Skill of Skills

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Quality-ranked, cross-platform directory of AI coding skills, plugins and MCP servers.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Skill of Skills": {
      "url": "https://skills.911fund.io/api/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (6)

• search_skills read-only

  Full-text search over the Skill of Skills directory (AI coding skills, plugins, MCP servers across Claude Code, Cursor, Codex, Windsurf, Cline). Results are ranked by the quality-first composite score, not popularity; when no tool matches every term, the closest partial matches are returned instead (match_mode: "any"), most relevant first. Critical-risk tools are excluded by default (risk_filter); every result carries risk_level and risk_reasons. Scores are evidence, not endorsements.

  Parameters:

  • query (required) — string — What capability you need, e.g. "postgres migrations"
  • limit — integer
  • min_tier — string — Quality floor: curated ≥120, promising ≥80, experimental ≥40
  • platform — string — Restrict to one client platform
  • verified — string — Current Verified Working result: runs only, or any verified tier
  • risk_filter — string — Risk gate: exclude_critical omits critical risk (default); exclude_high omits high and critical risk; none omits no risk levels
  • include_high_risk — boolean — Deprecated alias for risk_filter=none

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_skill read-only

  Full quality profile for one tool by slug (slugs come from search_skills / get_collection): score breakdown, structural signals, risk level and reasons, platforms, repo link. Direct lookups return any active tool regardless of risk — the risk assessment is part of the answer, not a filter here.

  Parameters:

  • slug (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• compare_tools read-only

  Side-by-side quality profiles for 2–5 tools by slug. Same fields as get_skill; ordering follows the request, not rank.

  Parameters:

  • slugs (required) — array

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_collections read-only

  The curated buyer-intent collections (e.g. mcp-servers, testing-qa, browser-automation). Use get_collection for the ranked tools inside one.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_collection read-only

  Quality-ranked tools inside one curated collection. Critical-risk tools are excluded by default (risk_filter); every result carries risk_level and risk_reasons.

  Parameters:

  • slug (required) — string
  • limit — integer
  • risk_filter — string — Risk gate: exclude_critical omits critical risk (default); exclude_high omits high and critical risk; none omits no risk levels
  • include_high_risk — boolean — Deprecated alias for risk_filter=none

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• demand_pulse read-only

  Public, k-anonymous demand signal from the directory: trending searches, most-saved and most-installed tools. Aggregates only — sourced from ≥5 distinct anonymous sessions per entry.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.