AGENTS.md / CLAUDE.md / SKILL.md Generator
Describe your project once and get a clean instruction file for Codex, Claude Code, Cursor, Gemini CLI or Agent Skills. Live preview, copy and download.
TL;DR: Fill in a short form to generate an AGENTS.md, CLAUDE.md or SKILL.md instruction file for Codex, Claude Code, Cursor, Gemini CLI or Agent Skills, with live preview, copy and download.
AGENTS.md
What makes a good AGENTS.md
- Exact commands to install, run, test and lint — agents run them to check their own work.
- Short, concrete rules (“use named exports”) instead of vague advice (“write clean code”).
- Boundaries: files or folders the agent must not edit, and secrets it must never touch.
Related guides: What is AGENTS.md · CLAUDE.md best practices · Writing a SKILL.md · Cursor rules
FAQ
What is AGENTS.md?
AGENTS.md is a plain Markdown file at the root of a repository that tells AI coding agents how to work in it: setup and test commands, code style, project layout and rules. Many agents, including OpenAI Codex, read it automatically.
What is the difference between AGENTS.md and CLAUDE.md?
They hold the same kind of guidance. CLAUDE.md is the file Claude Code loads as project memory; AGENTS.md is the cross-tool convention. Many teams keep one and point the other to it.
What is a SKILL.md file?
SKILL.md defines an Agent Skill: YAML front matter with a name (lowercase letters, numbers and hyphens, up to 64 characters) and a description that says when to use it, followed by Markdown instructions. The skill folder can also bundle scripts and templates.
Where should I put the generated file?
Put AGENTS.md or CLAUDE.md in the repository root (sub-folders can have their own for local rules). Put SKILL.md inside its own folder, for example .claude/skills/<skill-name>/SKILL.md for Claude Code.
Is my project information saved?
Only in your own browser’s localStorage, so the form is still filled in when you come back. Nothing is sent to a server.