Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.
100
100%
Does it follow best practices?
Impact
100%
1.28xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Quality
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 a strong skill description that clearly communicates what the skill does and when to use it. It uses third person voice, lists concrete actions, includes natural trigger terms, and is scoped narrowly enough to avoid conflicts with other skills. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Find bugs, security vulnerabilities, and code quality issues in local branch changes.' These are distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Find bugs, security vulnerabilities, and code quality issues in local branch changes') and when ('Use when asked to review changes, find bugs, security review, or audit code on the current branch') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'review changes', 'find bugs', 'security review', 'audit code', 'current branch'. These cover common variations of how users would request code review. | 3 / 3 |
Distinctiveness Conflict Risk | Scoped specifically to local branch changes and code review/audit, which distinguishes it from general coding skills, linting tools, or broader code assistance. The 'local branch changes' qualifier creates a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that provides a thorough, well-structured methodology for code review. It's concise yet comprehensive, with concrete commands, detailed security checklists, explicit verification steps, and a clear output format. The five-phase workflow with built-in validation (Phase 4 verification and Phase 5 audit) demonstrates strong workflow design for a potentially complex and high-stakes task.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section serves a clear purpose. No unnecessary explanations of what bugs or security vulnerabilities are. The checklists are dense with actionable items and no padding. Claude doesn't need to be told what SQL injection is—just to check for it. | 3 / 3 |
Actionability | Provides a concrete git command for getting the diff, specific checklists to evaluate against, a clear output format with severity levels and required fields, and explicit instructions like 'read each changed file individually.' The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | Five clearly sequenced phases with logical dependencies (gather input → map attack surface → check against checklist → verify findings → audit completeness). Phase 4 is an explicit verification/feedback loop ensuring issues are real, and Phase 5 is a pre-conclusion audit that prevents premature or incomplete reporting. | 3 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines of substantive content), the structure is well-organized with clear section headers and logical progression. No external references are needed since the content is self-contained and appropriately scoped. The checklist format enables quick scanning. | 3 / 3 |
Total | 12 / 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.
45417f2
Table of Contents
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.