name: qmd description: Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information. license: MIT compatibility: Requires qmd CLI or MCP server. Install via npm install -g @tobilu/qmd. metadata: author: tobi version: "1.3.0"

allowed-tools: Bash(qmd:), mcpqmd

QMD - Quick Markdown Search

Local search engine for markdown content.

Status

!qmd status 2>/dev/null || echo "Not installed: npm install -g @tobilu/qmd"

MCP: `structured_search`

{
  "searches": [
    { "type": "lex", "query": "CAP theorem consistency" },
    { "type": "vec", "query": "tradeoff between consistency and availability" }
  ],
  "collections": ["notes", "docs"],
  "limit": 10
}

Search Types

Type	Method	Input
`lex`	BM25	Keywords — exact terms, names, code
`vec`	Vector	Question — natural language
`hyde`	Vector	Answer — hypothetical result (50-100 words)

Writing Good Queries

lex (keyword)

2-5 terms, no filler words
Include synonyms: "auth authentication login"
Use exact names: "PostgreSQL connection pool"
Code identifiers work: "handleError async"

vec (semantic)

Full natural language question
Be specific: "how does the rate limiter handle burst traffic" not "rate limiting"
Include context: "in the payment service, how are refunds processed"

hyde (hypothetical document)

Write 50-100 words of what the answer looks like
Use the vocabulary you expect in the result
Example: "The rate limiter uses a sliding window algorithm with a 60-second window. When a client exceeds 100 requests per minute, subsequent requests return 429 Too Many Requests until the window resets."

Combining Types

Goal	Approach
Know exact terms	`lex` only
Don't know vocabulary	`vec` only
Best recall	`lex` + `vec`
Complex topic	`lex` + `vec` + `hyde`

First query gets 2x weight in fusion — put your best guess first.

Collection Filtering

{ "collection": "docs" }           // Single collection
{ "collections": ["docs", "notes"] }  // Multiple (OR)

Omit both to search all collections.

Other MCP Tools

Tool	Use
`get`	Retrieve doc by path or `#docid`
`multi_get`	Retrieve multiple by glob/list
`status`	Collections and health

CLI

qmd query "question"              # Auto-expand + rerank
qmd query $'lex: X\nvec: Y'       # Structured
qmd search "keywords"             # BM25 only
qmd vsearch "question"            # Vector only
qmd get "#abc123"                 # By docid

Setup

npm install -g @tobilu/qmd
qmd collection add ~/notes --name notes
qmd embed

SKILL.md 2.8 KB Verlauf Originalformat