miro-code-review
Use when the user wants to create a visual code review on a Miro board from a pull/merge request (GitHub, GitLab, or any forge), local uncommitted changes, or a branch comparison — produces a file-changes table, summary/architecture/security docs, and architecture diagrams, then links them back from the PR/MR.
67
81%
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 an excellent skill description that clearly articulates what the skill does (visual code review on Miro with specific deliverables), when to use it (explicit 'Use when' clause with multiple trigger scenarios), and includes rich natural trigger terms spanning multiple platforms and workflows. The description is concise yet comprehensive, with strong distinctiveness from other potential skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating a file-changes table, summary/architecture/security docs, architecture diagrams, and linking them back from the PR/MR. Also specifies multiple input sources (pull/merge request, local uncommitted changes, branch comparison). | 3 / 3 |
Completeness | Clearly answers both 'what' (creates visual code review artifacts on Miro: file-changes table, docs, diagrams, links back to PR) and 'when' with an explicit 'Use when' clause specifying the trigger scenarios (user wants visual code review from PR/MR, local changes, or branch comparison). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'code review', 'Miro board', 'pull request', 'merge request', 'GitHub', 'GitLab', 'PR', 'MR', 'uncommitted changes', 'branch comparison', 'architecture diagrams'. These are terms users would naturally use when requesting this functionality. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — the combination of Miro board output, code review context, and specific forge integrations (GitHub, GitLab) creates a very clear niche. Unlikely to conflict with generic code review skills or generic Miro skills due to the specific intersection described. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is exceptionally thorough and actionable, with concrete commands, templates, and clear multi-step workflows covering multiple platforms and edge cases. However, it is severely over-length — the Background section is entirely unnecessary (Claude knows what code review is), linking conventions are repeated across sections, and the document templates could be externalized. The skill would benefit greatly from splitting into a concise SKILL.md overview with references to detailed template and convention files.
Suggestions
Remove the entire 'Background' section (Review Philosophy, Visual Review Benefits, Visualization Patterns, Layout Reference) — these explain concepts Claude already knows and add ~80 lines of zero-value content.
Extract document templates (Summary, Architecture, Security) and diagram conventions (marking, classDef, selection guide) into separate reference files (e.g., references/templates.md, references/diagram-conventions.md) and link to them from the main skill.
Consolidate the linking conventions — they're explained in §2 (LINK_TEMPLATE), §5 (Linking conventions), and then repeated per-artifact (table, documents, diagrams). Define once and reference.
Provide the referenced bundle files (references/risk-assessment.md, references/review-patterns.md) or remove the dangling references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. The Background section explains review philosophy, visual review benefits, and visualization patterns — all concepts Claude already knows. The Layout Reference ASCII art duplicates information already given in the positioning notes. Many sections repeat information (e.g., linking conventions are restated multiple times across §2 and §5). The skill could be cut by 50%+ without losing actionable content. | 1 / 3 |
Actionability | Highly actionable with concrete, executable bash commands for every platform (GitHub, GitLab, REST fallback, local). Includes specific CLI flags, JSON field names, exact Mermaid classDef syntax, table column definitions, and document templates with markdown formatting. Nearly everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (§1→§2→§3→§4→§4.5→§5→§6), explicit validation/bail-out gates (§4.5 triage with specific thresholds), permission failure fallbacks (§6), idempotency rules for PR description updates, and degradation paths (shallow clone, no remote, no CLI). The feedback loops for error cases are well-defined. | 3 / 3 |
Progressive Disclosure | References two bundle files (references/risk-assessment.md, references/review-patterns.md) that don't exist in the bundle, which is a minor issue. The main problem is that the skill is monolithic — the Background section, detailed document templates, and diagram selection guides could be split into separate reference files. The inline content is too long for a single SKILL.md, though the section headers provide reasonable navigation. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (583 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- miroapp/miro-ai
- Commit
706b24b
- 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.