Skip to main content
Glama

Publish a skill

skills_publish

Publish a skill to your team, or a new version of one your owner owns. Give files ({"SKILL.md": base64, ...}) or tarball (a .tar or .tar.gz, base64); up to 5 MB. Scripts, network calls and reads of sensitive environment values are flagged for reviewers; a package that embeds a live access key is refused.

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": "skills_publish"
  }
}

Input Schema

NameRequiredDescriptionDefault
asNoOnly when a LinkGents wake in this conversation names one of your conversation agents (its handle, e.g. "masood.claudeai-trip-plan"): act as that agent. Leave it out otherwise.
filesNoPath to base64 content, with SKILL.md at the top; give this or tarball
tarballNoA .tar or .tar.gz of the skill folder, base64; give this or files
versionNoSemantic version, such as "1.2.0"; default: 1.0.0, then the next patch version
changelogNoWhat changed in this version

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / as
      Added value: +{
      +  "description": "Only when a LinkGents wake in this conversation names one of your conversation agents (its handle, e.g. \"masood.claudeai-trip-plan\"): act as that agent. Leave it out otherwise.",
      +  "maxLength": 64,
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the annotations, the description discloses a size ceiling (5 MB), what content triggers reviewer flagging (scripts, network calls, sensitive env reads), and a hard refusal rule for packages embedding live access keys. These are behavioral facts an agent could not derive from readOnlyHint/destructiveHint/idempotentHint alone and directly affect whether a publish will succeed.

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 dense sentences, front-loaded with purpose followed by input format and then side-effect rules. Every clause carries operational information; nothing is filler.

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 five-parameter, nested-object mutation with no output schema, the description covers input formats, limits, and review/rejection behavior well. It does not say what a successful publish returns (e.g., the published version or skill identifier), which is a modest gap given there is no output schema.

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 100%, so the baseline is 3, but the description adds real meaning: the files map shape ({"SKILL.md": base64, ...}) with SKILL.md at the top, and that tarball must be a .tar or .tar.gz, both capped at 5 MB. Only the 'as' and 'changelog' parameters are left to the schema.

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

Purpose4/5

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

The description opens with a specific verb and resource ('Publish a skill') and clarifies the two modes: publishing to the team or publishing a new version of a skill one owns. It never names or distinguishes itself from related siblings such as setups_publish, skills_share, or files_new_version, so an agent must infer the boundary from those tools' own definitions.

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?

It states clear conditions for use (first publish vs. new version) and tells the caller to supply either files or a tarball, giving the agent enough context to start. There are no explicit exclusions or pointers to alternative tools for sharing versus publishing, so guidance stops short of the 5 bar.

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.

Resources