dashboard-design
Use this skill first when the user wants to design or plan a dashboard, especially Vizro dashboards. Enforces a 3-step workflow (requirements, layout, visualization) before implementation. Activate when the user asks to create, design, or plan a dashboard. For implementation, use the dashboard-build skill after completing Steps 1-3.
91
87%
Does it follow best practices?
Impact
99%
1.83xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 solid description that clearly communicates when to use the skill (dashboard design/planning) and distinguishes itself from the companion build skill. Its main weakness is that the specific capabilities within the 3-step workflow could be more concretely described. The description also uses second-person framing ('Use this skill') which is acceptable as instructional guidance to Claude rather than addressing a user.
Suggestions
Expand the 3-step workflow description with concrete actions, e.g., 'Gathers dashboard requirements, designs page layouts and component placement, and recommends appropriate visualization types (charts, tables, filters) before implementation.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dashboard design/planning) and mentions a 3-step workflow (requirements, layout, visualization), but doesn't describe concrete actions beyond the workflow steps. It tells us the process structure but not specific capabilities like 'gather user requirements', 'create wireframe layouts', or 'recommend chart types'. | 2 / 3 |
Completeness | Clearly answers both 'what' (enforces a 3-step workflow for dashboard design/planning: requirements, layout, visualization) and 'when' ('when the user wants to design or plan a dashboard', 'when the user asks to create, design, or plan a dashboard'). Also clarifies the boundary with the dashboard-build skill. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'design', 'plan', 'dashboard', 'Vizro dashboards', 'create'. These are terms users would naturally use when requesting dashboard planning help. Good coverage of common variations. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishes itself as the planning/design phase skill versus the implementation/build skill. The explicit mention of 'Vizro dashboards' and the 3-step pre-implementation workflow creates a clear niche. The handoff to 'dashboard-build' further clarifies boundaries. | 3 / 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 well-structured planning/design skill with a clear 3-step workflow, explicit validation gates, and concrete YAML spec outputs at each stage. Progressive disclosure is handled well with a reference table and companion skills. The main weakness is moderate verbosity—some sections could be tightened without losing clarity, particularly the interaction style guidance and navigation architecture diagram.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts Claude already knows, but some sections are verbose—e.g., the navigation architecture tier diagram and some of the YAML templates include placeholder comments that add bulk. The interaction style paragraph could be tightened. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: exact YAML spec file templates to produce, specific questions to ask, numbered option formats, validation checklists, and clear decision trees for handling partial user context. Every step has a defined required output. | 3 / 3 |
Workflow Clarity | The 3-step workflow is clearly sequenced with explicit dependencies, validation checklists at each step gate, a progress tracker, and clear rules for handling users who arrive at different starting points. Feedback loops are present (validate before proceeding, user approval of wireframes). | 3 / 3 |
Progressive Disclosure | The skill is an excellent overview that delegates detailed content to one-level-deep references (information_architecture.md, wireframe_templates.md, common_mistakes.md, and companion skills). The reference table at the bottom clearly signals when to load each resource. | 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
- mckinsey/vizro
- Commit
124060f
- 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.