REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
A meta-skill that produces skills. Point it at any codebase and it distills the project's rules, workflows, and hard-won lessons into a dedicated skills/ / directory — a project skill that becomes the single source of truth every AI agent (Cursor, Claude Code, Codex, Windsurf, Gemini) consults befo…
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/wojisama-skill-based-architecture)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 skill-based-architecture | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | WoJiSama | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 625 | 465,460 | 233,910 | 149,364 | 144,149 |
| 最近代码更新 | 2026年11月13日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月17日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
WoJiSama 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 CodeCodexCursorGemini CLIGitHub CopilotWindsurfOpenCode
依据开发者 README 和 repo 中的文件夹
GitHub account WoJiSama (person), 4 years old
★ 625 stars · code last changed 2026年11月13日
25 scripts that can run on a computer: .claude/hooks/session-start, scripts/check-all.sh, scripts/check-live-agent-journey.sh, scripts/check-self-scenarios.sh and 21 more
Could not check every script (some are too large); read them first
Installing the maker’s way adds hooks that run without you asking: run every time the AI edits a file · run every time a chat starts · Installed as a plugin (/plugin) it will run every time the AI edits a file in every project
Checked automatically from the repo files at commit 17612cb (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 (414). 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 /skill-based-architecture,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。
正在检查命令 · 通过后才会显示复制按钮
摘自开发者 README,会下载并运行开发者的代码
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 skill-based-architecture 文件夹放到 ~/.agents/skills/skill-based-architecture
~ 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 skill-based-architecture
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: skill-based-architecture
description: >
This skill should be used when the user asks to "organize the project rules",
"clean up scattered documentation", "把规则迁移到 skills 目录", "优化 skill 路由",
"提高 description 命中率", or "减少薄壳重复维护".
Activate when a SKILL.md is too large, rules are duplicated across agent entry
files, task routing or trigger_examples miss natural user language, or
templates / thin shells / validation scripts need drift-resistant maintenance.
---
# Skill-Based Architecture
Restructure oversized single-file Skills or scattered project rules into a well-organized Skill directory. Builds on the official minimal Agent Skill contract (`name` + `description`) and kicks in when a single small `SKILL.md` is no longer enough.
## When to Use
- A single `SKILL.md` exceeds ~150 lines, mixing rules, workflows, and background material; or project rules are scattered across `AGENTS.md`, `CLAUDE.md`, `CODEX.md`, `.cursor/rules/`, `.claude/`, etc.
- Recurring tasks need procedures, fitted verification, or reliable completion checks; or the user explicitly requests Skill-based architecture or rule consolidation.
- Skip temporary repos with no durable routing need, teams with a working compact instruction system, and small projects; an explicit SBA request may still materialize a complete direct `SKILL.md` carrier.
## Progressive Rigor
Grow only under pressure. The materializer derives **Single-file**, **Folder-light**, or **Full/broad** internally from target evidence; users do not select a tier, profile, capability pack, or install mode. `routing.yaml`, Task Execution, Task Closure, maintenance checks, and each harness surface need their own routing/loading/ownership pressure. **Split by abstraction (骨架/肉)** when content tangles invariant design theory with current-code facts: abstract theory → `architecture/`, code maps → `references/`, house style → `conventions/`, per-module landmines → `gotchas/` (methodology stays in `rules/`). Downgrade when content shrinks. Details: [references/progressive-rigor.md](references/progressive-rigor.md).
## Evidence-Selected Structure
```text
# direct
skills/<name>/SKILL.md
# folder-light or broad: only admitted owners/directories
skills/<name>/{SKILL.md,rules/,workflows/,references/,scripts/}
```
`routing.yaml` appears only when route data has an independent owner; root/tool entry and registration surfaces appear only for proven readers. Existing root entries are preserved. Emitted routed entries use a generated `routing.yaml` bootstrap; direct entries point to the sole `SKILL.md` procedure. Cursor registration exists only when Cursor is detected, declared, currently used, or explicitly requested. See [REFERENCE.md](REFERENCE.md) for sources.
## Core Principles
1. **Single concise entry** — `SKILL.md` keeps a dual budget: description ≤ 25 lines (trigger phrases + activation) + body ≤ 90 lines (navigation); it navigates, not exhausts. ✓ Check: smoke-test reports both separately; over either → split intent clusters / move detail to sub-files.
2. **One skill folder when a folder is admitted** — folder-light and broad results keep formal docs under `skills/<name>/`; a direct result may remain a complete single `SKILL.md` carrier. ✓ Check: no emitted root entry becomes a second rule/workflow owner.
3. **Rules ≠ Flows** — `rules/` for constraints, `workflows/` for procedures. ✓ Check: any numbered steps in `rules/`, or "always/never" in `workflows/`, = mixing.
4. **Routing.yaml as source when admitted** — a direct carrier owns its sole route in `SKILL.md`; multiple/shared routes live only in `routing.yaml`, with routed shells generated from it. ✓ Check: is there an independent selector or consumer that justifies the manifest, and does its fitted sync check pass?
5. **Harness surfaces follow readers** — create/merge only entries and registrations supported by existing files/config, the current harness, repository/team declaration, or an explicit request. ✓ Check: can every emitted surface name its reader, and was every existing entry preserved?
6. **Progressive Rigor** — three carriers (Single-file / Folder-light / Full) grow only under pressure and are not user package choices. ✓ Check: can you name the independent responsibility that forced every generated file?
7. **Description = coarse activation** — domain boundary + real user trigger phrases; never enumerate workflow keywords nor summarize a workflow's steps. ✓ Check: can `routing.yaml` task routes change without rewriting the description, and does no description/label carry HOW an agent could act on without opening the body?
8. **Gotchas are highest-value** — maintain costly pitfalls actively; keep them discoverable. ✓ Check: is each high-cost gotcha activated by the admitted route owner (`SKILL.md` or `routing.yaml`), not only buried in `references/`?
9. **Progressive disclosure** — every loaded file needs an independent task-time reason; conditional content leaves the startup read set; files every real caller co-loads should merge unless ownership/generation requires separate storage. ✓ Check: for each route read, can you name a request that needs it now and a next action it changes? No → conditionally route, merge, or remove.
10. **Task Execution + Closure** — only one clear read-only or fixed-contract maintenance action with no new desired behavior executes directly; anything that adds or changes user-visible behavior, a business flow/state, or an external contract follows `requirement-ready -> Task Anchor -> implementation-ready -> Native Plan -> mutation`; Present alignment proportionally and run a compact Anchor Checkpoint before each main step. Workflow is the domain procedure; Native Plan is only this Session's runtime step owner, with no planning-file persistence. Full protocol: [references/protocols.md § Task Execution Protocol](references/protocols.md#task-execution-protocol).
11. **Durable-record rule** — generic records generalize across projects; business global models stay project-specific but must survive implementation replacement. ✓ Check: use the destination's test—cross-project pattern or cross-implementation business truth—without mixing code details into either ([ref](references/protocols.md#generalization-rule)).
12. **Self-maintenance** — line counts signal evaluation, not automatic action; split only for independently selected tasks; merge files universally co-loaded/co-changed unless ownership or generation explains the boundary. ✓ Check: can the before/after load matrix prove less irrelevant reading without losing definitions, conditions, boundaries, or reasons?
13. **Activation over storage** — content in `references/` alone is not "captured"; it must be on the task path **and change what the agent does when read**; reached-but-inert (correct, on-route, yet the agent would have proceeded identically) is a distinct failure no structural gate can see, only judgment can. ✓ Check: trace the normal route — does hitting the entry change the next action (a file read, a check run, a step skipped)?
14. **Token efficiency** — Always Read defaults to empty; every addition needs proof that all real tasks require it before workflow selection; domain and lifecycle knowledge loads only when evidence or a phase boundary can change the next action. ✓ Check: can any startup read be delayed without changing the first workflow decision? If yes, move it to that workflow checkpoint.
15. **Rationalizations Table** — captures verbatim excuses from real pressure-test failures only. ✓ Check: every row traces to a real failure — no failure observed and unwilling to baseline it → imagined-pain, drop it ([ref](templates/skill/workflows/task-closure.md#rationalizations-to-reject), [Phase 9](workflows/full-migration.md#phase-9-pressure-test-the-skill)).
16. **Response discipline** — output short, precise, direct answers; avoid process narration, self-congratulation, gratuitous confirmations, and requirement restatement. ✓ Check: does each s提问、分享技巧或报告无法使用。按“有帮助”数量排序。