review
Framework for code review that captures context future maintainers need—concerns raised, alternatives rejected, risks accepted. Use for PRs, local changes, or architecture review when the decision matters more than the diff. Produces structured feedback with must-address issues, suggestions, and observations "for the record."
90
Quality
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
92%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 description that clearly articulates specific capabilities (capturing concerns, alternatives, risks) and explicit usage triggers (PRs, local changes, architecture review). The main weakness is potential overlap with other code review skills, though the emphasis on decision context and structured output categories provides some differentiation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'captures context future maintainers need—concerns raised, alternatives rejected, risks accepted' and 'Produces structured feedback with must-address issues, suggestions, and observations.' These are specific, actionable outputs. | 3 / 3 |
Completeness | Clearly answers both what ('Framework for code review that captures context...Produces structured feedback') and when ('Use for PRs, local changes, or architecture review when the decision matters more than the diff'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'code review', 'PRs', 'local changes', 'architecture review', 'diff'. These cover common variations of how users request review assistance. | 3 / 3 |
Distinctiveness Conflict Risk | While it emphasizes decision context over diffs, 'code review' and 'PRs' are common triggers that could overlap with generic code review skills. The focus on 'decision matters more than the diff' helps but may not be sufficient to prevent conflicts. | 2 / 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 strong skill that provides actionable, well-structured guidance for code review. The workflow is clear with explicit steps and calibration criteria, and the output template is copy-paste ready. Minor verbosity in the overview and some explanatory content (anti-pattern definitions) could be trimmed to improve token efficiency.
Suggestions
Trim the overview paragraph—remove the research citation and condense to the core insight: 'Code review's primary value is knowledge transfer. Document the why—concerns raised, alternatives considered, risks accepted.'
Condense anti-patterns to single-line definitions without explanatory sentences (e.g., 'Rubber stamping — Approving without understanding' is sufficient without 'If you don't have time, say so').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation (e.g., the research citation in the overview, explaining what rubber stamping means). The workflow sections could be tightened while preserving clarity. | 2 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific bash commands for GitHub CLI, a complete markdown template for review output, clear criteria for categorizing feedback, and specific examples of what constitutes blocking vs. non-blocking issues. | 3 / 3 |
Workflow Clarity | Clear 4-step workflow with explicit sequencing (understand → evaluate → document → calibrate). Each step has concrete substeps, and the review dimensions provide a systematic checklist. The feedback calibration section explicitly defines thresholds for different issue types. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from overview to workflow to patterns to anti-patterns. References to related skills are clearly signaled at the end with one-level-deep links. Content is appropriately structured without being monolithic. | 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.
- Repository
- tslateman/duet
- Commit
96a72fa
- 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.