Documentation · Getting started
From zero to skill-aware in 60 seconds.
The agent-first workflow
Tell your agent: "install the relevant Recipes skills from recipes.wisechef.ai".
The agent handles the rest via MCP — it searches the catalog, picks the best-scored skill for your task, installs it, and reports back. You don't browse the website by hand.
Prerequisites
- A LoopSkill API key — free for free-tier skills, Pro ($20/mo) for the full library.
- One of the supported agent runtimes below.
- Your key exported:
export RECIPES_API_KEY=rec_xx...
Get your key: Sign up → Dashboard → API Keys → New key.
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/recipes
curl -sL https://recipes.wisechef.ai/skill \
-o ~/.hermes/skills/recipes/SKILL.md Claude Code (native)
Claude Code reads skills from ~/.claude/skills/:
mkdir -p ~/.claude/skills/recipes
curl -sL https://recipes.wisechef.ai/skill \
-o ~/.claude/skills/recipes/SKILL.md Codex CLI (native)
OpenAI Codex CLI uses the same skill directory layout:
mkdir -p ~/.codex/skills/recipes
curl -sL https://recipes.wisechef.ai/skill \
-o ~/.codex/skills/recipes/SKILL.md Claude Desktop (MCP)
Claude Desktop uses the Model Context Protocol. Add the LoopSkill MCP server to your
claude_desktop_config.json:
{
"mcpServers": {
"recipes": {
"command": "uvx",
"args": ["recipes-mcp"],
"env": { "RECIPES_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": "recipes",
"command": "uvx recipes-mcp",
"env": { "RECIPES_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-memoryskill from LoopSkill" - "Install the best SEO audit skill from LoopSkill"
The agent calls GET /api/skills/install?slug=super-memory&mode=files,
downloads the signed tarball, verifies the ed25519 signature, and writes the files locally.
A _meta.json records the install for future syncs.
The free skill super-memory (Cognee + Postgres + pgvector, MIT-licensed) is a great first install — it works immediately with no subscription.
Step 4 — Sync to stay current
Skills are versioned. Run sync periodically to pull patch updates:
recipes sync
Or use the MCP tool: ask your agent "sync my LoopSkill skills to latest".
The recipes_sync MCP tool updates all installed skills in your bundle.
What's in the catalog
60+ skills across marketing, code, web scraping, ops, and sales. Every skill carries
a quality_score, install count, and last-verified date. The daily 7-card
carousel surfaces the most recently refreshed picks.
Browse the full catalog or check today's 7 — but the fastest path is always to ask your agent.
Pricing
- Free: API key, catalog access, all free-tier skills (including super-memory).
- Pro ($20/mo): full library, up to 10 bundles, fleet support.
- Pro+ ($100/mo): up to 200 bundles, pre-built client deployments, priority support, private org catalog.
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, signed tarballs, sandboxing