review-docs

Review and fix ChatJS Blume documentation and MDX files. Use when checking docs for correctness, broken links, stale examples, unclear prose, or consistency with the implementation.

Quality

85%

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

86%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 concise, well-structured instruction-only skill with a clear review-fix-report workflow and an explicit verification checkpoint. It could push actionability higher with a concrete fix example and a post-fix re-verification step.

Suggestions

Add one short before/after fix example to make the 'fix directly' guidance fully executable rather than relying on 'when the correct change is clear'.

State an explicit post-edit re-verification step (e.g., re-check links/paths after fixing) to close the validation gap and lift workflow_clarity toward 5.

Tighten the report criterion by giving one or two concrete examples of what counts as a 'product, architecture, or domain decision' to reduce reliance on judgment.

Dimension	Reasoning	Score
Conciseness	At roughly 80 words with no concept explanations Claude already knows, the body is lean and every token earns its place, matching the 'lean and efficient' 5 anchor rather than the minor-over-explanation 4.	5 / 5
Actionability	Provides concrete enumerated lists of what to verify and what to fix directly plus a clear fix-vs-report policy, but relies on judgment phrases ('when the correct change is clear') and offers no concrete fix examples, leaving it just short of fully executable guidance.	4 / 5
Workflow Clarity	A clear sequence is present (read completely -> verify against the repository -> fix clear cases -> report decisions and summarize) with an upfront verify checkpoint, but there is no explicit validate-fix-retry feedback loop, leaving a minor validation gap below the 5 anchor.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, needs no external references, and is organized into a clear heading, intro, fix list, and report instructions, qualifying for the simple-skill exception that lets progressive disclosure score 5 on well-organized sections alone.	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 description that clearly states both capability and trigger conditions with concrete, natural-language phrases. It is scoped to a named project but retains some overlap risk with general documentation-review skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('ChatJS Blume documentation and MDX files') and two concrete actions ('Review and fix') plus an enumerated checklist (broken links, stale examples, unclear prose, consistency), giving several specific items with minor coverage gaps rather than the comprehensive action list of a 5.	4 / 5
Completeness	Explicitly answers both 'what' ('Review and fix ChatJS Blume documentation and MDX files') and 'when' ('Use when checking docs for correctness, broken links, stale examples, unclear prose, or consistency with the implementation') with concrete trigger phrases, matching the 5 anchor rather than the less-explicit 4.	5 / 5
Trigger Term Quality	Includes natural terms users say ('documentation', 'docs', 'broken links', 'MDX files') with the synonym pair documentation/docs, but misses additional synonyms and the file extension '.mdx', so it falls short of the comprehensive coverage anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The named project 'ChatJS Blume' carves a clear niche, but the triggers (checking docs for correctness, broken links, stale examples) are generic doc-review territory that could overlap with other documentation skills, indicating minor overlap risk rather than minimal conflict risk.	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: FranciscoMoretti/chat-js
Path: .agents/skills/review-docs/SKILL.md
Commit: 4584f09

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.