agentleFS
chrisgliddonchrisgliddon/bevy-skills/AGENTS.md

bevy-skills

AGENTS.md29 starsChanged 11 days agoMITView on GitHub

You are an AI coding agent that has landed in the bevy-skills repository. A collection of Agent Skills (SKILL.md files) that teach AI agents how to write correct Bevy 0.20 code. Targets Claude Code, OpenCode, Cursor, Codex, Pi, and any other Agent Skills consumer. You are in the wrong place. Skills load automatically from your agent's skill directory (e.g. ~/.claude/skills/). See README.md for install instructions, then close this checkout and let the skills load via your normal workflow. Read CLAUDE.md.…

The file

We split this AGENTS.md into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read CLAUDE.md. It is the authoritative editor guide.

    line 15
  2. Very specific:

    Every skill is a folder under skills/ with a SKILL.md (YAML frontmatter + body) and optional references/.

    line 17
  3. Very specific:

    Every code snippet must cargo check against bevy = "0.20" in the companion bevy-skills-tester crate (not in this repo — see CLAUDE.md).

    line 19
  4. Very specific:

    Use dex for persistent project work.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md

You are an AI coding agent that has landed in the bevy-skills repository.

What this repo is

A collection of Agent Skills (SKILL.md files) that teach AI agents how to write correct Bevy 0.20 code. Targets Claude Code, OpenCode, Cursor, Codex, Pi, and any other Agent Skills consumer.

If you are HERE TO USE the skills

You are in the wrong place. Skills load automatically from your agent's skill directory (e.g. ~/.claude/skills/). See README.md for install instructions, then close this checkout and let the skills load via your normal workflow.

If you are HERE TO EDIT the skills

Read CLAUDE.md. It is the authoritative editor guide. Highlights:

  • Every skill is a folder under skills/ with a SKILL.md (YAML frontmatter + body) and optional references/.
  • Frontmatter must pass scripts/lint-skills.py — name regex ^[a-z0-9]+(-[a-z0-9]+)*$ matching the directory, description 1–1024 chars, keys limited to name/description/license/compatibility/metadata.
  • Every code snippet must cargo check against bevy = "0.20" in the companion bevy-skills-tester crate (not in this repo — see CLAUDE.md).
  • Pin Bevy 0.20 explicitly in every current skill's description. Historical migration skills pin their own target with metadata.target_version; no guidance is unversioned.
  • Use dex for persistent project work. Repository-local tasks live in .dex/tasks.jsonl and automatically sync root tasks to GitHub Issues.

License

MIT. See LICENSE.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.