dashboard-build
Use this skill to build, implement, and test Vizro dashboards (Phase 2). Activate when the user wants to create a working app, says "just build it", or has data ready for implementation. Requires spec files from the dashboard-design skill (Phase 1), or user confirmation to skip design.
91
87%
Does it follow best practices?
Impact
96%
1.92xAverage 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 well-crafted description that clearly defines its niche as the implementation phase of Vizro dashboards, with explicit trigger conditions and a clear relationship to a companion design skill. Its main weakness is that the specific capabilities could be more concrete (e.g., what exactly building and testing entails). The use of 'Use this skill' in second-person-adjacent phrasing is a minor style issue but doesn't significantly harm clarity.
Suggestions
Replace 'Use this skill to build, implement, and test' with more specific concrete actions like 'Generates Vizro app code, configures dashboard layouts, wires up data sources, and runs tests for Vizro dashboards (Phase 2)' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Vizro dashboards) and some actions (build, implement, test), but doesn't list specific concrete actions like 'create charts', 'configure layouts', 'deploy app'. The actions are somewhat generic verbs applied to a specific domain. | 2 / 3 |
Completeness | Clearly answers both what ('build, implement, and test Vizro dashboards') and when ('when the user wants to create a working app, says "just build it", or has data ready for implementation'). Also specifies prerequisites (spec files from Phase 1 or user confirmation to skip), which adds useful context. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'build', 'implement', 'test', 'Vizro dashboards', 'working app', 'just build it', 'data ready for implementation'. These cover natural phrases a user would say when they want to move from design to implementation. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct niche: specifically Phase 2 of Vizro dashboard building, clearly differentiated from the Phase 1 'dashboard-design' skill. The phase distinction and explicit dependency on spec files make it unlikely to conflict with other skills. | 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 strong, well-structured implementation skill with excellent actionability and workflow clarity. The multi-step build-validate-test process includes proper feedback loops, explicit validation checkpoints, and required output artifacts. The main weakness is moderate verbosity from repeated terminal handling warnings and emphatic formatting, though these serve legitimate safety purposes for a destructive-adjacent workflow.
Suggestions
Consolidate the terminal handling warnings into a single prominent callout block rather than repeating across multiple steps — this would save tokens while maintaining the safety message.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and contains necessary domain-specific guidance, but has some verbosity — repeated warnings about terminal handling (mentioned 3+ times), and some instructions that could be tightened. The emphasis markers (ABSOLUTELY NEVER, CRITICAL, MUST) add bulk but arguably serve a safety purpose. | 2 / 3 |
Actionability | Provides fully concrete, executable commands (e.g., `uv run ./scripts/get_model_json_schema.py <model_name>`), specific script paths, exact YAML output templates, and step-by-step validation scripts. The guidance is copy-paste ready with clear tool invocations. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (Build → Validate → Test → Report) with explicit validation checkpoints (checklist before Step 2, automated validation scripts, browser testing, required output specs). Feedback loops are present — errors found in testing loop back to Step 1 for fixes, and re-validation is explicitly called out. | 3 / 3 |
Progressive Disclosure | Content is well-structured as an overview with clear one-level-deep references to external files (custom_charts_guide.md, data_management.md, example_app.py, validation scripts, and companion skills). The reference table at the bottom provides excellent navigation with 'When to Load' guidance. | 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
e630476
- 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.