agents-md-generator

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AGENTS.md Generation Capability

AGENTS.md生成能力

This skill enables the agent to generate

AGENTS.md

files that serve as contributor guides for AI agents working on a codebase.

本技能使Agent能够生成

AGENTS.md

文件，作为AI Agent参与代码库开发的贡献者指南。

Core Capability

核心能力

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

功能：分析仓库结构并生成或更新标准化的
```
AGENTS.md
```
文档
输出格式：带有结构化章节的Markdown文件
字符限制：动态调整，基于仓库代码行数（LOC）
单体仓库（Monorepo）支持：自动检测单体仓库结构，生成层级化文档（根目录 + 各包）
更新支持：刷新现有
```
AGENTS.md
```
中的标准章节，同时保留用户定义的自定义章节

Output Sections

输出章节

Single Repo / Package Document (5 Sections)

单仓库/包文档（5个章节）

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: Logging, error handling, control flow, module structure patterns observed in code
Conventions: Naming, comments, code style derived from analysis
Working Agreements: Rules for agent behavior and communication

适用于单仓库或单体仓库中的单个包：

概述：1-2句话的项目描述（为摘要形式，不包含工具/框架列表）
文件夹结构：关键目录及其内容
核心行为与模式：代码中观察到的日志、错误处理、控制流、模块结构模式
约定：从代码分析中提炼的命名、注释、代码风格规范
工作协议：Agent行为与沟通规则

Monorepo Root Document (3 Sections)

单体仓库根目录文档（3个章节）

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

适用于单体仓库的根目录：

概述：1-2句话描述单体仓库的用途
文件夹结构：应用、包和共享配置的高层级映射
工作协议：适用于所有包的通用工作协议

Operation Modes

操作模式

Generate vs Update

生成 vs 更新

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 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.

生成：从头创建新的
```
AGENTS.md
```
（当不存在
```
AGENTS.md
```
时默认使用该模式）
更新：刷新现有
```
AGENTS.md
```
中的标准章节，同时保留自定义章节。详细工作流和章节匹配规则请参考./references/update_strategy.md。 Agent会根据目标位置是否已存在
```
AGENTS.md
```
文件自动选择合适的模式。

Generation Modes (Monorepo)

生成模式（单体仓库）

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

支持三种模式：全部（根目录 + 所有包，默认）、仅根目录和单个包。详细策略和模式选择标准请参考./references/monorepo_strategy.md。

Tools

工具

This skill uses the following read-only tools for repository analysis. See ./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

本技能使用以下只读工具进行仓库分析。详细使用模式请参考./references/read_only_commands.md。

tokei
：代码行数（LOC）统计（必需）
rg
（ripgrep）：内容搜索（优先使用）
grep
/
Select-String
：内容搜索（根据操作系统备选）
sed -n
/
Get-Content | Select-Object
：分页读取文件（根据操作系统）
tree
：目录结构可视化
find
：文件和目录查找（Linux / macOS）
ls
,
pwd
：基础目录导航

Domain Knowledge

领域知识

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

LOC统计：统计仓库大小并确定字符限制的能力。请参考./references/loc_measurement.md
仓库分析：检查并理解代码库结构的能力。请参考./references/read_only_commands.md
输出模板：标准化AGENTS.md结构规范。请参考./references/agents_md_template.md
工作协议：生成文档中的Agent行为规则。请参考./references/working_agreements.md
单体仓库检测：识别单体仓库结构的能力。请参考./references/monorepo_detection.md
单体仓库策略：在单体仓库中生成文档的策略。请参考./references/monorepo_strategy.md
更新策略：选择性刷新章节以更新现有AGENTS.md文件的策略。请参考./references/update_strategy.md

Scope Boundaries

范围边界

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

只读分析：支持用于仓库检查的非破坏性命令
输出范围：仅生成文档内容；不包含运行/测试/构建/部署说明
排除输入：锁文件（
```
pnpm-lock.yaml
```
、
```
package-lock.json
```
、
```
yarn.lock
```
等）不在分析范围内