REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/jamesshi96-project-butler)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 project-butler | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | JamesShi96 | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 377 | 468,733 | 234,332 | 150,287 | 144,566 |
| 最近代码更新 | 2026年7月29日 | 2026年11月19日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
JamesShi96 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude CodeCodexCursor
依据开发者 README 和 repo 中的文件夹
GitHub account JamesShi96 (person), 4 years old
★ 377 stars, few users so far · code last changed 2026年7月29日
1 scripts that can run on a computer: scripts/check-update.sh
No internet calls found in the scripts
Scripts that touch settings folders (~/.claude or settings.json): scripts/check-update.sh
Checked automatically from the repo files at commit 246dd66 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (565). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /project-butler,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 project-butler 文件夹放到 ~/.agents/skills/project-butler
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 project-butler
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
显示前 8,000 个字符 · 在 GitHub 打开完整文件
---
name: project-butler
description: "Project memory workflow for init/upgrade, profile-aware setup, end session, normal/full close, file organization, document archiving, language switching, versioned update logs, rule review, status, wiki sync, and context recovery. Use for /project-butler, setup/初始化, foundation setup, profile setup, end session/收工, normal close, full close, foundation repair, organize files/整理文件, change language/切换语言, continue/接着上次, continue full context/全面回顾, review claude, sync wiki, status. Maintains project memory files. Runs version freshness check before trigger routing."
---
# Project Butler — Project Memory Stack
Initialize standardized project memory:
```
上层(稳定原则)
┌─────────────────────────────────────┐
│ CLAUDE.md(项目宪法)← 人工确认 │
│ ↑ candidates(AI 自动收集候选) │
└─────────────────────────────────────┘
↑ 抽象沉淀
中层(当前快照)
┌─────────────────────────────────────┐
│ PROJECT.md(项目 Wiki)← AI 自动同步 │
│ 概览 / 结构 / 模块状态 / 文件索引 │
│ STRUCTURE.md(文件管理规则)← AI 自动│
│ 目录规则 / 匹配条件 / 整理历史 │
│ UPDATE_LOG.md(里程碑变化)← AI 自动 │
│ DOCS.md(文档索引 + 元数据)← AI 自动 │
│ .claude/project-profile.json(画像配置)│
│ .claude/profile-pending.json(画像待处理)│
└─────────────────────────────────────┘
↑ 状态汇总
下层(事实流水)
┌────────────────────┐ ┌────────────────────┐
│ log/(会话日志) │ │ TODO.md(执行清单)│
│ raw + summaries │ │ owner/deadline/ │
│ + archive(分级) │ │ deps │
└────────────────────┘ └────────────────────┘
↓
session-handoff.md(下次接手点)
```
Core idea: bottom feeds top, top constrains bottom. Logs and TODOs are raw facts. Handoff marks the next resume point. Wiki is the current snapshot. Structure manages file organization. Docs index manages document output. Update Log records versioned milestone changes. Constitution is stable principles.
Supports 3 language modes: English (`en`), Chinese (`zh`), or bilingual. All content adapts to the selected language.
---
## Step -1: Version Freshness Check (always run first)
<EXTREMELY_IMPORTANT>
Before any other step, read `references/update-check.md` and execute
the version freshness check described there.
- If the check prints nothing → continue to Step 0 silently.
- If the check prints a `VERSION_NOTICE:` block → do NOT print it
verbatim. Instead present ONE interactive update prompt with
AskUserQuestion, worded in the project's CLAUDE.md language:
- Question: "project-butler is N commits behind upstream. Update now?"
(read N from the `VERSION_NOTICE:` line).
- Option "Update now" → run
`bash "<SKILL_DIR>/scripts/check-update.sh" --pull "<SKILL_DIR>"`
as a single Bash call, then report its `UPDATE_OK` / `UPDATE_FAILED`
output to the user.
- Option "Remind me later" → do nothing; the script throttles the
prompt to at most once per 24h, so it will not ask again today.
- Option "Stop reminding" → tell the user to set
`PROJECT_BUTLER_NO_UPDATE_CHECK=1` to silence permanently.
Present this prompt once, before the triggered work. The script already
limits it to once per 24h, so do not add your own suppression.
- Never run `git pull` on the skill directory yourself EXCEPT as the
"Update now" action the user explicitly selected (which runs the
`--pull` subcommand above).
- If you cannot find the "Base directory for this skill: <path>" line
in the current skill loading prompt, skip the check silently and
continue to Step 0.
</EXTREMELY_IMPORTANT>
---
## Step 0: Trigger Routing
Determine how this skill was triggered:
**A. "整理文件" / "organize files":**
1. Read `references/file-reorganization.md`
2. Execute **Mode A: Four-Phase Organize** (Discover → Ask or Plan → Plan → Execute)
3. Report and stop
**B. "收工" / "end session" / "结束会话" / "we're done" / "wrap up" / "done for today" / "normal close" / "full close":**
1. Execute the **End Session Flow** below (inline)
2. Report and stop
**C. Initialization (/project-butler, 初始化项目, setup project, etc.):**
→ Continue to **Init Flow** below
**D. "切换语言" / "change language":**
1. Read `references/language-change.md` + `references/language-adaptation.md`
2. Execute the Language Change Protocol
3. Report and stop
**E. "continue" / "接着上次" / "上次做到哪了":**
1. Read `references/continue.md`
2. Execute the Continue process (recover last session context)
3. Report and stop
**F. "continue full context" / "全面回顾" / "项目全景" / "full context":**
1. Read `references/continue-full-context.md`
2. Execute the Continue Full Context process (full project trajectory recovery)
3. Report and stop
**G. "review claude" / "审查规则" / "更新宪法" / "check the rules":**
1. Read `.claude/candidates.md`
2. Present pending candidates one by one for accept / reject / rewrite
3. For accepted or rewritten candidates, append to CLAUDE.md only after explicit user confirmation
4. Move processed candidates to adopted or rejected sections in `.claude/candidates.md`
5. Report and stop
**H. "sync wiki" / "同步项目" / "update overview" / "refresh overview":**
1. Read PROJECT.md, STRUCTURE.md, UPDATE_LOG.md, DOCS.md, TODO.md, and session-handoff.md if present
2. Rescan current project files and update PROJECT.md current snapshot, module map, file structure, key file index, links, and progress sections
3. Preserve user-authored content where possible
4. Report and stop
**I. "status" / "项目现状" / "where are we":**
1. Read PROJECT.md and session-handoff.md
2. Also read TODO.md and latest UPDATE_LOG.md entry if present
3. If `.claude/project-profile.json` or `.claude/profile-pending.json` exists, read `references/project-profile-system.md` and include profile debt / review queue in the dashboard
4. Present a compact project dashboard in the configured language: Project, Active Work, Recent Change, Profile, Next Best Step
5. Report and stop
**J. "foundation setup" / "profile setup" / "foundation repair" / "profile repair" / "profile sync":**
1. Read `references/project-profile-system.md`
2. Execute the matching Profile System flow
3. Report and stop
---
## End Session Flow
When triggered by "end session" / "结束会话" / "收工" / "we're done" / "wrap up" / "done for today" / "normal close" / "full close", execute in order:
1. **Write session log** → `log/session-YYYY-MM-DD-{slug}.md`
- Same-day multiple sessions: use slug to distinguish (e.g., `session-2026-04-21-prd-draft.md`)
- Format: see Session Log Format below
2. **Log Compaction** → if unarchived raw logs ≥ threshold (default 10, configured in CLAUDE.md):
read `references/log-compaction.md` and execute
3. **Update session-handoff.md** → refresh "current progress" and "next steps"
4. **Update PROJECT.md** → if structure/module status changed
5. **Update TODO.md** → mark completed tasks
6. **Collect constitution candidates** → append to `.claude/candidates.md` (see rules below)
7. **Profile impact scan** → if `.claude/project-profile.json` exists, `.claude/profile-pending.json` exists, or the user explicitly requested Normal Close / Full Close / profile sync:
- Read `references/project-profile-system.md`
- Run the Profile-Aware End Session flow
- For Normal Close: record profile-impacting changes in `.claude/profile-pending.json`
- For Full Close: produce a Scope Plan before changing profile docs
- Do not rewrite protected sections, document policies, or stable baselines without explicit confirmation
8. **File reorganization (incremental)** → read `references/file-reorganization.md`, execute Mode B
- If STRUCTURE.md missing: execute Mode A first to establish baseline
- Update `.claude/.file-snapshot.json`
9. **Document archiving** → read `references/document-archiving.md`, scan and archive document output
- Identify documents created/modified this session
- Classify by type, archive to `docs/` subdirectories
- Update `DOCS.md` index and metadata
- If DOCS.md missing: create it (upgrade compatibility)
10. **Evaluate & write update log** → read `references/update-log.md`
- Evaluate session significance
- If significa提问、分享技巧或报告无法使用。按“有帮助”数量排序。