agent-skills
AGENTS.md68 starsChanged 14 days agoApache-2.0View on GitHub
Rules for contributing to this repository. Skills in this repository should be narrowly focused on a specific task or workflow. A good skill helps an agent take a concrete action, for example: Do not create skills that mainly provide generic background information or broad documentation. If content is mostly reference material, it should usually live in docs, not as a standalone skill. Reference material is fine inside a skill when it directly helps complete the task the skill is for.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- convex/agent-skillsword for word, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 1
- convex/agent-skills★ 68100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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 repository33 other files it gives its agents.
- convex-addSkill
- convex-advisorSkill
- convex-agentSkill
- convex-authSkill
- convex-authzSkill
- convex-backupSkill
- convex-billingSkill
- convex-costSkill
- convex-create-componentSkill
- convex-cronsSkill
- convex-deploy-guardSkill
- convex-designSkill
- convex-docsSkill
- convex-domainsSkill
- convex-envSkill
- convex-expertSkill
- convex-explain-appSkill
- convex-improve-convex-pluginSkill
- convex-insightsSkill
- convex-launch-readinessSkill
- convex-migrate-rehearseSkill
- convex-migrateSkill
- convex-monitorSkill
- convex-optimizeSkill
- convex-quickstartSkill
- convex-reviewerSkill
- convex-seedSkill
- convex-self-healSkill
- convex-sentinelSkill
- convexSkill
- convex-suggestSkill
- convex-testSkill
- convex-verifySkill
The file
Show its rules and text
We split this AGENTS.md into the rules it gives an agent
13 rules. About 0 are common, 9 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
create a Convex function
- Distinctive: line 17
Do not create skills that mainly provide generic background information or broad documentation.
- Distinctive: line 24
Before contributing, review the core Agent Skills docs:
- Distinctive: line 32
If the skill uses bundled scripts, also review Using scripts in skills.
- Very specific: line 38
Use Yes/No in tables instead of checkmarks or emoji
- Distinctive: line 39
Keep examples concise and focused
- Very specific: line 40
Use // Bad: and // Good: comments in code examples
- Very specific: line 41
Follow existing file patterns in skills/
- Distinctive: line 55
If skills are added, removed, renamed, or substantially repositioned, update the root README.md
- Very specific: line 57
Keep the skill list in the root README.md in sync with the current contents of skills/
- Distinctive: line 62
Do not assume a skill is good just because it reads well
- Distinctive: line 65
If human intervention is required, stop and ask explicitly for the exact step needed
- Distinctive: line 67
After the run, feed what you learned back into the skill with clearer instructions, steps, gotchas, or validation checks
≈ “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
Agent Instructions
Rules for contributing to this repository.
Skill Philosophy
Skills in this repository should be narrowly focused on a specific task or workflow.
A good skill helps an agent take a concrete action, for example:
- set up authentication
- design a schema
- create a Convex function
- plan a migration
Do not create skills that mainly provide generic background information or broad documentation. If content is mostly reference material, it should usually live in docs, not as a standalone skill.
Reference material is fine inside a skill when it directly helps complete the task the skill is for.
Before contributing, review the core Agent Skills docs:
If the skill uses bundled scripts, also review Using scripts in skills.
Style Guidelines
- No emojis in any markdown files or code comments
- Use
Yes/Noin tables instead of checkmarks or emoji - Keep examples concise and focused
- Use
// Bad:and// Good:comments in code examples - Follow existing file patterns in
skills/
File Structure
Each skill should have:
- Clear heading with brief description
- "When to Use" section
- Code examples showing bad vs good patterns
- Complete, runnable examples
- Checklist at the end
Maintenance
- If skills are added, removed, renamed, or substantially repositioned, update
the root
README.md - Keep the skill list in the root
README.mdin sync with the current contents ofskills/
Validation
- Do not assume a skill is good just because it reads well
- Validate skills by trying to use them in a realistic temp project or sandbox
- Push the task as far as possible without human help
- If human intervention is required, stop and ask explicitly for the exact step needed
- After the run, feed what you learned back into the skill with clearer instructions, steps, gotchas, or validation checks
- For UI-facing skills, validate the browser flow as part of skill authoring, not just the code or CLI steps
Code Examples
// Bad: description of the problem
// Good: description of the solutionDoes 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.