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.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ory/lumen --skill doctor --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Doctor?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ory-doctor-lumen)More formats (shields.io, HTML) on the badges page.
---
name: doctor
description: 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.
---
# 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.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.