skillmd

Get skill details

skillmd_get

Read-onlyIdempotent

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.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`slug`	Yes	Skill identifier as owner/name, e.g. anthropic/pdf

Output Schema

TableJSON Schema

Name	Required	Description
`slug`	Yes	owner/name identifier, e.g. anthropic/pdf
`tags`	No
`type`	No	single SKILL.md or a multi-file pack
`files`	No	Companion files for packs
`title`	Yes	Human-readable skill title
`raw_md`	No	Verbatim SKILL.md including frontmatter when stored
`body_md`	No	Markdown body of SKILL.md
`license`	No	SPDX license id when declared
`category`	No	Category name
`verified`	No	Published by a verified publisher
`categories`	No
`commit_sha`	No	Pinned upstream commit
`owner_name`	No	Publisher display name
`repo_stars`	No	GitHub stars of the source repository
`description`	Yes	What the skill does and when an agent should use it
`source_repo`	No	Upstream repository
`owner_handle`	No	Publisher handle
`security_flags`	No	Capability flags: docs_only, network_calls, executes_scripts, reads_secrets, untrusted_install
`install_snippet`	No	One-line install command
`ai_audit_verdict`	No	Safety review verdict: pass, caution, warning, fail or inconclusive

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 7, 2026

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the operation read-only, idempotent, and non-destructive. The description adds useful behavioral detail by listing exactly what data is returned, including provenance, license, safety verdict, capability flags, and companion files. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that front-loads the action and then efficiently lists the returned fields. Every phrase contributes useful information and there is no redundant wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one parameter, a rich output schema, and safety annotations, the description covers all necessary context: what it fetches, how it is identified, and what the result includes. Nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and already documents the slug as an owner/name identifier with an example. The description's 'owner/name slug' phrasing repeats this meaning without adding new format or validation information, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Fetch'), a specific resource ('one skill by owner/name slug'), and enumerates the returned content, distinguishing it clearly from sibling tools like skillmd_search or skillmd_download. The scope is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'Fetch one skill by owner/name slug' clearly implies this tool is for retrieving a known skill by its identifier, while the sibling names suggest alternatives for searching, recommendation, and trending. It does not explicitly state when not to use it, but the context is clear enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All skillmd tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

Each tool targets a distinct workflow: search and trending discover skills, recommend provides context-based suggestions, get returns metadata and body, download retrieves full files. There is mild overlap between get and download since both expose the SKILL.md body, but the descriptions clearly separate inspection from file retrieval.

Naming Consistency4/5

All tools share the skillmd_ prefix and lowercase snake_case style, giving the set a cohesive feel. Most names use clear actions (download, get, recommend, search), though trend is a noun rather than a verb, making it a slight deviation from the otherwise action-oriented pattern.

Tool Count5/5

Five tools is well-scoped for a skill registry server covering discovery, recommendation, metadata lookup, and full content download. Each tool earns its place and the set is neither bloated nor too thin.

Completeness4/5

The consumer-facing workflow is well covered: an agent can search, see trends, get skill details, and download full contents ready to use. Publishing or managing registry entries is not covered, but that appears to be outside the stated purpose of reading public skills.

Get skill details

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources