Doctor

by oryf60f9ecee417No licenseListed Oct 8, 2026Updated Oct 8, 2026

Run a health check on the bundled Lumen semantic search setup for the current project, verify backend reachability and index freshness, and summarize remediation steps.

Instructions onlyDevOps & Cloud
AI-generated overview

Runs a health check on a project's bundled Lumen semantic search setup, verifying backend reachability and index freshness.

What it does
Guides the agent through calling the Lumen health_check and index_status tools for the current project, then reporting a concise summary of embedding service status, index totals, storage totals, and any MCP or plugin setup issues. It also explains that the semantic_search tool seeds the index on first use and suggests running lumen index . for eager indexing. The deliverable is a diagnostic summary with remediation steps, not a file.
When to use it
Use when a project's Lumen semantic search seems unavailable, stale, or misconfigured, or when the user asks for a health check of the Lumen setup. Also useful before relying on semantic search, to confirm the embedding backend is reachable and the index is fresh.
Requirements
Requires the Lumen MCP or plugin tools health_check and index_status to be available, plus access to the current project directory. No scripts ship with the skill; it is instructions only.

Lumen Doctor

Run a health check on the bundled Lumen semantic search setup for the current project.

Steps

  1. Call the Lumen health_check tool to verify the embedding service is reachable.
  2. Call the Lumen index_status tool with path or cwd set to the current working directory to check index freshness.
  3. Report a concise summary:
    • Embedding service status, backend, host, and model
    • Index totals: files, chunks, last indexed time, stale or fresh
    • Storage totals: unique vectors, shared references, deduplication ratio, vector precision, database bytes, and reclaimable bytes
    • Any MCP or plugin setup issue that blocks the tools
  4. If no index exists yet, explain that the Lumen semantic_search tool seeds the index on first use.
  5. If the user wants eager indexing instead of waiting for the next search, suggest running lumen index . in the repository root.
  6. Interpret storage totals as collection-wide values shared by compatible Git worktrees; file, chunk, freshness, and indexing values are project-local. A high deduplication ratio is expected and is not an index-health problem.

Source and attribution

Source:ory/lumeninskills/doctorat commitf60f9ec

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal