agents-md-generator

分类: 工具与效率 | 上传者: buYoung | 下载: 0 | 版本: v1.0（最新）

分析存储库结构并生成或更新标准化 AGENTS.md 文件，作为 AI 代理的贡献者指南。支持单一存储库和单一存储库结构。测量 LOC 以确定字符限制并生成涵盖概述、文件夹结构、模式、约定和工作协议的结构化文档。更新模式仅刷新标准部分，同时保留用户定义的自定义部分。在设置新存储库、将 AI 代理加入现有代码库、更新现有 AGENTS.md 或用户提及 AGENTS.md 时使用。

更新日志: Source: GitHub https://github.com/buYoung/skills

目录结构

当前层级: tree/main/skills/agents-md-generator/

📁 references/
- 📄 agents_md_template.md 18.2 KB
- 📄 loc_measurement.md 3.0 KB
- 📄 monorepo_detection.md 2.1 KB
- 📄 monorepo_strategy.md 2.1 KB
- 📄 read_only_commands.md 7.7 KB
- 📄 update_strategy.md 4.7 KB
- 📄 working_agreements.md 3.2 KB
📁 updates/
- 📁 2026-02-25-json-template-formatting-review/
  - 📄 agents-v1-test.patch 9.3 KB
  - 📄 agents-v2-test.patch 14.3 KB
  - 📄 no-agents-test.patch 17.3 KB
  - 📄 review.md 7.4 KB
  - 📄 review_en.md 7.1 KB
- 📁 2026-03-11-json-query-explanation-review/
  - 📄 review.md 6.3 KB
  - 📄 review_en.md 6.7 KB
- 📁 2026-03-21-claude-skill-2_0-apply/
  - 📄 benchmark.md 6.9 KB
- 📄 README.md 1.0 KB
- 📄 README_en.md 882 B
📄 LICENSE 1.0 KB
📄 SKILL.md 5.2 KB

SKILL.md

---
name: agents-md-generator
description: Analyze repository structure and generate or update standardized AGENTS.md files that serve as contributor guides for AI agents. Supports both single-repo and monorepo structures. Measures LOC to determine character limits and produces structured documents covering overview, folder structure, patterns, conventions, and working agreements. Update mode refreshes only the standard sections while preserving user-defined custom sections. Use when setting up a new repository, onboarding AI agents to an existing codebase, updating an existing AGENTS.md, or when the user mentions AGENTS.md.
license: MIT
---

# AGENTS.md Generation Capability

This skill enables the agent to generate `AGENTS.md` files that serve as contributor guides for AI agents working on a codebase.

## Core Capability

- **Function**: Analyze repository structure and generate or update a standardized `AGENTS.md` document
- **Output Format**: Markdown file with structured sections
- **Character Limit**: Dynamic, based on repository LOC (Lines of Code)
- **Monorepo Support**: Automatically detects monorepo structures and generates hierarchical documentation (Root + Packages)
- **Update Support**: Refreshes only standard sections in an existing `AGENTS.md`, preserving user-defined custom sections

## Output Sections

### Single Repo / Package Document (5 Sections)
For single repositories or individual packages in a monorepo:

- **Overview**: 1-2 sentence project description (abstract, no tool/framework lists)
- **Folder Structure**: Key directories and their contents
- **Core Behaviors & Patterns**: Cross-cutting patterns traced through full flows — error propagation chains, state lifecycle transitions, cross-boundary wiring mechanisms, resilience/recovery strategies, shared resource management. Discovered via multi-phase analysis: surface idiom detection, then deep tracing across layers.
- **Conventions**: Naming, code style, API/interface design conventions (callback naming, return value shapes, method responsibility splitting), configuration/registration structure, boundary conventions (error flattening, schema drift absorption, containment rules), component composition patterns.
- **Working Agreements**: Rules for agent behavior and communication

### Monorepo Root Document (3 Sections)
For the root of a monorepo structure:

- **Overview**: 1-2 sentences describing the monorepo's purpose
- **Folder Structure**: High-level map of apps, packages, and shared configs
- **Working Agreements**: Common working agreements applicable to all packages

## Operation Modes

### Generate vs Update

- **Generate**: Creates a new `AGENTS.md` from scratch (default when no `AGENTS.md` exists)
- **Update**: Refreshes standard sections in an existing `AGENTS.md` while preserving custom sections. See [./references/update_strategy.md](./references/update_strategy.md) for detailed workflow and section matching rules.

The agent automatically selects the appropriate mode based on whether an `AGENTS.md` file already exists at the target location.

### Generation Modes (Monorepo)

Supports three modes: **All** (root + all packages, default), **Root Only**, and **Single Package**. See [./references/monorepo_strategy.md](./references/monorepo_strategy.md) for detailed strategy and mode selection criteria.

## Tools

This skill uses the following read-only tools for repository analysis. See [./references/read_only_commands.md](./references/read_only_commands.md) for detailed usage patterns.

- **`tokei`**: LOC measurement (required)
- **`rg` (ripgrep)**: Content search (preferred)
- **`grep` / `Select-String`**: Content search (fallback per OS)
- **`sed -n` / `Get-Content \| Select-Object`**: Paginated file reading per OS
- **`tree`**: Directory structure visualization
- **`find`**: File and directory discovery (Linux / macOS)
- **`ls`, `pwd`**: Basic directory navigation

## Domain Knowledge

- **LOC Measurement**: Capability to measure repository size and determine character limits. See [./references/loc_measurement.md](./references/loc_measurement.md)
- **Repository Analysis**: Capability to inspect and understand codebase structure. See [./references/read_only_commands.md](./references/read_only_commands.md)
- **Output Template**: Standardized AGENTS.md structure specification. See [./references/agents_md_template.md](./references/agents_md_template.md)
- **Working Agreements**: Agent behavior rules for generated documents. See [./references/working_agreements.md](./references/working_agreements.md)
- **Monorepo Detection**: Capability to identify monorepo structures. See [./references/monorepo_detection.md](./references/monorepo_detection.md)
- **Monorepo Strategy**: Strategy for generating documentation in monorepos. See [./references/monorepo_strategy.md](./references/monorepo_strategy.md)
- **Update Strategy**: Strategy for updating existing AGENTS.md files with selective section refresh. See [./references/update_strategy.md](./references/update_strategy.md)

## Scope Boundaries

- **Read-Only Analysis**: Supports non-destructive commands for repository inspection
- **Output Scope**: Produces documentation content only; excludes run/test/build/deploy instructions
- **Excluded Inputs**: Lock files (`pnpm-lock.yaml`, `package-lock.json`, `yarn.lock`, etc.) are outside analysis scope

登录后下载/点赞/收藏 ❤ 11 | ★ 0

agents-md-generator

目录结构

SKILL.md

举报内容

提示