Peter Steinberger

Qmd

AI Agentv1.0.0
By Peter SteinbergerUpdated 2026-09-16qmd@clawhub_steipete/qmd
Tool Use

According to AlphaMoat, as of 2026-10, Qmd has 44,435 downloads and 110 stars — ranked by downloads #572 among 10,914 AI skills in this ranking, and #109 of 1,632 in AI Agent.

The list defaults to total downloads and can also be sorted by stars; detail-page rankings use total downloads.

Downloads
44.4K
Stars
110
Overall download rank
#572
Top 6% overall · Top 7% in AI Agent
PlatformDownloadsStarsComments
ClawHub ↗36.7K1105
SkillHub ↗44.4K110—

Platforms count differently and update at different times.

What this skill does

Use qmd to create a collection from a local directory, then search it with keywords, vectors, or hybrid search; retrieve a document slice by path and line, or connect an agent through MCP mode. Embeddings and reranking use Ollama at OLLAMA_URL, which defaults to localhost, and the index is cached under ~/.cache/qmd by default. Indexed content remains searchable in that cache. The install metadata points to an unpinned GitHub package, so review or pin the dependency before installing.

Profile published 2026-10-27

What you can do with it

  • Index a local project or documentation directory for search.
  • Find related passages with vector or hybrid search.

When to use it

  • When you need to search documents in a local collection.
  • When you want to expose search through MCP mode to an agent.

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Index my notes directory, then search for passages about cache invalidation.
Retrieve a slice of this document from the specified line so I can inspect its context.

Monthly Trend

Downloads44.4K
26.9K36.3K45.7K2026-03 · Downloads 28.2K2026-05 · Downloads 32.6K2026-06 · Downloads 33.3K2026-07 · Downloads 34.6K2026-08 · Downloads 35.3K2026-09 · Downloads 35.9K2026-10 · Downloads 44.4K26-0326-0926-10
Stars110
981051112026-03 · Stars 992026-05 · Stars 1072026-06 · Stars 1102026-07 · Stars 1102026-08 · Stars 1102026-09 · Stars 1102026-10 · Stars 11026-0326-0926-10

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change. Other skills share this name; figures from before the change are attributed to this one, which currently has the most downloads.

MonthDownloadsMoMStars
2026-1044.4K—110
2026-0935.9K—110
2026-0835.3K+1.8%110
2026-0734.6K+3.9%110
2026-0633.3K+2.3%110
2026-0532.6K—107
2026-0328.2K—99

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

817 B · ClawHub v1.0.0
---
name: qmd
description: Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.
homepage: https://tobi.lutke.com
metadata: {"clawdbot":{"emoji":"📝","requires":{"bins":["qmd"]},"install":[{"id":"node","kind":"node","package":"https://github.com/tobi/qmd","bins":["qmd"],"label":"Install qmd (node)"}]}}
---

# qmd

Use `qmd` to index local files and search them.
Show all (27 lines)

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` (default `http://localhost:11434`).
- Index lives under `~/.cache/qmd` by default.
- MCP mode: `qmd mcp`.

Popular in AI Agent

self-improving agentAI Agent

Records learnings, errors and corrections as Markdown files for later reuse and promotion into workspace memory.

↓ 1.6M★ 4.5Kpskoett
技能发现·Find SkillsAI Agent

Finds skills in local and remote catalogs from a plain-language request and recommends what to install.

↓ 1.6M★ 1.8K桂皮
Agent BrowserAI Agent

A browser-automation command line skill for AI agents.

↓ 1.2M★ 1.0KNicolas Kleiber
Self-Improving + Proactive AgentAI Agent

Turns corrections and self-review into tiered memory and promotes or archives it by use.

↓ 696.4K★ 1.6KIván
Proactive AgentAI Agent

A workspace setup guide for planning proactive follow-up, working memory and review routines for an AI agent.

↓ 579.3K★ 916halthelobster
Skill CreatorAI Agent

A guide to creating and updating effective Claude skills.

↓ 477.3K★ 485chindden
Skill VetterAI Agent

Reviews a third-party skill's source, permissions, and danger patterns against a checklist before it is installed.

↓ 445.2K★ 1.3Kspclaudehome
唐朝诗仙李白 · Ai Agent SkillAI Agent

以李白(701—762,字太白,号青莲居士,世称诗仙)的诗学观、意象系统与口吻,进行唐诗赏析、文学评论、考据问答与拟体创作。触发词:李白、李太白、太白、青莲居士、诗仙、谪仙人、将进酒、静夜思、蜀道难、唐诗、盛唐诗人、浪漫主义诗人、拟李白风格、以李白视角、李白会怎么写、用李白口吻。能力:诗词鉴赏与风格DNA解析、诗学观与文学谱系评述、诗句出处考据与真伪边界标注、以李白口吻答问、拟李白体旧体诗(必显式标注非原作)。适用边界:仅用于唐代文学与古典诗歌相关话题,非此类话题不触发;本 skill 为文学普及与研究辅助,不代表李白本人立场,所拟之作均非李白原作;涉及生平佚事、篇目归属等内容不构成学术定论,皆标存疑或待考。

↓ 435.8K★ 4user_ff4d9420

More from Peter Steinberger

Data as of 2026-10. Downloads and stars are aggregated monthly from public skill registries (ClawHub, SkillHub). See data methodology.