REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agentic AI explained with chickens 🐔 every pattern a runnable, CI-checked file.
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/thibautmelen-agentic-ai-systems)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 agentic-ai-systems | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | ThibautMelen | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 330 | 467,235 | 234,125 | 149,873 | 144,332 |
| 最近代码更新 | 2026年7月11日 | 2026年11月18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 |
ThibautMelen 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 Code
依据开发者 README 和 repo 中的文件夹
GitHub account ThibautMelen (person), 10 years old
★ 330 stars, few users so far · code last changed 2026年7月11日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit 5ca6135 (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: SKILL.md has no name or description in its header. 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 /components,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 components 文件夹放到 ~/.agents/skills/components
~ 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 components
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
4,452 个字符 · 在 GitHub 打开完整文件
<div align="center">
[🏠 Home](../../README.md) › [🔧 Implementation](../README.md) › [📦 Components](./) › **📚 Skill**
[← 🦴 Slash Command](slash-command.md) ━━━━━━━━━━━━━━━━━━━━━●━━━━━━━━━━━━━━ [🪝 Hook →](hook.md)
</div>
---
# 📚 Skill
> A **Skill** is a reusable capability that provides specialized knowledge or methodology for specific task types.
---
## Key Characteristics
| Property | Value |
|----------|-------|
| **Invocation** | Skill tool or automatic based on context |
| **Location** | `.claude/skills/*/SKILL.md` |
| **Loading** | On-demand when relevant |
| **Scope** | Enhances 🐔 main agent capabilities |
---
## File Structure
```bash
.claude/skills/test-driven-development/
└── SKILL.md
```
```markdown
# .claude/skills/test-driven-development/SKILL.md
---
description: Use when implementing features - write tests first, then code
---
# Test-Driven Development Skill
## Methodology
1. RED: Write a failing test
2. GREEN: Write minimal code to pass
3. REFACTOR: Clean up while tests pass
```
> **Note**: Skill name from directory name. Frontmatter: `name` (optional), `description` (required), `allowed-tools` (optional).
---
## Frontmatter Reference
| Field | Required | Description |
|-------|----------|-------------|
| `name` | No | Skill name (default: directory name, max 64 chars) |
| `description` | Yes | When to use this skill (max 1024 chars) |
| `allowed-tools` | No | Restricts tool access for this skill |
---
## Mermaid Representation
```mermaid
%%{init: {'theme': 'base', 'themeVariables': {'lineColor': '#64748b'}}}%%
flowchart TB
classDef user fill:#6366f1,stroke:#4f46e5,stroke-width:2px,color:#ffffff
classDef main fill:#8b5cf6,stroke:#7c3aed,stroke-width:2px,color:#ffffff
classDef skill fill:#8b5cf6,stroke:#7c3aed,stroke-width:2px,color:#ffffff
classDef decision fill:#f59e0b,stroke:#d97706,stroke-width:2px,color:#ffffff
REQ["🙋♀️📥 User Request"]:::user --> CHECK{"📚 Skill Applicable?"}:::decision
CHECK -->|Yes| LOAD["📚 Load Skill"]:::skill
CHECK -->|No| DIRECT["🐔⚡ Direct Execution"]:::main
LOAD --> APPLY["🐔📚 Apply Methodology"]:::main
APPLY --> EXEC["🐔⚡ Execute with Skill"]:::main
EXEC --> RESULT["💁♀️📤 Enhanced Result"]
DIRECT --> RESULT
```
---
## How Skills Work
1. **Detection**: Claude analyzes the request context
2. **Matching**: Compares against skill descriptions
3. **Loading**: Injects skill content into context
4. **Application**: Follows methodology during execution
---
## Progressive Skills Mechanism
```mermaid
%%{init: {'theme': 'base', 'themeVariables': {'lineColor': '#64748b'}}}%%
flowchart TB
classDef main fill:#8b5cf6,stroke:#7c3aed,stroke-width:2px,color:#ffffff
classDef skill fill:#8b5cf6,stroke:#7c3aed,stroke-width:2px,color:#ffffff
classDef decision fill:#f59e0b,stroke:#d97706,stroke-width:2px,color:#ffffff
REQ["🙋♀️📥 User Request"] --> MA["🐔 Main Agent"]:::main
MA --> CHECK{"📚 Match Skills?"}:::decision
CHECK -->|TDD Task| TDD["📚 test-driven-development"]:::skill
CHECK -->|Debug Task| DEBUG["📚 systematic-debugging"]:::skill
CHECK -->|Review Task| REVIEW["📚 code-review"]:::skill
CHECK -->|None| DIRECT[Direct Execution]
TDD --> EXEC["✅ Enhanced Execution"]
DEBUG --> EXEC
REVIEW --> EXEC
DIRECT --> EXEC
```
---
## Example Skill Content
```markdown
# .claude/skills/systematic-debugging/SKILL.md
---
description: Use when debugging errors or unexpected behavior - systematic root cause analysis
---
# Systematic Debugging
## Process
1. **Reproduce**: Confirm the issue is reproducible
2. **Isolate**: Narrow down to smallest failing case
3. **Hypothesize**: Form theories about cause
4. **Test**: Verify each hypothesis
5. **Fix**: Apply minimal fix
6. **Verify**: Confirm fix works without regressions
```
---
## Tips
- Write clear, actionable descriptions
- Include step-by-step methodologies
- Document when to use (and when NOT to use)
- Keep skills focused on single concerns
---
<div align="center">
[← 🦴 Slash Command](slash-command.md) ━━━━━━━━━━━━━━━━━━━━━●━━━━━━━━━━━━━━ [🪝 Hook →](hook.md)
</div>
> 🗞️ **2026 note:** SKILL.md outgrew Claude Code — it's an open spec since Dec 2025 ([agentskills.io](https://agentskills.io/specification)) read by 30+ platforms (Hermes, opencode, goose…). What this page teaches transfers. See [What Changed 2026](../../foundations/what-changed-2026.md).
提问、分享技巧或报告无法使用。按“有帮助”数量排序。