code-review
Review PRs, MRs, and Gerrit changes with focus on security, maintainability, and architectural fit. Leverages github, gitlab, or gerrit skills based on repository context. Use when asked to review my code, check this PR, review a pull request, look at a merge request, review a patchset, or provide code review feedback.
Install with Tessl CLI
npx tessl i github:odyssey4me/agent-skills --skill code-review96
Does it follow best practices?
Evaluation — 98%
↑ 1.42xAgent success when using this skill
Validation for skill structure
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 an excellent skill description that hits all the key criteria. It provides specific capabilities with clear focus areas, includes a comprehensive 'Use when...' clause with natural trigger terms users would actually say, and clearly distinguishes itself as a code review skill across multiple platforms.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Review PRs, MRs, and Gerrit changes' with clear focus areas: 'security, maintainability, and architectural fit'. Also mentions leveraging specific platform skills (github, gitlab, gerrit). | 3 / 3 |
Completeness | Clearly answers both what ('Review PRs, MRs, and Gerrit changes with focus on security, maintainability, and architectural fit') and when (explicit 'Use when...' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'review my code', 'check this PR', 'pull request', 'merge request', 'patchset', 'code review feedback'. These are exactly what users would naturally type. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on code review across specific platforms (GitHub, GitLab, Gerrit). The combination of review focus areas and platform-specific triggers makes it distinct from general coding or git skills. | 3 / 3 |
Total | 12 / 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-crafted orchestration skill with excellent workflow clarity and actionability. The multi-step review process is clearly sequenced with validation checkpoints, and all commands are executable. Minor verbosity in some sections (authentication delegation, repeated platform examples) prevents a perfect conciseness score, but overall the skill effectively guides Claude through complex cross-platform code review.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy, such as repeating platform detection logic multiple times and explaining concepts like 'workflow skill' that could be more concise. The authentication section could be trimmed since it just points to other skills. | 2 / 3 |
Actionability | Provides fully executable commands for each platform (GitHub, GitLab, Gerrit) with specific script paths and CLI syntax. The workflow steps contain copy-paste ready commands and clear examples of user invocations. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clearly numbered steps (0-6), explicit validation checkpoints (Step 3 CI assessment before proceeding), and clear decision points for platform detection. The workflow includes feedback guidance for different CI states. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections (Commands, Workflow, Examples, Troubleshooting). References external checklist via one-level-deep link to 'references/review-checklist.md' and delegates to platform-specific skills appropriately. Content is appropriately split between overview and detailed workflow. | 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.