code-review-excellence

This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/code-review-excellence/SKILL.md

Quality

Content

56%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.

The body is well-structured and actionable with a clear four-phase review workflow, templates, and severity labels. Its main weaknesses are heavy verbosity from textbook material Claude already knows and significant duplication between the inline content and the existing bundle files.

Suggestions

Trim the language-specific bug catalogs and generic feedback-psychology advice (Python mutable defaults, 'any' avoidance, sandwich method, pitfalls list) down to team-specific conventions or move them entirely to references/common-bugs-checklist.md, since they restate knowledge Claude already has.

Remove the inline duplicated content — the security checklist, the PR review comment template, and the review checklists — replacing each with a single pointer to the corresponding references/ or assets/ file to eliminate the duplication between SKILL.md and the bundle.

Convert the phase bullet-question lists into a compact executable summary (a few decisive steps per phase) and lead the Resources section earlier so the reference files are discovered before the 400+ lines of inline detail.

Dimension	Reasoning	Score
Conciseness	The ~500-line body extensively re-explains concepts Claude already knows: Python mutable default arguments, avoiding 'any' in TypeScript, prop mutation, race conditions, N+1 queries, the sandwich feedback method, and generic pitfalls like 'bike shedding'. This matches anchor 2 (noticeably verbose, several padded sections of unnecessary explanation) — above 1 because nothing explains true basics like what a PR is, below 3 because the volume of textbook material is substantial.	2 / 5
Actionability	Concrete, usable artifacts: a copy-paste PR review comment template, severity labels with usage examples, executable Python/TypeScript snippets, phase timings, and a runnable script (scripts/pr-analyzer.py). This fits anchor 4 (concrete code or commands with minor gaps) rather than 5 because the four-phase process steps are largely bullet questions rather than fully executable instructions.	4 / 5
Workflow Clarity	The four-phase process (Context Gathering -> High-Level -> Line-by-Line -> Summary & Decision) is clearly sequenced with time budgets, explicit checkpoints ('Check PR size (>400 lines? Ask to split)', 'Review CI/CD status'), a defined decision step (Approve/Comment/Request Changes), and escalation guidance for disagreements. This matches anchor 4 (clear sequence, most checkpoints present, minor validation gaps).	4 / 5
Progressive Disclosure	All six bundle files exist and are clearly listed in a Resources section with descriptions, but the body inlines large checklists and templates that duplicate them (inline security checklist vs references/security-review-guide.md, inline PR template vs assets/pr-review-template.md, language bug patterns vs references/common-bugs-checklist.md). This matches anchor 3 (references present and signaled, but content that should be separate is inline) rather than 4 due to the duplication.	3 / 5
	Total	13 / 20 Passed

Description

80%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 with concrete, action-oriented language and an explicit trigger clause. Its main weaknesses are the inverted structure (the 'what' is embedded in the 'when' clause rather than stated separately) and a few missing natural synonyms like 'PR'.

Dimension	Reasoning	Score
Specificity	The description lists five concrete actions ('review a diff or pull request', 'write review comments', 'audit code quality', 'establish review standards', 'improve how a team performs code review') covering the skill's domain comprehensively, matching the anchor-5 pattern of multiple specific concrete actions. It uses third-person voice ('This skill should be used'), so no person-voice penalty applies.	5 / 5
Completeness	It has an explicit 'when' ('when the user asks to...') and a 'what' embedded in the enumerated trigger actions, so both are present. It falls short of anchor 5 because the what and when are not separately and explicitly framed as in 'Extract text... Use when working with PDF files', and above anchor 3 because the when clause is explicit rather than weakly implied.	4 / 5
Trigger Term Quality	Natural phrases users would say ('review a diff', 'pull request', 'write review comments') are covered well, but common synonyms and abbreviations like 'PR', 'review my changes', or 'critique my code' are missing. This fits anchor 4 (good keyword coverage, a few natural terms missing) rather than 5 (comprehensive synonyms and extensions).	4 / 5
Distinctiveness Conflict Risk	Distinct triggers like 'review a diff or pull request' and 'write review comments' establish a clear niche, but 'audit code quality' and 'improve how a team performs code review' carry minor overlap risk with general code-quality or team-process skills. This matches anchor 4 (mostly distinct, minor overlap with closely related skills) rather than 5 (minimal conflict risk).	4 / 5
	Total	17 / 20 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
skill_md_line_count	SKILL.md is long (522 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Galaxy-Dawn/claude-scholar
Path: skills/code-review-excellence/SKILL.md
Commit: 9037873

Reviewed: 2 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.