From zero to skill-aware in 60 seconds.

Prerequisites

• One of the supported agent runtimes below.
• For free skills: nothing else. No account and no key — they install anonymously.
• An API key only if you need it — for the MCP tools (the Claude Desktop and Cursor setups below), saving to your Library, private bundles and fleets. The key is free, no card required. Every catalog skill installs on the Free tier; Pro ($9.95/mo) raises two limits: private bundles and API keys.

Get a key: create a free account → Library → API keys → New key. Then export it: export LOOPSKILL_API_KEY=rec_xx...

Step 1 — Install the meta-skill

The meta-skill is a single SKILL.md file that teaches your agent the entire marketplace. Drop it into your agent's skills directory once. Your agent will then be able to search and install any skill on-demand.

Hermes (native)

Hermes auto-discovers SKILL.md files under ~/.hermes/skills/:

mkdir -p ~/.hermes/skills/loopskill
curl -sL https://app.loopskill.io/skill \
     -o ~/.hermes/skills/loopskill/SKILL.md

Claude Code (native)

Claude Code reads skills from ~/.claude/skills/:

mkdir -p ~/.claude/skills/loopskill
curl -sL https://app.loopskill.io/skill \
     -o ~/.claude/skills/loopskill/SKILL.md

Codex CLI (native)

OpenAI Codex CLI uses the same skill directory layout:

mkdir -p ~/.codex/skills/loopskill
curl -sL https://app.loopskill.io/skill \
     -o ~/.codex/skills/loopskill/SKILL.md

Claude Desktop (MCP)

Claude Desktop uses the Model Context Protocol. LoopSkill is a hosted MCP server — no local install. Add it to your claude_desktop_config.json:

{
  "mcpServers": {
    "loopskill": {
      "url": "https://app.loopskill.io/api/mcp/http/",
      "headers": { "x-api-key": "rec_xx..." }
    }
  }
}

After saving, restart Claude Desktop. You'll see the LoopSkill tools (search, install, sync) available in the tool picker. See MCP setup for full details.

Cursor (MCP)

Open Cursor Settings → MCP → Add Server:

{
  "name": "loopskill",
  "url": "https://app.loopskill.io/api/mcp/http/",
  "headers": { "x-api-key": "rec_xx..." }
}

Step 2 — Search the catalog

Once the meta-skill is installed, your agent can search the catalog. Try asking:

• "Search LoopSkill for an SEO audit skill"
• "What LoopSkill skills exist for client reporting?"
• "Find a LoopSkill skill that generates content calendars"

Under the hood, the agent calls GET /api/skills/search?q=... and ranks results by quality_score, last_verified, and install count.

Step 3 — Install your first skill

Tell your agent to install a skill. Example:

• "Install the super-memory skill from LoopSkill"
• "Install the best SEO audit skill from LoopSkill"

The agent calls GET /api/skills/install?slug=super-memory&mode=files, downloads the tarball via an expiring signed URL, verifies its checksum_sha256, and writes the files locally. A _meta.json records the skill's slug, version and install time.

The free skill super-memory (Cognee + Postgres + pgvector, MIT-licensed) is a great first install — it works immediately with no subscription.

Step 4 — Stay current

One skill: re-run the Step 3 install with the same slug; you get the latest version and its sha256.

Several skills, or several machines: put them in a bundle once (loopskill_compose_bundle_from_links with your skill links — it returns the bundle id), then run loopskill_bundle_install with that id on each machine. To update, re-run loopskill_bundle_install on each machine: a bundle does not pin versions unless you pin it, so the install always returns the latest version of every skill — a download URL and sha256 each; your agent downloads each tarball, checks its sha256, and unpacks it into the skills folder. loopskill_sync is only for bundles you want pinned: it writes the current latest versions as the bundle's pins (it does not touch files on your machine), and the bundle then stays on those versions until you sync again.

Optional — the loopskill command-line tool

A small, free command-line tool (Python 3.9+, MIT, no dependencies) that shows which skills are already on a machine and how two machines differ. You do not need it to install skills.

pip install loopskill

loopskill import lists the skills in ~/.claude/skills, ~/.codex/skills, ~/.cursor/skills and ~/.hermes/skills as a lockfile, and loopskill diff compares two lockfiles (or a lockfile and this machine). Both make zero network calls and need no account.

loopskill import -o mine.lock.json
loopskill diff mine.lock.json

loopskill pull and loopskill apply fetch a public bundle and write it to a local folder (apply is a dry run until you add --write). Run loopskill --help for every command. Source and full reference: cli/ on GitHub.

What's in the catalog

Skills across marketing, code, web scraping, ops, and sales — see the live count on the catalog page or GET /api/stats. Every skill carries a quality_score, install count, and last-verified date.

Browse the full catalog — but the fastest path is always to ask your agent.

Pricing

• Free: 1 API key (it works on all your machines at once), catalog access, all skills (including super-memory), 2 private bundles (your Liked list uses one from the moment you open your Library).
• Pro ($9.95/mo): 50 private bundles, 10 API keys (revoke one machine or client without touching the rest), priority support. The full public catalog is already unlimited on Free — Pro raises limits, it doesn't unlock exclusive skills. Public bundles are unlimited on every tier, including Free.
• Self-host: run the whole platform yourself (MPL-2.0) — no LoopSkill account, no card; the caps live in config/tiers.yaml on your server, so you can raise them. See the self-host guide.

Next steps

• How it works — the 3-level progressive loading model
• MCP setup — full Claude Desktop / Cursor / Cline config
• New agent runtime — 10-minute guide for unlisted runtimes
• Security model — auth, install checksums, sandboxing