Agent skill

Qmd

by compozy in compozy/compozy

Search markdown knowledge bases, notes, and documentation using QMD.

MITAuto-check passedKnowledge Management

Install Qmd

skills CLI
$ npx skills add compozy/compozy --skill qmd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install compozy/compozy qmd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/compozy/compozy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/qmd .claude/skills/qmd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
qmd
GitHub stars
2.8k
Token cost
~1k tokens
SKILL.md length
314 words
Files
2 (incl. references)
Skills in repo
47
Repo updated
First seen
Licence
MIT

At a glance

Search markdown knowledge bases, notes, and documentation using QMD.

  • Users ask to search notes
  • SKILL.md covers Status, MCP: query, Other MCP Tools and CLI, plus 2 more sections
  • Calls curl and npm
  • Look up information

What it does

Qmd is an agent skill from compozy/compozy. Search markdown knowledge bases, notes, and documentation using QMD. Use when users ask to search notes, find documents, or look up information.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/mcp-setup.md`). Compatibility notes: Requires qmd CLI or MCP server. Install via npm install -g @tobilu/qmd.

It sits in Knowledge Management, covering Knowledge bases and Markdown. The repository describes itself as: An operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) and they become a team: they split the work, hand tasks to each… The licence is MIT.

When your agent uses it

  • Users ask to search notes
  • Look up information

Example prompts

  • “/qmd”

Requirements

  • Node.js
  • Compatibility (from SKILL.md): Requires qmd CLI or MCP server. Install via `npm install -g @tobilu/qmd`.
  • Pre-approved tools (allowed-tools): Bash(qmd:*), mcp__qmd__*

What it can do on your machine

Read from SKILL.md and the folder at commit eec2ed1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(qmd:*)
    • mcp__qmd__*

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • npm

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use curl and npm, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires qmd CLI or MCP server. Install via `npm install -g @tobilu/qmd`.

    From compatibility in the SKILL.md frontmatter.

Context cost

Qmd loads about 1k tokens when it runs, and up to ~1.5k if it reads all its reference files. Until then it costs about 37 tokens; SKILL.md has 314 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from compozy/compozy at commit eec2ed1, republished under its MIT licence (© compozy). 314 words, ~1,017 tokens.

Download SKILL.mdSave it as .claude/skills/qmd/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
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.
allowed-tools
Bash(qmd:*), mcp__qmd__*
compatibility
Requires qmd CLI or MCP server. Install via `npm install -g @tobilu/qmd`.
license
MIT
metadata.author
tobi
metadata.version
2.0.0

Local search engine for markdown content.

Status

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

MCP: query

json
{
  "searches": [
    { "type": "lex", "query": "CAP theorem consistency" },
    { "type": "vec", "query": "tradeoff between consistency and availability" }
  ],
  "collections": ["docs"],
  "limit": 10
}
Query Types
TypeMethodInput
lexBM25Keywords — exact terms, names, code
vecVectorQuestion — natural language
hydeVectorAnswer — hypothetical result (50-100 words)
Writing Good Queries

lex (keyword)

  • 2-5 terms, no filler words
  • Exact phrase: "connection pool" (quoted)
  • Exclude terms: performance -sports (minus prefix)
  • Code identifiers work: handleError async

vec (semantic)

  • Full natural language question
  • Be specific: "how does the rate limiter handle burst traffic"
  • 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

expand (auto-expand)

  • Use a single-line query (implicit) or expand: question on its own line
  • Lets the local LLM generate lex/vec/hyde variations
  • Do not mix expand: with other typed lines — it's either a standalone expand query or a full query document
Intent (Disambiguation)

When a query term is ambiguous, add intent to steer results:

json
{
  "searches": [
    { "type": "lex", "query": "performance" }
  ],
  "intent": "web page load times and Core Web Vitals"
}

Intent affects expansion, reranking, chunk selection, and snippet extraction. It does not search on its own — it's a steering signal that disambiguates queries like "performance" (web-perf vs team health vs fitness).

Combining Types
GoalApproach
Know exact termslex only
Don't know vocabularyUse a single-line query (implicit expand:) or vec
Best recalllex + vec
Complex topiclex + vec + hyde
Ambiguous queryAdd intent to any combination above

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

Lex Query Syntax
SyntaxMeaningExample
termPrefix matchperf matches "performance"
"phrase"Exact phrase"rate limiter"
-termExcludeperformance -sports

Note: -term only works in lex queries, not vec/hyde.

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

Omit to search all collections.

Other MCP Tools

ToolUse
getRetrieve doc by path or #docid
multi_getRetrieve multiple by glob/list
statusCollections and health

CLI

bash
qmd query "question"              # Auto-expand + rerank
qmd query $'lex: X\nvec: Y'       # Structured
qmd query $'expand: question'     # Explicit expand
qmd query --json --explain "q"    # Show score traces (RRF + rerank blend)
qmd search "keywords"             # BM25 only (no LLM)
qmd get "#abc123"                 # By docid
qmd multi-get "journals/2026-*.md" -l 40  # Batch pull snippets by glob
qmd multi-get notes/foo.md,notes/bar.md   # Comma-separated list, preserves order

HTTP API

bash
curl -X POST http://localhost:8181/query \
  -H "Content-Type: application/json" \
  -d '{"searches": [{"type": "lex", "query": "test"}]}'

Setup

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

© compozy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/qmd of compozy/compozy.

  • SKILL.md
  • references/mcp-setup.md

Open the folder on GitHubat commit eec2ed1

Compare with similar skills

Qmd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Qmd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Qmd this skillcompozy/compozy2.8k—~1kAutomated safety check: PassMIT
QmdSAP/e-mobility-charging-stations-simulator2271 repos~2.8kAutomated safety check: PassMIT
Wiki Viewerrohitg00/pro-workflow2.9k—~1.1kAutomated safety check: PassNone
Okf Open Knowledge Formatfabricioctelles/skills106—~5.7kAutomated safety check: PassApache-2.0
Kb SetupBlackBeltTechnology/pi-agent-dashboard315—~776Automated safety check: PassMIT
Ingest SourceAbilityai/cornelius109—~4.3kAutomated safety check: NotesMIT

Similar skills

  • Qmd

    SAP/e-mobility-charging-stations-simulator

    Official

    Search local markdown knowledge bases, notes, docs, and wikis with QMD.

    227 GitHub starsUsed in 1 repo~2.8k tokens
    Knowledge ManagementAuto-check passed
  • Wiki Viewer

    rohitg00/pro-workflow

    Render a self-contained HTML viewer for a pro-workflow wiki.

    2.9k GitHub stars~1.1k tokensUpdated 9 days ago
    Knowledge ManagementAuto-check passed
  • Okf Open Knowledge Format

    fabricioctelles/skills

    Create, validate, and enrich Open Knowledge Format (OKF) bundles — the open spec for representing organizational knowledge as markdown files with YAML frontmatter.

    106 GitHub stars~5.7k tokensUpdated 4 days ago
    Knowledge ManagementAuto-check passed
  • Kb Setup

    BlackBeltTechnology/pi-agent-dashboard

    Set up, initialize, or configure the local markdown knowledge base for a project.

    315 GitHub stars~776 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Ingest Source

    Abilityai/cornelius

    Fully autonomous end-to-end ingestion of a SINGLE source (book, paper, article, transcript) into the knowledge base - prepare to markdown, extract insights against the live index, refresh the index…

    109 GitHub stars~4.3k tokensUpdated 15 days ago
    Knowledge ManagementAuto-check: notes
  • Outline

    Vortiago/mcp-outline

    Conventions and efficient workflows for Outline knowledge bases via mcp-outline tools.

    156 GitHub stars~818 tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

More from compozy/compozy

All 47 skills in this repo
  • Eng Real Scenario QA

    compozy/compozy

    Dogfoods Compozy through an autonomous startup scenario with live providers, cross-surface observation, and strict evidence audit.

    2.8k GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Eng Test Conventions

    compozy/compozy

    Go test-shape discipline for Compozy. An agent skill from compozy/compozy.

    2.8k GitHub stars~467 tokensUpdated today
    Auto-check passed
  • Assistant UI

    compozy/compozy

    Guide for assistant-ui library - AI chat UI components. An agent skill from compozy/compozy.

    2.8k GitHub stars~958 tokensUpdated today
    Auto-check passed
  • Guide for assistant-ui UI primitives - ThreadPrimitive, ComposerPrimitive, MessagePrimitive.

    2.8k GitHub stars~999 tokensUpdated today
    Auto-check passed
  • Assistant UI Runtime

    compozy/compozy

    Guide for assistant-ui runtime system and state management. An agent skill from compozy/compozy.

    2.8k GitHub stars~856 tokensUpdated today
    Auto-check passed
  • Assistant UI Streaming

    compozy/compozy

    Guide for assistant-stream package and streaming protocols. An agent skill from compozy/compozy.

    2.8k GitHub stars~813 tokensUpdated today
    Auto-check passed

Questions about Qmd

What does Qmd do?

Search markdown knowledge bases, notes, and documentation using QMD. Qmd is an agent skill from compozy/compozy. Search markdown knowledge bases, notes, and documentation using QMD.

When should I use Qmd?

Qmd fits situations like: users ask to search notes; look up information.

How do I install Qmd in Claude Code?

Run `npx skills add compozy/compozy --skill qmd -a claude-code`. Or copy the skill folder (.agents/skills/qmd in compozy/compozy) into .claude/skills/qmd in your project. Claude Code loads it when a task matches its description.

How do I install Qmd in Codex?

Run `npx skills add compozy/compozy --skill qmd -a codex`. Or copy the skill folder (.agents/skills/qmd in compozy/compozy) into .agents/skills/qmd in your project. Codex loads it when a task matches its description.

Can I use Qmd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add compozy/compozy --skill qmd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/qmd, .gemini/skills/qmd, .github/skills/qmd and .opencode/skills/qmd in your project.

What does Qmd need to run?

Going by SKILL.md and its folder, Qmd needs the command-line tools its instructions call (curl and npm). Our summary lists: Node.js. Its frontmatter pre-approves these tools: Bash(qmd:*), mcp__qmd__*. Compatibility (from SKILL.md): Requires qmd CLI or MCP server. Install via `npm install -g @tobilu/qmd`..

Does Qmd access the network?

SKILL.md contains no URLs. Its commands use curl and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Qmd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Qmd use?

Qmd is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Qmd use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 499 tokens, read only when the agent opens those files.

What are the alternatives to Qmd?

Skills that share tags, products or a category with Qmd: Qmd (SAP/e-mobility-charging-stations-simulator, 227 stars), Wiki Viewer (rohitg00/pro-workflow, 2.9k stars), Okf Open Knowledge Format (fabricioctelles/skills, 106 stars) and Kb Setup (BlackBeltTechnology/pi-agent-dashboard, 315 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Qmd?

compozy (a GitHub organization) maintains it in compozy/compozy, which has 2,792 GitHub stars. The repository holds 47 skills in this directory. The repository was last updated on October 8, 2026.

Source: compozy/compozy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.