Skip to main content
Glama

Install a skill from GitHub

install_skill_from_github
Idempotent

Install a single skill from a GitHub repository into a coding harness, with the skills-library server enforcing its path and tier policy.

Instructions

Fetch one skill from a GitHub repository and install it into a coding harness, with the install performed by the skills-library server so its path and tier policy applies. Not covered by add_github_source, which registers a whole repository as a source.

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": {
      "repo": "<repo>",
      "path": "<path>",
      "harness": "<harness>"
    },
    "name": "install_skill_from_github"
  }
}

Input Schema

NameRequiredDescriptionDefault
refNoBranch, tag or commit to fetch.
modeNoHow the entry is installed.
pathYesPath to the skill within the repository.
repoYesowner/repo, owner/repo@ref, or a github.com URL.
applyNoWhen false, the install is described but nothing is written.
harnessYesHarness to install into.
timeout_msNoHow long the fetch may take, in milliseconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare the operation is a mutating, open-world, idempotent, non-destructive write. The description adds genuinely useful behavioral context beyond that: the write is executed server-side, so the server's path and tier policy governs where and how the skill lands. It does not mention GitHub auth or rate limits, nor that the schema's apply=false flag yields a dry run.

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?

Two tight sentences, front-loaded with the action and scope, followed by a single disambiguation clause. No filler or restated title.

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?

For a 7-parameter mutation tool with full schema coverage, annotations, and no output schema, the description covers what happens, where it happens, and which policy applies. The main residual gap is return/outcome reporting — whether it reports the installed path or tier — which the description leaves unstated.

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%, so repo/path/ref/mode/harness/apply/timeout_ms are all documented in the schema itself. The description adds no parameter-level detail (no format hints, no symlink vs copy tradeoff), so the baseline 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?

States a specific verb+resource ('Fetch one skill from a GitHub repository and install it into a coding harness') and immediately scopes it to a single skill rather than a repository, which is exactly the axis that separates it from add_github_source.

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?

Explicitly names the alternative and the condition that selects it: add_github_source registers a whole repository as a source, whereas this installs one skill. This is a clear when-not-to-use rule, but it stops short of stating prerequisites (e.g. that no prior source registration is needed) or listing other siblings.

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