update-docs

Audit and update documentation after code changes. Use when architecture, APIs, or behavior changed and docs may have drifted.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A dense, actionable docs-maintenance skill with executable commands and a clear locations map. Its main weaknesses are a restated caveat that hurts conciseness and a fixing workflow that lacks an explicit error-recovery feedback loop.

Suggestions

Consolidate the orbit CI byte-equal-sync caveat into one place (e.g., 'What drifts most') and reference it from step 6 rather than restating it, to remove the redundancy.

Add an explicit feedback loop after the lint step, e.g. 'If lint fails, fix the flagged docs and re-run mise run lint:docs until it passes,' to raise workflow clarity.

Consider a one-line 'Verify' checkpoint confirming AGENTS.md/CLAUDE.md identity holds after mirroring, since CI enforces that constraint.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes competence, but the orbit CI byte-equal-sync caveat is restated almost verbatim in both 'What drifts most' and 'Fixing' step 6, which is the kind of redundancy the rubric penalizes.	2 / 3
Actionability	Provides fully executable shell commands (git log, glab issue/mr list, mise run lint:docs), a concrete locations table, and specific file paths — copy-paste ready guidance.	3 / 3
Workflow Clarity	The 'Fixing' section gives a clear 7-step sequence with an explicit validation step (step 4) and conditional branches, but lacks a validate→fix→retry feedback loop, matching the score-2 anchor pattern of a sequence with a validation gap.	2 / 3
Progressive Disclosure	No bundle files exist and none are needed; at ~55 lines the skill is organized into well-signaled sections (Where to look, Gathering context, What drifts most, Fixing, Self-improvement), meeting the simple-skill allowance for a top score.	3 / 3
	Total	10 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, third-person description that clearly answers both what it does and when to use it, with a distinct niche. It is held back from full marks only by limited action specificity and incomplete trigger-term coverage.

Suggestions

Expand the action list beyond 'audit and update' to concrete verbs (e.g., 'locate stale docs, cross-reference code changes, patch drifted sections') to lift specificity.

Add common natural trigger phrasings such as 'stale docs', 'documentation out of date', or 'docs behind the code' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('documentation') and two concrete actions ('Audit and update'), but stops at two verbs rather than listing multiple specific actions as the score-3 anchor requires.	2 / 3
Completeness	Explicitly states what ('Audit and update documentation after code changes') and when via an explicit 'Use when...' trigger clause, satisfying the score-3 anchor.	3 / 3
Trigger Term Quality	Includes relevant terms ('architecture, APIs, or behavior changed', 'docs may have drifted') but misses common natural variations a user might say like 'stale docs' or 'docs out of date'.	2 / 3
Distinctiveness Conflict Risk	The post-code-change docs-drift niche with explicit triggers is clearly distinguishable from general documentation skills and unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: gitlabhq/orbit-knowledge-graph
Commit: 00ca361

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.