npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

skillgarden

v0.0.9

Published

A portable, index-now-load-later runtime for agent skills.

Readme

SkillGarden (TypeScript)

Part of LoopEngine — a runtime for defining and running AI agents through a transparent ReAct loop — handling SKILL.md-based skill discovery and lazy loading. Works standalone too, no dependency on LoopEngine itself.

See the root README for the pitch, the prior-art landscape, and the scope decisions. This file only covers what's specific to running the code.

Install

npm install

Quickstart

npm run quickstart
import { SkillGarden } from './src/index.js'

const garden = new SkillGarden({ dirs: ['examples/skills'] })
const { included, truncated } = garden.buildIndex()

console.log(garden.invoke('greet', 'world'))
// -> "Hello, world!"

const eligible = garden.eligibleFor(included, ['apps/web/index.tsx'])
// -> includes "deploy:web", since its `paths` glob matches

CLI

npx skillgarden add firecrawl --agent file-agent
# -> Added file-agent:firecrawl -> agents/file-agent/skills/firecrawl/SKILL.md

npx skillgarden add firecrawl
# -> Added firecrawl -> skills/firecrawl/SKILL.md

Copies a skill from the bundled registry/<category>/<skill>/ into a default location that depends on whether --agent is given:

  • With --agent <name> (and no --dir): agents/<name>/skills/<skill>/ — a per-agent skills folder, discovered by pointing that agent's own skillsDirs at it.
  • Without --agent: the flat skills/<skill>/.

<skill> is a bare name (searched across every category — ambiguous only if the same skill name exists under more than one, which none of the bundled ones do today) or an explicit <category>/<skill>, e.g. npx skillgarden add web/firecrawl. Either way the installed copy is always named after the bare skill alone — category is just how this registry organizes its own bundled skills, not something forced onto your own skills/ folder.

Bundled skills

A skill earns a place here only if it teaches the model something it doesn't already reliably know — a private convention, an external API's exact contract, a specific safety procedure — not general reasoning it can already do unprompted (a proofreading pass, a unit conversion, a JSON⇄CSV reshape). Bundling those anyway would spend every caller's index budget for no behavior change.

| Skill | Category | What it does | | --- | --- | --- | | firecrawl | web | Scrape, crawl, or map a website into markdown/structured data via the Firecrawl API — a specific external API's exact endpoints/auth/parameters. | | batch-rename-plan | files | Turn a batch-rename request into an explicit old-name -> new-name mapping, without renaming anything yet — a safety procedure (never execute silently, always show a reviewable plan, flag collisions), not just "how to rename files." |

Pass --dir <path> to use a different root instead of either default. An explicit --dir combined with --agent nests by agent under it — <dir>/<agent>/<skill>/, ready for discoverSkillFiles to pick up as <agent>:<skill> — for the shared-root pattern (one skills root serving several agents, namespaced by subfolder). Pass --force to overwrite an existing install.

Test / build

npm test        # vitest
npm run build   # tsc -> dist/

Status

Loader, budget-aware index, directory discovery with colon-namespacing, and path-conditional activation are real and tested. Published as skillgarden on npm.