rill-canvas

Detailed instructions and examples for developing canvas dashboard resources in Rill

Quality

32%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/rill-canvas/SKILL.md

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability with comprehensive, executable YAML examples for every canvas component type, making it a strong reference. However, it is severely undermined by its length and monolithic structure—it reads like a full reference manual crammed into a single file, wasting context window tokens on repetitive patterns and explanations Claude doesn't need. Splitting component references into separate files and trimming introductory/explanatory content would dramatically improve its effectiveness.

Suggestions

Extract the detailed component type references (line_chart, bar_chart, stacked_bar, etc.) into a separate COMPONENTS_REFERENCE.md file, keeping only a summary table with one-line descriptions and links in the main SKILL.md.

Remove the introductory section explaining what canvas dashboards are and when to use them—Claude can infer this from the examples. Cut the field type definitions (nominal, temporal, quantitative) as these are standard concepts.

Add validation/debugging guidance: how to verify a canvas renders correctly, common YAML errors, and what to check when a component shows no data.

Reduce redundant examples—most chart types share the same x/y/color pattern. Show one canonical chart example in detail, then use minimal diffs for variants.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~600+ lines. It explains concepts Claude already knows (what canvas dashboards are, how they differ from explore dashboards, what nominal/temporal/quantitative types mean). The introduction section, 'when to use' bullets, and field type definitions are unnecessary padding. Nearly every component type includes multiple full YAML examples when one would suffice, and many patterns are repetitive across chart types.	1 / 3
Actionability	The skill provides fully executable, copy-paste-ready YAML configurations for every component type. The metrics_sql examples, Vega-Lite specs, and complete dashboard example are concrete and specific. Field names, property values, and configuration options are all explicitly documented with working examples.	3 / 3
Workflow Clarity	The 'Dashboard Composition Best Practices' section provides a clear recommended sequence for building dashboards (Row 1 context, Row 2 KPIs, Row 3 analysis, etc.), and chart type selection guidance is helpful. However, there are no validation checkpoints, no error recovery steps, and no guidance on how to verify a canvas dashboard renders correctly or debug common issues.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files. The detailed component reference for every chart type (line, bar, stacked bar, area, donut, heatmap, combo, scatter, funnel, pivot, table, image, custom chart) should be split into separate reference files. The SKILL.md should be a concise overview with links to component-specific documentation.	1 / 3
	Total	7 / 12 Passed

Description

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—it describes what the skill contains ('instructions and examples') rather than what concrete actions it enables. It lacks a 'Use when...' clause, specific actions, and sufficient trigger terms. The mention of 'Rill' and 'canvas dashboard' provides some distinctiveness but is not enough to make this a strong description.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks about creating or editing Rill canvas dashboards, YAML dashboard definitions, or dashboard layouts.'

Replace the meta-description with concrete actions, e.g., 'Creates and configures canvas dashboard resources in Rill, including layout definitions, chart components, filters, and metric visualizations.'

Include natural trigger terms users would say, such as 'Rill dashboard', 'canvas YAML', 'dashboard layout', 'metrics dashboard', 'visualization', '.yaml'.

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. 'Developing canvas dashboard resources' is vague.	1 / 3
Completeness	The description partially addresses 'what' (developing canvas dashboard resources in Rill) but has no explicit 'when' clause or trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak, so this scores a 1.	1 / 3
Trigger Term Quality	It includes some relevant keywords like 'canvas', 'dashboard', and 'Rill' that users might naturally say. However, it misses common variations and related terms (e.g., 'visualization', 'charts', 'metrics', 'YAML', 'layout').	2 / 3
Distinctiveness Conflict Risk	'Rill' and 'canvas dashboard' provide some specificity that distinguishes it from generic dashboard skills, but 'dashboard resources' is broad enough to potentially overlap with other dashboard or visualization skills.	2 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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 (1332 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: rilldata/agent-skills
Commit: e7c833e

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.