code-reviewer
Use when reviewing pull requests, conducting code quality audits, or identifying security vulnerabilities. Invoke for PR reviews, code quality checks, refactoring suggestions.
Install with Tessl CLI
npx tessl i github:jeffallan/claude-skills --skill code-reviewer68
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillAgent success when using this skill
Validation for skill structure
Discovery
64%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 strong trigger terms that match developer vocabulary but lacks specificity about concrete capabilities. It focuses heavily on 'when' scenarios without clearly articulating 'what' specific actions the skill performs. The broad scope covering multiple concerns (PR review, security, quality, refactoring) may cause conflicts with more specialized skills.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Analyzes code diffs for bugs, checks for common security vulnerabilities (SQL injection, XSS), suggests naming improvements, identifies code smells'
Narrow the scope or clarify the relationship between the different capabilities (PR review vs security audit vs refactoring) to reduce conflict risk with specialized skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code review, security) and some actions (reviewing PRs, audits, identifying vulnerabilities), but lacks concrete specific actions like 'analyze diff', 'check for SQL injection', or 'suggest refactoring patterns'. | 2 / 3 |
Completeness | Has a 'Use when...' clause addressing when to invoke, but the 'what does this do' portion is weak - it describes scenarios rather than concrete capabilities. The description tells when to use it but not specifically what actions it performs. | 2 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'pull requests', 'PR reviews', 'code quality', 'security vulnerabilities', 'refactoring suggestions', 'code quality checks' - these are terms developers naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to code review domain, but could overlap with general coding skills, security-specific skills, or refactoring tools. The broad scope (PR review + security + quality + refactoring) increases conflict risk. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has strong progressive disclosure with a well-organized reference table, but lacks the concrete, executable guidance that would make it highly actionable. The workflow is clear at a high level but missing validation checkpoints and specific examples of how to apply the review criteria. The role definition adds unnecessary tokens explaining concepts Claude already knows.
Suggestions
Add concrete code examples showing good vs bad patterns for each review category (e.g., actual N+1 query example with fix)
Remove the 'Role Definition' section - Claude doesn't need persona framing to perform code review
Add validation checkpoints to the workflow, such as 'Before providing feedback, verify you understand the PR's intent by summarizing it'
Include specific questions or checks to perform at each workflow step rather than abstract descriptions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary framing ('Senior engineer with 12+ years') and the 'Role Definition' section explains what Claude already understands about code review. The reference table and constraints are well-structured. | 2 / 3 |
Actionability | Provides clear categories and checklists but lacks concrete code examples. The workflow is described abstractly ('Check code quality, security, performance') without executable guidance or specific review commands/patterns to apply. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced but lacks validation checkpoints. No guidance on what to do if issues are found mid-review, how to handle disagreements, or feedback loops for iterating with the author. | 2 / 3 |
Progressive Disclosure | Excellent use of reference table with clear 'Load When' conditions. Content is appropriately split between overview and detailed reference files. Navigation is one level deep and well-signaled. | 3 / 3 |
Total | 9 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- 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.