skill-repo
Skill0 starsChanged 29 days agoMITView on GitHub
Sets up a plugin repository with its README as the spec, licence, changelog, CI, topics and one product.json for every tool's manifest. Use when starting a plugin repo.
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- netresearch/skill-repo-skilltheir own version, first seen May 12, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- netresearch/skill-repo-skill★ 22same 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-packageSkill
- skill-planSkill
- skill-pluginSkill
- skill-publishSkill
- skill-releaseSkill
- 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
- Very specific: line 14
Ask what you can't read from the project or .agents/skill/setup.md, one question at a time, and write profile.json:
≈ “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
Set up a plugin repository
A plugin repository that passes every tool's validator from the first commit saves a week of small failures later.
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.
1. The profile
Ask what you can't read from the project or .agents/skill/setup.md, one question at a time, and write profile.json:
| Field | Ask for |
name, displayName | The plugin's name, lowercase with hyphens, and how people write it |
description | One line: what it is, for whom, then the words people search for. It becomes the README's first line and the repository's description, in the same words |
keywords | What people type to find it; they become the search topics |
prefix | One short word every skill's name starts with, so it can't clash with another plugin |
author | Name and web address. Never an email address in a public repository: it gets scraped |
repository | owner/name on GitHub |
licence | MIT unless they say otherwise |
pullRequests | Whether to accept them; by default issues are welcome and pull requests are not |
2. Write it
Show what it will write first with --dry, then:
npx -y @thenavidm/skill-builder@latest repo new <folder> --profile profile.jsonIt never overwrites a file that's already there and says which it kept. It builds every tool's manifest and runs check.
3. Prove it
npx -y @thenavidm/skill-builder@latest install <folder>Each tool's own validator should pass. Two warnings are expected and right: the root AGENTS.md and CLAUDE.md guide people working on the repository and aren't plugin content.
4. What to fill in
The README is the specification: the parts left as comments (a real example, what you can ask it, the data it keeps) are theirs to write before the first release. Then skill-plugin or skill-create builds the skills, and skill-publish puts it on GitHub.
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.