codex-skill-maintainer
Skill2 starsChanged 2 months agoMITView on GitHub
Use when creating, reviewing, splitting, updating, or validating this repository's local Codex skills. Do not use for ordinary product code changes or global-skill installation.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- apple-accessibility-reviewSkill
- apple-app-marketing-siteSkill
- apple-design-systemSkill
- apple-development-foundationSkill
- apple-error-statesSkill
- apple-platform-plannerSkill
- apple-security-privacy-reviewSkill
- codex-bootstrapSkill
- ios-macos-platform-adaptationSkill
- maestro-apple-app-testingSkill
- reusable-code-extractorSkill
- swift-concurrency-reviewSkill
- swift-package-module-authorSkill
- swift-testing-verificationSkill
- swiftui-component-authorSkill
- swiftui-tab-navigationSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 8
Keep one repeatable job per skill.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
Codex skill maintainer
Keep one repeatable job per skill. Check trigger overlap, exclusions, concise frontmatter, inputs, outputs, planning behavior, and verification. Move long content to references, preserve names unless intentionally renamed, update manifest/index, validate metadata, and dry-run the safe installer.
Inputs: repository-local skill source and intended behavior. Output: a semantic evaluation or focused skill update plus schema and installer verification. Do not modify global Codex files or claim automatic activation without reliable evidence.
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.