miro-code-review
Knowledge and patterns for effective code review visualization
49
Quality
22%
Does it follow best practices?
Impact
97%
1.38xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/miro-code-review/SKILL.mdQuality
Discovery
22%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 description is too vague to be effective for skill selection. It fails to specify concrete actions the skill performs and provides no guidance on when Claude should select it. The phrase 'knowledge and patterns' is abstract fluff that doesn't help distinguish this skill from others.
Suggestions
Replace vague language with specific actions (e.g., 'Generates visual diagrams of code review feedback, creates summary charts of review comments, visualizes diff coverage')
Add an explicit 'Use when...' clause with trigger terms like 'visualize review', 'code review diagram', 'PR feedback chart', 'review summary'
Specify the output formats or visualization types to distinguish from other code review or visualization skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'knowledge and patterns' and 'effective' without listing any concrete actions. It doesn't specify what the skill actually does (e.g., generate diagrams, create reports, highlight issues). | 1 / 3 |
Completeness | The description only vaguely hints at 'what' (something about code review visualization) and completely lacks any 'when' guidance or explicit triggers for when Claude should use this skill. | 1 / 3 |
Trigger Term Quality | Contains 'code review' and 'visualization' which are relevant keywords users might say, but lacks common variations like 'PR review', 'diff', 'review comments', 'code changes', or specific visualization types. | 2 / 3 |
Distinctiveness Conflict Risk | While 'code review visualization' is somewhat specific, the vague phrasing could overlap with general code review skills, documentation skills, or other visualization tools. The lack of specific triggers increases conflict risk. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a conceptual overview or documentation page than an actionable skill. It explains what code reviews are and why visualizations help, but provides no concrete guidance on how to actually perform reviews or create Miro artifacts. The content assumes Claude needs to learn basic review concepts while failing to provide the specific, executable instructions that would make this skill useful.
Suggestions
Add concrete, executable code examples showing how to create Miro artifacts (API calls, SDK usage) for each visualization type mentioned in the table
Define a clear step-by-step workflow: e.g., 1) Analyze PR, 2) Score risk using criteria, 3) Create summary document, 4) Generate appropriate diagrams, with validation at each step
Remove the 'Review Philosophy' and 'Visual Review Benefits' sections - Claude already understands these concepts; replace with specific patterns or templates
Include example inputs (a sample PR or code diff) and expected outputs (what the Miro board should contain) to make the skill actionable
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'Review Philosophy' section explains concepts Claude already knows (what correctness, security, maintainability mean). The 'Visual Review Benefits' section is also somewhat obvious. However, the tables and layout diagram add value without excessive padding. | 2 / 3 |
Actionability | The skill describes concepts and benefits but provides no executable code, API calls, or concrete commands. The layout diagram is illustrative but not actionable - there's no actual Miro API usage, no code to create these artifacts, just abstract guidance. | 1 / 3 |
Workflow Clarity | There is no clear workflow or sequence of steps. The skill lists concepts and artifact types but doesn't explain how to actually conduct a code review or create visualizations. No validation checkpoints or process flow is defined. | 1 / 3 |
Progressive Disclosure | References to external files (risk-assessment.md, review-patterns.md) are mentioned with one-level-deep linking, which is good. However, the main content lacks clear structure between overview and details - the 'Core Concepts' section contains content that could be trimmed or moved. | 2 / 3 |
Total | 6 / 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.