Agent skill

search

Semantic search across GTM knowledge base using qmd - find context by meaning, not just keywords

majiayu000534★ · 1 repos on radarProfile →
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill search-hathbanger-fridas-choppers-gtm --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Path: skills/analysis/search-hathbanger-fridas-choppers-gtm/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Search Semantic search across your GTM workspace. Find decisions, context, and knowledge by meaning. Uses [qmd](https://github.com/tobi/qmd) - local hybrid search combining BM25 keywords, vector embeddings, and LLM reranking. ## Usage ``` /search "what did we decide about pricing" /search "authentication flow" /search --keyword "API" # Fast keyword-only /search --semantic "how to deploy" # Vector-only ``` ## Setup **New workspaces:** Search is set up automatically during `jfl init` if you choose to enable it. **Existing workspaces:** Follow the manual setup below. ## On Skill Invoke ### Step 1: Check if qmd is installed ```bash which qmd ``` **If not installed:** ``` qmd not found. It's a local search engine for your markdown files. Install it? bun install -g https://github.com/tobi/qmd [Yes] [No] ``` If yes, run: ```bash bun install -g https://github.com/tobi/qmd ``` ### Step 2: Check if GTM is indexed ```bash qmd status ``` Look for a collection that matches this workspace (check `.jfl/config.json` for the collection name). **If no collection exists, guide setup:** ``` This GTM workspace isn't indexed yet. To set up search, run these commands: # Add the workspace as a collectio

What's inside
Steps it walks through
  1. Usage
  2. Setup
  3. On Skill Invoke
  4. Step 1: Check if qmd is installed
  5. Step 2: Check if GTM is indexed
  6. Step 3: Run the search
  7. Step 4: Present results
  8. Search Modes
  9. Keeping Index Fresh
  10. Advanced Options
  11. MCP Server (Optional)
  12. What Gets Indexed
  13. Why Local Search
Ships with 1 file
  • metadata.json
Commands it runs
which qmd
bun install -g https://github.com/tobi/qmd
qmd status
qmd query "USER_QUERY" -n 10
qmd search "USER_QUERY" -n 10
qmd vsearch "USER_QUERY" -n 10
qmd get "FILE_PATH" --full
Re-index all collections
qmd update
Re-index and pull git changes first
More from claude-skill-registry
All skills →
About this skill
What does the search skill do?

Semantic search across GTM knowledge base using qmd - find context by meaning, not just keywords

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill search-hathbanger-fridas-choppers-gtm --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going