rill-canvas

Detailed instructions and examples for developing canvas dashboard resources in Rill

Quality

57%

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

61%Weight 40%Scale 1-5

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

The body is highly actionable with comprehensive, executable YAML examples and a clear composition workflow, but it is a monolithic wall of reference content with no progressive disclosure via separate files and no validation checkpoints.

Suggestions

Split the per-component reference and the custom-chart/Vega-Lite guide into separate reference files (e.g. COMPONENTS.md, CUSTOM_CHARTS.md) and keep SKILL.md as a concise overview pointing to them.

Deduplicate the repeated color-configuration examples by referencing a single Field Configuration section instead of restating the same config inline per chart type.

Add a validation/verification step to the composition workflow (e.g. preview the canvas, confirm every referenced metrics_view and field exists, and check the YAML renders without errors before finishing).

Dimension	Reasoning	Score
Conciseness	The body is a ~1230-line monolithic reference; it avoids explaining concepts Claude already knows, but it repeats field configuration (e.g. color config) inline multiple times and is long enough that substantial material arguably belongs in separate reference files.	3 / 5
Actionability	Dozens of complete, copy-paste-ready YAML examples per component type plus concrete field schemas and a full end-to-end example cover the common cases comprehensively.	5 / 5
Workflow Clarity	A clear composition sequence is present ('Row 1 - Context ... Row 2 - Key Metrics ... Row 3 - Primary Analysis'), but there are no validation or verification checkpoints for catching YAML errors before publishing the dashboard.	3 / 5
Progressive Disclosure	No bundle files exist and the entire per-component reference, field configuration, and custom-chart/Vega-Lite guidance is inlined into one SKILL.md; well-sectioned headers prevent a 1, but content clearly belonging in separate files is inlined.	2 / 5
	Total	13 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 clearly identifies a niche domain (Rill canvas dashboards) and a purpose, but it omits any 'Use when...' trigger guidance and relies on a single generic verb, which limits specificity and completeness.

Suggestions

Add a 'Use when...' clause listing concrete triggers, e.g. 'Use when building canvas dashboards in Rill, adding KPI grids/charts, or laying out report-style dashboards.'

Replace the single generic verb 'developing' with several concrete actions (e.g. 'design, lay out, and configure canvas dashboards with KPI grids, charts, and tables').

Include common synonyms users might say ('dashboards', 'reports', 'Rill dashboards') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('canvas dashboard resources in Rill') and an action ('developing') with a hint at content ('instructions and examples'), but only one generic verb rather than multiple concrete actions, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Provides a clear 'what' ('Detailed instructions and examples for developing canvas dashboard resources in Rill') but no 'Use when...' or equivalent 'when' clause; per the guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant domain keywords users would say ('canvas dashboard', 'Rill') but is missing common variations and synonyms ('dashboards', 'reports', 'dashboards in Rill'), so it lands at 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	'canvas dashboard resources in Rill' is a clearly niche, domain-specific scope unlikely to trigger for the wrong skill, but lacks an explicit trigger phrase that would push it to a 5.	4 / 5
	Total	13 / 20 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: 84f7d7c

Reviewed: about 7 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.