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.
65
51%
Does it follow best practices?
Impact
86%
1.28xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./tests/ext_conformance/artifacts/agents-wshobson/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 structure with an explicit 'Use when...' clause and covers the domain adequately. However, the capabilities listed lean toward abstract goals (catch bugs, foster knowledge sharing) rather than concrete actions, and the trigger terms, while relevant, miss common variations. The description also uses imperative voice ('Master effective...') rather than third person, though this is in the instructional framing rather than capability description.
Suggestions
Replace abstract goals with concrete actions, e.g., 'Analyzes pull request diffs for bugs, security issues, and style violations; suggests inline comments; provides approval/rejection recommendations'.
Expand trigger terms to include common variations like 'PR review', 'code feedback', 'review comments', 'diff review', '.patch files'.
| 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 'Extract text and tables from PDF files, fill forms, merge documents' which lists discrete operations. | 2 / 3 |
Completeness | Clearly answers both 'what' (effective code review practices, constructive feedback, catch bugs, knowledge sharing) and 'when' with an explicit 'Use when...' clause covering pull requests, review standards, and mentoring developers. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'code review', 'pull requests', 'review standards', and 'mentoring developers', which are natural phrases users might say. However, it misses common variations like 'PR review', 'CR', 'code feedback', 'review comments', or 'approve/request changes'. | 2 / 3 |
Distinctiveness Conflict Risk | While 'code review' and 'pull requests' are fairly specific, the mention of 'mentoring developers' and 'knowledge sharing' could overlap with general mentoring or team management skills. The description could also conflict with a general coding best practices skill. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
35%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 textbook chapter than a targeted skill file. It extensively explains concepts Claude already knows (feedback principles, common anti-patterns, interpersonal communication strategies) rather than providing lean, actionable instructions. The language-specific examples and severity labeling system add value, but the overall content could be reduced by 60-70% without losing actionable information.
Suggestions
Reduce content by 60%+ by removing explanations of concepts Claude already knows (what good feedback is, basic anti-patterns, interpersonal skills) and focus only on the specific review workflow, severity labels, and templates.
Move language-specific patterns, security checklists, and advanced patterns into the referenced files (which are listed but don't exist) to make the main SKILL.md a concise overview.
Add explicit validation checkpoints in the review workflow, such as 'Before submitting review, verify: all blocking issues have suggested fixes, severity labels are applied, summary includes verdict.'
Convert the review process from descriptive prose into a concrete, step-by-step checklist that Claude can directly execute when asked to review code.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensively 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 'Goals of Code Review' and 'Common Pitfalls' are textbook material Claude already possesses. | 1 / 3 |
Actionability | Provides concrete code examples for language-specific patterns and useful templates/checklists, but much of the content is advisory rather than executable. The skill describes how to think about reviews rather than giving Claude specific, copy-paste-ready instructions for performing reviews. The review process phases are described in markdown code blocks but are really just prose guidelines. | 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 for verifying review quality, no explicit decision points for when to escalate vs. approve, and the phases are more descriptive checklists than an actionable workflow with clear gates. | 2 / 3 |
Progressive Disclosure | References six external files (references/, assets/, scripts/) at the bottom, which is good structure, but none of these files exist in the bundle. The main file itself is monolithic — the language-specific patterns, security checklists, and advanced patterns could all be in separate referenced files rather than inline, making the SKILL.md much leaner. | 2 / 3 |
Total | 7 / 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 (539 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dicklesworthstone/pi_agent_rust
- Commit
895269a
- 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.