Codex Writes an AGENTS.md for This Repository From the Real Setup
Has Codex inspect your repository and write a short, accurate AGENTS.md with the real build, test and lint commands, conventions and boundaries, checked by actually running them.
13 prompts
Prompts that write reusable instructions for AI agents: SKILL.md files, AGENTS.md and CLAUDE.md project guides, and the other standing instructions an agent loads before it starts work. Fill in your stack and conventions, and the result is a file you commit once and every later task benefits from.
1 result
Has Codex inspect your repository and write a short, accurate AGENTS.md with the real build, test and lint commands, conventions and boundaries, checked by actually running them.
A folder of instructions, and sometimes scripts, that an agent loads when a task calls for it. Its SKILL.md names the skill, says when to use it and lists the steps.
AGENTS.md and CLAUDE.md go in the repository root. Skills go wherever your agent looks for them, such as a skills folder in the project or in your user settings.
Give the agent a task the skill is meant for and watch whether it loads the skill and follows the steps. If it doesn't, make the skill's description more specific.