Skip to main content
Glama

update_skill_files

Change specific files in a skill that already exists, including its runbook (SKILL.md). Paths you do not name are kept unchanged, so you never need to read back or resend the rest of the tree. Use this for any edit to a skill whose files you did not just author in full. To create a skill, change its name, description, or tags, or replace the entire tree at once, use save_skill.

Send each file's complete new content, not a diff. A file's executable flag and purpose label keep their current values unless you set them. The skill's description, outcome, tags, and verifier references carry forward untouched.

This writes the next version of the skill. Requires edit access. Returns skill_id, version, the new version_token, the sorted changed and deleted paths, and carried_forward, the count of files left untouched.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filesNoThe files to write, one entry per path, each carrying that file's complete new content. A path may appear only once. Use the path 'SKILL.md' to rewrite the runbook itself.
sourceNoAttributes the new version to how it was produced ('manual', 'teach', 'optimization', 'description_optimization', or 'audit'); omit to leave it unset.
skill_idYesThe skill to act on, identified by its UUID, slug, or name.
delete_pathsNoPaths to remove from the skill's file tree. Each must already be in the tree, and 'SKILL.md' cannot be removed.
expected_version_tokenYesConcurrency token for the version you last read, returned by get_skill and by every write. A stale token is rejected so you never overwrite a change someone else made.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Discloses that it writes new version, requires edit access, returns version details, and that executable/purpose default to carry-forward. Doesn't contradict annotations (readOnlyHint=false, destructiveHint=false).

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?

Concise, front-loaded, every sentence adds value, no fluff.

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?

Given output schema exists and annotations, description covers auth, return values, and key behavioral traits; no gaps.

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 coverage is 100% with detailed descriptions; the description adds minor behavioral context (complete content, no diff) but does not significantly enhance parameter meaning beyond schema.

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?

Specific verb 'Change specific files' + resource 'skill that already exists', distinguishes from 'save_skill' for creation/rename/replace.

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?

Explicitly says when to use (existing skill, not just authored) vs when to use save_skill; also describes that untouched paths are preserved.

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.