documentation-verify

Verifies documentation accuracy by cross-referencing claims, CLI commands, API signatures, and configuration against source code. Use when validating documentation correctness or checking code-docs consistency. Flags unsupported or outdated claims.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%Weight 40%Scale 1-5

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

A well-structured instruction skill: a lean overview body with a clear three-stage workflow, an explicit verification-before-reporting checkpoint, and clean progressive disclosure into real reference files. Main improvement area is tightening minor repetition and adding slightly more executable detail inline.

Suggestions

Consolidate the repeated 'complete verification before reporting' guidance so it appears once (e.g., in Constraints) rather than restated in Stage 2 and Stage 3.

Add one or two concrete example search commands (e.g., a sample grep/entrypoint-trace pattern) inline in Stage 2 so the 'at least two search strategies' rule is immediately executable without loading the reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining known concepts, with only minor repetition of the 'complete verification before reporting' injunction across stages and constraints.	4 / 5
Actionability	Provides concrete methodology guidance (run git diff, use at least two named search strategies, apply a classification taxonomy) and points to detailed checklists, with minor gaps in fully executable specificity.	4 / 5
Workflow Clarity	A clear three-stage sequence with an explicit validation checkpoint ('Complete the verification pass before reporting any claims'), a reclassify-on-evidence feedback loop, and referenced checklists for the complex process.	5 / 5
Progressive Disclosure	The body is an overview that clearly signals one-level-deep references to real files (references/verification_procedures.md and references/report_format.md), with detail appropriately split out.	5 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

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 strong, specific description that clearly states capabilities and an explicit trigger condition, with concrete cross-referencing actions rather than vague fluff. Minor room to add more natural synonyms and sharpen distinctiveness from adjacent review skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions (cross-referencing claims, CLI commands, API signatures, configuration against source code; flags unsupported/outdated claims), with only minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what it does and when to use it, with a concrete 'Use when...' trigger clause and a clear capability statement.	5 / 5
Trigger Term Quality	Includes natural trigger phrases ('Use when validating documentation correctness or checking code-docs consistency'), with good keyword coverage though a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (documentation-vs-code consistency) with distinct triggers, though minor overlap risk exists with general code-review or documentation skills.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: canonical/copilot-collections
Path: skills/documentation-verify/SKILL.md
Commit: d41d8d9

Reviewed: 1 day 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.