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

62%

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

50%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 content is well-organized and contains genuinely executable code, a working script, templates, and a clear phased workflow. Its main weaknesses are verbosity from restating general knowledge Claude already has and weak progressive disclosure where inline content duplicates the bundle files instead of pointing to them.

Suggestions

Trim sections that restate general knowledge Claude already has (review goals, feedback principles, common pitfalls, generic best practices) and keep only the novel operational details such as the severity labels and language-specific bug patterns.

Replace the inlined security checklist and PR review template with pointers to the corresponding bundle files (security-review-guide.md, pr-review-template.md) and signal each reference inline at the relevant section rather than only in a trailing Resources list.

Add an explicit validation/verification checkpoint to the review workflow (e.g., re-confirm each blocking comment cites the failing code path before posting the verdict) to close the validation-gap that caps workflow clarity.

Dimension	Reasoning	Score
Conciseness	At ~515 lines the body extensively explains concepts Claude already knows (review goals, good-feedback principles, common pitfalls, generic best practices like 'review within 24 hours', the sandwich method), making it noticeably verbose with several padded sections rather than the mostly-efficient profile of a 3.	2 / 5
Actionability	Provides genuinely executable code (Python mutable-default and TS async examples), a working pr-analyzer.py script, concrete templates, and a severity-label system; the code is real rather than pseudocode, with only minor gaps keeping it below 5.	4 / 5
Workflow Clarity	A clear 4-phase review process with time budgets and checklists is present, but validation checkpoints are largely implicit (only 'check CI/CD status' qualifies) and there is no explicit validate-fix-retry feedback loop, matching the validation-gaps anchor.	3 / 5
Progressive Disclosure	The body is well-sectioned and real bundle files exist and are listed in a Resources section, but references are signaled only at the end rather than inline at the relevant sections, and inline content (security checklist, PR template) duplicates what already lives in the bundle files.	3 / 5
	Total	12 / 20 Passed

Description

75%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.

The description is strong: it opens with an explicit 'use when' trigger clause and lists multiple concrete, natural-language actions, answering both what and when. It falls just short of top marks because the what is embedded in the triggers and a few synonyms are missing.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('review a diff or pull request, write review comments, audit code quality, establish review standards'), with only minor abstraction in the last two; not quite comprehensive enough for a 5.	4 / 5
Completeness	Explicitly states 'This skill should be used when the user asks to...' giving a concrete when-clause, and the action list conveys the what; the what is blended into the triggers rather than a standalone capability statement, keeping it just below 5.	4 / 5
Trigger Term Quality	Uses natural phrases users would say ('review a diff or pull request', 'audit code quality'), giving good keyword coverage, but omits common synonyms like 'PR' and 'merge request' that would justify a 5.	4 / 5
Distinctiveness Conflict Risk	Targets a clear code-review niche with distinct triggers; only minor overlap risk with closely related general code-quality skills, not the minimal-conflict profile of a 5.	4 / 5
	Total	16 / 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: 2847aa1

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.