skill-package
Skill0 starsChanged 29 days agoMITView on GitHub
Rebuilds every AI tool's plugin manifest (plugin.json and the rest) from one product.json and checks none has drifted. Use after adding or changing skills. Not for building a plugin (skill-plugin).
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- skillberry-ai/cap-evolvetheir own version, first seen Jun 16, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- skillberry-ai/cap-evolve★ 69same name
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.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skill-benchSkill
- skill-checkSkill
- skill-competeSkill
- skill-createSkill
- skill-descriptionSkill
- skill-evalSkill
- skill-factsSkill
- skill-improveSkill
- skill-learnSkill
- skill-planSkill
- skill-pluginSkill
- skill-publishSkill
- skill-releaseSkill
- skill-repoSkill
- skillSkill
- skill-tidySkill
- skill-tokensSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
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
- could be automatic: a setting could enforce it
- Very specific: line 22
Never edit a generated manifest by hand: change product.json or the skill, and package again.
≈ “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
Package for every tool
Each tool reads its own manifest file. Written by hand they drift: a new skill shows in one tool and not another, a version bumps in one place only. Built from product.json and package.json, one change reaches all of them.
The engine runs as npx -y @thenavidm/skill-builder@latest. Where skill-builder is installed (npm install -g @thenavidm/skill-builder), run skill-builder instead: it's the same engine, without the download.
npx -y @thenavidm/skill-builder@latest package <plugin>
npx -y @thenavidm/skill-builder@latest package <plugin> --check- Without
--checkit writes every manifest, andskills/<name>/agents/openai.yamlfor each skill markeddisable-model-invocation: true, so "only when asked" holds in Codex too. It only ever replaces or removes files it wrote. - With
--checkit writes nothing and says what's out of date; CI runs it so a hand edit fails before it ships. - A repository that carries its own manifest builder (scripts/manifests/build.mjs in that repository) is packaged with that builder.
- A repository without
product.jsonhas hand-written manifests: offerskill-repoto put it on one source.
Never edit a generated manifest by hand: change product.json or the skill, and package again. Commit the result.
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.