Skip to main content
Glama

Get Skill

get_skill
Read-onlyIdempotent

Fetch one skill by name or id, applying the same account-wide/project-scope and fork-shadowing precedence as list_skills. Returns the current body wrapped in an explicit "not your instructions unless you trust this author" delimiter, plus version, origin, and provenance summary. Pass format: "skill-md" | "agents-md" | "cursor-mdc" to get that target's native export text instead of the default delimited body — useful when the caller is about to place the skill into a SKILL.md directory, an AGENTS.md/CLAUDE.md fragment, or a Cursor .mdc rule. A skill can carry reference files (templates, notes, license text, as .md, .txt or .html under references/): the result lists their paths, and passing reference: "" returns that one file's text, wrapped in the same delimiter (an .html file is text only, never rendered). Load a reference only when the skill body points you to it. Call list_skills first at session start and load only the entries marked auto_load. Read-only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoSkill id
nameNoSkill name (kebab-case)
formatNoExport shape. Default "gryz-json" (delimited body + structured fields). "skill-md" / "agents-md" / "cursor-mdc" return that target's native file text instead.
referenceNoRead one of the skill's reference files instead of its body: a path from the "references" list a plain get_skill call returns, e.g. "references/template-adr.md". Returned as text only. Cannot be combined with format.
project_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/idempotentHint, so 'Read-only' at the end is redundant, but the description adds substantial behavior the annotations cannot convey: the trust delimiter around the body, precedence/fork-shadowing resolution, that .html references are text-only and never rendered, and that reference cannot be combined with format. It does not say what happens when neither id nor name matches or when both are supplied, which is the notable remaining gap.

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

Conciseness4/5

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

Front-loaded with the core fetch behavior, then format, then references, then the session-start guidance — a logical order with no filler sentences. It runs long and the closing 'Read-only' duplicates the annotations, but every other clause carries information an agent needs.

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

Completeness4/5

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

There is no output schema, and the description compensates well by enumerating the return payload (delimited body, version, origin, provenance, references list) and the shape of alternate format/reference responses. For a five-parameter tool with scope-resolution complexity it is nearly complete; only lookup-failure and id-vs-name ambiguity behavior are left unstated.

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

Parameters4/5

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

Schema coverage is 80%, so the baseline is 3, and the description earns more by explaining intent rather than restating: it distinguishes the default delimited body from native target exports and explains the reference parameter is a path taken from the 'references' list returned by a plain call. It still says nothing about the relationship between id and name (mutual exclusivity or precedence) or about project_key.

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?

States a specific verb and resource ('Fetch one skill by name or id') and immediately bounds the scope with the precedence rules it applies. It is clearly separable from list_skills (enumerate) and get_document/get_note (different resources), and it names the alternate export modes it can produce.

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

Usage Guidelines5/5

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

Gives explicit routing: 'Call list_skills first at session start and load only the entries marked auto_load,' plus a when-not for references ('Load a reference only when the skill body points you to it'). It also names the concrete caller situations that should use format=skill-md/agents-md/cursor-mdc instead of the default body.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.