AGENT SKILL

qmd

Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.

License 许可
MIT
最近更新
2026-11-10
Stars
★ 1
Forks
0

01 前言 Front Matter

name
qmd
description
Local hybrid search for markdown notes and docs. Use when searching notes, finding related content, or retrieving documents from indexed collections.
description_en
Local search engine for Markdown notes
description_zh
本地 Markdown 笔记搜索引擎

03 SKILL.md 正文

qmd - Quick Markdown Search

Local search engine for Markdown notes, docs, and knowledge bases. Index once, search fast.

When to use (trigger phrases)

  • "search my notes / docs / knowledge base"
  • "find related notes"
  • "retrieve a markdown document from my collection"
  • "search local markdown files"

Default behavior (important)

  • Prefer qmd search (BM25). It's typically instant and should be the default.
  • Use qmd vsearch only when keyword search fails and you need semantic similarity (can be very slow on a cold start).
  • Avoid qmd query unless the user explicitly wants the highest quality hybrid results and can tolerate long runtimes/timeouts.

Prerequisites

  • Bun >= 1.0.0
  • macOS: brew install sqlite (SQLite extensions)
  • Ensure PATH includes: $HOME/.bun/bin

Install Bun (macOS): brew install oven-sh/bun/bun

Install

bun install -g https://github.com/tobi/qmd

Setup

qmd collection add /path/to/notes --name notes --mask "**/*.md"
qmd context add qmd://notes "Description of this collection"  # optional
qmd embed  # one-time to enable vector + hybrid search

What it indexes

  • Intended for Markdown collections (commonly **/*.md).
  • In our testing, "messy" Markdown is fine: chunking is content-based (roughly a few hundred tokens per chunk), not strict heading/structure based.
  • Not a replacement for code search; use code search tools for repositories/source trees.

Search modes

  • qmd search (default): fast keyword match (BM25)
  • qmd vsearch (last resort): semantic similarity (vector). Often slow due to local LLM work before the vector lookup.
  • qmd query (generally skip): hybrid search + LLM reranking. Often slower than vsearch and may timeout.

Performance notes

  • qmd search is typically instant.
  • qmd vsearch can be ~1 minute on some machines because query expansion may load a local model (e.g., Qwen3-1.7B) into memory per run; the vector lookup itself is usually fast.
  • qmd query adds LLM reranking on top of vsearch, so it can be even slower and less reliable for interactive use.
  • If you need repeated semantic searches, consider keeping the process/model warm (e.g., a long-lived qmd/MCP server mode if available in your setup) rather than invoking a cold-start LLM each time.

Common commands

qmd search "query"             # default
qmd vsearch "query"
qmd query "query"
qmd search "query" -c notes     # Search specific collection
qmd search "query" -n 10        # More results
qmd search "query" --json       # JSON output
qmd search "query" --all --files --min-score 0.3

Useful options

  • -n <num>: number of results
  • -c, --collection <name>: restrict to a collection
  • --all --min-score <num>: return all matches above a threshold
  • --json / --files: agent-friendly output formats
  • --full: return full document content

Retrieve

qmd get "path/to/file.md"       # Full document
qmd get "#docid"                # By ID from search results
qmd multi-get "journals/2025-05*.md"
qmd multi-get "doc1.md, doc2.md, #abc123" --json

Maintenance

qmd status                      # Index health
qmd update                      # Re-index changed files
qmd embed                       # Update embeddings

Keeping the index fresh

Automate indexing so results stay current as you add/edit notes.

  • For keyword search (qmd search), qmd update is usually enough (fast).
  • If you rely on semantic/hybrid search (vsearch/query), you may also want qmd embed, but it can be slow.

Example schedules (cron):

# Hourly incremental updates (keeps BM25 fresh):
0 * * * * export PATH="$HOME/.bun/bin:$PATH" && qmd update

# Optional: nightly embedding refresh (can be slow):
0 5 * * * export PATH="$HOME/.bun/bin:$PATH" && qmd embed

If your Clawdbot/agent environment supports a built-in scheduler, you can run the same commands there instead of system cron.

Models and cache

  • Uses local GGUF models; first run auto-downloads them.
  • Default cache: ~/.cache/qmd/models/ (override with XDG_CACHE_HOME).

Relationship to Clawdbot memory search

  • qmd searches your local files (notes/docs) that you explicitly index into collections.
  • Clawdbot's memory_search searches agent memory (saved facts/context from prior interactions).
  • Use both: memory_search for "what did we decide/learn before?", qmd for "what's in my notes/docs on disk?".

04 同仓库更多 Skills

YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

vercel-sandbox

Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

slack

Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

electron

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

dogfood

Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

★ 1
YYC-Cube
YYC-Cube/YYC3-Knowledge-Base

shadcn

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.

★ 1