Menu
This skill should be used when the user asks to "search notes",
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
Capture feedback about wf, util, or vault plugins and file it as a GitHub issue for improvement. Use after any session where the tooling fell short — wrong agent behavior, missing skill coverage, misleading prompts, workflow friction, or convention gaps. Only for generic plugin improvements that would help ANY project, not repo-specific config. Files to JSai23/claude-tooling with the plugin-feedback label.
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
| name | vault-sem-search-a |
| description | This skill should be used when the user asks to "search notes", |
| metadata | {"source-plugin":"vault","source-skill":"sem-search-a"} |
Action skill — Semantic search operations: BM25, vector search, hybrid search, reindexing.
Search the vault by meaning using qmd, a local semantic search engine for markdown. BM25 + vector search + LLM re-ranking, all local. No cloud APIs.
If qmd is not installed:
brew install oven-sh/bun/bun # Bun runtime (if not installed)
bun install -g github:tobi/qmd # qmd itself
Register the vault as a collection:
qmd collection add "<vault-path>" --name vault
Build initial embeddings (~2GB models downloaded on first run):
qmd embed
Index stored at ~/.cache/qmd/index.sqlite — outside vault, no gitignore needed.
When invoked with --reindex or after batch changes to the vault:
qmd update # Re-index all collections (picks up new/changed/deleted files)
qmd embed # Rebuild vector embeddings (needed after first install or model change)
Use qmd update for routine reindexing. Use qmd embed only for initial setup or embedding model changes.
Fast keyword search. Good for finding notes that mention specific terms.
qmd search "prediction market pricing"
Vector similarity search. Finds conceptually related content even without keyword overlap.
qmd vsearch "how do agents maintain context across sessions"
This is the most useful search mode for finding related notes, confirming filing destinations, and discovering connections.
Combines BM25 + vector search + LLM re-ranking with 6 parallel searches. Highest quality but slower.
qmd query "what patterns emerge in agentic development workflows"
Use for thorough exploration. Overkill for quick lookups.
Retrieve the content of a specific document by path:
qmd get "2-Areas/ai-dev-ecosystem/2025-01-21_agentic-learnings.md"
Append format flags for programmatic use:
--json — JSON output (for parsing results)--csv — CSV output--md — Markdown formatted--files — File paths only (one per line, useful for piping)Example: qmd vsearch "agentic development" --files returns just paths.
| Need | Command | Speed |
|---|---|---|
| Find notes mentioning a term | qmd search | Fast |
| Find conceptually similar notes | qmd vsearch | Medium |
| Thorough exploration of a topic | qmd query | Slower |
| Confirm filing destination | qmd vsearch | Medium |
| Discover cross-area connections | qmd query | Slower |
qmd vsearch to confirm filing destinationsqmd vsearch or qmd query to find semantically similar notesqmd query for thorough connection discoveryqmd update after batch processingqmd collection add "<vault-path>" --name vaultqmd embed (first time takes a few minutes)qmd update to re-indexqmd collection list shows registered collections