agent-rules-skill

为什么要用

核心特性

Follows the agents.md convention
Detects build / test / lint commands automatically
Captures coding conventions from existing code
One file works across Claude Code, Cursor, Codex, etc.
Keeps the file short — agents.md is for orientation, not novels

实时演示

实际使用效果

agent-rules-skill.replay ▶ 就绪

0/0

安装

作者仓库 · Claude Skills 官方文档

使用场景

实战用法： agent-rules-skill

Generate an AGENTS.md for a repo that doesn't have one

👤 Teams introducing AI coding agents to an existing codebase ⏱ ~15 min beginner

何时使用： Your team just started using Claude Code / Cursor and nobody's written the orientation doc.

步骤

Run it on your repo

Use agent-rules-skill. Analyze this repo and draft an AGENTS.md following the convention.✓ 已复制

→ Draft with build/test commands, lint config, style notes, gotchas
Refine

Add a section on where not to edit (generated files, vendor/).✓ 已复制

→ Section added with explicit paths
Commit

Commit as docs/AGENTS.md.✓ 已复制

→ File committed at repo root or in docs/

结果： A living AGENTS.md that makes future agent sessions start with context.

注意事项

AGENTS.md balloons into an everything-doc — Keep it focused on what an agent needs. Link to README for humans.

搭配使用： filesystem · git

Generate per-package AGENTS.md files in a monorepo

👤 Monorepo maintainers ⏱ ~30 min intermediate

何时使用： Different packages have different conventions; a single root AGENTS.md isn't enough.

步骤

Scan packages

Use agent-rules-skill. For each package in packages/, generate a tailored AGENTS.md capturing its specifics.✓ 已复制

→ One AGENTS.md per package
Root summary

Generate a root AGENTS.md that links to per-package files and lists shared rules.✓ 已复制

→ Root file with pointers

结果： Agents pick up the right context based on which package they're working in.

搭配使用： filesystem

Keep AGENTS.md in sync with an evolving repo

👤 Repos where AGENTS.md goes stale fast ⏱ ~10 min beginner

何时使用： You added new build commands or changed conventions and AGENTS.md lies about them.

步骤

Diff

Use agent-rules-skill. Compare current AGENTS.md to what the repo actually has now. What's stale?✓ 已复制

→ List of drift items
Update

Update only the stale parts; leave human-written sections alone.✓ 已复制

→ Minimal diff preserving human commentary

结果： AGENTS.md stays trustworthy.

搭配使用： git

组合

与其他 MCP 搭配，撬动十倍杠杆

agent-rules-skill + filesystem

Apply generated files directly

Write the draft to AGENTS.md at repo root.✓ 已复制

agent-rules-skill + git

Commit as a focused change

Commit the new AGENTS.md with a message describing what it covers.✓ 已复制

工具

此 MCP 暴露的能力

工具	输入参数	何时调用
scan_repo	repo path	First step on any repo
draft_agents_md	scan output	Drafting new file
diff_check	existing AGENTS.md + current repo	Staleness check

成本与限制

运行它的成本

API 配额: None
每次调用 Token 数: Modest — repo scan + short output
费用: Free
提示: Run on focused directories in huge monorepos; whole-repo scans are token-heavy.

安全

权限、密钥、影响范围

凭据存储： None

数据出站： Repo contents go through Claude API during scan

故障排查

常见错误与修复

Generated commands don't match CI

Verify against actual CI config; skill infers from common files but not always correct

File is too long

Prompt for conciseness; agents.md is meant to be short

替代方案