Skip to content
Back to skills

Agents Md Generator

ASecurity

Analyze repository structure and generate standardized AGENTS.md files that serve as contributor guides for AI agents. Measures LOC to determine character limits and produces 5-section documents covering overview, folder structure, patterns, conventions, and working agreements.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 27, 2026
documentation

Security analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned September 27, 2026

npx -y skills add David-Li0406/meta-skill-evloving --skill agents-md-generator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agents Md Generator?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agents Md Generator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/david-li0406-agents-md-generator/badge)](https://www.skillsdirectory.com/skills/david-li0406-agents-md-generator)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agents-md-generator
description: Analyze repository structure and generate standardized AGENTS.md files that serve as contributor guides for AI agents. Measures LOC to determine character limits and produces 5-section documents covering overview, folder structure, patterns, conventions, and working agreements.
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 a standardized `AGENTS.md` document
- **Output Format**: Markdown file with structured sections
- **Character Limit**: Dynamic, based on repository LOC (Lines of Code)

## Output Sections

The generated `AGENTS.md` consists of exactly 5 sections:

| # | Section | Purpose |
|---|---------|---------|
| 1 | Overview | 1-2 sentence project description (abstract, no tool/framework lists) |
| 2 | Folder Structure | Key directories and their contents |
| 3 | Core Behaviors & Patterns | Logging, error handling, control flow patterns observed in code |
| 4 | Conventions | Naming, comments, code style derived from analysis |
| 5 | Working Agreements | Rules for agent behavior and communication |

## 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)

## Constraints

- **Read-Only Analysis**: Repository inspection uses only non-destructive commands
- **No Run/Test/Build/Deploy**: Generated AGENTS.md excludes execution instructions
- **Files to Ignore**: Lock files (`pnpm-lock.yaml`, `package-lock.json`, `yarn.lock`, etc.)

Files in this skill

  • LICENSE1 KB
  • SKILL.md2.1 KB
  • references/agents_md_template.md4.5 KB
  • references/loc_measurement.md2 KB
  • references/read_only_commands.md2.3 KB
  • references/working_agreements.md2.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…