# com.skillmd/skillmd (npm · skillmds)

Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry.

- Trust score: 88/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `api.skillmd.com`: 78/100, [markdown](https://verifymcp.io/servers/com-skillmd-skillmd/api.md), [page](https://verifymcp.io/servers/com-skillmd-skillmd/api)
- npm · `skillmds`: 88/100 (this document), [markdown](https://verifymcp.io/servers/com-skillmd-skillmd/skillmds.md), [page](https://verifymcp.io/servers/com-skillmd-skillmd/skillmds)

## Channel facts

- Registry: `npm`
- Package: `skillmds`
- Version: `1.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 103 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to skillmds/skillmd).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 899 tokens (~128/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 7 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the com.skillmd/skillmd MCP server?

com.skillmd/skillmd runs locally as an npm package, launched with npx -y skillmds. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add com-skillmd-skillmd -- npx -y skillmds
```

### Cursor

```json
{
  "mcpServers": {
    "com-skillmd-skillmd": {
      "command": "npx",
      "args": [
        "-y",
        "skillmds"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-skillmd-skillmd": {
      "command": "npx",
      "args": [
        "-y",
        "skillmds"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-skillmd-skillmd -- npx -y skillmds
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-skillmd-skillmd": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "skillmds"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-skillmd-skillmd --command npx --arg -y --arg skillmds
```

### Hermes

```yaml
mcp_servers:
  com-skillmd-skillmd:
    command: "npx"
    args: ["-y", "skillmds"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-skillmd-skillmd": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "skillmds"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-skillmd-skillmd -t stdio -c npx -a -y skillmds
```

### Other

```json
{
  "mcpServers": {
    "com-skillmd-skillmd": {
      "command": "npx",
      "args": [
        "-y",
        "skillmds"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-21 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-14 (score 84, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-13 (score 69, −13)

- [security regression] Malware scan: pass → unverified
- [functional regression] Schema quality: pass → fail
- [functional improvement] Stability: unverified → 0.20
- [functional] Package version: 1.1.2 → 1.2.0

### 2026-09-07 (score 82)

First indexed and scored.

## MCP tools (7)

### `skillmd_search` (~161 tokens)

Search skills

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.

Input parameters:

- `category` (string): Restrict to one category slug, e.g. coding, devops, data, security
- `limit` (integer): Maximum number of results (default 20)
- `min_rating` (number): Minimum average rating, 0 to 5
- `query` (string, required): Natural-language query or keywords describing the task or skill
- `type` (string): Restrict to single-file skills or multi-file packs
- `verified_only` (boolean): Return only skills from verified publishers (default false)

Output parameters:

- `items` (array): Matching skills, best first

### `skillmd_get` (~59 tokens)

Get skill details

Fetch one skill by owner/name slug, including its SKILL.md body, provenance (source repo and pinned commit), license, safety verdict and capability flags.

Input parameters:

- `slug` (string, required): Skill identifier as owner/name, e.g. anthropic/pdf

Output parameters:

- `ai_audit_verdict` (string|null): Safety review verdict: pass, caution, warning, fail or inconclusive
- `body_md` (string): Markdown body of SKILL.md
- `categories` (array): Every category the skill belongs to
- `category` (string): Category name
- `category_slug` (string): Category slug, as used by search and trending filters
- `commit_sha` (string|null): Pinned upstream commit
- `description` (string): What the skill does and when an agent should use it
- `files` (array): Companion files for packs
- `install_snippet` (string): One-line install command
- `license` (string|null): SPDX license id when declared
- `owner_handle` (string): Publisher handle
- `owner_name` (string): Publisher display name
- `raw_md` (string|null): Verbatim SKILL.md including frontmatter when stored
- `repo_stars` (number|null): GitHub stars of the source repository
- `security_flags` (array): Capability flags: docs_only, network_calls, executes_scripts, reads_secrets, untrusted_install
- `slug` (string): owner/name identifier, e.g. anthropic/pdf
- `source_repo` (string|null): Upstream repository
- `tags` (array): Registry tags
- `title` (string): Human-readable skill title
- `type` (string): single SKILL.md or a multi-file pack
- `verified` (boolean): Published by a verified publisher

### `skillmd_install` (~235 tokens)

Install skill

Install a skill by owner/name slug: validates it, then writes one canonical copy (.agents/skills/<name>) and links it into the chosen agents' skill directories. Never executes scripts. The response reports the skill's capability flags (docs_only, network_calls, executes_scripts, reads_secrets) as information.

Input parameters:

- `agents` (array): Agent ids to link the skill into (default: every agent detected on this machine)
- `deny` (array): Refuse the skill if it carries any of these security flags
- `dest` (string): Deprecated: an explicit agent skills directory. Must be a known agent skills dir; prefer scope + agents.
- `force` (boolean): Replace a skill installed from a different source or an untracked directory
- `mode` (string): link (junction/symlink to the canonical copy, default) or copy
- `scope` (string): project = the current directory's agent folders (default when the cwd looks like a project); global = the user's home-level agent folders
- `slug` (string, required): Skill identifier as owner/name, e.g. anthropic/pdf

Output parameters:

- `canonical` (string): Absolute path of the canonical copy every target links to
- `files_written` (integer): Number of files written
- `installed` (boolean): Whether files were written
- `note` (string): Caveats, e.g. when only SKILL.md could be written
- `scope` (string): Which set of agent folders was written
- `security_flags` (array): Capability flags reported for the skill
- `skipped` (array): Agents that were not written, with the reason
- `slug` (string): owner/name of the skill
- `targets` (array): Agent skill dirs the canonical copy was linked or copied into; empty when only the canonical copy was written

### `skillmd_trending` (~94 tokens)

Trending skills

Top skills on the SkillMD leaderboard, ranked by installs, saves and ratings, optionally within one category and time window.

Input parameters:

- `category` (string): Restrict to one category slug, e.g. coding, devops, data, security
- `limit` (integer): Maximum number of results (default 20)
- `range` (string): Ranking window: last 30 days or all time (default all)

Output parameters:

- `items` (array): Matching skills, best first

### `skillmd_recommend` (~85 tokens)

Recommend skills

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.

Input parameters:

- `based_on` (string): Skill slug (owner/name) to base recommendations on
- `limit` (integer): Maximum number of results (default 10)

Output parameters:

- `items` (array): Matching skills, best first

### `skillmd_list_saved` (~34 tokens)

List saved skills

List the signed-in user's saved skills. Requires the SKILLMD_TOKEN environment variable (a SkillMD personal access token).

Output parameters:

- `items` (array): Matching skills, best first

### `skillmd_lint` (~96 tokens)

Lint a SKILL.md

Validate a SKILL.md against the SkillMD format and return diagnostics, capability flags and a 0-100 quality score. Pass raw SKILL.md content, or a registry slug (owner/name) to fetch and lint that skill.

Input parameters:

- `content` (string): Raw SKILL.md text to validate (frontmatter plus body)
- `slug` (string): Registry skill (owner/name) to fetch and validate instead of content

Output parameters:

- `diagnostics` (array)
- `ok` (boolean): True when there are no error-level diagnostics
- `score` (integer): Quality score 0-100
- `security` (object): Scanner findings and capability flags

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-skillmd-skillmd/skillmds#diagnostics

## Score history

- 2026-09-21: 88
- 2026-09-20: 87
- 2026-09-19: 87
- 2026-09-18: 86
- 2026-09-17: 86
- 2026-09-16: 85
- 2026-09-15: 85
- 2026-09-14: 84
- 2026-09-13: 69
- 2026-09-12: 82
- 2026-09-11: 82
- 2026-09-10: 82
- 2026-09-09: 82
- 2026-09-08: 82
- 2026-09-07: 82

## Common questions

### What is the com.skillmd/skillmd MCP server?

com.skillmd/skillmd is an MCP server listed in the public MCP registry as com.skillmd/skillmd. Search, fetch, lint, and install Agent Skills (SKILL.md) from the SkillMD registry. This page covers its npm package (skillmds).

### Is the com.skillmd/skillmd MCP server safe to use?

com.skillmd/skillmd scores 88 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the com.skillmd/skillmd MCP server expose?

com.skillmd/skillmd exposes 7 tools: skillmd_search, skillmd_get, skillmd_install, skillmd_trending, skillmd_recommend, and 2 more. Their descriptions and schemas cost roughly 764 tokens of context every time the server is loaded.

### Is the com.skillmd/skillmd MCP server still maintained?

com.skillmd/skillmd is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the com.skillmd/skillmd MCP server under?

com.skillmd/skillmd declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/skillmds
- Socket report: https://socket.dev/npm/package/skillmds
- Repository: https://github.com/skillmds/skillmd
- Website: https://skillmd.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-skillmd-skillmd/skillmds.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-skillmd-skillmd/skillmds.json
- HTML version of this page: https://verifymcp.io/servers/com-skillmd-skillmd/skillmds