code-reviewer
Provides structured code review against plans and standards. Use when a feature is complete and needs validation, when reviewing code before merge, or when assessing quality and test coverage—e.g., "finished step X", "ready for review", "validate architecture", "check quality and tests".
90
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/skillValidation for skill structure
Discovery
89%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 a well-crafted description that excels at completeness and trigger term quality, providing explicit 'Use when' guidance with natural user phrases. The main weakness is moderate specificity—it describes the general purpose but could benefit from listing more concrete review actions. Overall, it would perform well in skill selection scenarios.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code review) and mentions some actions like 'validation', 'reviewing code', 'assessing quality and test coverage', but doesn't list multiple concrete specific actions like 'check for security vulnerabilities, verify naming conventions, analyze cyclomatic complexity'. | 2 / 3 |
Completeness | Clearly answers both what ('structured code review against plans and standards') and when ('when a feature is complete', 'before merge', 'assessing quality') with explicit 'Use when' clause and concrete trigger examples. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'finished step X', 'ready for review', 'validate architecture', 'check quality and tests', 'before merge'. These are realistic phrases developers use when requesting code reviews. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on structured code review with specific triggers like 'finished step X', 'ready for review', 'validate architecture'. The combination of plan-based review and quality/test assessment creates a distinct identity unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured code review skill with excellent workflow clarity and progressive disclosure. The actionability is strong with concrete output contracts and severity labels. Minor verbosity in the emphatic warnings ('Every time.', 'No exceptions.') could be trimmed without losing clarity.
Suggestions
Remove redundant emphasis phrases like 'Every time.' and 'No exceptions.' - Claude understands importance from context and structure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some redundant emphasis phrases like 'Every time.' repeated twice and 'No exceptions.' The warnings about skipping steps are somewhat verbose given Claude's competence. | 2 / 3 |
Actionability | Provides concrete, specific guidance with exact output structure, severity labels, required fields, and clear step-by-step procedure. The output contract is copy-paste ready with explicit formatting requirements. | 3 / 3 |
Workflow Clarity | Clear 6-step sequence with explicit ordering, validation checkpoint ('Before finalizing: Verify you checked every file'), and communication protocol for handling deviations. Steps are numbered and logically ordered. | 3 / 3 |
Progressive Disclosure | Well-structured with clear overview in main file and appropriately signaled one-level-deep references to checklists.md and examples.md. References are clearly labeled with when to load them. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.