rill-canvas

Detailed instructions and examples for developing canvas dashboard resources in Rill

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/rill-canvas/SKILL.md

Quality

Content

65%

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

The body is a thorough, highly actionable reference with executable examples throughout, but it is over-long and monolithic with no progressive disclosure or validation checkpoints. Splitting reference material into bundled files and trimming redundant examples would improve it.

Suggestions

Move the per-component reference and custom-chart/Vega-Lite specifications into bundled reference files (e.g. COMPONENTS.md, CUSTOM_CHARTS.md) and keep SKILL.md as a concise overview with one-level-deep links.

Reduce redundant example variants per component to one canonical example plus one variant, trimming total length.

Add a verification step to the composition workflow, e.g. confirm field names match the metrics view schema and that the canvas renders before declaring the dashboard complete.

Dimension	Reasoning	Score
Conciseness	The prose is lean and avoids re-explaining basics Claude already knows, but the body runs ~1350 lines with multiple redundant example variants per component (e.g. three line_chart and two bar_chart examples) that could be tightened without losing value.	2 / 3
Actionability	It provides fully executable, copy-paste-ready YAML examples with specific field configurations for every component type, plus a complete end-to-end dashboard example.	3 / 3
Workflow Clarity	A clear sequenced recommended structure (Row 1 context through additional rows) and explicit field constraints are present, but there are no validation or verification checkpoints and no feedback loop for confirming the dashboard renders or fields resolve.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is entirely monolithic with no bundle files; the component catalog, custom-chart/Vega-Lite details, and field configuration reference are all inline when they could be split into one-level-deep reference files.	2 / 3
	Total	9 / 12 Passed

Description

57%

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 identifies a clear, distinctive niche but is generic in its action language and lacks an explicit 'Use when' trigger clause. Adding concrete capabilities and natural trigger terms would raise its score.

Suggestions

Add 2-3 concrete capabilities, e.g. 'Define canvas dashboards, configure KPI grids, charts, leaderboards, and custom Vega-Lite visualizations'.

Append an explicit trigger clause, e.g. 'Use when building or editing Rill canvas dashboards, reports, or executive summary dashboards'.

Include natural term variations users might say (dashboards, reports, visualizations, charts) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('canvas dashboard resources in Rill') and a general action ('developing'), but 'instructions and examples' describes the skill's content rather than multiple concrete capabilities, so it falls short of the anchor listing several specific actions.	2 / 3
Completeness	It states what the skill covers but provides no 'Use when...' or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	'canvas dashboard' and 'Rill' are terms a user of the tool would naturally say, but coverage is thin with no common variations such as dashboards, reports, visualizations, or charts.	2 / 3
Distinctiveness Conflict Risk	'canvas dashboard resources in Rill' is a clearly bounded niche tied to a specific product feature, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1355 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: rilldata/agent-skills
Path: skills/rill-canvas/SKILL.md
Commit: aa23a8e

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.