agents-md-assistant

Inspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.

⭐106stars🔀38forks📁View on GitHub🕐Updated Jan 2, 2026

When & Why to Use This Skill

The agents-md-assistant is a specialized Claude skill designed to automate the creation of AGENTS.md files by performing deep repository inspections. It intelligently analyzes project structures, extracts critical build and test commands from configuration files (like package.json or Makefile), and maps out architectural entry points. This skill streamlines the onboarding process for AI agents and developers by providing a standardized, machine-readable guide to the codebase's workflow and environment.

Use Cases

  • AI Agent Onboarding: Automatically generate comprehensive AGENTS.md files to help AI coding assistants understand how to build, test, and navigate a new repository without manual instruction.
  • Technical Documentation Automation: Rapidly document project workflows by extracting exact commands from build scripts and configuration files, reducing manual writing effort.
  • Codebase Architecture Mapping: Identify and document key components, data flows, and entry points to provide a high-level overview for new team members or system audits.
  • Standardizing Development Environments: Ensure all repositories within an organization maintain a consistent set of workflow rules and environment requirements for better cross-team collaboration.
nameagents-md-assistant
descriptionInspect a repository and draft an AGENTS.md file using the standard template, capturing commands, structure, and workflow rules.

AGENTS.md Assistant

Quick start

  • Review README.md, CONTRIBUTING.md, and docs/CI configs to learn the intended workflow.
  • Pull exact commands from build scripts (Makefile, package.json, pyproject.toml, justfile).
  • Map key directories (source, tests, docs, scripts) and mark generated or vendor paths.
  • Capture architecture: key entrypoints, components, and configuration locations.
  • Fill unknowns with TODOs and confirm them with the user.

Workflow

  1. Inspect the repository

    • Read README.md, CONTRIBUTING.md, and /docs for goals and workflows.
    • Check build/config files: Makefile, package.json, pyproject.toml, justfile, Dockerfile, CI pipelines.
  2. Extract commands

    • Record install, dev, lint, format, typecheck, test, and build commands exactly as documented.
    • If multiple options exist, capture the preferred default and note alternates.
  3. Map structure

    • Identify primary code, tests, docs, scripts, and generated/ignored folders.
    • Note where key configs live and any build artifacts to avoid editing.
  4. Summarize architecture & environment

    • Document key components, data flow, and entrypoints.
    • Capture required versions, services, env vars, and migration/seed steps.
  5. Author AGENTS.md

    • Use references/agents_md_template.md as the base.
    • Place AGENTS.md at the repo root unless instructed otherwise.
    • Flag missing info with TODOs and ask for confirmation.

Reference

  • references/agents_md_template.md: base template to fill.