Skip to main content
Glama

Fork Skill

fork_skill

Copy a readable skill (a first-party Library skill, or any skill you can see) into your own editable row, so you can customize it without changing the original. Requires Pro or higher. The fork shadows the parent in your own list_skills/get_skill from then on.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "parent_id": "<parent_id>",
      "scope": "<scope>"
    },
    "name": "fork_skill"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeYes
auto_loadNo
parent_idYes
project_keyNoRequired when scope is "project"

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare a non-readonly, non-destructive, non-idempotent, closed-world mutation, so the bar is lower and the description clears it. It adds real context annotations cannot express: a plan entitlement gate (Pro or higher) and a post-condition side effect (the fork shadows the parent in the caller's list_skills/get_skill). It stops short of saying whether repeated forks create additional rows or how shadowing can be undone.

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?

Three short sentences, each carrying distinct load: what it copies, the entitlement gate, and the resulting shadowing effect. Front-loaded with the action and free of padding.

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

Completeness3/5

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

With four parameters, a low schema coverage and no output schema, the definition covers the conceptual model well but leaves two parameters (scope values, auto_load) undefined and never says what a successful fork returns or how the caller learns the new skill's id. Adequate for understanding the operation, incomplete for invoking it correctly.

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

Parameters2/5

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

Schema description coverage is only 25% – just project_key carries a description, while parent_id, scope (enum personal/project) and auto_load are undocumented. The description mentions no parameter at all, so it does not compensate: an agent gets no guidance on how 'scope' interacts with the shadowing behavior or what auto_load does.

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 ('Copy a readable skill ... into your own editable row') and names the admissible sources (first-party Library skill, or any skill you can see). The distinction from create_skill is implicit but unambiguous: this clones an existing skill, it does not author a new one.

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?

Gives a clear when-to-use rationale ('so you can customize it without changing the original') plus a hard prerequisite ('Requires Pro or higher'). It does not name an alternative path such as editing the original directly via update_skill, so an explicit exclusion is missing, but the intended context is clear.

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.