matts-skills-into-chatgpt
AGENTS.md8 starsChanged 2 months agoMITView on GitHub
This repository is the public source for the matt-skills-curated ChatGPT/Codex plugin.
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 6
Every Skill must have SKILL.md and agents/openai.yaml.
- Distinctive: line 7
Every packaged Skill is model-invoked in this curated edition so the router can reach it automatically.
- Distinctive: line 9
Keep upstream provenance and MIT attribution accurate.
- Distinctive: line 10
Do not exclude a Skill solely because upstream called it misc or beta.
- Very specific: line 11
Run python3 scripts/validate_plugin.py and deterministic double packaging before committing a release.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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.
Files
Repository maintenance
This repository is the public source for the matt-skills-curated ChatGPT/Codex plugin.
skills/is flat and contains only public, curated Skills.- Every Skill must have
SKILL.mdandagents/openai.yaml. - Every packaged Skill is model-invoked in this curated edition so the router can reach it automatically. Do not add manual-only invocation flags to public Skills.
engineering-workflow-guideis the model-invoked router and its catalog must cover every other packaged Skill exactly once.- Keep upstream provenance and MIT attribution accurate.
- Do not exclude a Skill solely because upstream called it misc or beta. Promote useful capabilities after portability, safety, dependency, and quality review; exclude only duplicates, host-specific surfaces, deprecated material, telemetry, credentials, symlinks, or generated noise.
- Run
python3 scripts/validate_plugin.pyand deterministic double packaging before committing a release.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 28,693 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository42 other files it gives its agents.
- ai-data-remediationSkill
- ai-engineeringSkill
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- engineering-workflow-guideSkill
- git-safety-guardrailsSkill
- goalSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- implement-specSkill
- improve-codebase-architectureSkill
- j-spaceSkill
- migrate-to-shoehornSkill
- ml-best-practicesSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- retroSkill
- scaffold-exercisesSkill
- setup-engineering-workflowsSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- skill-conductorSkill
- tddSkill
- teachSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wait-whatSkill
- wayfinderSkill
- wizardSkill
- workflow-designerSkill
- writing-beatsSkill
- writing-for-agentsSkill
- writing-fragmentsSkill
- writing-shapeSkill
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
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.

