rill-canvas

Detailed instructions and examples for developing canvas dashboard resources in Rill

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

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 copy-paste YAML for every component, but it is a monolithic single file and offers no validation checkpoint for the dashboard-authoring workflow. Splitting reference material into bundle files would improve progressive disclosure.

Suggestions

Move the per-component reference and the custom-chart/Vega-Lite guide into separate files under references/ and link to them from a concise overview in SKILL.md.

Add a validation checkpoint to the composition workflow (e.g., 'validate the canvas YAML renders by previewing the dashboard before finalizing').

Trim repeated near-duplicate example variants per chart type to reduce length without losing the representative patterns.

Dimension	Reasoning	Score
Conciseness	Mostly efficient Rill-specific reference that assumes Claude knows YAML/Vega-Lite, but it is very long (~1335 lines) with repeated per-component example variants and some generic advice ('Add 1-2 more rows with relevant charts') that could be tightened.	2 / 3
Actionability	Every component type ships complete, copy-paste-ready YAML examples with real field names and values, plus concrete query rules for custom charts.	3 / 3
Workflow Clarity	'Dashboard Composition Best Practices' provides a light numbered sequence (context row, KPI grid, analysis rows), but there are no validation or verification checkpoints for the authoring task (e.g., checking the canvas renders or the YAML is valid).	2 / 3
Progressive Disclosure	No bundle files exist and all content lives inline in one ~1335-line SKILL.md; it is well-sectioned with clear headers, but content that should be split into separate reference files (per-component details, custom-chart guide) is inline.	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 is domain-specific and clear about what it covers, but lacks explicit trigger guidance and only names a single general action. Adding a 'Use when...' clause would lift completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when building Rill canvas dashboards, reports, or executive summary dashboards').

Replace the single vague action 'developing' with several concrete actions (e.g., 'configure KPI grids, charts, leaderboards, and custom layouts').

Include common user-facing variations like 'reports', 'KPI dashboards', or 'fixed-layout dashboards' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('canvas dashboard resources in Rill') and a general action ('developing') plus 'instructions and examples', but lists only one broad action rather than multiple specific concrete actions like 'build KPI grids' or 'configure layouts'.	2 / 3
Completeness	It clearly states what the skill does, but provides no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Terms like 'canvas dashboard' and 'Rill' are natural for a Rill user, but the description omits common variations users might say ('reports', 'KPI dashboards', 'executive summaries') and carries no trigger phrasing.	2 / 3
Distinctiveness Conflict Risk	The niche (Rill canvas dashboards) is specific and clearly distinguishable from other skills, 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 (1335 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: rilldata/agent-skills
Commit: 892996d

Reviewed: about 10 hours 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.