agents-skills
AGENTS.md19 starsChanged 20 days agoMITView on GitHub
This repository is the source of truth for personal, cross-project skills.
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 31,439 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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- brand-domain-researchSkill
- performance-aware-codingSkill
- review-and-refineSkill
- untangle-codebaseSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 5
Keep each skill focused, stack-neutral where possible, and useful across more than one project.
- Distinctive: line 6
Add a rule only when it changes a decision and is supported by a concrete, reusable lesson.
- Distinctive: line 8
Check for overlap before adding a new skill or rule.
- Distinctive: line 9
Keep project-specific conventions in that project's guidance rather than generalizing them here.
- Distinctive: line 12
Do not commit or push changes unless the user asks.
≈ “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
Skill maintenance
This repository is the source of truth for personal, cross-project skills.
- Keep each skill focused, stack-neutral where possible, and useful across more than one project.
- Add a rule only when it changes a decision and is supported by a concrete, reusable lesson.
- For a proposed lesson, retain the trigger, mechanism, conditions, evidence, and trade-off. Do not have a skill edit itself or append lessons automatically.
- Check for overlap before adding a new skill or rule; prefer a narrow update to an existing skill when ownership is clear.
- Keep project-specific conventions in that project's guidance rather than generalizing them here.
- Validate changed skills with the Codex skill validator before installing them. Skills are also installed for Claude Code and Antigravity, so keep instructions tool-neutral and front matter limited to
nameanddescription. - Edit skills in this repository, then run the installer (
--target codex|claude|antigravity|all) to refresh the local copies. Do not edit generated copies directly. - Do not commit or push changes unless the user asks.
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.