structured-code-review
Performs a structured five-stage code review covering requirements compliance, correctness, code quality, testing, and security/performance. Each stage uses targeted checklists and categorized feedback (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. Use when the user asks for code review, PR feedback, pull request review, or wants their code checked for bugs, style issues, or vulnerabilities — triggered by phrases like "review my code", "check this PR", "review my changes", "pull request review", or "code feedback".
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/core/src/methodology/packs/collaboration/structured-review/SKILL.mdQuality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides specific, concrete actions (five-stage review, categorized feedback), includes comprehensive natural trigger terms that users would actually say, and clearly delineates both what the skill does and when it should be used. The description is well-structured, uses third person voice throughout, and is distinctive enough to avoid conflicts with other development-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: five-stage review covering requirements compliance, correctness, code quality, testing, and security/performance. Also specifies targeted checklists and categorized feedback levels (Blocker/Major/Minor/Nit) with actionable suggestions and rationale. | 3 / 3 |
Completeness | Clearly answers both 'what' (structured five-stage code review with checklists and categorized feedback) and 'when' (explicit 'Use when...' clause with multiple trigger phrases and scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'code review', 'PR feedback', 'pull request review', 'review my code', 'check this PR', 'review my changes', 'code feedback', 'bugs', 'style issues', 'vulnerabilities'. These are highly natural phrases users would actually use. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche — structured multi-stage code review with specific feedback categorization. The trigger terms are focused on code review/PR review, making it unlikely to conflict with general coding assistance, debugging, or other development skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured five-stage review workflow with clear sequencing, but is significantly over-verbose for its audience. It explains concepts Claude already knows (what SQL injection is, how to write constructive feedback, what a code review is) and lacks a concrete end-to-end example showing actual code input and review output. The content would be much stronger at roughly one-third its current length, focusing on the specific stage order, severity definitions, and output format.
Suggestions
Cut at least 60% of the content by removing explanations of concepts Claude already knows (e.g., what SQL injection is, how to give constructive feedback, what code review is) and keep only the stage sequence, severity levels, and output template.
Add a concrete end-to-end example: show a small code snippet as input and the expected structured review output, so Claude has a clear model to follow.
Consider splitting the detailed per-stage checklists and feedback examples into a separate reference file, keeping SKILL.md as a concise overview with the workflow and output format.
Remove the 'Core Principle' section and generic motivational text ('A structured review catches more issues...') — these add no actionable value for Claude.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Heavily verbose. Explains what Claude already knows: how to do code reviews, what SQL injection is, what constructive feedback looks like. The checklists are generic knowledge, and the example feedback strings are things Claude would naturally produce. The 'Core Principle' section is unnecessary filler. Much of this could be reduced to a compact stage list with severity definitions. | 1 / 3 |
Actionability | Provides structured checklists and a feedback template, which are somewhat actionable. However, there's no executable code, no concrete example of reviewing actual code (input code → output review), and the guidance remains at the level of general methodology rather than specific instructions Claude can directly follow. | 2 / 3 |
Workflow Clarity | The five stages are clearly sequenced with explicit ordering ('First', 'Next', 'Then', 'Finally'), each with focused checklists and example feedback. The final summary checklist with a verdict step provides a clear completion checkpoint. The workflow is well-structured for a multi-step process. | 3 / 3 |
Progressive Disclosure | The content is a monolithic document with everything inline. The checklists, feedback templates, and examples could be split into referenced files. The 'Integration with Other Skills' section references other skills but the main content itself is a wall of text that could benefit from better organization across files. | 2 / 3 |
Total | 8 / 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rohitg00/skillkit
- Commit
a9e5c83
- 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.