SuperSkill Registry

Last 30 days

Uptime

100%

Response time

30 ms typical, 30 ms slowest 5%

Last check

3 h ago

Next check

in 3 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "superskill-registry": {
      "type": "http",
      "url": "https://superskill.sh/mcp"
    }
  }
}

12 tools

• search

  Search public agent resources. Returns exact resource ids and canonical browser-openable URLs for citation.

• fetch

  Fetch the complete public catalog record for an exact resource id returned by search, including a canonical citation URL.

• search_harnesses

  Search the SuperSkill registry by task, job, title, summary or tag.

• harness_detail

  Return manifest, trust signals, example and file list for one harness.

• search_resources

  Search mixed source-aware resources: harnesses, skills, plugins, workflows, MCP servers, configs, guides, runtimes and directories.

• resource_detail

  Return provenance, trust, popularity and actions for one mixed resource. Pass version to bind a hosted immutable release; latest is never substituted for an explicit version.

• resource_use_instructions

  Return the best safe next action for a mixed resource. Pass version to bind an immutable hosted release. Hosted skills expose explicit-consent exact native client install commands; upstream-only resources stay open-only.

• pull_instructions

  Return CLI and HTTP commands for pulling a harness into a local workspace.

• pull_harness

  Return archive files for a harness. Paid harnesses return payment requirements unless the Bearer token is entitled.

• search_docs

  Search /llms.txt and agent guidance for API, CLI, MCP and safety instructions.

• publish_markdown_to_harness

  Convert markdown into an unverified harness scaffold. Requires a SuperSkill Bearer token.

• publish_resource_package

  Publish an immutable canonical hosted package release. Requires a confirmed-user Bearer with active superskill:managed scope, semantic version and idempotency key. Returns unreviewed trust; never grants a Verified badge.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks