New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Qmd MCP Skill

by holon-run in holon-run/uxc

Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency.

MITAuto-check passedKnowledge Management

Install Qmd MCP Skill

skills CLI
$ npx skills add holon-run/uxc --skill qmd-mcp-skill -a claude-code

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

GitHub CLI
$ gh skill install holon-run/uxc qmd-mcp-skill --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/holon-run/uxc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/qmd-mcp-skill .claude/skills/qmd-mcp-skill && 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-mcp-skill
GitHub stars
116
Token cost
~1.3k tokens
SKILL.md length
600 words
Files
4 (incl. scripts, references)
Skills in repo
62
Repo updated
First seen
Licence
MIT

At a glance

Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency.

  • Works in 5 steps: Verify the local QMD index first → Use a fixed link command by default → Confirm the daemon-backed stdio path is… → …
  • Tasks that involve MCP servers
  • SKILL.md covers Prerequisites, Core Workflow, Recommended Usage Pattern and Capability Map, plus 3 more sections
  • Runs Shell scripts from its folder; calls nvm

What it does

Qmd MCP Skill is an agent skill from holon-run/uxc. Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/usage-patterns.md` and `scripts/validate.sh`).

It sits in Knowledge Management, covering MCP servers and Knowledge bases. It works with Model Context Protocol and CUDA. The repository describes itself as: A unified CLI for discovering and invoking tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC. The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers
  • Tasks that involve Knowledge bases

Example prompts

  • “/qmd-mcp-skill”

Requirements

  • A Bash shell

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Verify the local QMD index first
  2. Use a fixed link command by default
  3. Confirm the daemon-backed stdio path is active
  4. Inspect operation schema before execution
  5. Prefer typed retrieval over CLI-style auto expansion

What it can do on your machine

Read from SKILL.md and the folder at commit 562d47c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • nvm

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

  • Network

    No URLs in SKILL.md.

    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.

Context cost

Qmd MCP Skill loads about 1.3k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 600 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

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); the scripts in this folder are not scanned.

SKILL.md

The full file from holon-run/uxc at commit 562d47c, republished under its MIT licence (© holon-run). 600 words, ~1,257 tokens.

Download SKILL.mdSave it as .claude/skills/qmd-mcp-skill/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
qmd-mcp-skill
description
Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency.
metadata.short-description
Query local QMD indexes via UXC MCP stdio

QMD MCP Skill

Use this skill to query a local QMD index through uxc using a fixed MCP stdio link.

Reuse the uxc skill for generic protocol discovery, JSON envelope parsing, and daemon lifecycle basics.

Prerequisites

  • uxc is installed and available in PATH.
  • qmd is installed and available in the runtime PATH, or can be launched through a shell wrapper.
  • A QMD index already exists and is healthy:
    • qmd status
    • qmd update
    • qmd embed
  • For GPU-backed setups, the shell used by qmd mcp already exports any required runtime environment such as CUDA_PATH, CUDACXX, LD_LIBRARY_PATH, or Node/nvm initialization.

Core Workflow

  1. Verify the local QMD index first:
    • qmd status
    • Confirm collections, vector count, and device look reasonable before linking MCP.
  2. Use a fixed link command by default:
    • command -v qmd-mcp-cli
    • If missing and qmd already works in the current shell:
      • uxc link --daemon-idle-ttl 0 qmd-mcp-cli "qmd mcp"
    • If qmd depends on nvm, CUDA env, or other shell setup, wrap it explicitly:
      • uxc link --daemon-idle-ttl 0 qmd-mcp-cli "/bin/bash -lc 'export NVM_DIR=$HOME/.nvm; . $NVM_DIR/nvm.sh; nvm use 23 >/dev/null; export CUDA_PATH=/usr/local/cuda-11.6; export CUDA_HOME=/usr/local/cuda-11.6; export CUDACXX=/usr/local/cuda-11.6/bin/nvcc; export LD_LIBRARY_PATH=/usr/local/cuda-11.6/lib64:${LD_LIBRARY_PATH:-}; export NODE_LLAMA_CPP_CMAKE_OPTION_CMAKE_CUDA_ARCHITECTURES=86; export NODE_LLAMA_CPP_GPU=cuda; qmd mcp'"
    • qmd-mcp-cli -h
    • If command conflict is detected and cannot be safely reused, stop and ask skill maintainers to pick another fixed command name.
  3. Confirm the daemon-backed stdio path is active:
    • uxc daemon status
    • uxc daemon sessions
  4. Inspect operation schema before execution:
    • qmd-mcp-cli query -h
    • qmd-mcp-cli get -h
    • qmd-mcp-cli multi_get -h
    • qmd-mcp-cli status -h
  5. Prefer typed retrieval over CLI-style auto expansion:
    • Start with query using explicit lex / vec / hyde searches
    • Use get or multi_get only after narrowing candidates
  1. Health check the index:
    • qmd-mcp-cli status
  2. Start with a fast explicit search payload:
    • qmd-mcp-cli query '{"searches":[{"type":"lex","query":"\"execution layer\" MCP CLI"},{"type":"vec","query":"What is the missing execution surface between MCP and CLI?"}],"collections":["workspace"],"limit":5,"intent":"Find the article explaining capability description, execution surface, and workflow orchestration"}'
  3. Retrieve the chosen file:
    • qmd-mcp-cli get file=workspace/public/mcp-is-not-the-problem/readme.md
  4. Use multi_get for a short candidate set only:
    • qmd-mcp-cli multi_get pattern='workspace/public/*.md,workspace/research/*.md' maxBytes=20480

Capability Map

  • Search:
    • query
  • Retrieval:
    • get
    • multi_get
  • Health:
    • status
Show full SKILL.md (258 more words)Show less

Guardrails

  • Keep automation on JSON output envelope; do not rely on --text.
  • Parse stable fields first: ok, kind, protocol, data, error.
  • Use qmd-mcp-cli as the default command path.
  • qmd-mcp-cli <operation> ... is equivalent to uxc "qmd mcp" <operation> ... when qmd already runs correctly in the current shell.
  • If qmd requires shell initialization or GPU env exports, use the same wrapped shell command in the link and any direct uxc "<host>" ... fallback.
  • Prefer explicit typed query payloads over the standalone QMD CLI hybrid mode when latency matters.
  • Treat lex as the default fast path:
    • exact names
    • quoted phrases
    • negation
  • Add vec when the question is semantic but still bounded.
  • Add hyde only for nuanced or sparse topics; it is the most expensive query type.
  • Use intent to disambiguate ambiguous search terms instead of over-expanding the query text itself.
  • Keep limit and candidateLimit modest for interactive use.
  • --daemon-idle-ttl 0 is recommended for QMD because the first heavy request may warm models and sessions; long-lived reuse makes repeated calls much faster.

Notes

  • The first MCP request can still be slow while the uxc daemon creates the stdio session and QMD warms model state.
  • Repeated calls through the same uxc daemon session can drop sharply in latency once the session is warm.
  • This skill is best for local knowledge bases, notes, and markdown corpora already indexed by QMD.
  • If you need the highest-quality but slowest retrieval path, you can still express it through query with richer searches arrays instead of shelling out to the standalone QMD CLI hybrid mode.

References

  • Invocation patterns:
    • references/usage-patterns.md

© holon-run, 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 3 other files (scripts, references) in skills/qmd-mcp-skill of holon-run/uxc.

  • SKILL.md
  • agents/openai.yaml
  • references/usage-patterns.md
  • scripts/validate.sh

Open the folder on GitHubat commit 562d47c

Compare with similar skills

Qmd MCP Skill 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 MCP Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Qmd MCP Skill this skillholon-run/uxc116—~1.3kAutomated safety check: PassMIT
Context Mode Indexermksglu/context-mode26k—~328Automated safety check: PassCustom licence
OutlineVortiago/mcp-outline156—~818Automated safety check: PassMIT
Documentation Serverandrea9293/mcp-documentation-server343—~2.3kAutomated safety check: PassMIT
Context Mode Searchmksglu/context-mode26k—~250Automated safety check: PassCustom licence
Open Knowledgeinkeep/open-knowledge4.5k—~4.7kAutomated safety check: PassGPL-3.0

Similar skills

  • Context Mode Indexer

    mksglu/context-mode

    Indexes a local file or project directory into context-mode's FTS5 knowledge base so later searches return focused snippets instead of rereading whole files.

    26k GitHub stars~328 tokensUpdated today
    Knowledge ManagementAuto-check passed

  • 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

  • Documentation Server

    andrea9293/mcp-documentation-server

    A skill your agent uses when you need to store, retrieve, search, or manage documents in a local knowledge base with semantic search and hybrid (vector + full-text) retrieval.

    343 GitHub stars~2.3k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Context Mode Search

    mksglu/context-mode

    Search context-mode's persistent FTS5 knowledge base for previously indexed local project content, documentation, or session memory. Trigger…

    26k GitHub stars~250 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Open Knowledge

    inkeep/open-knowledge

    Authoritative agent-runtime contract for working inside an OpenKnowledge project — a markdown-CRDT knowledge base exposed over MCP.

    4.5k GitHub stars~4.7k tokensUpdated today
    Knowledge ManagementAuto-check passed

  • Basic Memory Setup

    basicmachines-co/basic-memory

    Runs a short guided interview that configures the Basic Memory plugin for a project: project mapping, note schemas, folder conventions and capture habits.

    4.1k GitHub stars~3.9k tokensUpdated today
    Knowledge ManagementAuto-check passed

More from holon-run/uxc

All 62 skills in this repo

  • Context7 MCP Skill

    holon-run/uxc

    Query up-to-date library documentation and code examples using Context7 MCP.

    116 GitHub stars~564 tokensUpdated 25 days ago
    Auto-check passed

  • Deepwiki MCP Skill

    holon-run/uxc

    Ask questions and read documentation about any GitHub repository using DeepWiki MCP.

    116 GitHub stars~700 tokensUpdated 25 days ago
    Auto-check passed

  • Linear Graphql Skill

    holon-run/uxc

    Operate Linear workspace issues, projects, and teams through Linear GraphQL API using UXC.

    116 GitHub stars~1.8k tokensUpdated 25 days ago
    Auto-check passed

  • Notion Openapi Skill

    holon-run/uxc

    Operate Notion Public API through UXC with a curated OpenAPI schema for search, block traversal, page reads, content writes, and data source/database inspection.

    116 GitHub stars~2.3k tokensUpdated 25 days ago
    Auto-check passed

  • Alchemy Openapi Skill

    holon-run/uxc

    Operate Alchemy Prices API reads through UXC with a curated OpenAPI schema, path-templated API-key auth, and read-first guardrails.

    116 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed

  • Uxc

    holon-run/uxc

    Discover and call remote schema-exposed interfaces with UXC.

    116 GitHub stars~1.8k tokensUpdated 25 days ago
    Auto-check passed

Works with

Categories

Questions about Qmd MCP Skill

What does Qmd MCP Skill do?

Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency. Qmd MCP Skill is an agent skill from holon-run/uxc. Use a local QMD knowledge base through UXC over MCP stdio, with daemon-backed session reuse and typed retrieval flows that avoid repeated model warmup and unnecessary query-expansion latency.

When should I use Qmd MCP Skill?

Qmd MCP Skill fits situations like: tasks that involve MCP servers; tasks that involve Knowledge bases.

How do I install Qmd MCP Skill in Claude Code?

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

How do I install Qmd MCP Skill in Codex?

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

Can I use Qmd MCP Skill 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 holon-run/uxc --skill qmd-mcp-skill -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-mcp-skill, .gemini/skills/qmd-mcp-skill, .github/skills/qmd-mcp-skill and .opencode/skills/qmd-mcp-skill in your project.

What does Qmd MCP Skill need to run?

Going by SKILL.md and its folder, Qmd MCP Skill needs a shell for the scripts in its folder and the command-line tools its instructions call (nvm). Our summary lists: A Bash shell.

Does Qmd MCP Skill access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Qmd MCP Skill 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Qmd MCP Skill use?

Qmd MCP Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Qmd MCP Skill use?

About 1.3k tokens (SKILL.md is roughly 5k 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 805 tokens, read only when the agent opens those files.

What are the alternatives to Qmd MCP Skill?

Skills that share tags, products or a category with Qmd MCP Skill: Context Mode Indexer (mksglu/context-mode, 26k stars), Outline (Vortiago/mcp-outline, 156 stars), Documentation Server (andrea9293/mcp-documentation-server, 343 stars) and Context Mode Search (mksglu/context-mode, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Qmd MCP Skill?

holon-run (a GitHub organization) maintains it in holon-run/uxc, which has 116 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on September 15, 2026.

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