Qmd
Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
Peter Steinberger
@steipete
What This Skill Does
Command-line tool for indexing local files and searching them with BM25, vector, or hybrid retrieval, plus optional reranking. Supports MCP mode for integration with AI agents.
Replaces building custom local search pipelines by providing a single CLI that combines BM25, vector embeddings, and reranking with minimal setup.
When to Use It
- Index a directory of markdown files for fast local search
- Search local documentation using BM25 keyword matching
- Find semantically similar documents with vector search
- Run hybrid search combining keyword and semantic results
- Retrieve a specific document snippet by path and line number
- Expose indexed files to an AI agent via MCP mode
Install
$ openclaw skills install @steipete/qmdqmd
Use qmd to index local files and search them.
Indexing
- Add collection:
qmd collection add /path --name docs --mask "**/*.md" - Update index:
qmd update - Status:
qmd status
Search
- BM25:
qmd search "query" - Vector:
qmd vsearch "query" - Hybrid:
qmd query "query" - Get doc:
qmd get docs/path.md:10 -l 40
Notes
- Embeddings/rerank use Ollama at
OLLAMA_URL(defaulthttp://localhost:11434). - Index lives under
~/.cache/qmdby default. - MCP mode:
qmd mcp.
Top skills in this category
Self-Improving + Proactive Agent
@ivangdavilaSelf-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
ontology
@oswalpalashTyped knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
Humanizer
@biostartechnologyRemove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
Obsidian
@steipeteWork with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
YouTube Watcher
@michaelgatharaFetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract information from it.