odyssey4me/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.
74
92%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 its purpose, scope, and trigger conditions. It covers multiple platforms (GitHub, GitLab, Gerrit) with specific review focus areas and includes a comprehensive 'Use when' clause with natural language trigger phrases. The description is concise yet thorough, making it easy for Claude to select appropriately.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions ('Review PRs, MRs, and Gerrit changes') and specifies 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/Gerrit changes with focus on security, maintainability, architectural fit) and 'when' (explicit 'Use when...' clause with multiple trigger phrases). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural user terms: 'review my code', 'check this PR', 'review a pull request', 'look at a merge request', 'review a patchset', 'code review feedback'. These are phrases users would naturally say, covering multiple platform variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to code review across specific platforms (GitHub, GitLab, Gerrit). The combination of review focus areas and platform specificity makes it distinct from general coding skills or individual platform skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 orchestration skill with strong actionability and clear workflow sequencing across three platforms. The main weaknesses are moderate verbosity (examples that restate the workflow, a thin 'Model Guidance' section, troubleshooting for obvious issues) and a referenced bundle file (review-checklist.md) that doesn't exist. The multi-step workflow is well-designed with appropriate decision points and platform-specific concrete commands.
Suggestions
Trim the Examples section — most examples just restate what the workflow already covers; keep only examples that demonstrate non-obvious usage patterns like 'focus only on security'.
Provide the referenced `references/review-checklist.md` file, since Step 5 explicitly delegates to it for the full checklist — without it, the review criteria are incomplete.
Remove or condense the 'Model Guidance' and 'Troubleshooting' sections, which add little value Claude wouldn't already know.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity — the examples section largely restates what the workflow already explains, the 'Model Guidance' section adds little value, and the troubleshooting section covers things Claude would naturally try. The YAML config example and workflow steps are useful but could be tighter. | 2 / 3 |
Actionability | Provides fully concrete, executable commands for each platform at every step — specific CLI invocations for GitHub, GitLab, and Gerrit, exact file paths for scripts, a complete output template for review findings, and specific bash commands for authentication checks and diff fetching. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit decision points (CI status assessment in Step 3 that changes review behavior, platform detection logic in Step 1). Step 3 acts as a validation checkpoint that adjusts downstream behavior. The review output format provides a structured checklist. The workflow handles error/edge cases (CI failing, pending, platform not detected). | 3 / 3 |
Progressive Disclosure | References `references/review-checklist.md` for the full checklist and delegates to github/gitlab/gerrit skills, which is good progressive disclosure design. However, no bundle files were provided, so the referenced checklist file doesn't exist, and the SKILL.md itself is quite long (~250 lines) with content like the full YAML config example and troubleshooting that could be split into separate files. | 2 / 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.
Reviewed
Table of Contents