Skip to content

Skillcaddy

Local AI Skills central library with per-project symlink enablement. One AISkills folder holds every skill source; symlink on demand into any project's .agents/skills or…

Install

$git clone https://github.com/chenweil/skillcaddy

Install command taken from the project's README or registry entry. Always review code before running it.

Skillcaddy

English · 中文

Local AI skills central library + scoped symlink enablement. One AISkills directory holds every skill source; symlink what you need into a project, the shared user-level Agents directory, or Hermes on demand.

Why Skillcaddy?

If you use Claude Code, Codex, OpenCode, or Pi across multiple projects, you eventually hit one of these:

  • The same skill lives in three repos, slightly drifted each time
  • A new project means copying skills over and wondering which version is current
  • An upstream skill gets updated but your local copy is weeks behind
  • A Claude-Code-only entry needs to coexist with the agents-side list
  • An archived skill slips back in because no one gated it

Skillcaddy fixes this with one AISkills directory as the source of truth and explicit project/global/Hermes symlink scopes as the delivery mechanism.

  • One source of truth — ~/AISkills/ aggregates official / github / personal / archived / skills
  • Zero project pollution — enable by symlink into .agents/skills/; never copy
  • Project or global scope — project links stay local; global links go only to ~/.agents/skills/
  • Independent Hermes scope — official/github/personal skills explicitly link to ~/.hermes/skills/; it ignores HERMES_HOME and never changes project/global scopes
  • Multi-Agent by default — one symlink reaches Claude Code, Codex, OpenCode, Pi via their standard paths
  • Independent enable / disable — agents-side and Claude-Code-side are tracked separately
  • Safe by default — disable only removes the symlink; archived/ requires explicit naming
  • Contribute-friendly — new skills land under skills/<name>/ with SKILL.md + agents/openai.yaml and ship with the repo

Whether you're a solo dev with half a dozen repos, a small team standardizing on shared skills, or an author publishing reusable ones — the contract is the same: skills belong to your library, not to any one project.

Installation

git clone https://github.com/chenweil/skillcaddy.git
cd skillcaddy
npm install
npm start

Requires Node.js >= 20. The web manager uses the fixed default URL http://127.0.0.1:4173. Fill in the target project path on the page, and enable/disable skills. If that port is temporarily occupied, start with PORT=<other-port> npm start.

Bundled spec-pipeline skills

This repository ships three skills under skills/spec-pipeline/ that implement the direction-confirmation gate described in docs/research/0037. They are tracked in git, so a clone has the content — but the project enablement links are not, by design: ADR 0011 Decision 4 keeps project enablements out of the library image (lib/libraryImage.js carries only global and hermes triples). Recreate the links once per checkout:

npm run enable:spec-pipeline
# preview without touching anything
npm run enable:spec-pipeline -- --dry-run

Then check that every spec in this repository satisfies the gate:

npm run check:specs

Both commands are idempotent. check:specs is also part of npm test; a repository with no specs/ directory passes, and --strict inverts that.

Similar plugs

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…

Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.