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

67%

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

35%

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-intentioned and rich with templates and a working script, but it is far too verbose — restating code-review fundamentals Claude already knows — and keeps material inline that the bundle files were meant to hold. The workflow is sequenced but lacks explicit checkpoints, and progressive disclosure is undermined by inline duplication of bundled content.

Suggestions

Cut generic knowledge Claude already has (review goals, feedback principles, common Python/TS bug examples, the inline security checklist) and point to the existing references instead, trusting Claude's competence.

Move the inline PR review comment template, security checklist, and language-specific patterns into the matching assets/references files, leaving SKILL.md as a concise overview with well-signaled one-level-deep links.

Add explicit validation/decision checkpoints between phases (e.g., 'Stop and confirm all blocking items are resolved before approving') to turn the sequenced phases into a workflow with feedback loops.

Dimension	Reasoning	Score
Conciseness	The ~515-line body explains concepts Claude already knows — "Goals of Code Review", "Good Feedback is…", Python mutable-default and TypeScript `any` bug examples, and generic security checklists — padding the context with unnecessary material as in the level-1 anchor; it never tightens to lean, assumes-competence content.	1 / 3
Actionability	There is concrete material (the executable `scripts/pr-analyzer.py`, copy-paste review templates, a severity taxonomy, and checklists), but the bulk is abstract advice ("Review Promptly", "Build Rapport") and illustrative bad/good snippets rather than executable instructions, leaving it incomplete like the level-2 anchor rather than copy-paste ready throughout.	2 / 3
Workflow Clarity	The four review phases are sequenced with time budgets and supported by checklists, but there are no explicit validation checkpoints or feedback loops — checkpoints are implicit, matching the level-2 anchor rather than the explicit-validate level-3 anchor.	2 / 3
Progressive Disclosure	A Resources section signals real, verified one-level-deep files (references/, assets/, scripts/), but large chunks that should live in those files are duplicated inline (language-specific patterns, security checklist, PR review template), so content is not appropriately split as the level-3 anchor requires.	2 / 3
	Total	7 / 12 Passed

Description

100%

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 states five concrete actions and pairs them with an explicit 'use when' trigger in a clear code-review niche. It is concise, third-person, and unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review" — matching the level-3 anchor for several specific actions; not merely naming a domain.	3 / 3
Completeness	Explicitly answers both what (the listed review actions) and when ("This skill should be used when the user asks to…"), an explicit trigger clause equivalent to a 'Use when…' form, so it clears the level-2 cap.	3 / 3
Trigger Term Quality	Covers natural terms users would say ("diff", "pull request", "review comments", "code quality", "code review") with good variation; it is not jargon or overly generic, so it sits above level 2.	3 / 3
Distinctiveness Conflict Risk	A clear code-review niche with distinct triggers (diffs, PRs, review comments, review standards) that are unlikely to fire for unrelated skills; not generic enough to conflict as in the level-1 example.	3 / 3
	Total	12 / 12 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: 2f7766f

Reviewed: about 14 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.