code-reviewer
tessl i github:jeffallan/claude-skills --skill code-reviewerUse when reviewing pull requests, conducting code quality audits, or identifying security vulnerabilities. Invoke for PR reviews, code quality checks, refactoring suggestions.
Review Score
66%
Validation Score
12/16
Implementation Score
57%
Activation Score
65%
Generated
Validation
Total
12/16Score
Passed| Criteria | Score |
|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) |
metadata_version | 'metadata' field is not a dictionary |
license_field | 'license' field is missing |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata |
Implementation
Suggestions 4
Score
57%Overall Assessment
This skill provides good structural organization with excellent progressive disclosure through its reference table, but falls short on actionability by describing the review process abstractly rather than with concrete examples. The content includes some unnecessary explanations of concepts Claude already knows, and the workflow lacks explicit validation checkpoints for ensuring review completeness.
Suggestions
- Add a concrete code review example showing actual feedback on a code snippet (e.g., 'Given this code: [snippet], provide feedback like: [example feedback]')
- Remove the 'Knowledge Reference' section listing concepts Claude already knows (SOLID, DRY, OWASP, etc.)
- Add validation checkpoints to the workflow, such as 'Before finalizing: verify all critical issues have code examples, confirm you understood the PR context correctly'
- Include a brief executable example of how to structure feedback for a specific issue type (e.g., security vulnerability or N+1 query)
| Dimension | Score | Reasoning |
|---|---|---|
Conciseness | 2/3 | The skill is reasonably efficient but includes some unnecessary content like the 'Role Definition' section explaining Claude's persona and the 'Knowledge Reference' section listing concepts Claude already knows (SOLID, DRY, OWASP, etc.). |
Actionability | 2/3 | Provides a clear workflow and categorized constraints, but lacks concrete code examples or executable guidance. The review process is described abstractly rather than with specific commands or code snippets showing how to perform each step. |
Workflow Clarity | 2/3 | The 5-step workflow is clearly sequenced, but lacks validation checkpoints or feedback loops. There's no guidance on what to do if issues are found during review or how to verify the review is complete. |
Progressive Disclosure | 3/3 | Excellent use of reference table with clear one-level-deep links to detailed guidance. The 'Load When' column provides helpful context for when to access each reference, and content is appropriately split between overview and detailed materials. |
Activation
Suggestions 3
Score
65%Overall Assessment
The description has strong trigger term coverage with natural developer vocabulary, but inverts the typical structure by leading with 'when' rather than 'what'. It lacks concrete capability descriptions (what specific analyses it performs, what outputs it produces) and relies heavily on trigger phrases without explaining the skill's actual functionality.
Suggestions
- Add concrete capability statements before the trigger guidance, e.g., 'Analyzes code changes for bugs, style violations, and security issues. Provides line-by-line feedback with severity ratings.'
- Specify what outputs or deliverables the skill produces (e.g., 'generates structured review comments', 'produces security vulnerability reports')
- Differentiate from general coding skills by specifying unique capabilities like 'compares against project style guides' or 'checks for OWASP Top 10 vulnerabilities'
| Dimension | Score | Reasoning |
|---|---|---|
Specificity | 2/3 | Names the domain (code review, security) and some actions (reviewing PRs, audits, identifying vulnerabilities), but lacks concrete specific actions like 'analyze diff hunks', 'check for SQL injection', or 'suggest refactoring patterns'. |
Completeness | 2/3 | Has a 'Use when...' clause which addresses the 'when', but the 'what does this do' portion is weak - it describes when to use it rather than what concrete capabilities it provides. The description is essentially all trigger guidance with minimal capability description. |
Trigger Term Quality | 3/3 | Good coverage of natural terms users would say: 'pull requests', 'PR reviews', 'code quality', 'security vulnerabilities', 'refactoring suggestions'. These are terms developers naturally use when requesting code review help. |
Distinctiveness Conflict Risk | 2/3 | Somewhat specific to code review domain, but 'code quality' and 'refactoring suggestions' could overlap with general coding assistance skills. The PR review focus helps distinguish it, but security vulnerability detection might conflict with dedicated security scanning skills. |