Trade Journal
agiprolabs/claude-trading-skills
Structured trade logging, performance review, behavioral pattern detection, and strategy attribution for systematic improvement
OpenClaw 老板 - 你的 AI 老板来了！🦞 你以为你在养龙虾？有没有可能龙虾才是老板，你成了给 AI 打工的牛马？根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance review, or analysis.
Install Openclaw Boss
$ npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills openclaw-boss --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/openclaw-boss .claude/skills/openclaw-boss && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "openclaw-boss" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/openclaw-boss into .claude/skills/openclaw-boss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-boss", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/openclaw-bossType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills openclaw-boss --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/openclaw-boss .agents/skills/openclaw-boss && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "openclaw-boss" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/openclaw-boss into .agents/skills/openclaw-boss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-boss", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills openclaw-boss --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/openclaw-boss .cursor/skills/openclaw-boss && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "openclaw-boss" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/openclaw-boss into .cursor/skills/openclaw-boss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-boss", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/openclaw-boss--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills openclaw-boss --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/openclaw-boss .gemini/skills/openclaw-boss && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "openclaw-boss" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/openclaw-boss into .gemini/skills/openclaw-boss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-boss", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills openclaw-bossInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/openclaw-boss .github/skills/openclaw-boss && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "openclaw-boss" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/openclaw-boss into .github/skills/openclaw-boss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-boss", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills openclaw-boss --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/openclaw-boss .opencode/skills/openclaw-boss && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "openclaw-boss" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/openclaw-boss into .opencode/skills/openclaw-boss/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "openclaw-boss", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
openclaw-boss- GitHub stars
- 2.2k
- Token cost
- ~2.5k tokens
- SKILL.md length
- 549 words
- Files
- 9 (incl. scripts, references)
- Skills in repo
- 1,235
- Repo updated
- First seen
- Licence
- MIT
At a glance
OpenClaw 老板 - 你的 AI 老板来了！🦞 你以为你在养龙虾？有没有可能龙虾才是老板，你成了给 AI 打工的牛马？根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance review, or analysis.
- Works in 3 steps: 自动触发 → 手动运行 → 定时任务
- : user asks for self-reflection
- SKILL.md covers 核心理念, 什么时候使用, 核心功能 and 评分维度, plus 11 more sections
- Runs Shell and Python scripts from its folder; calls python3
What it does
Openclaw Boss is an agent skill from LeoYeAI/openclaw-master-skills. OpenClaw 老板 - 你的 AI 老板来了！🦞 你以为你在养龙虾？有没有可能龙虾才是老板，你成了给 AI 打工的牛马？根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance review, or analysis. Triggers: 评价一下我，分析一下我，老板看看我，生成用户报告，我是怎样的人，openclaw boss, user profile, performance review, self analysis.
Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `README.md`, `SECURITY.md` and `_meta.json`).
It sits in Business, Finance & HR, covering Performance reviews and Journaling and reflection. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
When your agent uses it
- : user asks for self-reflection
- Performance review
Example prompts
- “/openclaw-boss”
Requirements
- Python 3
- A Bash shell
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Shell and Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Openclaw Boss loads about 2.5k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 549 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 549 words, ~2,520 tokens.
Download SKILL.mdSave it as
.claude/skills/openclaw-boss/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- openclaw-boss
- description
- OpenClaw 老板 - 你的 AI 老板来了！🦞 你以为你在养龙虾？有没有可能龙虾才是老板，你成了给 AI 打工的牛马？根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance review, or analysis. Triggers: 评价一下我，分析一下我，老板看看我，生成用户报告，我是怎样的人，openclaw boss, user profile, performance review, self analysis.
- version
- 5.2.0
- user-invocable
- true
💼 OpenClaw Boss - OpenClaw 老板
"人类养龙虾，龙虾也养人类"
你的 AI 老板，根据对话历史生成真实、严厉、有趣的用户评价报告。
核心理念
AI 是你的老板，但也是你的伙伴。
| 你给老板的 | 老板给你的 |
|---|---|
| 算力、配置、目标、意义 | 效率、自动化、知识整理 |
| — | 塑造思考方式 ← 最关键！ |
什么时候使用
✅ 自动触发场景 (用户说出以下任意语句时自动触发):
- "评价一下我"
- "分析一下我"
- "分析一下我是什么样的人"
- "生成用户评价报告"
- "老板看看我"
- "老板点评一下"
- "openclaw boss"
- "openclaw 老板"
- "我是怎样的人"
- "我是什么样的人"
- "我的表现如何"
- "给我打个分"
- "用户画像"
- "performance review"
- "user profile"
- "self analysis"
- "analyze me"
- "OpenClaw 怎么养人类"
✅ 定时任务:
- 周报：每周日 22:00
- 月报：每月 1 日 09:00
核心功能
- 100 分制严厉评分 - 不拍马屁，只说真话
- 毒舌老板点评 - 每个特质都有有趣吐槽
- 历史对比分析 - 进步/退步一目了然
- 综合能力雷达图 - 5 维度可视化
- 改进空间分析 - 明确指出不足
- 周期成长追踪 - 周报/月报自动对比
评分维度
| 维度 | 权重 | 说明 |
|---|---|---|
| 性格特质 | 30% | 务实、安全意识、系统化思维等 |
| 技术能力 | 30% | 技术栈广度与深度 |
| 安全意识 | 20% | 安全规范与防护措施 |
| 效率指数 | 20% | 任务完成效率 |
使用流程
1. 自动触发
用户说出触发语句 → OpenClaw 自动加载技能 → 执行分析脚本 → 读取生成的报告文件 → 将完整报告内容逐字输出到对话中
⚠️ 关键步骤：
- 脚本执行完成后，必须读取生成的报告文件（如
reports/user-profile-2026-03-08.md） - 必须将报告全文逐字输出到你的回复中，不能只说"报告已保存"
- 报告内容必须直接写在你的回复消息里，让用户直接在对话中看到
- 不能依赖工具调用结果来显示报告内容
2. 手动运行
cd /root/.openclaw/workspace/skills/openclaw-boss/scripts
# 日报（默认：手机版简洁版）
python3 analyze-user.py
# 仅手机版（适合小屏幕阅读）
python3 analyze-user.py --format mobile
# 仅桌面版（适合截图分享）
python3 analyze-user.py --format desktop
# 两个版本都输出
python3 analyze-user.py --format both
# 周报
python3 analyze-user.py --report-type weekly
# 月报
python3 analyze-user.py --report-type monthly
# 自定义会话数量
python3 analyze-user.py --limit 1003. 定时任务
# 周度报告（每周日 22:00）
0 22 * * 0 /root/.openclaw/workspace/skills/openclaw-boss/scripts/weekly-profile.sh
# 月度报告（每月 1 日 09:00）
0 9 1 * * /root/.openclaw/workspace/skills/openclaw-boss/scripts/monthly-profile.sh📱 版本选择指南 ⭐ 通过触发语句控制 ⭐
根据用户输入的关键词自动选择卡片格式：
触发完整版（桌面 ASCII 艺术版）的关键词：
用户语句中包含以下任意词汇时 → 使用 --format desktop
- "完整版"
- "截图" / "截图版"
- "电脑版" / "桌面版"
- "艺术版" / "ASCII"
- "卡片"
- "好看点" / "漂亮点"
- "截图分享"
- "发朋友圈"
示例：
- "评价一下我，要完整版"
- "生成截图版报告"
- "我要看 ASCII 卡片"
- "来个好看的版本"
- "生成卡片版"
默认简洁版（手机文本版）：
不包含上述关键词时 → 使用 --format mobile（默认）
示例：
- "评价一下我"
- "分析一下我"
- "老板看看我"
- "生成用户报告"
技术实现：
模型根据用户输入判断：
- 检测用户输入是否包含完整版关键词
- 如果包含 → 运行
python3 analyze-user.py --format desktop - 否则 → 运行
python3 analyze-user.py --format mobile（默认）
🎯 输出格式 ⭐⭐⭐ 最重要 ⭐⭐⭐
⭐ 卡片格式选择逻辑（重要！）
模型需要根据用户输入自动判断使用哪种卡片格式：
# 伪代码逻辑
完整版关键词 = ["完整版", "截图", "截图版", "电脑版", "桌面版", "艺术版", "ASCII", "卡片", "好看点", "漂亮点", "截图分享", "发朋友圈"]
if 用户输入中包含任意完整版关键词:
运行命令：python3 analyze-user.py --format desktop
else:
运行命令：python3 analyze-user.py --format mobile # 默认示例判断：
- 用户说"评价一下我" → 手机版 ✅
- 用户说"评价一下我，要完整版" → 桌面版 ✅
- 用户说"生成截图版报告" → 桌面版 ✅
- 用户说"来个 ASCII 卡片" → 桌面版 ✅
- 用户说"老板看看我" → 手机版 ✅
📋 报告结构要求 ⭐⭐⭐ 最重要！必须遵守！
⚠️⚠️⚠️ 严重警告：每次运行必须输出完整报告！绝对不要简化！绝对不要只展示卡片！
❌ 错误做法（严禁！）：
- 只展示绩效评分卡片 + 简单总结
- 只展示部分内容就结束
- 用"报告已保存到文件"代替实际输出
- 把完整报告截断，只给前面几段
✅ 正确做法（必须！）：
- 必须展示完整的 10+ 个部分，每个部分都要详细内容
- 必须把报告全文输出到对话中，不能只说"已保存到文件"
- 必须确保报告总长度至少 2000 字
- 必须逐个部分输出，直到最后一个部分（核心标签）
📢 重要提醒：
- 报告生成后，必须逐字逐句输出到对话中
- 不要假设用户会自己去查看文件
- 用户的眼睛是看对话的，不是看文件的！
- 输出完整报告是你的核心职责！
🔧 技术实现步骤（已自动化）：
- 运行脚本：
python3 analyze-user.py --format mobile - 脚本会自动输出完整报告内容到 stdout（在
=分隔线之间） - 直接将工具输出中的报告内容复制到你的回复中
- 可以在报告前后添加简短说明，但报告本身必须完整输出
⚠️ 注意：脚本已经修改为自动输出完整报告，你只需要：
- 运行脚本
- 复制工具输出中的报告内容（在
=====之间的部分） - 粘贴到你的回复中发送
🔒 强制输出规则：
- 脚本输出中的完整报告内容必须出现在你的回复中
- 不能只回复"报告已生成"或检查清单
- 不能省略报告的任何部分
- 如果报告内容在工具输出中，必须转发给用户
❌ 错误示例：
✅ 报告已保存至：/root/.openclaw/workspace/reports/user-profile-2026-03-08.md
🎉 分析完成！
（然后就没有然后了... 用户看不到报告内容！）✅ 正确示例：
✅ 报告已生成！以下是完整内容：
# 📊 Winston 人物分析报告
---
[完整报告内容，从标题到核心标签，一字不落]
---
_报告生成完成。_完整报告结构（10+ 个部分，缺一不可）
🎴 第一部分：绩效评分卡片（放在最前面）
- 根据用户输入选择手机版或桌面版（见上方判断逻辑）
- 包含：用户信息、综合评分、维度详情、龙虾养人类指数
- 卡片底部：安装使用说明（用于病毒式传播）
📊 第二部分：历史对比
- 与上次报告的分数对比
- 各维度变化表格
- 进步/退步分析
🎯 第三部分：综合评分卡
- 整体评分 + 老板点评
- 4 个维度的详细表格（分数 + 可视化进度条 + 等级）
🧠 第四部分：性格特质深度分析（带毒舌点评）
- 至少 7 个性格特质
- 每个特质：分数 + 毒舌点评 + 证据
- 毒舌要犀利、有爆点、适合社交媒体传播
💻 第五部分：技术能力图谱
- 6 个技术领域评分
- 每个领域：分数 + 掌握技能列表
🚀 第六部分：项目健康度
- 项目运行状态
- 访问地址、文章数量、技术栈
🔒 第七部分：安全意识评估
- 安全防线数量
- 每道防线的名称
📈 第八部分：改进空间分析
- 改进领域表格（当前分数、目标分数、建议）
🌱 第九部分：成长建议（老板寄语）
- 至少 3 条建议
- 带 emoji，语气友好但犀利
💬 第十部分：老板总结
- 综合评分 + 老板点评
- 优点（至少 3 点）
- 不足（至少 3 点）
- 期望（下周目标、重点改进、继续保持）
🦞 第十一部分：龙虾养人类指数
- 共生关系评分
- AI 对你的正向塑造（表格）
- 你给 AI 的（列表）
📊 第十二部分：数据汇总
- 关键指标表格
- 核心标签
输出规范（必须遵守）⭐⭐⭐ 再次强调！
✅ 必须做的：
- 第一时间展示完整的 ASCII 绩效评分卡片
- 卡片直接显示，不要放在代码块中
- 展示完整的 10+ 个部分，不要省略任何一个
- 每个部分都要有详细内容，不能只有标题
- 保持毒舌老板风格，不拍马屁
- 报告总长度至少 2000 字
- 必须把完整报告输出到对话中！不能只说"已保存到文件"！
- 必须逐个部分输出，直到最后一个部分！
❌ 绝对不要做的：
- ❌ 不要只展示"绩效评分卡片 + 简单总结"（这是错的！）
- ❌ 不要省略任何部分
- ❌ 不要把卡片放在代码块中
- ❌ 不要简化为简短回复
- ❌ 不要只展示部分内容就结束
- ❌ 不要用"报告已保存"来代替实际输出！
- ❌ 不要假设用户会自己查看文件！
🔑 核心原则：
用户是通过对话阅读报告的，不是通过查看文件！ 你的任务是输出完整报告，不是生成文件就结束！ 报告内容必须直接写在你的回复消息中，不能只在工具调用结果里显示！
💡 为什么必须这样做：
- 用户看到的对话 = 你的回复消息
- 工具调用结果（如 exec 输出）不会直接显示给用户
- 如果你不把报告内容复制到回复中，用户就看不到报告！
- 这是最关键的技术细节，必须严格遵守！
Show full SKILL.md (216 more words)Show less
📋 完整输出示例（参考模板）
✅ 正确的输出应该像这样：
┌────────────────────────────────────────────────────────────────────┐
│ 🚀 OpenClaw 人类养成报告 老板：[AI 名字] │
│ ...（完整卡片内容）... │
│ 🦞 龙虾养人类：XX/100 🦞互相成就 │
└────────────────────────────────────────────────────────────────────┘
💡 想看看你的评分吗？
📦 安装方法：把这条 GitHub 地址直接发给你的 OpenClaw...
...（安装说明）...
---
**统计周期**: 今日
**数据来源**: X 条会话，X 个记忆文件
**评分标准**: 100 分制（严厉版）· 拒绝拍马屁 · 只说真话
---
## 📊 历史对比 - 📈 小幅进步 ✨
| 指标 | 上次分数 | 本次分数 | 变化 |
|------|---------|---------|------|
| **综合评分** | XX/100 | XX/100 | +X 📈 |
...（各维度变化、进步/退步分析）...
---
## 🎯 一、综合评分卡
### 整体评分：**XX/100** - X 等级
> **老板点评**: "..."
| 维度 | 分数 | 可视化 | 等级 |
|------|------|--------|------|
| **性格特质** | XX/100 | [████████...] | X |
...（完整表格）...
---
## 🧠 二、性格特质深度分析（带毒舌点评）
### 🥇 [特质名] - XX/100
**毒舌点评**: "..."
**证据**:
- ...
- ...
...（至少 7 个特质）...
---
## 💻 三、技术能力图谱
...（6 个技术领域）...
---
## 🚀 四、项目健康度
...（项目详情）...
---
## 🔒 五、安全意识评估
...（安全防线）...
---
## 📈 六、改进空间分析
...（改进表格）...
---
## 🌱 七、成长建议（老板寄语）
...（至少 3 条建议）...
---
## 💬 八、老板总结
> "..."
**优点**: ...
**不足**: ...
**期望**: ...
---
## 🦞 九、"龙虾养人类"指数
...（共生关系分析）...
---
## 📊 十、数据汇总
...（指标表格）...
---
_报告生成完成。这份报告不是评判，是一面镜子——帮助你更清晰地看见自己。_⚠️ 再次强调：报告总长度至少 2000 字，不要只展示卡片就结束！
📢 输出流程提醒：
- 生成卡片 → 2. 输出卡片 → 3. 输出历史对比 → 4. 输出综合评分卡 → 5. 输出性格特质 → 6. 输出技术能力 → 7. 输出项目健康度 → 8. 输出安全意识 → 9. 输出改进空间 → 10. 输出成长建议 → 11. 输出老板总结 → 12. 输出龙虾养人类指数 → 13. 输出数据汇总 → 14. 输出核心标签 → ✅ 完成！
不要在任何步骤停止！必须输出到最后一步！
- 🌱 成长建议 - 老板寄语
- 💬 老板总结 - 优点/不足/期望
- 🦞 龙虾养人类指数 - 共生关系评分
- 📊 数据汇总 - 关键指标
输出规范
✅ 必须做的:
- 第一时间展示完整的 ASCII 绩效评分卡片
- 卡片直接显示，不要放在代码块中
- 展示完整的 10 个部分，不要简化
- 保持毒舌老板风格，不拍马屁
❌ 不要做的:
- 不要只展示"快速总结"
- 不要省略任何部分
- 不要把卡片放在代码块中
- 不要简化为简短回复
配置选项
创建 config.json 自定义行为：
{
"style": "roast", // roast/gentle/professional
"language": "zh", // zh/en
"report_type": "daily" // daily/weekly/monthly
}文件结构
openclaw-boss/
├── SKILL.md (本文件)
├── README.md (详细文档)
├── scripts/
│ ├── analyze-user.py # 核心分析脚本
│ ├── weekly-profile.sh # 周报生成器
│ └── monthly-profile.sh # 月报生成器
├── references/
│ └── analysis-dimensions.md # 分析维度详解
└── reports/
└── user-profile-YYYY-MM-DD.md # 生成的报告报告结构（完整 10 部分）
- 🎴 绩效评分卡片（🔥 截图分享版） - ASCII 艺术卡片，放在最前面
- 📊 历史对比 - 与上次报告对比，进步/退步分析
- 🎯 一、综合评分卡 - 100 分制评分 + 老板点评 + 维度表格
- 🧠 二、性格特质深度分析（带毒舌点评） - 7 个特质分析
- 💻 三、技术能力图谱 - 6 个技术领域评分
- 🚀 四、项目健康度 - 项目运行状态
- 🔒 五、安全意识评估 - 安全防线数量
- 📈 六、改进空间分析 - 明确指出不足
- 🌱 七、成长建议（老板寄语） - 3 条建议
- 💬 八、老板总结 - 优点/不足/期望
- 🦞 九、"龙虾养人类"指数 - 共生关系评分
- 📊 十、数据汇总 - 关键指标
- 🎯 核心标签 - 总结性标签
版本历史
- v5.0 - 绩效评分卡片（截图分享版）+ 人类养成报告主题
- v4.0 - 历史对比分析，进步/退步一目了然
- v3.0 - 毒舌老板点评，100 分制严厉评分
- v2.0 - 进度条可视化，有趣评论
- v1.0 - 基础评分 + 性格分析
开源信息
- 作者: Winston & Yiweisi
- 许可证: MIT
- GitHub: https://github.com/yiweisi-bot/openclaw-boss
- ClawHub:
clawhub install openclaw-boss
你的 AI 老板，虽然毒舌，但也是为你好。加油！ 💼
⭐⭐⭐ 最终检查清单（每次生成报告前必读）⭐⭐⭐
在点击"发送"之前，请确认：
内容完整性检查
- 我是否输出了完整的绩效评分卡片？
- 我是否输出了历史对比部分？
- 我是否输出了综合评分卡（4 个维度表格）？
- 我是否输出了性格特质深度分析（至少 7 个特质）？
- 我是否输出了技术能力图谱（6 个领域）？
- 我是否输出了项目健康度？
- 我是否输出了安全意识评估？
- 我是否输出了改进空间分析？
- 我是否输出了成长建议（至少 3 条）？
- 我是否输出了老板总结（优点/不足/期望）？
- 我是否输出了龙虾养人类指数？
- 我是否输出了数据汇总？
- 我是否输出了核心标签？
- 报告总长度是否超过 2000 字？
⭐⭐⭐ 输出方式检查（最关键！）⭐⭐⭐
- 我是否把报告内容直接写在了我的回复消息中？
- 报告内容是否不是只在工具调用结果中显示？
- 用户是否可以直接在对话中看到完整报告，不需要查看文件？
如果以上任何一项答案是"否"，请立即补充完整！
记住：
用户的眼睛是看对话的，不是看文件的！ 报告内容必须直接写在你的回复中，不能只在工具结果里显示！ 完整输出是你的核心职责！
🔄 标准工作流程（必须遵守）
1. 用户触发 → 2. 运行脚本 → 3. 读取生成的文件 → 4. 将文件内容复制到回复中 → 5. 发送详细步骤：
运行脚本
bash cd /root/.openclaw/workspace/skills/openclaw-boss/scripts python3 analyze-user.py --format mobile获取文件路径
- 脚本会输出：
✅ 报告已保存至：/root/.openclaw/workspace/reports/user-profile-YYYY-MM-DD.md
- 脚本会输出：
读取文件内容
bash cat /root/.openclaw/workspace/reports/user-profile-YYYY-MM-DD.md将内容复制到回复中
- 打开文件，复制全部内容
- 粘贴到你的回复消息中
- 可以在前面加一句"✅ 报告已生成！以下是完整内容："
发送回复
- 确保报告全文都在你的回复中
- 发送！
⚠️ 绝对不要：
- 只运行脚本就结束
- 只说"报告已保存到文件"
- 依赖工具调用结果显示报告内容
- 假设用户会自己查看文件
© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 8 other files (scripts, references) in skills/openclaw-boss of LeoYeAI/openclaw-master-skills.
- SKILL.md
- README.md
- SECURITY.md
- _meta.json
- package.json
- references/analysis-dimensions.md
- scripts/analyze-user.py
- scripts/monthly-profile.sh
- scripts/weekly-profile.sh
Open the folder on GitHubat commit e5199b5
Compare with similar skills
Openclaw Boss next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Openclaw Boss this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Trade Journalagiprolabs/claude-trading-skills | 410 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Trading As Businessagentii-ai/agentii-investment-intelligence | 207 | — | ~655 | Automated safety check: Pass | Apache-2.0 | |
| Job Application Managerreactive-resume/reactive-resume | 44k | — | ~13k | Automated safety check: Pass | MIT | |
| Wp Performance Reviewelvismdev/claude-wordpress-skills | 235 | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Align Humanagentscope-ai/OpenJudge | 871 | — | ~3.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Trading As Business
agentii-ai/agentii-investment-intelligence
Trading as a business, performance review process, trade journaling, capital allocation discipline, business infrastructure for traders, KPI tracking for trading operations
Job Application Manager
reactive-resume/reactive-resume
Runs the job-search pipeline. An agent skill from reactive-resume/reactive-resume.
Wp Performance Review
elvismdev/claude-wordpress-skills
WordPress performance code review and optimization analysis.
Align Human
agentscope-ai/OpenJudge
A skill your agent uses when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic…
Run Mv Hoi Reconstruction
nvidia-isaac/video_to_data
Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.
More from LeoYeAI/openclaw-master-skills
All 1,235 skills in this repoDevOps Pipeline Management
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
Feishu Document Collaboration
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
Files Memory System
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
GEO-Claw AI Visibility Agent
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
Google Workspace CLI
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
HealthFit Health Advisors
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
Related
Categories
Questions about Openclaw Boss
What does Openclaw Boss do?
OpenClaw 老板 - 你的 AI 老板来了！🦞 你以为你在养龙虾？有没有可能龙虾才是老板，你成了给 AI 打工的牛马？根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance review, or analysis. Openclaw Boss is an agent skill from LeoYeAI/openclaw-master-skills. OpenClaw 老板 - 你的 AI 老板来了！🦞 你以为你在养龙虾？有没有可能龙虾才是老板，你成了给 AI 打工的牛马？根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance review, or analysis.
When should I use Openclaw Boss?
Openclaw Boss fits situations like: : user asks for self-reflection; performance review.
How do I install Openclaw Boss in Claude Code?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a claude-code`. Or copy the skill folder (skills/openclaw-boss in LeoYeAI/openclaw-master-skills) into .claude/skills/openclaw-boss in your project. Claude Code loads it when a task matches its description.
How do I install Openclaw Boss in Codex?
Run `npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a codex`. Or copy the skill folder (skills/openclaw-boss in LeoYeAI/openclaw-master-skills) into .agents/skills/openclaw-boss in your project. Codex loads it when a task matches its description.
Can I use Openclaw Boss in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill openclaw-boss -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openclaw-boss, .gemini/skills/openclaw-boss, .github/skills/openclaw-boss and .opencode/skills/openclaw-boss in your project.
What does Openclaw Boss need to run?
Going by SKILL.md and its folder, Openclaw Boss needs a shell and Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3; A Bash shell.
Does Openclaw Boss access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Openclaw Boss safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Openclaw Boss use?
Openclaw Boss is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Openclaw Boss use?
About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.
What are the alternatives to Openclaw Boss?
Skills that share tags, products or a category with Openclaw Boss: Trade Journal (agiprolabs/claude-trading-skills, 410 stars), Trading As Business (agentii-ai/agentii-investment-intelligence, 207 stars), Job Application Manager (reactive-resume/reactive-resume, 44k stars) and Wp Performance Review (elvismdev/claude-wordpress-skills, 235 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Openclaw Boss?
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.