agentleFS
skilld-devskilld-dev/vue-ecosystem-skills/CLAUDE.md

vue-ecosystem-skills

CLAUDE.md184 starsChanged 37 days agoMITView on GitHub

packages.json lists every package with a Skill. skills-lock.json records the version each Skill was built from. Each skill follows a consistent structure: packages.json names every package this repository maintains a Skill for. skills-lock.json records the version each Skill was built from. The sync runs generate-package-skill through skilld-harness, using OpenCode as the agent runtime and skilld-harness/sandbox-local as the sandbox. It needs OPENCODE_API_KEY, or an opencode auth login session on this computer. Choose the model with --model= or SKILLD_MODEL. Choose how many…

  • Reads credentials

The file

We split this CLAUDE.md 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
  1. Distinctive:

    All code examples must be TypeScript + Composition API unless the skill specifically targets Options API

    line 26

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Vue Ecosystem Skills — Development Guide

Skill Scopes

packages.json lists every package with a Skill. skills-lock.json records the version each Skill was built from.

Skill Structure

Each skill follows a consistent structure:

skills/<name>/
├── SKILL.md                    # Overview with API changes + best practices
└── references/
    └── <topic>.md              # One topic each, linked from SKILL.md

Guidelines

  • SKILL.md must stay under 500 lines — use references for deep-dive content
  • At most eight reference files per Skill, one topic each, every one linked from SKILL.md
  • Cite release notes, issues, and discussions by URL. Never copy them into the repository
  • API Changes section: only version-specific additions and breaking changes with [source] links
  • Best Practices section: patterns derived from official docs, not general JS knowledge
  • All code examples must be TypeScript + Composition API unless the skill specifically targets Options API
  • Skill licenses use this collection's package.json license, rather than the described package's license. Sync applies it after generation.

Keeping Skills current

packages.json names every package this repository maintains a Skill for. skills-lock.json records the version each Skill was built from.

pnpm validate                   # check every Skill against the rules below
pnpm sync:check                 # report which packages moved ahead of the lockfile
pnpm sync                       # rebuild every Skill whose package moved
pnpm sync @vueuse/core pinia    # rebuild named packages, whatever the lockfile says

The sync runs generate-package-skill through skilld-harness, using OpenCode as the agent runtime and skilld-harness/sandbox-local as the sandbox. It needs OPENCODE_API_KEY, or an opencode auth login session on this computer.

Choose the model with --model= or SKILLD_MODEL. Choose how many run at once with --concurrency= or SKILLD_CONCURRENCY.

One Skill takes about four to seven minutes to rebuild.

The Sync Skills workflow runs the same thing on GitHub, and only when you start it by hand. It needs an OPENCODE_API_KEY repository secret, and it opens a pull request rather than pushing to main.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.