common-code-review
Conduct high-quality, persona-driven code reviews. Use when reviewing PRs, critiquing code quality, or analyzing changes for team feedback. (triggers: review, pr, critique, analyze code)
82
77%
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 ./.github/skills/common/common-code-review/SKILL.mdQuality
Discovery
82%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 solid description that clearly communicates its purpose and includes explicit trigger guidance. Its main weaknesses are the somewhat vague 'persona-driven' qualifier without explaining what that means concretely, and the lack of more specific concrete actions beyond the general category of code review. The trigger terms are well-chosen and natural.
Suggestions
Clarify what 'persona-driven' means concretely — e.g., 'Reviews code as different team roles (security engineer, senior dev, architect)' to improve specificity and distinctiveness.
Add more specific concrete actions such as 'checks for security vulnerabilities, suggests refactors, evaluates naming conventions, assesses test coverage' to strengthen specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (code reviews) and mentions some actions like 'reviewing PRs', 'critiquing code quality', and 'analyzing changes for team feedback', but doesn't list specific concrete actions like checking for security issues, suggesting refactors, or evaluating test coverage. 'Persona-driven' is somewhat vague. | 2 / 3 |
Completeness | Clearly answers both 'what' (conduct persona-driven code reviews) and 'when' (reviewing PRs, critiquing code quality, analyzing changes for team feedback) with an explicit 'Use when' clause and trigger terms. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'review', 'pr', 'critique', 'analyze code', 'code quality', 'changes', 'team feedback'. These cover common variations of how users would request code review assistance. | 3 / 3 |
Distinctiveness Conflict Risk | While 'code review' and 'PR' are fairly specific, terms like 'analyze code' and 'critique' could overlap with general code analysis or linting skills. The 'persona-driven' aspect adds some distinctiveness but isn't well-defined enough to clearly separate it from a generic code review skill. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
72%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, concise skill that effectively establishes a code review persona and framework. Its strengths are excellent token efficiency, clear severity categorization, and good progressive disclosure. The main weaknesses are the lack of a concrete worked example showing the output format applied to real code, and the absence of an explicit step-by-step review workflow.
Suggestions
Add a brief concrete example showing a real code snippet and the corresponding review comment in the specified output format (e.g., [BLOCKER] [auth.py] with actual code and fix).
Add an explicit numbered workflow sequence (e.g., 1. Read the full diff, 2. Run through security checklist, 3. Check performance, 4. Write summary with severity counts) to clarify the review process order.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No unnecessary explanations of what code review is or how it works. Assumes Claude's competence as a principal engineer and provides only the delta knowledge needed. | 3 / 3 |
Actionability | The output format template and severity labels are concrete and actionable, and the checklist provides specific inspection points. However, there are no concrete code examples showing a real review comment applied to actual code, which would make it fully copy-paste ready. | 2 / 3 |
Workflow Clarity | The checklist provides a clear sequence of what to inspect, and the output format is well-defined. However, there's no explicit workflow for the review process itself (e.g., read diff → check security → check performance → write summary), and no validation/feedback loop for ensuring review completeness. | 2 / 3 |
Progressive Disclosure | Clean overview with well-signaled one-level-deep references to checklist.md and output-format.md. The main skill file stays concise while pointing to detailed materials for deeper inspection points and templates. | 3 / 3 |
Total | 10 / 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.
- Repository
- HoangNguyen0403/agent-skills-standard
- Commit
19a1140
- 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.