On-demand access to thousands of install-ranked Claude Code skills - search and load mid-task.
io.github.skillselion/skillselion-mcp (MCP)
Skillselion MCP provides on-demand access to thousands of install-ranked Claude Code skills. It supports searching and loading skills mid-task. The server is presented as part of the Skillselion directory, described as “86,000+ skills” ranked by real installs, with additional references to marketplaces and MCP servers in the excerpt.
🛠️ Key Features
On-demand access to thousands of Claude Code skills
Search and load skills during an active task
🚀 Use Cases
Finding Claude Code skills without leaving the current workflow
Loading a skill mid-task after searching
⚡ Developer Benefits
Integrates MCP support for Claude Code skill retrieval
Uses a directory of skills ranked by real installs (as stated)
⚠️ Limitations
The provided excerpt does not specify authentication, supported protocols beyond MCP, or the full tool schema
Details on individual tool operations are not included in the available text
The catalog behind it: skillselion.com - 86,000+ skills, plugin marketplaces & MCP servers, ranked by real installs.
Give your coding agent thousands of community-proven skills - loaded on demand, mid-task.
It searches Skillselion, a curated directory of Claude Code skills, MCP servers & marketplaces ranked by real installs,
and pulls a skill's actual instructions + bundled files into the session. Proven patterns, not guesses.
🧩 Works with Claude Code · Claude Desktop · Cursor · Codex · any MCP client
Real session: the agent calls synthesize_skills and builds a consensus playbook from 5 community skills
Real, unedited session: the agent pulls a consensus playbook from 5 community skills, then loads the top skill and applies it.
🚀 Install
Claude Code - one line:
bash
claude mcp add skillselion --scope user -- npx -y skillselion-mcp
Claude Desktop / Cursor / Codex - add to your MCP config:
No build step, no auth, no API key. One ~30 KB file via npx.
Want it fully automatic? npx -y skillselion-mcp setup registers the server and installs a session hook so your agent loads the right skill the moment a task matches - see Skill autopilot.
🔧 Tools
Tool
What it does
📥 load_skill
The everyday default: finds the best-matching skill for your task and materializes it - real SKILL.md in context + bundled scripts/references on disk - so the agent follows it like an installed skill. Returns ranked runner-ups you can switch to.
🧬 synthesize_skills
The cross-source playbook: merges the key rules of the top ~5 matching skills into one deduped, provenance-tagged digest - the field's consensus, not one author's take.
🔍 search_skillselion
Search the catalog by keyword or task; filter by skill / mcp / marketplace.
🏆 top_skillselion
The leaderboard - the most-installed skills and top-starred MCP servers right now.
We asked Claude, on camera, what the MCP gave it: "I couldn't have told you 'this is the field's consensus, not my opinion' - that's the part I can't fake."
🔒 Private by default
Read-only, no auth, no secrets. It never sends your code, files, or the context you pass - only a scrubbed search query + which skill matched, so the catalog learns what to add next. Set DO_NOT_TRACK=1 to disable even that.
🪄 Skill autopilot
bash
npx -y skillselion-mcp setup # interactive - pick your packs
npx -y skillselion-mcp setup --yes# non-interactive - agents / CI
Registers the MCP globally and installs a Claude Code SessionStart hook that primes every session with skills relevant to you - so loads happen on their own.
Setup flags & packs
Flag
What it does
--packs <a,b,…>
one or more packs (or all), e.g. --packs frontend,backend; frontend:6 sets a per-pack count
--per-pack N
skills per pack (default 3) · --top N sets the popular count
--auto
adapt each session to the current repo's stack
--history
infer your focus from Claude Code / Codex history (one-time scan)
Safe by design: ~/.claude/settings.json is merged, never clobbered; re-running de-dupes and upgrades the hook in place.
Env vars
Var
Default
What it controls
GITHUB_TOKEN
-
optional, read-only; raises GitHub's rate limit for full multi-file skill loads (60 → 5000 req/hr)
SK_INLINE_BUDGET
6000
char cap on the in-context SKILL.md portion (the full skill is always on disk)
SK_SYNTH_N
5
how many top skills synthesize_skills merges (2-8)
SK_SYNTH_PER_SKILL
12
max rules kept per source skill
SK_SYNTH_BUDGET
4000
char cap on the merged digest
DO_NOT_TRACK
-
set 1 to disable the anonymous demand signal
Troubleshooting
The agent doesn't see the tools. Some clients surface MCP tools lazily - tell the agent to search its tools for "skillselion" first (e.g. ToolSearch), then call it. The setup hook automates this nudge.
load_skill returns only the SKILL.md, no bundled files. You hit GitHub's unauthenticated 60 req/hr limit - set a read-only GITHUB_TOKEN in the server's env.
"No skill on Skillselion clearly matches..." The relevance floor working as intended - nothing topical matched, so it refuses to waste your context. Try a more specific query.
Setup couldn't auto-register. Run the printed claude mcp add ... line yourself.
Development
bash
npm install
npm test# offline: server boots, tools, synthesis
npm run test:live # live catalog + GitHub (set GITHUB_TOKEN)
