Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.
Model Context Protocol (MCP) Server — com.skillmd/skillmd
The MCP server com.skillmd/skillmd supports searching, fetching, linting, and installing Agent Skills defined as SKILL.md from the SkillMD registry. It is part of the open-source SkillMD toolchain used behind skillmd.com, including the CLI and the MCP server.
🛠️ Key Features
Search Agent Skills in the registry
Fetch Agent Skill content (SKILL.md)
Lint Agent Skills
Install Agent Skills
Publish is referenced for the toolchain
🚀 Use Cases
Locate and retrieve Agent Skills from a centralized registry
Validate SKILL.md files via linting
Install skills for Claude Code, Cursor, Codex, and other agents (60+ referenced)
⚡ Developer Benefits
Standardizes Agent Skills using SKILL.md
Integrates with MCP-compatible workflows
Provides access to registry-backed operations (search/fetch/lint/install)
⚠️ Limitations
Details are limited to the registry-related operations; specifics of the five tools are not provided.
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.
Parameters6
query
string
required
Natural-language query or keywords describing the task or skill
category
string
optional
Restrict to one category slug, e.g. coding, devops, data, security
verified_only
boolean
optional
Return only skills from verified publishers (default false)
type
string
optional
Restrict to single-file skills or multi-file packs
min_rating
number
optional
Minimum average rating, 0 to 5
limit
integer
optional
Maximum number of results (default 20)
Raw schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Natural-language query or keywords describing the task or skill"
},
"category": {
"type": "string",
"description": "Restrict to one category slug, e.g. coding, devops, data, security"
},
"verified_only": {
"type": "boolean",
"description": "Return only skills from verified publishers (default false)"
},
"type": {
"type": "string",
"enum": [
"single",
"pack"
],
"description": "Restrict to single-file skills or multi-file packs"
},
"min_rating": {
"type": "number",
"minimum": 0,
"maximum": 5,
"description": "Minimum average rating, 0 to 5"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Maximum number of results (default 20)"
}
},
"required": [
"query"
],
"additionalProperties": false
}
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.
Parameters1
slug
string
required
Skill identifier as owner/name, e.g. anthropic/pdf
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.
Parameters1
slug
string
required
Skill identifier as owner/name, e.g. anthropic/pdf
Top skills on the SkillMD leaderboard, ranked by installs, saves and ratings, optionally within one category and time window.
Parameters3
range
string
optional
Ranking window: last 30 days or all time (default all)
category
string
optional
Restrict to one category slug, e.g. coding, devops, data, security
limit
integer
optional
Maximum number of results (default 20)
Raw schema
{
"type": "object",
"properties": {
"range": {
"type": "string",
"enum": [
"30d",
"all"
],
"description": "Ranking window: last 30 days or all time (default all)"
},
"category": {
"type": "string",
"description": "Restrict to one category slug, e.g. coding, devops, data, security"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Maximum number of results (default 20)"
}
},
"additionalProperties": false
}
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.
Parameters2
based_on
string
optional
Skill slug (owner/name) to base recommendations on
limit
integer
optional
Maximum number of results (default 10)
Raw schema
{
"type": "object",
"properties": {
"based_on": {
"type": "string",
"pattern": "^[^/]+/[^/]+$",
"description": "Skill slug (owner/name) to base recommendations on"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Maximum number of results (default 10)"
}
},
"additionalProperties": false
}
The registry that lints.
Search, install, lint and publish Agent Skills (SKILL.md) for Claude Code, Cursor, Codex and 60+ other agents.
This repo is the open-source toolchain behind skillmd.com: the CLI, the MCP server, the GitHub Action and the SKILL.md engine they share.
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:
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
bash
# 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.
bash
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.
Give any MCP-capable agent the whole registry. It can search, inspect, lint and install skills mid-conversation.
bash
# Claude Code
claude mcp add skillmd -- npx -y get-skill
jsonc
// 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:
code
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
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:
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
bash
skillmd login # log in from your browser (CI: set SKILLMD_TOKEN)
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:
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.
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.
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