dev-skills
AGENTS.md5 starsChanged 36 days agoMITView on GitHub
This repository maintains a production-grade collection of development Skills. Each Skill's entry point is skills/<skill-name>/SKILL.md.
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 31,774 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 repository15 other files it gives its agents.
- agent-prompt-rulesSkill
- core-grillSkill
- core-specSkill
- cross-reviewSkill
- deliverSkill
- design-for-reviewSkill
- dev-feedbackSkill
- explain-as-foolSkill
- merge-gateSkill
- mr-for-humanSkill
- plan-for-agentsSkill
- recon-to-contractSkill
- repo-readinessSkill
- review-rulesSkill
- tech-diagramSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
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 7
Add references, scripts and assets as needed, and say in the entry point when to read them.
- Distinctive: line 8
Check triggering and results with real requests.
- Distinctive: line 10
After adding or removing a Skill, update the navigation and setup status in the README.
- Distinctive: line 11
Write Skill content in English, using the terms in docs/glossary.md.
≈ “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
dev-skills
This repository maintains a production-grade collection of development Skills. Each Skill's entry point is skills/<skill-name>/SKILL.md.
- Scope a new Skill by the real task and use case the user gives; keep changes to existing Skills within the request.
namematches the directory name.descriptionstates what the Skill does and when to use it; the body holds the judgment criteria and procedure needed at run time.- Add references, scripts and assets as needed, and say in the entry point when to read them. Facts that can be observed directly come from the actual files or command output.
- Check triggering and results with real requests; any new or changed script must be run to verify it. Say which results are verified and which still need confirmation in real use.
- This repository is the single source; clients reference whole Skill directories through symlinks. When installing or migrating existing Skills, keep the scope the user explicitly chose.
- After adding or removing a Skill, update the navigation and setup status in the README. Each commit should be understandable on its own; examples use de-identified data.
- Write Skill content in English, using the terms in docs/glossary.md. Text a Skill produces for people (questions, decision summary, spec, verify, plan, decision list, MR description, reports) follows the user's language as each Skill states; keys that scripts read stay as written.
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.

