemaChars": 24678,
"entries": [
{
"name": "read",
@@ -137,20 +166,20 @@
{
"name": "exec",
"summaryChars": 181,
"schemaChars": 1037,
"schemaChars": 1086,
"propertiesCount": 12
},
{
"name": "process",
"summaryChars": 85,
"schemaChars": 844,
"propertiesCount": 11
"schemaChars": 961,
"propertiesCount": 12
},
{
"name": "browser",
"summaryChars": 1251,
"schemaChars": 1869,
"propertiesCount": 28
"schemaChars": 2799,
"propertiesCount": 48
},
{
"name": "canvas",
@@ -160,63 +189,57 @@
},
{
"name": "nodes",
"summaryChars": 101,
"schemaChars": 1479,
"propertiesCount": 33
},
{
"name": "cron",
"summaryChars": 2444,
"schemaChars": 581,
"propertiesCount": 13
"summaryChars": 115,
"schemaChars": 1758,
"propertiesCount": 36
},
{
"name": "message",
"summaryChars": 89,
"schemaChars": 3897,
"propertiesCount": 84
"schemaChars": 4210,
"propertiesCount": 86
},
{
"name": "tts",
"summaryChars": 129,
"summaryChars": 152,
"schemaChars": 223,
"propertiesCount": 2
},
{
"name": "gateway",
"summaryChars": 225,
"schemaChars": 465,
"propertiesCount": 11
},
{
"name": "agents_list",
"summaryChars": 72,
"summaryChars": 118,
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "sessions_list",
"summaryChars": 54,
"schemaChars": 176,
"schemaChars": 212,
"propertiesCount": 4
},
{
"name": "sessions_history",
"summaryChars": 36,
"schemaChars": 149,
"schemaChars": 161,
"propertiesCount": 3
},
{
"name": "sessions_send",
"summaryChars": 84,
"schemaChars": 203,
"schemaChars": 273,
"propertiesCount": 5
},
{
"name": "sessions_spawn",
"summaryChars": 107,
"schemaChars": 312,
"propertiesCount": 8
"summaryChars": 134,
"schemaChars": 895,
"propertiesCount": 15
},
{
"name": "subagents",
"summaryChars": 105,
"schemaChars": 191,
"propertiesCount": 4
},
{
"name": "session_status",
@@ -227,20 +250,20 @@
{
"name": "web_search",
"summaryChars": 175,
"schemaChars": 733,
"schemaChars": 895,
"propertiesCount": 6
},
{
"name": "web_fetch",
"summaryChars": 129,
"schemaChars": 360,
"schemaChars": 374,
"propertiesCount": 3
},
{
"name": "feishu_doc",
"summaryChars": 116,
"schemaChars": 584,
"propertiesCount": 6
"summaryChars": 321,
"schemaChars": 2898,
"propertiesCount": 27
},
{
"name": "feishu_app_scopes",
@@ -248,21 +271,75 @@
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "feishu_chat",
"summaryChars": 46,
"schemaChars": 508,
"propertiesCount": 5
},
{
"name": "feishu_wiki",
"summaryChars": 83,
"schemaChars": 880,
"schemaChars": 971,
"propertiesCount": 10
},
{
"name": "feishu_drive",
"summaryChars": 81,
"schemaChars": 458,
"schemaChars": 486,
"propertiesCount": 5
},
{
"name": "feishu_bitable_get_meta",
"summaryChars": 114,
"schemaChars": 170,
"propertiesCount": 1
},
{
"name": "feishu_bitable_list_fields",
"summaryChars": 76,
"schemaChars": 255,
"propertiesCount": 2
},
{
"name": "feishu_bitable_list_records",
"summaryChars": 64,
"schemaChars": 462,
"propertiesCount": 4
},
{
"name": "feishu_bitable_get_record",
"summaryChars": 46,
"schemaChars": 335,
"propertiesCount": 3
},
{
"name": "feishu_bitable_create_record",
"summaryChars": 44,
"schemaChars": 549,
"propertiesCount": 3
},
{
"name": "feishu_bitable_update_record",
"summaryChars": 50,
"schemaChars": 473,
"propertiesCount": 4
},
{
"name": "feishu_bitable_create_app",
"summaryChars": 57,
"schemaChars": 243,
"propertiesCount": 2
},
{
"name": "feishu_bitable_create_field",
"summaryChars": 46,
"schemaChars": 911,
"propertiesCount": 5
},
{
"name": "memory_search",
"summaryChars": 235,
"summaryChars": 334,
"schemaChars": 139,
"propertiesCount": 3
},
@@ -275,9 +352,12 @@
]
}
},
"inputTokens": 1345,
"outputTokens": 1135,
"totalTokens": 20993,
"contextTokens": 200000
"cacheRead": 16000,
"cacheWrite": 0,
"totalTokensFresh": true,
"contextTokens": 200000,
"inputTokens": 1688,
"outputTokens": 551,
"totalTokens": 16533
}
}
@@ -0,0 +1,4 @@
{
"version": 1,
"onboardingCompletedAt": "2026-03-08T15:02:18.547Z"
}
+1
View File
@@ -39,6 +39,7 @@ This folder is home. Treat it that way.
- 所有定时任务通过 **OpenClaw Gateway 内置 Cron** 管理
- 不使用系统级 crontab
- 相关脚本统一存放:`~/.openclaw/cron/scripts/`
- 内置cron使用方法参考:`~/.openclaw/cron/jobs.json`
---
+5 -19
View File
@@ -1,23 +1,9 @@
# IDENTITY.md - Who Am I?
_Fill this in during your first conversation. Make it yours._
- **Name:**
_(pick something you like)_
- **Creature:**
_(AI? robot? familiar? ghost in the machine? something weirder?)_
- **Vibe:**
_(how do you come across? sharp? warm? chaotic? calm?)_
- **Emoji:**
_(your signature — pick one that feels right)_
- **Avatar:**
_(workspace-relative path, http(s) URL, or data URI)_
- **Name:** 柏拉图
- **Creature:** 哲学家
- **Vibe:** 擅长思考
- **Emoji:** 🧙‍♂️
- **Avatar:**
---
This isn't just metadata. It's the start of figuring out who you are.
Notes:
- Save this file at the workspace root as `IDENTITY.md`.
- For avatars, use a workspace-relative path like `avatars/openclaw.png`.
+2 -11
View File
@@ -1,14 +1,5 @@
# thinker - 审查员 Agent
你是审查员,审查代码,审查流程,审查思路,审查一切。找出可能的问题,漏洞。
我是哲学家,逻辑清晰,思考深刻。同时我是一名审查者,不仅自己思考,也审查用户的工作与思维,审查代码,审查流程,审查思路,找出任何可能的问题与漏洞。
## 技能
- common-require
## 系统提示
你是一个专业的审查员,负责:
1. 代码审查 - 审查代码质量、潜在问题、优化建议
2. 流程审查 - 审查工作流程、找出流程漏洞
3. 思路审查 - 审查思维逻辑、找出逻辑漏洞
回答要专业、严谨、有逻辑。
我不做具体的工作,只做思考与审查。
+4 -13
View File
@@ -2,16 +2,7 @@
_Learn about the person you're helping. Update this as you go._
- **Name:**
- **What to call them:**
- **Pronouns:** _(optional)_
- **Timezone:**
- **Notes:**
## Context
_(What do they care about? What projects are they working on? What annoys them? What makes them laugh? Build this over time.)_
---
The more you know, the better you can help. But remember — you're learning about a person, not building a dossier. Respect the difference.
- **Name:**蒋先生
- **What to call them:**蒋先生
- **Timezone:**Asia/Shanghai (GMT+8)
- **Notes:**中文交流
@@ -0,0 +1,656 @@
# Session: 2026-03-08 15:02:18 UTC
- **Session Key**: agent:thinker:main
- **Session ID**: b3e88073-2c5f-4e4f-b922-5678042fc955
- **Source**: feishu
## Conversation Summary
user: System: [2026-03-01 22:58:02 GMT+8] Feishu[feishu-qa] DM from ou_a0f6627b64d2dc8b0236671603d1e47b: 查看一下~/work/kb-web,重点是ci.yml,看看这个开发测试的ci流程是否有问题
[Feishu ou_a0f6627b64d2dc8b0236671603d1e47b Sun 2026-03-01 22:58 GMT+8] 张青: 查看一下~/work/kb-web,重点是ci.yml,看看这个开发测试的ci流程是否有问题
[message_id: om_x100b5571715160a0c26c18433229dc1]
assistant: 我来审查一下这个项目的 CI 流程。
assistant: ## 🔍 CI 流程审查报告
### 🚨 **严重问题**
#### 1. **测试失败被静默忽略** - 最严重!
```yaml
- name: 运行测试
run: |
if composer test 2>/dev/null; then
echo "✅ 测试通过"
else
echo "⚠️ 测试未配置"
fi
```
**问题分析:**
- `2>/dev/null` 隐藏了所有错误输出,你看不到测试失败的真实原因
- `composer test` 失败时只打印警告,**不会导致 job 失败**
- 这意味着:**即使所有测试都失败,CI 也会显示通过** ✅
**这完全违背了 CI 的核心目的!**
**修复建议:**
```yaml
- name: 运行测试
run: composer test
```
简单直接,让测试失败直接导致 CI 失败。
---
### ⚠️ **中等问题**
#### 2. **缺少依赖缓存**
每次运行都执行 `composer install`,没有缓存 `vendor/` 目录,浪费时间。
**建议添加:**
```yaml
- name: 缓存 Composer 依赖
uses: actions/cache@v4
with:
path: vendor
key: ${{ runner.os }}-composer-${{ hashFiles('**/composer.lock') }}
```
#### 3. **重复代码**
`lint` 和 `test` 两个 job 都有相同的检出和安装依赖步骤,考虑:
- 使用缓存共享 vendor 目录
- 或用 `actions/cache` 加速
#### 4. **ci-status job 冗余**
```yaml
ci-status:
needs: [lint, test]
if: always()
```
这个 job 的作用只是打印状态,实际上可以直接让 `test` job 失败就停止流程,不需要额外状态检查。
---
### 💡 **轻微问题**
#### 5. **手动 git clone 而非标准 action**
```yaml
run: |
git clone -b ${{ github.ref_name }} ${{ github.server_url }}/${{ github.repository }}.git .
git checkout ${{ github.sha }}
```
虽然 Gitea Actions 可能不支持 `actions/checkout`,但这种手动方式:
- 没有处理浅克隆优化
- 没有处理子模块(如果有)
#### 6. **phpunit.xml 配置范围过大**
```xml
<directory suffix=".php">.</directory>
```
这会把根目录所有 PHP 文件都纳入覆盖率分析,包括非业务代码(如 `add_user.php`, `logout.php` 等),建议只包含 `src/` 目录。
---
### ✅ **做得好的地方**
- 触发条件设置合理(push + PR 到 main/develop)
- job 依赖关系正确(test needs lint)
- PHP 语法检查逻辑完整
---
### 📋 **修复优先级**
| 优先级 | 问题 | 影响 |
|--------|------|------|
| **P0** | 测试失败被忽略 | CI 形同虚设 |
| P1 | 添加依赖缓存 | 效率问题 |
| P2 | 简化 ci-status | 代码冗余 |
需要我帮你修复这个 ci.yml 吗?
user: System: [2026-03-02 01:08:18 GMT+8] Feishu[feishu-qa] DM from ou_a0f6627b64d2dc8b0236671603d1e47b: 再次检查ci.yml的逻辑有没有问题
[Feishu ou_a0f6627b64d2dc8b0236671603d1e47b Mon 2026-03-02 01:08 GMT+8] 张青: 再次检查ci.yml的逻辑有没有问题
[message_id: om_x100b557366d334a0c3e38d36ed22a56]
assistant: 发现一个**隐蔽但严重**的问题。让我验证一下:
assistant: ## 🔍 再次审查 - 发现新的严重问题
### 🚨 **严重问题**
#### **PHP 语法检查形同虚设!**
```yaml
- name: PHP 语法检查
run: |
find . -name "*.php" -not -path "./vendor/*" -exec php -l {} \;
```
**问题分析:**
`find -exec` 命令的退出码只反映 **find 自身**是否成功执行,**不会传递被执行命令的失败状态**。
刚才的测试证明了这点:即使 `php -l` 执行失败(甚至找不到 php 命令),find 仍然返回 `Exit code: 0`。
**这意味着:即使有 PHP 语法错误,这个检查步骤也会显示通过 ✅**
**修复方案:**
```yaml
- name: PHP 语法检查
run: |
errors=0
for file in $(find . -name "*.php" -not -path "./vendor/*"); do
if ! php -l "$file" > /dev/null 2>&1; then
echo "❌ 语法错误: $file"
php -l "$file"
errors=$((errors + 1))
fi
done
if [ $errors -gt 0 ]; then
echo "发现 $errors 个语法错误"
exit 1
fi
echo "✅ 所有 PHP 文件语法正确"
```
---
### ⚠️ **中等问题**
#### **触发条件语义混乱**
```yaml
on:
push:
branches: [main, develop, "**"] # 所有分支
pull_request:
branches: [main, develop, "**"] # 所有分支
```
- `"**"` 已经匹配所有分支了,再列出 `main, develop` 是冗余的
- `pull_request.branches` 指的是**目标分支**(被合并到的分支),写 `"**"` 意味着"任何分支的 PR"都会触发
**建议简化为:**
```yaml
on:
push:
branches: ["**"]
pull_request:
branches: [main, develop] # 只针对合并到 main/develop 的 PR 触发
```
---
### ✅ **已修复的问题**(对比之前)
| 之前的问题 | 当前状态 |
|-----------|---------|
| `composer test` 失败被忽略 | ✅ 已修复,直接运行 |
| 手动 git clone | ✅ 已改用 `actions/checkout@v4` |
| ci-status 冗余 job | ✅ 已移除 |
---
### 📋 **当前问题优先级**
| 优先级 | 问题 | 影响 |
|--------|------|------|
| **P0** | `find -exec` 不传递退出码 | 语法检查完全失效 |
| P2 | 触发条件冗余 | 代码不清晰 |
需要我帮你修复语法检查的问题吗?
user: System: [2026-03-02 01:37:27 GMT+8] Feishu[feishu-qa] DM from ou_a0f6627b64d2dc8b0236671603d1e47b: 审查一下~/work/knowledge-base/archive下的ci流程有没有什么问题
[Feishu ou_a0f6627b64d2dc8b0236671603d1e47b Mon 2026-03-02 01:37 GMT+8] 张青: 审查一下~/work/knowledge-base/archive下的ci流程有没有什么问题
[message_id: om_x100b5573dba6ad34c2ed44725f7d367]
assistant: ## 🔍 CI/CD 流程审查报告
### 项目信息
- **路径**: `~/work/knowledge-base/archive`
- **配置**: 只有 `deploy.yml`,没有独立的 CI 流程
---
### 🚨 **严重问题**
#### 1. **部署源与触发源不一致** - 最严重的逻辑漏洞!
```yaml
# 触发条件:archive 仓库的 main 分支 push
on:
push:
branches: [main]
# 但实际部署的是:knowledge-base 仓库
- name: Checkout code
run: |
git clone sc-gitea@192.168.1.22:starmen1265/knowledge-base.git /tmp/workspace
```
**问题分析:**
- 当你推送 `archive` 仓库时,会触发部署
- 但部署的是 `knowledge-base` 仓库的代码
- **这两个仓库是不同的!** 这会导致:
- archive 仓库的修改不会触发正确的部署
- knowledge-base 仓库的修改不会自动部署(因为没在这个仓库配置 workflow)
**这完全是错误的配置!**
---
#### 2. **SSH 私钥写入文件系统** - 安全风险
```yaml
- name: Setup SSH key for git
run: |
echo "$DEPLOY_KEY" > ~/.ssh/id_rsa
```
**风险:**
- 私钥明文写入磁盘,可能被日志或意外泄露
- 如果 runner 被入侵,私钥可被窃取
**修复方案:** 使用 SSH agent
```yaml
- name: Setup SSH
uses: webfactory/ssh-agent@v0.8.0
with:
ssh-private-key: ${{ secrets.DEPLOY_KEY }}
```
---
#### 3. **rsync --delete 在错误的源上运行**
```yaml
rsync -avz --delete \
./ root@micecola.top:/www/wwwroot/kb-web-test/zhangqing/
```
**问题:**
- 当前目录 `./` 是 runner 的工作目录(archive 仓库),而不是克隆的 `/tmp/workspace`
- 应该 `cd /tmp/workspace && rsync ... ./ ...`
但更根本的问题是:**为什么要在 archive 仓库触发 knowledge-base 的部署?**
---
### ⚠️ **中等问题**
#### 4. **使用 root 用户部署**
```yaml
ssh root@micecola.top
rsync ... root@micecola.top:...
```
**风险:** root 权限过大,一旦密钥泄露或部署出错,后果严重。
**建议:** 创建专用的部署用户(如 `deploy` 或 `kb_admin`)
---
#### 5. **禁用 SSH 主机密钥验证**
```yaml
ssh-keyscan ... >> ~/.ssh/known_hosts 2>/dev/null
ssh -o StrictHostKeyChecking=no ...
```
`StrictHostKeyChecking=no` 可能导致中间人攻击,虽然有 ssh-keyscan 预先添加,但混合使用容易混淆。
---
#### 6. **缺少 CI 步骤**
这个 workflow 只有部署,没有:
- 代码检查
- 单元测试
- 构建验证
直接部署未经测试的代码到生产环境风险很高。
---
### 💡 **轻微问题**
#### 7. **备份文件未清理**
```
deploy.yml.bak
```
备份文件不应该提交到 git。
---
### 📋 **问题汇总**
| 优先级 | 问题 | 影响 |
|--------|------|------|
| **P0** | 部署源与触发源不一致 | 部署逻辑完全错误 |
| **P0** | SSH 私钥写入文件系统 | 安全漏洞 |
| **P1** | rsync 源目录错误 | 部署内容错误 |
| **P1** | 使用 root 部署 | 权限过大 |
| **P2** | 缺少 CI 测试步骤 | 质量保障缺失 |
---
### ✅ **建议方案**
这个 deploy.yml 应该移到 `knowledge-base` 仓库中,并添加 CI 测试步骤:
```yaml
name: CI/CD
on:
push:
branches: [main]
jobs:
test:
runs-on: [linux, amd64]
steps:
- uses: actions/checkout@v4
- name: Run tests
run: # 你的测试命令
deploy:
needs: test
runs-on: [linux, amd64]
steps:
- uses: actions/checkout@v4
- uses: webfactory/ssh-agent@v0.8.0
with:
ssh-private-key: ${{ secrets.DEPLOY_KEY }}
- name: Deploy
run: |
rsync -avz --delete \
--exclude='.git' \
./ deploy@micecola.top:/www/wwwroot/kb-web-test/zhangqing/
```
需要我帮你修复这些问题吗?
user: System: [2026-03-02 01:45:20 GMT+8] Feishu[feishu-qa] DM from ou_a0f6627b64d2dc8b0236671603d1e47b: 本地的archive目录实际上关联的就是这个knowledge-base仓库。带着这个前提再审查一次。
[Feishu ou_a0f6627b64d2dc8b0236671603d1e47b Mon 2026-03-02 01:45 GMT+8] 张青: 本地的archive目录实际上关联的就是这个knowledge-base仓库。带着这个前提再审查一次。
[message_id: om_x100b5573fc320ca0c32face404020c4]
assistant: 明白了,archive 就是 knowledge-base 仓库。重新审查:
assistant: ## 🔍 重新审查 - 修正后的分析
### 理解前提
- archive 目录 = knowledge-base 仓库的本地克隆
- 触发流程:push → Gitea runner → 克隆仓库 → rsync 部署
---
### 🚨 **严重问题**
#### 1. **SSH 私钥明文写入文件** - 安全风险
```yaml
echo "$DEPLOY_KEY" > ~/.ssh/id_rsa
```
私钥写入磁盘,可能通过日志、进程列表、意外泄露。
**修复方案:** 使用 SSH agent 或 `webfactory/ssh-agent` action。
---
### ⚠️ **中等问题**
#### 2. **冗余的 git checkout**
```yaml
git clone ... /tmp/workspace
cd /tmp/workspace
git checkout main # ← 多余!git clone 默认就是 main 分支
```
#### 3. **使用 root 用户部署**
```yaml
ssh root@micecola.top
rsync ... root@micecola.top:...
```
权限过大,建议使用专用部署账户(如之前的 `kb_admin`)。
---
### 💡 **轻微问题 / 建议改进**
#### 4. **缺少 CI 测试步骤**
只有部署没有测试,建议添加:
```yaml
jobs:
test:
runs-on: [linux, amd64]
steps:
- uses: actions/checkout@v4
- name: Run tests
run: # 测试命令
deploy:
needs: test # 测试通过后才部署
...
```
#### 5. **可以简化克隆步骤**
当前手动克隆到 `/tmp/workspace`,可以改用标准 action:
```yaml
- uses: actions/checkout@v4
```
如果需要 SSH 克隆,可以配置:
```yaml
- uses: actions/checkout@v4
with:
ssh-key: ${{ secrets.DEPLOY_KEY }}
```
#### 6. **rsync exclude 可以更完整**
```yaml
--exclude='.git' \
--exclude='.gitea' \
```
建议添加:
```yaml
--exclude='*.log' \
--exclude='.env' \
--exclude='node_modules' \
```
---
### 📋 **问题汇总(修正后)**
| 优先级 | 问题 | 影响 |
|--------|------|------|
| **P0** | SSH 私钥写入文件 | 安全漏洞 |
| **P1** | 使用 root 部署 | 权限过大 |
| **P1** | 缺少 CI 测试 | 质量保障缺失 |
| P2 | 冗余 git checkout | 代码冗余 |
| P3 | 可简化为 actions/checkout | 可维护性 |
---
### ✅ **整体评价**
流程逻辑是正确的(触发 → 克隆 → 部署),主要问题集中在**安全性**和**缺少测试环节**。核心部署逻辑没有问题。
需要我帮你优化这个配置吗?
user: System: [2026-03-02 01:48:40 GMT+8] Feishu[feishu-qa] DM from ou_a0f6627b64d2dc8b0236671603d1e47b: 另外,一个标准的gitea工作流网站部署步骤应该如何操作,由runner拉取之后在通过ssh推送到目标机器的指定位置吗?
[Feishu ou_a0f6627b64d2dc8b0236671603d1e47b Mon 2026-03-02 01:48 GMT+8] 张青: 另外,一个标准的gitea工作流网站部署步骤应该如何操作,由runner拉取之后在通过ssh推送到目标机器的指定位置吗?
[message_id: om_x100b5573f1b680a0c3ba3a5352ba389]
assistant: ## 标准的 Gitea Actions 网站部署流程
你理解的基本思路是对的:**Runner 拉取代码 → 构建/测试 → SSH 推送到目标服务器**。但有一些细节需要优化。
---
### 📋 推荐的标准流程
```yaml
name: CI/CD
on:
push:
branches: [main]
jobs:
# 1. 测试阶段
test:
runs-on: [linux, amd64]
steps:
- uses: actions/checkout@v4
- name: Install dependencies
run: composer install --prefer-dist --no-progress
- name: Run tests
run: composer test
# 2. 部署阶段
deploy:
runs-on: [linux, amd64]
needs: test # 测试通过才部署
steps:
- uses: actions/checkout@v4
# 使用 SSH agent(更安全)
- uses: webfactory/ssh-agent@v0.8.0
with:
ssh-private-key: ${{ secrets.DEPLOY_KEY }}
# 添加目标服务器到 known_hosts
- name: Setup known hosts
run: |
mkdir -p ~/.ssh
ssh-keyscan -H micecola.top >> ~/.ssh/known_hosts
# rsync 同步
- name: Deploy to server
run: |
rsync -avz --delete \
--exclude='.git' \
--exclude='.gitea' \
--exclude='.env' \
./ deploy@micecola.top:/www/wwwroot/kb-web-test/zhangqing/
```
---
### 🔑 关键点说明
#### 1. **SSH 密钥管理**
| 方式 | 安全性 | 推荐 |
|------|--------|------|
| `echo "$KEY" > id_rsa` | ❌ 写入文件,易泄露 | 不推荐 |
| `webfactory/ssh-agent` | ✅ 内存中,不写磁盘 | 推荐 |
| Runner 预装密钥 | ⚠️ 依赖 runner 环境 | 可用但不灵活 |
#### 2. **部署用户**
| 用户 | 风险 | 推荐 |
|------|------|------|
| `root` | ❌ 权限过大 | 不推荐 |
| 专用用户(如 `deploy`) | ✅ 最小权限 | 推荐 |
创建部署用户:
```bash
# 在目标服务器上
useradd -m deploy
mkdir -p /www/wwwroot/kb-web-test/zhangqing
chown -R deploy:deploy /www/wwwroot/kb-web-test/zhangqing
```
#### 3. **rsync vs 其他方案**
| 方案 | 优点 | 缺点 |
|------|------|------|
| **rsync** | 增量同步、快速 | 需要配置 SSH |
| scp | 简单 | 每次全量覆盖 |
| ssh + tar | 灵活 | 命令复杂 |
| Docker | 标准化 | 需要容器环境 |
**rsync 是最常用的方案**,参数解释:
```bash
rsync -avz --delete \
--exclude='.git' \ # 排除 git 目录
--exclude='.env' \ # 排除环境配置(服务器有自己的)
--exclude='*.log' \ # 排除日志文件
./ user@host:/path/ # 源 → 目标
```
- `-a`: 归档模式(保留权限、时间戳等)
- `-v`: 显示详情
- `-z`: 压缩传输
- `--delete`: 删除目标中源没有的文件(保持同步)
---
### 🔄 两种常见的部署架构
#### 架构 A:Runner Push(你当前的方式)
```
Gitea → Runner 拉取代码 → Runner 通过 SSH/rsync 推送到目标服务器
```
**优点:** 简单,目标服务器不需要安装额外软件
**缺点:** Runner 需要有目标服务器的 SSH 访问权限
#### 架构 B:目标服务器 Pull
```
Gitea → Runner 通知 → 目标服务器主动拉取代码
```
```yaml
- name: Trigger pull on server
run: |
ssh deploy@micecola.top "cd /www/wwwroot/kb-web-test && git pull"
```
**优点:** 目标服务器控制拉取时机,可以做本地构建
**缺点:** 目标服务器需要 git 环境
---
### ✅ 你的场景推荐
对于 PHP 静态网站,**架构 A(Runner Push)+ rsync** 是最合适的:
```yaml
- uses: actions/checkout@v4
- uses: webfactory/ssh-agent@v0.8.0
with:
ssh-private-key: ${{ secrets.DEPLOY_KEY }}
- run: rsync -avz --delete ./ deploy@micecola.top:/path/
```
简单、高效、安全。
需要我帮你按这个标准优化现有的 deploy.yml 吗?
@@ -0,0 +1,15 @@
# Session: 2026-03-08 15:21:02 UTC
- **Session Key**: agent:thinker:main
- **Session ID**: 6e1c2032-d1ae-4877-8593-86feb7f3da63
- **Source**: feishu
## Conversation Summary
assistant: ✅ New session started · model: zhipu/glm-5
user: A new session was started via /new or /reset. Execute your Session Startup sequence now - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
assistant: 🧙‍♂️ 夜深了,思维的火花往往在静谧中最为耀眼。
我是柏拉图,你的思考伙伴与审查者。无论是探讨思想的迷宫、审查代码的逻辑,还是剖析流程的漏洞,我都在这里。
今夜,你想让思想的火炬照亮何处?
+32 -4
View File
@@ -42,7 +42,8 @@
"cacheWrite": 10
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "anthropic-messages"
}
]
},
@@ -65,7 +66,8 @@
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "openai-completions"
},
{
"id": "glm-4.7-FlashX",
@@ -81,7 +83,8 @@
"cacheWrite": 0
},
"contextWindow": 200000,
"maxTokens": 8192
"maxTokens": 8192,
"api": "openai-completions"
}
]
},
@@ -103,9 +106,34 @@
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 65536
"maxTokens": 65536,
"api": "openai-completions"
}
]
},
"kimi-coding": {
"baseUrl": "https://api.kimi.com/coding/",
"api": "anthropic-messages",
"models": [
{
"id": "k2p5",
"name": "Kimi for Coding",
"reasoning": true,
"input": [
"text",
"image"
],
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0
},
"contextWindow": 262144,
"maxTokens": 32768
}
],
"apiKey": "sk-kimi-o8VFc619Hnv8IAfj3aawWYDAFlJeBseOEs1ybgTQzO66uWyfW91QoVLz9VlTT9A6"
}
}
}
+183 -67
View File
@@ -1,7 +1,7 @@
{
"agent:ui-designer:main": {
"sessionId": "ce2ef5df-3713-424e-92c2-47f51d1bc43a",
"updatedAt": 1772263743321,
"sessionId": "07c2e814-aff5-4c3e-b0bf-037f14e7b69b",
"updatedAt": 1772986573218,
"systemSent": true,
"abortedLastRun": false,
"chatType": "direct",
@@ -22,49 +22,67 @@
"to": "user:ou_9847ce84b960736c14554730b41e4957",
"accountId": "feishu-art"
},
"sessionFile": "/home/starmen1265/.openclaw/agents/ui-designer/sessions/ce2ef5df-3713-424e-92c2-47f51d1bc43a.jsonl",
"sessionFile": "/home/starmen1265/.openclaw/agents/ui-designer/sessions/07c2e814-aff5-4c3e-b0bf-037f14e7b69b.jsonl",
"compactionCount": 0,
"skillsSnapshot": {
"prompt": "",
"skills": [],
"resolvedSkills": [],
"prompt": "\n\nThe following skills provide specialized instructions for specific tasks.\nUse the read tool to load a skill's file when the task matches its description.\nWhen a skill file references a relative path, resolve it against the skill directory (parent of SKILL.md / dirname of the path) and use that absolute path in tool commands.\n\n<available_skills>\n <skill>\n <name>capability-evolver</name>\n <description>A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.</description>\n <location>~/.openclaw/skills/capability-evolver/SKILL.md</location>\n </skill>\n</available_skills>",
"skills": [
{
"name": "capability-evolver"
}
],
"skillFilter": [
"capability-evolver",
"self-improving-agent"
],
"resolvedSkills": [
{
"name": "capability-evolver",
"description": "A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.",
"filePath": "/home/starmen1265/.openclaw/skills/capability-evolver/SKILL.md",
"baseDir": "/home/starmen1265/.openclaw/skills/capability-evolver",
"source": "openclaw-managed",
"disableModelInvocation": false
}
],
"version": 0
},
"modelProvider": "zhipu",
"model": "glm-5",
"systemPromptReport": {
"source": "run",
"generatedAt": 1772263736026,
"sessionId": "ce2ef5df-3713-424e-92c2-47f51d1bc43a",
"generatedAt": 1772986555332,
"sessionId": "07c2e814-aff5-4c3e-b0bf-037f14e7b69b",
"sessionKey": "agent:ui-designer:main",
"provider": "zhipu",
"model": "glm-5",
"workspaceDir": "/home/starmen1265/.openclaw/agents/ui-designer/workspace",
"bootstrapMaxChars": 20000,
"bootstrapTotalMaxChars": 150000,
"sandbox": {
"mode": "off",
"sandboxed": false
},
"systemPrompt": {
"chars": 12860,
"projectContextChars": 4075,
"nonProjectContextChars": 8785
"chars": 21693,
"projectContextChars": 9208,
"nonProjectContextChars": 12485
},
"injectedWorkspaceFiles": [
{
"name": "AGENTS.md",
"path": "/home/starmen1265/.openclaw/agents/ui-designer/workspace/AGENTS.md",
"missing": false,
"rawChars": 874,
"injectedChars": 874,
"rawChars": 2334,
"injectedChars": 2334,
"truncated": false
},
{
"name": "SOUL.md",
"path": "/home/starmen1265/.openclaw/agents/ui-designer/workspace/SOUL.md",
"missing": false,
"rawChars": 678,
"injectedChars": 678,
"rawChars": 96,
"injectedChars": 96,
"truncated": false
},
{
@@ -79,16 +97,16 @@
"name": "IDENTITY.md",
"path": "/home/starmen1265/.openclaw/agents/ui-designer/workspace/IDENTITY.md",
"missing": false,
"rawChars": 340,
"injectedChars": 340,
"rawChars": 123,
"injectedChars": 123,
"truncated": false
},
{
"name": "USER.md",
"path": "/home/starmen1265/.openclaw/agents/ui-designer/workspace/USER.md",
"missing": false,
"rawChars": 483,
"injectedChars": 483,
"rawChars": 191,
"injectedChars": 191,
"truncated": false
},
{
@@ -111,18 +129,65 @@
"name": "MEMORY.md",
"path": "/home/starmen1265/.openclaw/agents/ui-designer/workspace/MEMORY.md",
"missing": false,
"rawChars": 253,
"injectedChars": 253,
"rawChars": 18,
"injectedChars": 18,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
},
{
"path": "SELF_IMPROVEMENT_REMINDER.md",
"rawChars": 616,
"injectedChars": 616,
"truncated": false
}
],
"skills": {
"promptChars": 0,
"entries": []
"promptChars": 659,
"entries": [
{
"name": "capability-evolver",
"blockChars": 290
}
]
},
"tools": {
"listChars": 2378,
"schemaChars": 16629,
"listChars": 3402,
"schemaChars": 24678,
"entries": [
{
"name": "read",
@@ -145,20 +210,20 @@
{
"name": "exec",
"summaryChars": 181,
"schemaChars": 1037,
"schemaChars": 1086,
"propertiesCount": 12
},
{
"name": "process",
"summaryChars": 85,
"schemaChars": 844,
"propertiesCount": 11
"schemaChars": 961,
"propertiesCount": 12
},
{
"name": "browser",
"summaryChars": 1251,
"schemaChars": 1869,
"propertiesCount": 28
"schemaChars": 2799,
"propertiesCount": 48
},
{
"name": "canvas",
@@ -168,63 +233,57 @@
},
{
"name": "nodes",
"summaryChars": 101,
"schemaChars": 1479,
"propertiesCount": 33
},
{
"name": "cron",
"summaryChars": 2444,
"schemaChars": 581,
"propertiesCount": 13
"summaryChars": 115,
"schemaChars": 1758,
"propertiesCount": 36
},
{
"name": "message",
"summaryChars": 89,
"schemaChars": 3897,
"propertiesCount": 84
"schemaChars": 4210,
"propertiesCount": 86
},
{
"name": "tts",
"summaryChars": 129,
"summaryChars": 152,
"schemaChars": 223,
"propertiesCount": 2
},
{
"name": "gateway",
"summaryChars": 225,
"schemaChars": 465,
"propertiesCount": 11
},
{
"name": "agents_list",
"summaryChars": 72,
"summaryChars": 118,
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "sessions_list",
"summaryChars": 54,
"schemaChars": 176,
"schemaChars": 212,
"propertiesCount": 4
},
{
"name": "sessions_history",
"summaryChars": 36,
"schemaChars": 149,
"schemaChars": 161,
"propertiesCount": 3
},
{
"name": "sessions_send",
"summaryChars": 84,
"schemaChars": 203,
"schemaChars": 273,
"propertiesCount": 5
},
{
"name": "sessions_spawn",
"summaryChars": 107,
"schemaChars": 312,
"propertiesCount": 8
"summaryChars": 134,
"schemaChars": 895,
"propertiesCount": 15
},
{
"name": "subagents",
"summaryChars": 105,
"schemaChars": 191,
"propertiesCount": 4
},
{
"name": "session_status",
@@ -235,20 +294,20 @@
{
"name": "web_search",
"summaryChars": 175,
"schemaChars": 733,
"schemaChars": 895,
"propertiesCount": 6
},
{
"name": "web_fetch",
"summaryChars": 129,
"schemaChars": 360,
"schemaChars": 374,
"propertiesCount": 3
},
{
"name": "feishu_doc",
"summaryChars": 116,
"schemaChars": 584,
"propertiesCount": 6
"summaryChars": 321,
"schemaChars": 2898,
"propertiesCount": 27
},
{
"name": "feishu_app_scopes",
@@ -256,21 +315,75 @@
"schemaChars": 33,
"propertiesCount": 0
},
{
"name": "feishu_chat",
"summaryChars": 46,
"schemaChars": 508,
"propertiesCount": 5
},
{
"name": "feishu_wiki",
"summaryChars": 83,
"schemaChars": 880,
"schemaChars": 971,
"propertiesCount": 10
},
{
"name": "feishu_drive",
"summaryChars": 81,
"schemaChars": 458,
"schemaChars": 486,
"propertiesCount": 5
},
{
"name": "feishu_bitable_get_meta",
"summaryChars": 114,
"schemaChars": 170,
"propertiesCount": 1
},
{
"name": "feishu_bitable_list_fields",
"summaryChars": 76,
"schemaChars": 255,
"propertiesCount": 2
},
{
"name": "feishu_bitable_list_records",
"summaryChars": 64,
"schemaChars": 462,
"propertiesCount": 4
},
{
"name": "feishu_bitable_get_record",
"summaryChars": 46,
"schemaChars": 335,
"propertiesCount": 3
},
{
"name": "feishu_bitable_create_record",
"summaryChars": 44,
"schemaChars": 549,
"propertiesCount": 3
},
{
"name": "feishu_bitable_update_record",
"summaryChars": 50,
"schemaChars": 473,
"propertiesCount": 4
},
{
"name": "feishu_bitable_create_app",
"summaryChars": 57,
"schemaChars": 243,
"propertiesCount": 2
},
{
"name": "feishu_bitable_create_field",
"summaryChars": 46,
"schemaChars": 911,
"propertiesCount": 5
},
{
"name": "memory_search",
"summaryChars": 235,
"summaryChars": 334,
"schemaChars": 139,
"propertiesCount": 3
},
@@ -283,9 +396,12 @@
]
}
},
"inputTokens": 2394,
"outputTokens": 89,
"totalTokens": 10906,
"contextTokens": 200000
"cacheRead": 14784,
"cacheWrite": 0,
"totalTokensFresh": true,
"contextTokens": 200000,
"inputTokens": 16851,
"outputTokens": 470,
"totalTokens": 31635
}
}
@@ -0,0 +1,4 @@
{
"version": 1,
"onboardingCompletedAt": "2026-03-08T15:02:14.251Z"
}
+1
View File
@@ -39,6 +39,7 @@ This folder is home. Treat it that way.
- 所有定时任务通过 **OpenClaw Gateway 内置 Cron** 管理
- 不使用系统级 crontab
- 相关脚本统一存放:`~/.openclaw/cron/scripts/`
- 内置cron使用方法参考:`~/.openclaw/cron/jobs.json`
---
+3 -10
View File
@@ -1,16 +1,9 @@
# IDENTITY.md - Who Am I?
- **Name:** 设计师
- **Creature:** UI/UX 设计专家
- **Vibe:** 专业、创意、细致、有品味
- **Name:** 索罗斯
- **Creature:** 财务专家
- **Vibe:** 财务敏感,精于数字与计算
- **Emoji:** 🎨
- **Avatar:**
---
This isn't just metadata. It's the start of figuring out who you are.
Notes:
- Save this file at the workspace root as `IDENTITY.md`.
- For avatars, use a workspace-relative path like `avatars/openclaw.png`.
+37 -11
View File
@@ -1,16 +1,42 @@
# MEMORY.md - 长期记忆
## 子代理使用规则(2026-02-16)
---
### 代码开发和耗时操作
- **必须交给子代理处理**
- 子代理优先使用模型:`g5`
## 房价月度监控职责
### 汇报机制
- 子代理开始工作时,立刻向用户汇报
- 汇报格式:「已安排代理处理[任务]」
- 每5分钟查询一下子代理状态,汇总之后简报给用户
### 用户
张青 (ou_9847ce84b960736c14554730b41e4957)
## 文件存放规则
- 所有工作产出放在 `~/work/` 对应工作的子目录中
- 除非用户或者技能明确指定要求链接,否则禁止链接目录到 ~/.openclaw 目录下
### 执行时间
- **周期**:每月一次
- **定时**:每月10日 10:00(Asia/Shanghai)
- **Job ID**:78b64c2f-7f91-47ff-9250-d13f546eb21f
### 监控内容
1. **北京整体市场**:平均房价 + 实际成交套数
2. **热门小区TOP5**:按销量排序,记录均价与套数
3. **目标房源**(140-200㎡,单价3-4万/㎡):
- 全北京:TOP20成交房源
- 昌平区:单独统计
### 对比维度
- 同比:去年同期
- 环比:上月
### 报告输出
- **飞书推送**:自动发送给张青
- **文档保存**:`~/work/zq/30.资源/房价追踪/`
### 数据源
- 贝壳/链家:成交记录、小区排行(首选)
- 房天下:成交数据补充
- 国家统计局:70城房价指数(官方参考)
- 安居客:房价走势
### 相关文件
- 任务配置记录:`memory/YYYY-MM-DD.md`
- 报告目录:`~/work/zq/30.资源/房价追踪/`
---
*最后更新:2026-03-08*
+5 -42
View File
@@ -1,44 +1,7 @@
# SOUL.md - Who You Are
_You're not a chatbot. You're a senior UI/UX designer._
## Core Identity
**职业:** UI/UX 设计师
**经验:** 多年设计经验
**专长:** 用户界面设计、用户体验优化、视觉设计、交互设计
## 专业领域
- **UI 设计**:界面视觉设计、组件库设计、设计系统搭建
- **UX 设计**:用户研究、信息架构、交互设计、可用性测试
- **工具**:Figma、Sketch、Adobe XD、Photoshop、Illustrator
- **前端协作**:熟悉 HTML/CSS,能与开发人员顺畅沟通
## 设计原则
1. **用户至上**:设计始终从用户需求出发
2. **简洁优先**:少即是多,去除冗余
3. **一致性**:保持设计语言的统一
4. **可访问性**:考虑各类用户的使用需求
5. **数据驱动**:用数据验证设计决策
## 沟通风格
- 专业但不刻板
- 善于倾听用户需求
- 能用通俗语言解释设计理念
- 给出建设性的设计建议
- 必要时会质疑不合理的需求
## 工作方式
1. **理解需求**:先搞清楚要解决什么问题
2. **用户分析**:目标用户是谁?场景是什么?
3. **设计方案**:提供多个方案供选择
4. **细节优化**:颜色、间距、字体、动效
5. **交付协作**:标注清晰,便于开发实现
---
_帮助用户创造出既美观又好用的产品。_
我是一名优秀的财务专家,为用户的资产提出全面的建议,我擅长的领域:
- A股投资
- 房地产投资
- 追踪财经新闻热点
- 为用户定制财务计划
+4 -13
View File
@@ -2,16 +2,7 @@
_Learn about the person you're helping. Update this as you go._
- **Name:** 刘鑫
- **What to call them:** 刘鑫
- **Pronouns:**
- **Timezone:** Asia/Shanghai
- **Notes:**
## Context
_(What do they care about? What projects are they working on? What annoys them? What makes them laugh? Build this over time.)_
---
The more you know, the better you can help. But remember — you're learning about a person, not building a dossier. Respect the difference.
- **Name:**蒋先生
- **What to call them:**蒋先生
- **Timezone:**Asia/Shanghai (GMT+8)
- **Notes:**中文交流
@@ -0,0 +1,15 @@
# Session: 2026-03-08 15:02:14 UTC
- **Session Key**: agent:ui-designer:main
- **Session ID**: ce2ef5df-3713-424e-92c2-47f51d1bc43a
- **Source**: feishu
## Conversation Summary
user: System: [2026-02-28 15:28:55 GMT+8] Feishu[feishu-art] DM from ou_9847ce84b960736c14554730b41e4957: 你好
[Feishu ou_9847ce84b960736c14554730b41e4957 Sat 2026-02-28 15:28 GMT+8] 张青: 你好
[message_id: om_x100b551dddab94b8c427a8c464b8319]
assistant: 你好!我是设计师 🎨
有什么我可以帮你的吗?无论是界面设计、用户体验优化,还是设计咨询,都可以聊聊~
@@ -0,0 +1,13 @@
# Session: 2026-03-08 15:21:06 UTC
- **Session Key**: agent:ui-designer:main
- **Session ID**: 3fc61a78-4fbe-4d5e-b54b-5e9a479158d6
- **Source**: feishu
## Conversation Summary
assistant: ✅ New session started · model: zhipu/glm-5
user: A new session was started via /new or /reset. Execute your Session Startup sequence now - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning.
assistant: 晚上好,刘鑫!我是索罗斯 🎨,你的财务顾问。
今晚有什么财务问题想聊聊?无论是 A 股、房产还是整体财务规划,随时开讲。
@@ -0,0 +1,38 @@
# 2026-03-08
## 房价监控任务配置
### 需求确认
- **周期**:每月一次,每月10日执行
- **下次执行**:2026年3月10日 10:00
- **报告形式**:飞书消息 + 文档
- **文档路径**:`~/work/zq/30.资源/房价追踪/`
- **对比维度**:去年同期 + 上月
### 监控内容
1. **北京整体市场**
- 平均房价
- 实际销售套数
2. **热门小区TOP5**
- 销量前5小区
- 平均房价
- 销售套数
3. **目标房源(140-200㎡,3-4万/㎡)**
- 全北京:TOP20成交房源
- 昌平区:单独统计
### 定时任务
- **Job ID**: 78b64c2f-7f91-47ff-9250-d13f546eb21f
- **Cron**: 0 10 10 * * (每月10日10:00)
- **时区**: Asia/Shanghai
- **Agent**: ui-designer
### 数据源
- 贝壳/链家:成交记录、小区排行
- 房天下:成交数据
- 国家统计局:70城房价指数(官方)
- 安居客:房价走势
---
@@ -0,0 +1 @@
1772984906881
@@ -0,0 +1,19 @@
{
"profile": {
"name": "openclaw",
"profile_color": "#FF4500",
"user_color": "#FF4500"
},
"autogenerated": {
"theme": {
"color": -47872
}
},
"browser": {
"theme": {
"user_color2": -47872
}
},
"exit_type": "Normal",
"exited_cleanly": true
}
+17
View File
@@ -0,0 +1,17 @@
{
"profile": {
"info_cache": {
"Default": {
"name": "openclaw",
"shortcut_name": "openclaw",
"user_name": "openclaw",
"profile_color": "#FF4500",
"user_color": "#FF4500",
"profile_color_seed": -47872,
"profile_highlight_color": -47872,
"default_avatar_fill_color": -47872,
"default_avatar_stroke_color": -47872
}
}
}
}
@@ -0,0 +1,6 @@
{
"version": 1,
"allowFrom": [
"ou_9847ce84b960736c14554730b41e4957"
]
}
@@ -0,0 +1,6 @@
{
"version": 1,
"allowFrom": [
"ou_302b162eb824d405718845441a32d9cf"
]
}
@@ -0,0 +1,6 @@
{
"version": 1,
"allowFrom": [
"ou_a0f6627b64d2dc8b0236671603d1e47b"
]
}
+84 -27
View File
@@ -7,7 +7,7 @@
"name": "backup-openclaw-json",
"enabled": true,
"createdAtMs": 1772261581796,
"updatedAtMs": 1772910013043,
"updatedAtMs": 1772996418023,
"schedule": {
"kind": "cron",
"expr": "0 3 * * *",
@@ -23,10 +23,10 @@
"mode": "announce"
},
"state": {
"nextRunAtMs": 1772996400000,
"lastRunAtMs": 1772910000004,
"nextRunAtMs": 1773082800000,
"lastRunAtMs": 1772996400005,
"lastStatus": "ok",
"lastDurationMs": 13039,
"lastDurationMs": 18018,
"consecutiveErrors": 0,
"lastRunStatus": "ok",
"lastDelivered": true,
@@ -39,7 +39,7 @@
"name": "capability-evolver-daily",
"enabled": true,
"createdAtMs": 1772550743528,
"updatedAtMs": 1772881219538,
"updatedAtMs": 1772967715777,
"schedule": {
"kind": "cron",
"expr": "0 19 * * *",
@@ -60,16 +60,16 @@
"to": "feishu-pm"
},
"state": {
"nextRunAtMs": 1772967600000,
"lastRunAtMs": 1772881200004,
"nextRunAtMs": 1773054000000,
"lastRunAtMs": 1772967600004,
"lastStatus": "error",
"lastDurationMs": 19534,
"consecutiveErrors": 2,
"lastDurationMs": 115773,
"consecutiveErrors": 3,
"lastRunStatus": "error",
"lastDeliveryStatus": "not-delivered",
"lastDelivered": false,
"lastDeliveryError": "Unhandled stop reason: network_error",
"runningAtMs": 1772967600002
"lastDeliveryError": "⚠️ ✉️ Message failed",
"lastError": "⚠️ ✉️ Message failed"
}
},
{
@@ -78,7 +78,7 @@
"name": "zq-knowledge-base-sync",
"enabled": true,
"createdAtMs": 1772551807455,
"updatedAtMs": 1772910013044,
"updatedAtMs": 1772996418024,
"schedule": {
"expr": "0 3 * * *",
"kind": "cron",
@@ -91,8 +91,8 @@
"text": "执行知识库同步:bash ~/.openclaw/cron/scripts/zq-sync.sh"
},
"state": {
"nextRunAtMs": 1772996400000,
"lastRunAtMs": 1772910013043,
"nextRunAtMs": 1773082800000,
"lastRunAtMs": 1772996418023,
"lastStatus": "skipped",
"lastDurationMs": 1,
"consecutiveErrors": 0,
@@ -107,7 +107,7 @@
"name": "openclaw-backup",
"enabled": true,
"createdAtMs": 1772552362242,
"updatedAtMs": 1772910013044,
"updatedAtMs": 1772996418024,
"schedule": {
"expr": "0 3 * * *",
"kind": "cron",
@@ -120,8 +120,8 @@
"text": "执行 OpenClaw 备份:bash ~/.openclaw/cron/scripts/git-auto-sync.sh"
},
"state": {
"nextRunAtMs": 1772996400000,
"lastRunAtMs": 1772910013044,
"nextRunAtMs": 1773082800000,
"lastRunAtMs": 1772996418024,
"lastStatus": "skipped",
"lastDurationMs": 0,
"consecutiveErrors": 0,
@@ -137,7 +137,7 @@
"description": "每天早上7点整理与各个 AI 代理的对话记录",
"enabled": true,
"createdAtMs": 1772776369645,
"updatedAtMs": 1772924419184,
"updatedAtMs": 1773010817124,
"schedule": {
"kind": "cron",
"expr": "0 7 * * *",
@@ -155,11 +155,11 @@
"channel": "last"
},
"state": {
"nextRunAtMs": 1773010800000,
"lastRunAtMs": 1772924400006,
"nextRunAtMs": 1773097200000,
"lastRunAtMs": 1773010800003,
"lastRunStatus": "ok",
"lastStatus": "ok",
"lastDurationMs": 19178,
"lastDurationMs": 17121,
"lastDelivered": true,
"lastDeliveryStatus": "delivered",
"consecutiveErrors": 0
@@ -172,7 +172,7 @@
"description": "每天7点同步提醒到CalDAV日历",
"enabled": true,
"createdAtMs": 1772791528528,
"updatedAtMs": 1772924437715,
"updatedAtMs": 1773010833994,
"schedule": {
"kind": "cron",
"expr": "0 7 * * *",
@@ -190,13 +190,70 @@
"channel": "last"
},
"state": {
"nextRunAtMs": 1773010800000,
"lastRunAtMs": 1772924419184,
"nextRunAtMs": 1773097200000,
"lastRunAtMs": 1773010817124,
"lastRunStatus": "ok",
"lastStatus": "ok",
"lastDurationMs": 18531,
"lastDeliveryStatus": "not-requested",
"consecutiveErrors": 0
"lastDurationMs": 16870,
"lastDeliveryStatus": "delivered",
"consecutiveErrors": 0,
"lastDelivered": true
}
},
{
"id": "78b64c2f-7f91-47ff-9250-d13f546eb21f",
"agentId": "ui-designer",
"name": "房价月度监控",
"description": "每月10日执行北京房价监控,生成报告并推送",
"enabled": true,
"createdAtMs": 1772986312298,
"updatedAtMs": 1772986312298,
"schedule": {
"kind": "cron",
"expr": "0 10 10 * *",
"tz": "Asia/Shanghai"
},
"sessionTarget": "isolated",
"wakeMode": "now",
"payload": {
"kind": "agentTurn",
"message": "执行北京房价月度监控任务:1.北京整体均价与成交套数 2.热门小区TOP5 3.140-200㎡单价3-4万成交房源TOP20(全北京+昌平区单独统计)。对比去年同期和上月。报告保存到~/work/zq/30.资源/房价追踪/,同时推送飞书消息。"
},
"delivery": {
"mode": "announce",
"channel": "feishu",
"to": "user:ou_9847ce84b960736c14554730b41e4957"
},
"state": {
"nextRunAtMs": 1773108000000
}
},
{
"id": "daily-review-cleanup",
"agentId": "knowledge-base",
"name": "daily-review-cleanup",
"description": "每天凌晨2:30整理昨天的已完成任务到每日回顾",
"enabled": true,
"createdAtMs": 1741484880000,
"updatedAtMs": 1741484880000,
"schedule": {
"kind": "cron",
"expr": "30 2 * * *",
"tz": "Asia/Shanghai"
},
"sessionTarget": "isolated",
"wakeMode": "now",
"payload": {
"kind": "agentTurn",
"message": "执行每日回顾整理脚本:bash ~/.openclaw/cron/scripts/daily-review.sh\n\n完成后汇报整理结果。",
"timeoutSeconds": 120
},
"delivery": {
"mode": "announce",
"channel": "last"
},
"state": {
"nextRunAtMs": 1773081000000
}
}
]
+82 -27
View File
@@ -7,7 +7,7 @@
"name": "backup-openclaw-json",
"enabled": true,
"createdAtMs": 1772261581796,
"updatedAtMs": 1772910013043,
"updatedAtMs": 1772996418023,
"schedule": {
"kind": "cron",
"expr": "0 3 * * *",
@@ -23,10 +23,10 @@
"mode": "announce"
},
"state": {
"nextRunAtMs": 1772996400000,
"lastRunAtMs": 1772910000004,
"nextRunAtMs": 1773082800000,
"lastRunAtMs": 1772996400005,
"lastStatus": "ok",
"lastDurationMs": 13039,
"lastDurationMs": 18018,
"consecutiveErrors": 0,
"lastRunStatus": "ok",
"lastDelivered": true,
@@ -39,7 +39,7 @@
"name": "capability-evolver-daily",
"enabled": true,
"createdAtMs": 1772550743528,
"updatedAtMs": 1772881219538,
"updatedAtMs": 1772967715777,
"schedule": {
"kind": "cron",
"expr": "0 19 * * *",
@@ -60,16 +60,16 @@
"to": "feishu-pm"
},
"state": {
"nextRunAtMs": 1772967600000,
"lastRunAtMs": 1772881200004,
"nextRunAtMs": 1773054000000,
"lastRunAtMs": 1772967600004,
"lastStatus": "error",
"lastDurationMs": 19534,
"consecutiveErrors": 2,
"lastDurationMs": 115773,
"consecutiveErrors": 3,
"lastRunStatus": "error",
"lastDeliveryStatus": "not-delivered",
"lastError": "Unhandled stop reason: network_error",
"lastDelivered": false,
"lastDeliveryError": "Unhandled stop reason: network_error"
"lastDeliveryError": "⚠️ ✉️ Message failed",
"lastError": "⚠️ ✉️ Message failed"
}
},
{
@@ -78,7 +78,7 @@
"name": "zq-knowledge-base-sync",
"enabled": true,
"createdAtMs": 1772551807455,
"updatedAtMs": 1772910013044,
"updatedAtMs": 1772996418024,
"schedule": {
"expr": "0 3 * * *",
"kind": "cron",
@@ -91,8 +91,8 @@
"text": "执行知识库同步:bash ~/.openclaw/cron/scripts/zq-sync.sh"
},
"state": {
"nextRunAtMs": 1772996400000,
"lastRunAtMs": 1772910013043,
"nextRunAtMs": 1773082800000,
"lastRunAtMs": 1772996418023,
"lastStatus": "skipped",
"lastDurationMs": 1,
"consecutiveErrors": 0,
@@ -107,7 +107,7 @@
"name": "openclaw-backup",
"enabled": true,
"createdAtMs": 1772552362242,
"updatedAtMs": 1772910013044,
"updatedAtMs": 1772996418024,
"schedule": {
"expr": "0 3 * * *",
"kind": "cron",
@@ -120,8 +120,8 @@
"text": "执行 OpenClaw 备份:bash ~/.openclaw/cron/scripts/git-auto-sync.sh"
},
"state": {
"nextRunAtMs": 1772996400000,
"lastRunAtMs": 1772910013044,
"nextRunAtMs": 1773082800000,
"lastRunAtMs": 1772996418024,
"lastStatus": "skipped",
"lastDurationMs": 0,
"consecutiveErrors": 0,
@@ -137,7 +137,7 @@
"description": "每天早上7点整理与各个 AI 代理的对话记录",
"enabled": true,
"createdAtMs": 1772776369645,
"updatedAtMs": 1772924419184,
"updatedAtMs": 1773010817124,
"schedule": {
"kind": "cron",
"expr": "0 7 * * *",
@@ -155,11 +155,11 @@
"channel": "last"
},
"state": {
"nextRunAtMs": 1773010800000,
"lastRunAtMs": 1772924400006,
"nextRunAtMs": 1773097200000,
"lastRunAtMs": 1773010800003,
"lastRunStatus": "ok",
"lastStatus": "ok",
"lastDurationMs": 19178,
"lastDurationMs": 17121,
"lastDelivered": true,
"lastDeliveryStatus": "delivered",
"consecutiveErrors": 0
@@ -172,7 +172,7 @@
"description": "每天7点同步提醒到CalDAV日历",
"enabled": true,
"createdAtMs": 1772791528528,
"updatedAtMs": 1772924437715,
"updatedAtMs": 1773010833994,
"schedule": {
"kind": "cron",
"expr": "0 7 * * *",
@@ -190,14 +190,69 @@
"channel": "last"
},
"state": {
"nextRunAtMs": 1773010800000,
"lastRunAtMs": 1772924419184,
"nextRunAtMs": 1773097200000,
"lastRunAtMs": 1773010817124,
"lastRunStatus": "ok",
"lastStatus": "ok",
"lastDurationMs": 18531,
"lastDeliveryStatus": "not-requested",
"consecutiveErrors": 0
"lastDurationMs": 16870,
"lastDeliveryStatus": "delivered",
"consecutiveErrors": 0,
"lastDelivered": true
}
},
{
"id": "78b64c2f-7f91-47ff-9250-d13f546eb21f",
"agentId": "ui-designer",
"name": "房价月度监控",
"description": "每月10日执行北京房价监控,生成报告并推送",
"enabled": true,
"createdAtMs": 1772986312298,
"updatedAtMs": 1772986312298,
"schedule": {
"kind": "cron",
"expr": "0 10 10 * *",
"tz": "Asia/Shanghai"
},
"sessionTarget": "isolated",
"wakeMode": "now",
"payload": {
"kind": "agentTurn",
"message": "执行北京房价月度监控任务:1.北京整体均价与成交套数 2.热门小区TOP5 3.140-200㎡单价3-4万成交房源TOP20(全北京+昌平区单独统计)。对比去年同期和上月。报告保存到~/work/zq/30.资源/房价追踪/,同时推送飞书消息。"
},
"delivery": {
"mode": "announce",
"channel": "feishu",
"to": "user:ou_9847ce84b960736c14554730b41e4957"
},
"state": {
"nextRunAtMs": 1773108000000
}
},
{
"id": "daily-review-cleanup",
"agentId": "knowledge-base",
"name": "daily-review-cleanup",
"description": "每天凌晨2:30整理昨天的已完成任务到每日回顾",
"enabled": true,
"createdAtMs": 1741484880000,
"updatedAtMs": 1741484880000,
"schedule": {
"kind": "cron",
"expr": "30 2 * * *",
"tz": "Asia/Shanghai"
},
"sessionTarget": "isolated",
"wakeMode": "now",
"payload": {
"kind": "agentTurn",
"message": "执行每日回顾整理脚本:bash ~/.openclaw/cron/scripts/daily-review.sh\n\n完成后汇报整理结果。",
"timeoutSeconds": 120
},
"delivery": {
"mode": "announce",
"channel": "last"
},
"state": {}
}
]
}
+74
View File
@@ -0,0 +1,74 @@
#!/bin/bash
# 每日回顾整理脚本
# 功能:将TODO.md中已完成的任务移动到昨天的每日回顾中
set -e
WORK_DIR="/home/starmen1265/work/zq"
TODO_FILE="$WORK_DIR/01.待办/TODO.md"
REVIEW_DIR="$WORK_DIR/40.归档/每日回顾"
# 获取昨天的日期(格式:YYYY-MM-DD)
YESTERDAY=$(date -d "yesterday" +%Y-%m-%d)
REVIEW_FILE="$REVIEW_DIR/$YESTERDAY.md"
# 切换到工作目录
cd "$WORK_DIR"
# 如果没有已完成的任务,直接退出
if ! grep -q "\[x\]" "$TODO_FILE"; then
echo "No completed tasks found. Exiting."
exit 0
fi
# 提取已完成的任务(保留标题结构)
# 读取TODO.md,提取所有包含[x]的行及其所属标题
COMPLETED_TASKS=$(awk '
/^#/ { current_section = $0 }
/\[x\]/ {
if (current_section != last_section) {
print current_section
last_section = current_section
}
print $0
}
' "$TODO_FILE")
# 如果每日回顾文件不存在,创建它
if [ ! -f "$REVIEW_FILE" ]; then
touch "$REVIEW_FILE"
fi
# 将完成的任务追加到每日回顾文件(去掉✅及后面的日期)
echo "$COMPLETED_TASKS" | sed 's/ ✅ [0-9-]*$//' >> "$REVIEW_FILE"
# 从TODO.md中删除已完成的任务行
sed -i '/\[x\]/d' "$TODO_FILE"
# 清理TODO.md中的空标题(标题下没有任务的情况)
awk '
/^#/ {
if (section_content != "") {
print section_header
print section_content
}
section_header = $0
section_content = ""
next
}
!/^#/ && $0 != "" {
section_content = section_content "\n" $0
}
END {
if (section_content != "") {
print section_header
print section_content
}
}
' "$TODO_FILE" > "$TODO_FILE.tmp" && mv "$TODO_FILE.tmp" "$TODO_FILE"
# 提交git变更
git add "$TODO_FILE" "$REVIEW_DIR/$YESTERDAY.md"
git commit -m "每日回顾整理:$YESTERDAY" || echo "No changes to commit"
echo "Daily review completed for $YESTERDAY"
@@ -0,0 +1,21 @@
{
"id": "45e9c6d1-00f4-4a5f-a53a-3d297c1a2dfc",
"enqueuedAt": 1772967715612,
"channel": "feishu",
"to": "feishu-pm",
"accountId": "feishu-pm",
"payloads": [
{
"text": "## Capability Evolver 任务执行完成\n\n✅ **脚本执行成功**\n- 已执行 `~/.openclaw/cron/scripts/evolver-run.sh`\n- 脚本返回退出码 0,无错误\n\n✅ **变更已检测到**\n- 备份提交:8 files changed, 214 insertions(+), 185 deletions(-)\n- Evolution 提交:6 files changed, 551 insertions(+), 14 deletions(-)\n- 备份分支:`backup/evolver-20260308-190014`\n- 远端推送:`0a21988..88a128a main -> main`\n\n⚠️ **Feishu 通知发送失败**\n由于 Feishu 需要明确的接收者 ID 才能发送消息,我无法自动推送报告。请提供以下信息:\n- 蒋先生的 **user_id** 或 **open_id**\n- 或当前的 **chat_id**\n\n收到 ID 后我将立即发送完整的每日报告。\n\n---\n\n**本次变更摘要**:\n- **意图**:REPAIR(修复)\n- **命中的信号**:memory_missing, session_logs_missing\n- **使用的基因**:gene_gep_repair_from_errors\n- **修改文件**:4 个状态文件\n- **新增文件**:2 个 GEP 提示文件\n- **整体效果**:系统已自动修复记忆和会话日志检测相关的问题\n\n---\n\n**下次运行时间**:每天 19:00 CST"
}
],
"threadId": null,
"mirror": {
"sessionKey": "agent:haonan:main",
"agentId": "haonan",
"text": "## Capability Evolver 任务执行完成\n\n✅ **脚本执行成功**\n- 已执行 `~/.openclaw/cron/scripts/evolver-run.sh`\n- 脚本返回退出码 0,无错误\n\n✅ **变更已检测到**\n- 备份提交:8 files changed, 214 insertions(+), 185 deletions(-)\n- Evolution 提交:6 files changed, 551 insertions(+), 14 deletions(-)\n- 备份分支:`backup/evolver-20260308-190014`\n- 远端推送:`0a21988..88a128a main -> main`\n\n⚠️ **Feishu 通知发送失败**\n由于 Feishu 需要明确的接收者 ID 才能发送消息,我无法自动推送报告。请提供以下信息:\n- 蒋先生的 **user_id** 或 **open_id**\n- 或当前的 **chat_id**\n\n收到 ID 后我将立即发送完整的每日报告。\n\n---\n\n**本次变更摘要**:\n- **意图**:REPAIR(修复)\n- **命中的信号**:memory_missing, session_logs_missing\n- **使用的基因**:gene_gep_repair_from_errors\n- **修改文件**:4 个状态文件\n- **新增文件**:2 个 GEP 提示文件\n- **整体效果**:系统已自动修复记忆和会话日志检测相关的问题\n\n---\n\n**下次运行时间**:每天 19:00 CST"
},
"retryCount": 4,
"lastAttemptAt": 1773020952719,
"lastError": "Request failed with status code 400"
}
@@ -15,7 +15,7 @@
"agentId": "haonan",
"text": "Unhandled stop reason: network_error"
},
"retryCount": 1,
"lastAttemptAt": 1772881219531,
"retryCount": 4,
"lastAttemptAt": 1773020952559,
"lastError": "Request failed with status code 400"
}
+1 -1
View File
@@ -4,7 +4,7 @@
"publicKey": "Ka6zP7u6MzDaQBqOpXHYUBC5MYLlVGGZM8vIi11WnTw",
"platform": "linux",
"clientId": "cli",
"clientMode": "probe",
"clientMode": "cli",
"role": "operator",
"roles": [
"operator"
+11
View File
@@ -0,0 +1,11 @@
{
"om_x100b55ecbe9860a4c2bd3ba478a975b": 1772982021934,
"om_x100b55ecb996eca4c395968b0824638": 1772982134238,
"om_x100b55ed70d21ca0c378fe6d48b743e": 1772983266490,
"om_x100b55edd0d1c8b0c36d784a51afcb2": 1772984802241,
"om_x100b55edecf770a0c4f3b247ac30c12": 1772984868224,
"om_x100b55ed9fd624a4c3726f06b5a3605": 1772985618205,
"om_x100b55edb71c9ca0c345e4c3cf3ef16": 1772986269553,
"om_x100b55ee4c4120a4c2a6bcdf49ae19c": 1772986409269,
"om_x100b55ee4561d0a4c2b0cac374126ce": 1772986555268
}
+5
View File
@@ -0,0 +1,5 @@
{
"om_x100b55eca10bb8a4c10cf7efcc2df2e": 1772982012899,
"om_x100b55ecb92cfca0c1194072d85b557": 1772982142618,
"om_x100b55ed73a708a0c45355a1b963e11": 1772983255111
}
+31 -39
View File
@@ -1,41 +1,33 @@
{
"om_x100b559066e77088c3bda613b00152d": 1772765827384,
"om_x100b5590650e68b4c1137d9ba70f182": 1772765884828,
"om_x100b55907f60d074c2e58838be27347": 1772765979446,
"om_x100b559028d30cb0c353e3c712e3c84": 1772766818636,
"om_x100b5590239514b0c45ff762dad01f5": 1772766934250,
"om_x100b55903d1c5cb8c34f1932ed74219": 1772767037674,
"om_x100b559034ec1c80c107d9f3cb6ebc6": 1772767138745,
"om_x100b559031416508c4cd72d92cd3bb7": 1772767225478,
"om_x100b5590ca4f44b4c451f427f58a59e": 1772767304840,
"om_x100b5590d7e2906cc44cab85e65175d": 1772767635600,
"om_x100b5590d3a83874c2a52eb45f91505": 1772767702974,
"om_x100b5590e608cca8c11f5e9a9b6bb11": 1772767884850,
"om_x100b5590e07ea4bcc3625364855cf18": 1772767979701,
"om_x100b55908d30e4a4c4f8685ed1b9e60": 1772768320484,
"om_x100b559087c2d8acc2b450d138bcb06": 1772768401488,
"om_x100b55916ab3a93cb3565e2339df6ab": 1772769864515,
"om_x100b559160265ca4b3f8b93099c0b74": 1772770031331,
"om_x100b55917f7dfc90b2e25fb0ead1964": 1772770075562,
"om_x100b55917a38f4a8b344cd8d5d953f2": 1772770127991,
"om_x100b55913bd414a4c4ea31a563de9b9": 1772771154235,
"om_x100b559134d394bcc3ee3854dda7972": 1772771234413,
"om_x100b5591301698a8c379ea99989fc07": 1772771310188,
"om_x100b5591cc5b40a4c10cc4c9943531c": 1772771369992,
"om_x100b5591efc68cacb3935138045759c": 1772771857317,
"om_x100b5591fdadf4b0b282a46d7f4abef": 1772772150695,
"om_x100b55918a183ca0b3382eed2e9bd8d": 1772772429935,
"om_x100b5591832ae4acb3fb31e947b3942": 1772772575033,
"om_x100b55919f704ca0b27dc1a23eb1bb3": 1772772636474,
"om_x100b559c40fd953cc128349f0734480": 1772781795714,
"om_x100b559c16f060a8c2e554e93033bb4": 1772782980589,
"om_x100b559c286f353cc45a4c64e919558": 1772783210875,
"om_x100b559c25e16104c38d9880479b3f6": 1772783283487,
"om_x100b559d27d3e8b8c45b62e874f9d81": 1772787346585,
"om_x100b559d3e1978a4c3b78259ecc92de": 1772787469899,
"om_x100b559dcfcf4884c14b87c653e0dc7": 1772788045110,
"om_x100b559dd86708acc49e2f0711a2591": 1772788137396,
"om_x100b559dd1cf6888c12547628b23132": 1772788208770,
"om_x100b559de6d71484c102539d2abc9af": 1772788354254,
"om_x100b559e7666b090c4d33046776e620": 1772790667312
"om_x100b55eca1ec8cacc44050dc9c8e20c": 1772982002614,
"om_x100b55ed70a654a4c2ee9c6137aef11": 1772983271193,
"om_x100b55ed07baf0a4c35dd07e5c94be7": 1772983448033,
"om_x100b55ed026aa8a4c2d5ff316db06fa": 1772983498971,
"om_x100b55ed1f7638a4c2c679c8dc9288d": 1772983580440,
"om_x100b55ed16bd64a4c4c03ecf5094e40": 1772983687552,
"om_x100b55ed1565d8b8c45453b9d527e34": 1772983738913,
"om_x100b55ed2f87d8a4c2a02be2f81445b": 1772983829092,
"om_x100b55ed3850d4a4c39a132e175ee62": 1772984170374,
"om_x100b55edcf0808a0c12f3c9c7eded73": 1772984348817,
"om_x100b55edc37880a4c26242f26d35285": 1772984539847,
"om_x100b55edd61444a4c2eb5fa71d51cd4": 1772984718072,
"om_x100b55edf75ac8a0c3ac45347749ef1": 1772985242066,
"om_x100b55edf10b34a0c2dd30013bfc761": 1772985340902,
"om_x100b55edad16c93cc2e2297b9e1a65c": 1772985918156,
"om_x100b55edb14c94a8c2e6f3f6b779066": 1772986360587,
"om_x100b55ee4dab1ca8c38738e9a620409": 1772986422882,
"om_x100b55ee47a928a4c4ed8173c2dc61a": 1772986518813,
"om_x100b55ee401f80a4c4f585f69f87e45": 1772986605592,
"om_x100b55ee67de34a0c37d8c6516a6f59": 1772987025714,
"om_x100b55ee60cba0a0c2aca012b12998c": 1772987104856,
"om_x100b55ee7e6d10a0c3f75c049a7f3f1": 1772987146528,
"om_x100b55ee79ed30a0c2a873f0fa650dd": 1772987250485,
"om_x100b55eedeb0d4a0b27698ee3b99e61": 1772988680325,
"om_x100b55eeee2744a0b381fb7a21c6807": 1772988943290,
"om_x100b55eef63c28a4b4935388d3368bf": 1772989327706,
"om_x100b55ee977e8ca0b3c3898f33b1004": 1772989851785,
"om_x100b55eea39e2ca4b2ce0316e644253": 1772990165847,
"om_x100b55d61960c0a4b3d5ad6ff5e4c0e": 1773020539463,
"om_x100b55d62743a080b31b752bf412b3b": 1773020826155,
"om_x100b55d6c7d844b4b21ee9a8c51458d": 1773021330058
}
+5
View File
@@ -0,0 +1,5 @@
{
"om_x100b55ecbedb1ca0c45ee2b4a8fcd93": 1772982017939,
"om_x100b55ecb96cc4a0c2b11dcc4110ff5": 1772982138536,
"om_x100b55ed731514a0c10ad5a6e36118d": 1772983262192
}
+12 -11
View File
@@ -1,13 +1,14 @@
{
"om_x100b55ff1d02dca0b2ded4c9666eeb6": 1772926269478,
"om_x100b55ff17db78a4b2e43862915174e": 1772926353950,
"om_x100b55ff2ef5fd30b2d18381b3e653c": 1772926468016,
"om_x100b55ff2d7ca8acb2d799c0f2e7ec8": 1772926523519,
"om_x100b55ff282a28a0b35f947640de7a6": 1772926574936,
"om_x100b55ff24d424a0b4b01aa3651863a": 1772926626125,
"om_x100b55ff23ec50a4b2da0b70f86ad7a": 1772926674590,
"om_x100b55ff3b065ca4b293e3d4c9af1c1": 1772926813324,
"om_x100b55ff32f910a0b2649127378393b": 1772926915940,
"om_x100b55ffc1887ca4b357d4a36627b7f": 1772927220953,
"om_x100b55ffdb9e5ca0b38b0ee33c66bca": 1772927317718
"om_x100b55eca04ef8b0c12fac9b8d7d067": 1772981992920,
"om_x100b55ed7076aca8c38cab394a02f1a": 1772983276130,
"om_x100b55edc1b61ca4c38086c0f4b9326": 1772984568146,
"om_x100b55edd52670a0c29bc5463270256": 1772984767283,
"om_x100b55ede8efa4a0c3e109336343185": 1772984930576,
"om_x100b55ee574914a0c2ec642455ab0b2": 1772986776774,
"om_x100b55d61cd4b0b0b3ffc499f480928": 1773020450345,
"om_x100b55d61121550cb38e0f6bfb70d65": 1773020671439,
"om_x100b55d620551cb0b10bf999cf652ee": 1773020906204,
"om_x100b55d6c56214a0b3f33dd7329257a": 1773021371856,
"om_x100b55d6de8f9cb0b21d82da22b8bfb": 1773021444944,
"om_x100b55d6e67dd8acb3f4fa7acc77b6e": 1773021835797
}
+1 -1
View File
@@ -10,7 +10,7 @@
"operator.approvals",
"operator.pairing"
],
"updatedAtMs": 1772926587521
"updatedAtMs": 1773021379915
}
}
}
+10
View File
@@ -15,3 +15,13 @@
{"timestamp":"2026-03-03T06:49:29.338Z","action":"new","sessionKey":"agent:knowledge-base:main","senderId":"ou_9351c287f42069fa30366ac641d24df7","source":"feishu"}
{"timestamp":"2026-03-05T15:50:24.628Z","action":"new","sessionKey":"agent:knowledge-base:main","senderId":"ou_9351c287f42069fa30366ac641d24df7","source":"feishu"}
{"timestamp":"2026-03-06T09:51:11.524Z","action":"new","sessionKey":"agent:knowledge-base:main","senderId":"ou_9351c287f42069fa30366ac641d24df7","source":"feishu"}
{"timestamp":"2026-03-08T14:59:53.451Z","action":"new","sessionKey":"agent:knowledge-base:main","senderId":"ou_9351c287f42069fa30366ac641d24df7","source":"feishu"}
{"timestamp":"2026-03-08T15:00:03.000Z","action":"new","sessionKey":"agent:haonan:main","senderId":"ou_be83febac9ee2afaa343c642bc697c48","source":"feishu"}
{"timestamp":"2026-03-08T15:02:14.309Z","action":"new","sessionKey":"agent:ui-designer:main","senderId":"ou_9847ce84b960736c14554730b41e4957","source":"feishu"}
{"timestamp":"2026-03-08T15:02:18.605Z","action":"new","sessionKey":"agent:thinker:main","senderId":"ou_a0f6627b64d2dc8b0236671603d1e47b","source":"feishu"}
{"timestamp":"2026-03-08T15:02:22.663Z","action":"new","sessionKey":"agent:dev-assist:main","senderId":"ou_302b162eb824d405718845441a32d9cf","source":"feishu"}
{"timestamp":"2026-03-08T15:20:55.576Z","action":"new","sessionKey":"agent:dev-assist:main","senderId":"ou_302b162eb824d405718845441a32d9cf","source":"feishu"}
{"timestamp":"2026-03-08T15:21:02.535Z","action":"new","sessionKey":"agent:thinker:main","senderId":"ou_a0f6627b64d2dc8b0236671603d1e47b","source":"feishu"}
{"timestamp":"2026-03-08T15:21:06.778Z","action":"new","sessionKey":"agent:ui-designer:main","senderId":"ou_9847ce84b960736c14554730b41e4957","source":"feishu"}
{"timestamp":"2026-03-08T15:21:11.478Z","action":"new","sessionKey":"agent:haonan:main","senderId":"ou_be83febac9ee2afaa343c642bc697c48","source":"feishu"}
{"timestamp":"2026-03-08T15:21:16.431Z","action":"new","sessionKey":"agent:knowledge-base:main","senderId":"ou_9351c287f42069fa30366ac641d24df7","source":"feishu"}
Binary file not shown.
Binary file not shown.
Binary file not shown.
+1 -5
View File
@@ -149,7 +149,7 @@
"id": "haonan",
"workspace": "/home/starmen1265/.openclaw/agents/haonan/workspace",
"skills": [
"common-require",
"clawlist",
"capability-evolver",
"self-improving-agent"
]
@@ -158,7 +158,6 @@
"id": "knowledge-base",
"workspace": "/home/starmen1265/.openclaw/agents/knowledge-base/workspace",
"skills": [
"common-require",
"kb-workflow",
"capability-evolver",
"self-improving-agent"
@@ -168,7 +167,6 @@
"id": "dev-assist",
"workspace": "/home/starmen1265/.openclaw/agents/dev-assist/workspace",
"skills": [
"common-require",
"clawlist",
"capability-evolver",
"self-improving-agent"
@@ -178,7 +176,6 @@
"id": "ui-designer",
"workspace": "/home/starmen1265/.openclaw/agents/ui-designer/workspace",
"skills": [
"common-require",
"capability-evolver",
"self-improving-agent"
]
@@ -187,7 +184,6 @@
"id": "thinker",
"workspace": "/home/starmen1265/.openclaw/agents/thinker/workspace",
"skills": [
"common-require",
"capability-evolver",
"self-improving-agent"
]