documentation-review

Performs comprehensive documentation review including build validation, Diataxis analysis, structure audit, accuracy verification, and style compliance. Use when reviewing documentation changes or auditing documentation quality.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The content is a well-structured orchestration skill with strong actionability, clear gated workflow, and a properly externalized report template. The main weakness is repetitive checkpoint/verification boilerplate across stages that inflates token cost without adding clarity.

Suggestions

Deduplicate the repeated checkpoint template: define the '✓ Stage N complete: ...' and the 'found [N] ... OR ... found no ...' pattern once in the Execution Requirements section, then reference it from each stage instead of restating it six times.

Collapse the overlapping 'Execution Requirements' and 'Verification Pattern' subsections into a single concise verification contract to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	Assumes Claude's competence with no concept padding, but the near-identical checkpoint/verification templates repeat across six stages and the 'Execution Requirements'/'Verification Pattern' sections overlap, so it could be tightened — matching score 2 rather than the fully lean score 3.	2 / 3
Actionability	Concrete skill names to invoke per stage, an exact skill-to-report-section mapping table, explicit empty-result handling, and a priority order make the guidance copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	Sequential stages with explicit gating ('Do NOT proceed to Stage [N+1] until Stage [N] is verified complete'), a STOP decision point on build failure, per-stage checklists, and error-recovery feedback loops match the score-3 anchor.	3 / 3
Progressive Disclosure	The body is an orchestration overview pointing to one real, one-level-deep reference (references/doc-review-report-template.md, verified to exist) that is clearly signaled, matching the score-3 anchor for well-signaled single-level references.	3 / 3
	Total	11 / 12 Passed

Description

85%

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

The description is comprehensive and explicit, clearly stating both capabilities and a 'Use when' trigger. Its only weakness is trigger-term breadth, which covers the core need but misses common phrasings users might say.

Suggestions

Broaden trigger terms to include natural variations users would say, e.g. add 'docs', 'documentation review', 'documentation audit', or 'checking documentation quality' alongside the current two phrases.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions ('build validation, Diataxis analysis, structure audit, accuracy verification, and style compliance'), matching the score-3 anchor rather than the partial-coverage score 2.	3 / 3
Completeness	Explicitly answers both what ('Performs comprehensive documentation review including...') and when ('Use when reviewing documentation changes or auditing documentation quality'), with an explicit 'Use when' clause, matching score 3 rather than the implied-when score 2.	3 / 3
Trigger Term Quality	Trigger phrases ('reviewing documentation changes', 'auditing documentation quality') are natural but narrow and omit common variations like 'docs', '.md', or 'documentation review', matching score 2 rather than the broad coverage of score 3.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche (documentation review orchestration across named sub-skills) with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	11 / 12 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
Commit: d1b6440

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.