Ermöglicht es einem AI-Client, Agent Skills (SKILL.md) aus dem SkillMD-Registry zu suchen, zu inspizieren, zu linten und zu installieren.
Auch bekannt als skillmds/SkillMD, get-skill, skillmds
- Stars
- 144
- Tools
- 5
- Downloads, 30 Tage
- 1.111
- Neueste Version
- 1.3.11
- Letzter Commit
- 10. Nov. 2026
- Lizenz
- MIT
Was ist SkillMD MCP?
Ermöglicht es einem AI-Client, Agent Skills (SKILL.md) aus dem SkillMD-Registry zu suchen, zu inspizieren, zu linten und zu installieren. Er stellt 5 Tools bereit, etwa skillmd_search, skillmd_get, skillmd_download.
Zusammenfassung generiert aus dem README des Projekts
Über SkillMD MCP server
skillmd ermöglicht es dir, spezialisierte Agent-Instruktionen direkt aus einem AI-Client heraus zu suchen und zu installieren. Dieser MCP server bietet Zugriff auf ein offenes Registry mit über einer Million Agent Skills – das sind SKILL.md Dateien, die darauf ausgelegt sind, Agenten wie Claude Code, Cursor und Windsurf spezifische Fähigkeiten zu verleihen. Entwickler können diesen Server nutzen, um Skills direkt über ihr Chat-Interface zu finden, zu inspizieren und zu deployen, ohne die Konversation verlassen zu müssen.
Nutzer können sich entweder über eine lokale Installation via npx oder über einen gehosteten Remote-Server verbinden. Der Server enthält Tools für die Registry-Suche, das Abrufen detaillierter Skill-Informationen und die Durchführung sicherer Installationen, die per SHA-256 verifiziert werden und niemals Skripte ausführen. Er unterstützt zudem das sofortige Linting von Inhalten, um Qualität und Sicherheit zu gewährleisten. Nutzer mit einem SKILLMD_TOKEN können gespeicherte Skills verwalten, während das Sicherheitsmodell Capability-Flags nutzt, um zu identifizieren, ob ein Skill Netzwerkaufrufe tätigt, Skripte ausführt oder Secrets ausliest.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du SkillMD MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenSkillMD MCP in Claude Code installieren
$ claude mcp add --env 'SKILLMD_TOKEN=<YOUR_SKILLMD_TOKEN>' skillmd -- npx -y get-skillSkillMD MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"skillmd": {
"command": "npx",
"args": [
"-y",
"get-skill"
],
"env": {
"SKILLMD_TOKEN": "<YOUR_SKILLMD_TOKEN>"
}
}
}
}SkillMD MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"skillmd": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"get-skill"
],
"env": {
"SKILLMD_TOKEN": "<YOUR_SKILLMD_TOKEN>"
}
}
}
}SkillMD MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"skillmd","type":"stdio","command":"npx","args":["-y","get-skill"],"env":{"SKILLMD_TOKEN":"<YOUR_SKILLMD_TOKEN>"}}'SkillMD MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"skillmd": {
"command": "npx",
"args": [
"-y",
"get-skill"
],
"env": {
"SKILLMD_TOKEN": "<YOUR_SKILLMD_TOKEN>"
}
}
}
}SkillMD MCP in Codex installieren
$ codex mcp add skillmd --env 'SKILLMD_TOKEN=<YOUR_SKILLMD_TOKEN>' -- npx -y get-skillSkillMD MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.skillmd] command = "npx" args = ["-y", "get-skill"] [mcp_servers.skillmd.env] SKILLMD_TOKEN = "<YOUR_SKILLMD_TOKEN>"
SkillMD MCP in Gemini CLI installieren
$ gemini mcp add -s user -e 'SKILLMD_TOKEN=<YOUR_SKILLMD_TOKEN>' skillmd npx -- -y get-skillSkillMD MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"skillmd": {
"command": "npx",
"args": [
"-y",
"get-skill"
],
"env": {
"SKILLMD_TOKEN": "<YOUR_SKILLMD_TOKEN>"
}
}
}
}Von HostedMCP gestartet am 16. Nov. 2026
Wir haben diesen Befehl für get-skill 1.3.11 in einem isolierten Container ohne Netzwerk und ohne Schlüssel ausgeführt. Er hat geantwortet und 7 Tools gelistet.
SkillMD MCP tools 5
Vom Server mit tools/list gelesenskillmd_searchNur lesendSearch the SkillMD registry of Agent Skills (SKILL.md files) by task, name or keywords. Returns matching skills with their owner/name slug, description, category, safety verdict and install snippet, best match first.
skillmd_getNur lesendFetch one skill by owner/name slug: description, SKILL.md body, provenance (source repo and pinned commit), license, safety verdict and capability flags, plus companion file listing for packs.
skillmd_downloadNur lesendReturn the full contents of any public skill by owner/name slug: the SKILL.md text plus every companion file for packs, ready to write to disk. Skills are plain-text instructions an agent reads on demand; nothing executes, and every listed skill has passed SkillMD's safety review.
skillmd_trendingNur lesendTop skills on the SkillMD leaderboard, ranked by installs, saves and ratings, optionally within one category and time window.
skillmd_recommendNur lesendRecommend skills. With based_on set to a skill's owner/name slug, returns the top skills in that skill's category (excluding itself); without it, returns what is trending over the last 30 days.
| skillmd_search | Search the SkillMD registry of Agent Skills (SKILL.md files) by task, name or keywords. Returns matching skills with their owner/name slug, description, category, safety verdict and install snippet, best match first. | Nur lesend |
| skillmd_get | Fetch one skill by owner/name slug: description, SKILL.md body, provenance (source repo and pinned commit), license, safety verdict and capability flags, plus companion file listing for packs. | Nur lesend |
| skillmd_download | Return the full contents of any public skill by owner/name slug: the SKILL.md text plus every companion file for packs, ready to write to disk. Skills are plain-text instructions an agent reads on demand; nothing executes, and every listed skill has passed SkillMD's safety review. | Nur lesend |
| skillmd_trending | Top skills on the SkillMD leaderboard, ranked by installs, saves and ratings, optionally within one category and time window. | Nur lesend |
| skillmd_recommend | Recommend skills. With based_on set to a skill's owner/name slug, returns the top skills in that skill's category (excluding itself); without it, returns what is trending over the last 30 days. | Nur lesend |
Konfiguration
SKILLMD_TOKENSecretSkillMD personal access token (enables skillmd_list_saved and personalized recommendations)
SKILLMD_APIOverride the registry API base URL
| Name | Beschreibung | Typ |
|---|---|---|
| SKILLMD_TOKEN | SkillMD personal access token (enables skillmd_list_saved and personalized recommendations) | Secret |
| SKILLMD_API | Override the registry API base URL |
Automatisierte Checks
Geluften am 16. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren
- Source Repository verknüpft und erreichbarskillmds/skillmd is public and reachablegithub.com/skillmds/skillmd ↗Bestanden
- Paket nennt dieses Repository als Quelleget-skill, skillmds name skillmds/skillmd as sourcenpmjs.com/package/get-skill ↗Bestanden
- Build-Provenienz (Sigstore-Attestierung)Sigstore attestation for get-skill, skillmdsnpmjs.com/package/get-skill/v/1.3.11#provenance ↗Bestanden
- Open Source Lizenz (OSI)MITspdx.org/licenses/MIT.html ↗Bestanden
- Commit oder Release im letzten JahrLast commit or release 2026-11-10github.com/skillmds/skillmd ↗Bestanden
- OpenSSF ScorecardNicht geprüft
- Package-Name ähnelt keinem populären PackageNo popular package one edit away from get-skill, skillmdsBestanden
- Keine kritischen Advisories im Paket oder seinen Abhängigkeiten107 resolved dependencies checked; no critical advisoryosv.dev ↗Bestanden
- Keine versteckten Anweisungen an das Modell5 tool descriptions and the README read; no override phrases, credential paths or hidden charactersBestanden
- Destruktive Tools sind markiertNo tool named like delete, drop or execBestanden
- Remote-Endpoint beantwortet den MCP-Handshakeinitialize answered with protocol 2025-06-18 in 200 ms; tools/list returned 5 toolsBestanden
README
Auf GitHub ansehenWhat this is
An Agent Skill is a folder with a SKILL.md file: YAML frontmatter (name, description) plus Markdown instructions an agent loads on demand. Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, Windsurf and dozens of other agents read the same format, which is what makes a shared registry worth having. If the format is new to you, start with What is an Agent Skill? and the anatomy of a SKILL.md file.
skillmd.com is the open registry of those skills: 1,000,000+ skills from 30,000+ publishers, every one of them linted against the format, security-scanned for what it can do, and pinned to a commit. Verdicts, capability flags and independent scanner results sit on every skill page. Installing writes files and does nothing else.
This repository is everything that runs on your machine or in your CI, MIT-licensed:
| Package | What it is | Install |
|---|---|---|
get-skill |
One npm package: the CLI and the MCP server (get-skill, also installed as skillmd) |
npm i -g get-skill |
@skillmds/core |
The SKILL.md engine: parser, lint rules, security scanner, quality score, SARIF / JSON / GitHub formatters | npm i @skillmds/core |
skillmds/skillmd/action |
GitHub Action: lint every skill in a repo, results in GitHub Code Scanning | uses: skillmds/skillmd/action@v1 |
The registry applies the same engine, so a skill that passes locally passes on publish.
Quick start
# Search the registry and install a skill into every agent on your machine
npx get-skill search "pdf"
npx get-skill add anthropic/pdf
# Lint your own skill before you share it
npx get-skill lint ./my-skill
Plugins
A plugin is a bundle of skills that installs as one unit. In Claude Code it becomes a
real plugin — /plugin lists it, and enable, disable and uninstall work on the whole
set — and on every other agent the skills are installed individually.
npx get-skill add plugin:skillmd/design
To browse them inside Claude Code's Plugins tab instead, add this repository as a
marketplace: skillmds/skillmd. It carries the flagship plugins as real directories
under plugins/, listed in
.claude-plugin/marketplace.json and refreshed
weekly. The tab only understands plugins that live in git, which is why the whole
registry is not in there — every other plugin installs with the command above.
No account needed for any of the above. Skills land in each detected agent's own directory (.claude/skills/, .cursor/skills/, .agents/skills/, …). Per-agent walkthroughs: Claude Code · Cursor · Codex · Gemini CLI · GitHub Copilot · Windsurf · all agents.
The CLI: skillmd
npm i -g get-skill
| Command | What it does |
|---|---|
skillmd lint [path] |
Validate SKILL.md files. Diagnostics, a 0–100 quality score, --fix for the mechanical ones. |
skillmd scan [path] |
What would this skill do? Reports scripts, network calls and secret access. |
skillmd rules [id] |
List the lint rules, or explain one. |
skillmd init [name] |
Scaffold a new skill from a template. |
skillmd search <query> |
Search the registry from the terminal. |
skillmd add <source> |
Install from a registry slug, a GitHub repo or a local path. Lints first, never executes scripts. |
skillmd list / remove / update |
Manage installed skills across agents. |
skillmd publish [path] |
Publish to skillmd.com. Blocked on lint errors. |
skillmd lint . --format sarif > skillmd.sarif # GitHub Code Scanning
skillmd lint . --strict # warnings fail too
skillmd add owner/repo -a claude-code -g # one agent, global scope
skillmd add some/skill --deny executes_scripts # refuse skills that run code
skillmd add detects 68 agents by their config directories: Claude Code, Cursor, Codex, Windsurf, OpenCode, Gemini CLI, Antigravity, Kiro, Warp, GitHub Copilot, Cline, Roo Code, Goose, Trae, Qwen Code, Amp, Zed, Continue, Devin, OpenHands, Replit and more. Agents that share the .agents/skills convention are written once. Running plain skillmd opens a guided menu.
Full reference: docs/cli.md · CLI docs on skillmd.com · How one SKILL.md works in every agent
The MCP server: get-skill
Give any MCP-capable agent the whole registry. It can search, inspect, lint and install skills mid-conversation.
# Claude Code
claude mcp add skillmd -- npx -y get-skill
// Claude Desktop, Cursor, VS Code, Windsurf, … (examples/mcp/ has per-client files)
{ "mcpServers": { "skillmd": { "command": "npx", "args": ["-y", "get-skill"] } } }
Or use the hosted remote server, zero install, streamable HTTP:
https://api.skillmd.com/mcp
| Tool | What the agent gets |
|---|---|
skillmd_search |
Registry search with categories, ratings and install snippets |
skillmd_get |
Full skill detail: body, provenance, license, security flags |
skillmd_install |
Safe install: validated, SHA-256-verified, zip-slip-guarded, never executes scripts |
skillmd_trending / skillmd_recommend |
Leaderboard and similar-skill suggestions |
skillmd_list_saved |
Your saved skills (with SKILLMD_TOKEN) |
skillmd_lint |
Validate any SKILL.md content on the spot |
Full reference: docs/mcp.md · MCP docs on skillmd.com · Using SkillMD over MCP · MCP registry entry: com.skillmd/skillmd
The engine: @skillmds/core
npm i @skillmds/core
import { lint } from "@skillmds/core";
const { ok, score, diagnostics, security } = lint(rawSkillMd, { slug: "my-skill" });
Nine lint rules, a line-aware security scanner, a 0–100 quality score and SARIF / JSON / GitHub-annotation formatters. ESM, typed, no runtime dependency beyond yaml, runs in Node, browsers and edge runtimes.
The scanner classifies every skill into capability flags you can filter or deny on install:
| Flag | Meaning |
|---|---|
docs_only |
Nothing executable found. Pure instructions. |
network_calls |
Fetches, curls or otherwise talks to the network. |
executes_scripts |
Runs commands or bundled scripts. |
reads_secrets |
Touches env vars, tokens or credential files. |
untrusted_install |
Fetch-and-execute from a non-standard source. |
Rules and scoring: docs/rules.md · Debugging skills: lint, scan, score · Common SKILL.md mistakes
CI for your skills
- uses: skillmds/skillmd/action@v1
with:
path: .
Lints every skill in the repo and uploads SARIF to GitHub Code Scanning, so findings show up in pull requests. Full example: examples/github-action.yml · action/README.md
Publishing a skill
skillmd login # token from your skillmd.com account
skillmd publish ./my-skill # blocked on lint errors
skillmd publish ./my-skill --dry-run
Published skills get a page at skillmd.com/skills/<you>/<name>, a safety verdict, an install command for every agent, and a live README badge:
[](https://skillmd.com/skills/<you>/<name>)
Guides: Publishing a skill to the registry · Writing skills that get used · What a verified badge means · Skill packs
The registry API
Everything here is a thin client over the public API at api.skillmd.com (GET /v1/search?q=…, GET /v1/skills/<owner>/<name>, …). Described by docs/registry-api.md, skillmd.com/openapi.json and, for AI systems, skillmd.com/llms.txt. Every skill page also has a Markdown twin at …/<name>.md.
What's in the registry
Browse by category: Coding & Dev Tools · AI & ML · DevOps & Infra · Integrations & APIs · Security · Data & Analytics · Web & Frontend · Productivity · Docs & Writing · Design & Media
Or by publisher, official skills from verified publishers, the leaderboard, or what's new. Live counts: skillmd.com/stats.
Security model
Installing a skill writes files and does nothing else. No script execution, strict path containment (slug validation plus zip-slip guards), SHA-256 integrity verification against the registry's content-addressed store, and companion files pinned to GitHub raw hosts. Publishing runs the same lint and scan the CLI does, and every listed skill shows its verdict, capability flags and independent scanner results.
Details in SECURITY.md. Report vulnerabilities to hi@skillmd.com.
Learn more
- The complete guide to AI agent skills
- Agent Skills vs MCP servers
- Claude Code skills vs plugins vs subagents vs commands
- Cursor rules vs Cursor skills
- The case for an open skill format
- Glossary · The SKILL.md format · Getting started
Development
npm ci
npm run build # @skillmds/core, then skillmds
npm test # vitest across both packages, incl. an MCP stdio smoke test
npm run typecheck # strict tsc
See CONTRIBUTING.md for layout, PR guidelines and the release process, and CODE_OF_CONDUCT.md.
License
MIT © SkillMD · skillmd.com · hi@skillmd.com
SkillMD MCP Fragen
Wie füge ich SkillMD MCP zu Claude Code hinzu?
Führe claude mcp add --env 'SKILLMD_TOKEN=<YOUR_SKILLMD_TOKEN>' skillmd -- npx -y get-skill in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich SkillMD MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet SkillMD MCP?
Er stellt 5 Tools bereit, darunter skillmd_search, skillmd_get, skillmd_download, skillmd_trending, skillmd_recommend.
Welche Tools stellt der SkillMD MCP server bereit?
Er stellt Tools für die Registry-Suche, detaillierte Skill-Infos, sichere Installationen, Trending- und Empfehlungslisten, gespeicherte Skills sowie On-the-spot-Linting bereit.
Werden beim Installieren eines Skills Skripte ausgeführt?
Nein. Die Installation schreibt nur Dateien, verifiziert die SHA-256-Integrität, schützt vor Zip-Slip-Pfaden und führt niemals Skripte aus.
Kann ich eine SKILL.md Datei über MCP linten?
Ja, das skillmd_lint Tool validiert jeden SKILL.md Inhalt direkt vor Ort.
Benötige ich ein Konto, um Skills zu suchen und zu installieren?
Für die Suche oder Installation ist kein Konto erforderlich; ein Token wird nur für Aktionen wie das Auflisten gespeicherter Skills oder das Veröffentlichen benötigt.