rill-canvas
Detailed instructions and examples for developing canvas dashboard resources in Rill
36
32%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/rill-canvas/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.
The description is too vague and meta-level, describing what the skill contains ('instructions and examples') rather than what concrete actions it enables. It lacks a 'Use when...' clause entirely and fails to enumerate specific capabilities. The mention of 'Rill' and 'canvas dashboard' provides some domain specificity but is insufficient for reliable skill selection.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about creating or editing Rill canvas dashboards, defining dashboard layouts, or configuring visualization components in Rill.'
Replace the meta-description with concrete actions, e.g., 'Creates and configures canvas dashboard resources in Rill, including defining layouts, adding charts, setting up metrics, and customizing visual components.'
Include natural trigger terms users might say, such as 'Rill dashboard', 'canvas layout', 'visualization', 'metrics dashboard', '.yaml dashboard config'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'detailed instructions and examples for developing canvas dashboard resources' but does not list any concrete actions. It describes what the skill contains (instructions/examples) rather than what it does. No specific capabilities like 'create charts', 'configure layouts', or 'define metrics' are mentioned. | 1 / 3 |
Completeness | The 'what' is vaguely stated as 'instructions and examples for developing canvas dashboard resources' without specifics. There is no 'when' clause or explicit trigger guidance at all, which per the rubric should cap completeness at 2, and the weak 'what' brings it down to 1. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'canvas', 'dashboard', and 'Rill' that users might naturally use. However, it misses common variations and related terms (e.g., 'visualization', 'charts', 'metrics', 'data exploration', '.yaml') that would improve matching. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Rill' and 'canvas dashboard' provides some specificity that distinguishes it from generic dashboard skills. However, 'dashboard resources' is still somewhat broad and could overlap with other dashboard or visualization skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent, executable YAML examples covering every canvas component type, making it very useful as a reference. However, it is severely over-long and monolithic—the ~600+ lines of inline content would consume significant context window budget, and much of the repetitive chart-type documentation could be condensed or split into separate reference files. Adding validation steps and restructuring into a concise overview with linked references would dramatically improve its effectiveness.
Suggestions
Reduce the body to a concise overview (~100-150 lines) covering structure, layout system, best practices, and a single complete example, then move individual component type references to separate files (e.g., COMPONENTS.md, CUSTOM_CHARTS.md, FIELD_CONFIG.md).
Remove introductory explanations Claude doesn't need (what canvas dashboards are, how they differ from explore dashboards, what nominal/temporal/quantitative types mean) and condense repeated YAML patterns into a single template with a variations table.
Add validation checkpoints: how to verify a canvas dashboard renders correctly, common YAML errors to check for, and what to do when a component doesn't display as expected.
Consolidate chart type examples by showing one detailed example and a compact reference table for the remaining types, rather than full YAML blocks for every variant of every chart.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Includes unnecessary introductory explanations ('Canvas dashboards are lightweight resources...', 'Canvas dashboards differ from explore dashboards...'), explains concepts Claude already knows (what nominal/temporal/quantitative types mean), and repeats similar YAML patterns extensively across every chart type when a single pattern + variations table would suffice. | 1 / 3 |
Actionability | Highly actionable with complete, copy-paste-ready YAML examples for every component type, concrete field configurations, specific SQL query examples for custom charts, and valid Vega-Lite JSON specs. Every chart type has at least one fully executable example. | 3 / 3 |
Workflow Clarity | The 'Dashboard Composition Best Practices' section provides a clear recommended sequence for building dashboards, and chart type selection guidance is helpful. However, there are no validation checkpoints, no error recovery steps, and no guidance on how to verify the dashboard renders correctly after creation. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All component documentation, examples, field configuration, and advanced features are inlined in a single massive document. Content like the full Vega-Lite spec rules, individual chart type references, and field configuration details should be split into separate reference files. | 1 / 3 |
Total | 7 / 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 (1267 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- rilldata/agent-skills
- Commit
65ccd1f
- 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.