skill-plugin
Skill0 starsChanged 29 days agoMITView on GitHub
Builds a whole plugin, or bundles existing skills into one, with an entry skill, and proves each request reaches the right skill in every tool. Not for rebuilding manifests (skill-package).
- Installs packages
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-publishSkill
- skill-releaseSkill
- skill-repoSkill
- skillSkill
- skill-tidySkill
- skill-tokensSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use skill-plan, which starts the skill-architect agent: the jobs, what exists, which jobs are skills, agents or scripts, the routing …
- Very specific: line 18
Use skill-repo to set it up (or work in theirs if it exists).
- Distinctive: line 24
Write the entry skill last of all, once the others exist: a table from what people say to the skill that does it, plus setup and a health …
≈ “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
Build a plugin
A plugin is several skills that have to work together: each must fire on its own requests and not steal its siblings', the whole set must fit in every tool's skill list, and it must install everywhere from one source.
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. Plan
Use skill-plan, which starts the skill-architect agent: the jobs, what exists, which jobs are skills, agents or scripts, the routing prompts. Get their yes on the plan first.
2. The repository
Use skill-repo to set it up (or work in theirs if it exists). Every skill name starts with the plugin's prefix, and the entry skill is named after it.
3. The skills
Build each with skill-create, starting with the entry skill and the most-used job. The plan is the brief, so most interviews are short. Agents go in agents/<name>.md as flat files, with no model pinned, each started by a skill at a fixed step, and each job written so the skill can do it itself in tools without agents.
Write the entry skill last of all, once the others exist: a table from what people say to the skill that does it, plus setup and a health check.
4. Prove it works as a plugin
npx -y @thenavidm/skill-builder@latest check <plugin>
npx -y @thenavidm/skill-builder@latest tokens <plugin>
npx -y @thenavidm/skill-builder@latest trigger <plugin> --set evals/triggers.json --runs 3
npx -y @thenavidm/skill-builder@latest install <plugin>checkfinds nothing blocking across every skill and agent.tokensshows the plugin's share of each tool's skill list; over 100% on the models their users run means some skills will go quiet. Shorten descriptions, or let the entry skill route to skills that only run when asked.triggerwith anexpectfor each prompt is the routing test: every prompt must reach the right sibling in each tool. A prompt that lands on a sibling means two descriptions overlap; add a boundary to each.installruns each tool's own validator and loads the plugin to run its entry skill.
Then eval (or bench) each skill.
5. Ship
skill-package builds every tool's manifest from product.json, skill-release makes the version, skill-publish puts it on GitHub, each with their yes for anything that reaches a live system.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

