review-docs

Use when reviewing the documentation a branch changes — CLAUDE.md, READMEs and pages under wiki/ — or sweeping the whole wiki with --full. Cross-checks every claim a page makes against the code, finds wikilinks and heading anchors the branch broke, checks frontmatter and page shape, and reports D-C/H/M/L findings in the four-field format.

Quality

96%

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

92%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 tightly written, highly actionable review workflow with concrete commands, explicit validation/feedback loops, and clean one-level-deep reference splitting. Only minor conciseness trim opportunities keep it off the top mark on that single dimension.

Suggestions

Tighten rhetorical asides such as 'the worst failure this review exists to catch, and it is invisible to a read that does not open the source' to the load-bearing instruction ('open the source for every claim') to lift conciseness.

The 'When a step cannot run' preamble explains the Mac-only MCP/CLI absence at length; this could be one line ('Obsidian MCP/CLI are maintainer-Mac only; every check has a shell form — use it.') without losing the guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's intelligence (no padding about what git or a wiki is), but carries some rhetorical/editorial flourishes ('the worst failure this review exists to catch', 'however good the review inside it') that could be trimmed, fitting the efficient-but-minor-over-explanation 4 anchor rather than the lean 5.	4 / 5
Actionability	Provides copy-paste-ready bash throughout (git diff/git grep pipelines, comm trick, test -e checks), a verbatim report skeleton, an exact finding-format template, and named false-positive exceptions, matching the fully-executable 5 anchor.	5 / 5
Workflow Clarity	Steps 0–5 are clearly sequenced with an explicit validation checkpoint at the end ('Both must print 3') plus failure-mode feedback ('A first count under 3 means a section was renamed…'), and an in-progress discipline ('only ever edited, never rewritten'), matching the explicit-validation-and-feedback 5 anchor.	5 / 5
Progressive Disclosure	Clear sectioned overview in SKILL.md with the bulk per-section checklist correctly split to a one-level-deep, well-signaled reference ('The full per-section checklist … is in references/checklist.md', verified to exist), matching the clear-overview-with-well-signaled-references 5 anchor.	5 / 5
	Total	19 / 20 Passed

Description

100%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, third-person description that states concrete actions, natural trigger terms, an explicit 'Use when' clause, and a distinctive niche. Every dimension lands at the top anchor with no over-claiming or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Cross-checks every claim a page makes against the code', 'finds wikilinks and heading anchors the branch broke', 'checks frontmatter and page shape', 'reports D-C/H/M/L findings' — giving comprehensive coverage, matching the 5 anchor.	5 / 5
Completeness	Opens with an explicit 'Use when reviewing the documentation a branch changes … or sweeping the whole wiki with --full' trigger and follows it with a clear statement of what the skill does, satisfying the 5 anchor for explicit what AND when.	5 / 5
Trigger Term Quality	Covers natural terms a user would say ('reviewing the documentation', 'CLAUDE.md', 'READMEs', 'wiki', '--full', 'wikilinks', 'frontmatter') including synonyms and concrete file names, matching the comprehensive-coverage 5 anchor.	5 / 5
Distinctiveness Conflict Risk	Carves a clear doc-review niche (branch docs / wiki sweep, D-C/H/M/L format) and explicitly disambiguates from review-security, giving minimal conflict risk per the 5 anchor.	5 / 5
	Total	20 / 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: xchromo/osn
Path: .claude/skills/review-docs/SKILL.md
Commit: 5438649

Reviewed: 13 hours 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.