engineering-multi-ai-skills
AGENTS.md6 starsChanged 18 days agoMITView on GitHub
This repository ships a public, provider-neutral engineering toolkit. The role agreements under templates/project/ are starter artifacts for downstream projects, not this repository's active agent identity.
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 31,700 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 repository10 other files it gives its agents.
- claim-ledgerSkill
- critic-reviewSkill
- distributed-orchestrationSkill
- engineering-governanceSkill
- engineering-planSkill
- execution-integritySkill
- literature-provenanceSkill
- multi-agent-collaborationSkill
- technical-writingSkill
- worker-taskSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 1 is common, 0 are distinctive, and 1 is very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Common: line 5
Keep examples synthetic. Never add private research details, source snapshots, personal paths, node identities, credentials or actual …
- Very specific: line 8
Run scripts/validate.py for changed skills/docs/metadata.
≈ “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.
Files
Toolkit maintenance
This repository ships a public, provider-neutral engineering toolkit. The role agreements under templates/project/ are starter artifacts for downstream projects, not this repository's active agent identity.
- Keep examples synthetic. Never add private research details, source snapshots, personal paths, node identities, credentials or actual project data.
- Record user-facing changes under Unreleased in CHANGELOG.md. Do not bump a version for every edit; follow docs/releases.md when preparing a release.
- VERSION is authoritative. A release must align its changelog heading, README version badge/link, CLI output, immutable Git tag and GitHub Release. Do not repeat version numbers in each skill.
- Run scripts/validate.py for changed skills/docs/metadata. Run the tool tests when changing execution/routing, and run the full tests/ suite before release.
- The quickstart's labels.py intentionally contains a practice bug. Its tests should fail before the exercise; do not fix that fixture as part of routine toolkit maintenance.
- Review the intended staged files and publication content before pushing. Deployment, credentials, permissions and recurring automation are outside routine maintenance unless authorized by the user.
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.