writing-vizro-yaml
Use this skill when writing or debugging Vizro YAML dashboard configurations — component syntax, data_manager registration, custom function wiring, filter/parameter setup, or AG Grid tables. Activate when the user is building a Vizro app, encountering YAML or runtime errors, or asking about Vizro component patterns.
95
93%
Does it follow best practices?
Impact
96%
1.47xAverage score across 3 eval scenarios
Passed
No known issues
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 a strong skill description that clearly identifies the specific domain (Vizro YAML dashboards), lists concrete capabilities, and provides explicit trigger conditions. The only minor issue is the use of second-person imperative voice ('Use this skill when...', 'Activate when...') rather than third-person declarative, though this is a common pattern seen in good examples in the rubric. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: writing/debugging YAML dashboard configurations, component syntax, data_manager registration, custom function wiring, filter/parameter setup, and AG Grid tables. | 3 / 3 |
Completeness | Clearly answers both what ('writing or debugging Vizro YAML dashboard configurations — component syntax, data_manager registration, custom function wiring, filter/parameter setup, or AG Grid tables') and when ('Activate when the user is building a Vizro app, encountering YAML or runtime errors, or asking about Vizro component patterns'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Vizro', 'YAML', 'dashboard', 'data_manager', 'filter', 'parameter', 'AG Grid', 'runtime errors', 'component patterns'. These cover the domain well with terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Vizro is a specific framework, making this highly distinctive. The combination of 'Vizro', 'YAML dashboard configurations', and specific Vizro concepts like 'data_manager registration' creates a clear niche unlikely to conflict with generic YAML or dashboard skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%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-crafted skill that efficiently delivers Vizro-specific knowledge Claude wouldn't have natively. The critical mistakes list is high-value, the YAML patterns are immediately usable, and the progressive disclosure to the reference file is cleanly organized. The only weakness is the lack of explicit workflow sequencing for building a Vizro app from scratch or debugging runtime errors.
Suggestions
Consider adding a brief 3-4 step workflow for the common 'build a Vizro dashboard' task sequence (register data → define pages → configure controls → run), with a validation checkpoint like 'run Vizro().build(dashboard).run() and check for runtime errors before adding more components'.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every line earns its place. No explanation of what Vizro is, no padding about YAML basics. The numbered mistakes list is terse but informative, and the YAML examples are minimal yet complete. | 3 / 3 |
Actionability | Provides copy-paste ready YAML patterns for the four most common component types, concrete import statements, and specific error patterns with fixes. The parameter target format and filter behavior are precisely specified. | 3 / 3 |
Workflow Clarity | The skill is primarily a reference/pattern guide rather than a multi-step workflow, but the 'Critical Mistakes to Avoid' section implicitly describes a debugging workflow without explicit validation steps. The data registration flow (pre-process then register) lacks a clear step sequence with checkpoints. | 2 / 3 |
Progressive Disclosure | Excellent structure: concise overview in SKILL.md with a well-organized table pointing to specific sections in yaml-reference.md. References are one level deep and clearly signaled with searchable section headers. | 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.