code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
71
47%
Does it follow best practices?
Impact
85%
1.25xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/developer-essentials/skills/code-review-excellence/SKILL.mdQuality
Discovery
67%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 has good structural completeness with an explicit 'Use when' clause, but the capabilities listed lean toward abstract goals rather than concrete actions. The trigger terms cover the basics but miss common user phrasings. The description also uses imperative voice ('Master effective...') rather than third person, though this is in the instructional framing rather than describing what the skill does.
Suggestions
Replace abstract outcomes like 'catch bugs early' and 'foster knowledge sharing' with concrete actions such as 'comment on pull requests, suggest code improvements, flag security issues, verify test coverage'.
Add more natural trigger term variations users might say, such as 'PR review', 'code feedback', 'review comments', 'approve changes', or 'diff review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code review) and some actions ('provide constructive feedback, catch bugs early, foster knowledge sharing'), but these are more like goals/outcomes than concrete specific actions. Compare to a 3 which would list things like 'comment on pull requests, suggest code changes, check for security vulnerabilities, verify test coverage.' | 2 / 3 |
Completeness | Clearly answers both what ('provide constructive feedback, catch bugs early, foster knowledge sharing while maintaining team morale') and when ('Use when reviewing pull requests, establishing review standards, or mentoring developers') with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'pull requests', 'code review', 'review standards', and 'mentoring developers', but misses common variations users might say such as 'PR review', 'code feedback', 'review comments', 'approve PR', or 'request changes'. | 2 / 3 |
Distinctiveness Conflict Risk | While 'code review' and 'pull requests' provide some specificity, the description could overlap with general coding skills, mentoring skills, or team management skills due to broad terms like 'mentoring developers' and 'maintaining team morale'. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a comprehensive but overly verbose guide to code review that reads more like a blog post or training document than a concise skill for Claude. It explains many concepts Claude already understands (basic anti-patterns, feedback principles, common pitfalls) and packs everything into a single monolithic file. The language-specific code examples and severity labeling system add some value, but the overall token cost is very high relative to the actionable content.
Suggestions
Cut content by 60-70%: Remove sections explaining concepts Claude already knows (Core Principles, Giving Difficult Feedback, Common Pitfalls, Best Practices) and focus on the specific review process, severity labels, and templates.
Split language-specific patterns, security checklists, and templates into separate referenced files to improve progressive disclosure and reduce the main file size.
Make the skill more actionable by providing a concrete, step-by-step procedure Claude should follow when given code to review, rather than general advice about review philosophy.
Add explicit validation steps to the workflow, such as 'verify all blocking issues have specific fix suggestions' or 'confirm test coverage concerns reference specific untested paths.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Explains concepts Claude already knows well (what code review is, what good feedback looks like, basic Python/TypeScript anti-patterns, the sandwich method). Much of this is general software engineering knowledge that doesn't need to be taught. Lists like 'Common Pitfalls' and 'Best Practices' contain obvious advice. | 1 / 3 |
Actionability | Provides concrete code examples for language-specific patterns and good/bad feedback examples, which is useful. However, much of the content is descriptive guidance and checklists rather than executable instructions. The skill describes how to think about reviews rather than giving Claude specific, actionable steps to execute when performing a review. | 2 / 3 |
Workflow Clarity | The four-phase review process (Context Gathering → High-Level → Line-by-Line → Summary) provides a clear sequence, but lacks validation checkpoints or feedback loops. There's no mechanism to verify the review quality or handle situations where the process breaks down. The time estimates are a nice touch but the phases themselves are just nested checklists without explicit decision points. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files and no bundle files to support it. All content—from basic principles to language-specific patterns to security checklists to templates—is crammed into a single file. The language-specific patterns, security checklists, and templates could easily be split into separate referenced files. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (530 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
cf6059d
- Reviewed
Table of Contents
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.