rill-theme

Detailed instructions and examples for developing theme resources in Rill

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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 and well-sequenced with genuinely useful Rill-specific expertise, but it is weighed down by an oversized inline color-list example and an embedded schema reference that would be better placed in a separate file.

Suggestions

Move the full theme JSON schema (lines 282-388) into a references/ file and link to it from SKILL.md to improve progressive disclosure.

Trim the inline recommended-theme example by showing a representative subset of qualitative/sequential/diverging colors rather than all 44 entries in both modes.

Consider extracting the complete palette reference (all 24/9/11 color slots) into a separate reference file, keeping SKILL.md focused on the structure and guidelines.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient domain guidance, but the ~105-line inline light/dark theme example enumerating all 24 qualitative, 9 sequential, and 11 diverging colors is repetitive bulk that could be trimmed since the palette guidelines already convey the structure.	2 / 3
Actionability	It provides fully executable, copy-paste-ready YAML (recommended structure, minimal example, legacy format), concrete color values, and a precise 3-step brand process with specific rules ("rotate the primary hue ~20–40°", "≥ 4.5:1"), matching the fully-executable anchor.	3 / 3
Workflow Clarity	The on-brand theme workflow is a clearly sequenced 3-step process (extract → build light → adapt dark) with embedded verification checkpoints ("Ensure fg-primary meets WCAG AA", "Re-check contrast against the dark background"); the task is non-destructive so missing batch-style feedback loops is acceptable.	3 / 3
Progressive Disclosure	Sections are well organized, but all content is inline with no bundle files, and the 100+ line embedded JSON schema reference is content that should be split into a separate reference file, fitting the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 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 third-person and correctly names its Rill-theme niche, but it lacks explicit use-when trigger guidance and richer natural keywords, leaving it competent but not exemplary.

Suggestions

Add an explicit trigger clause, e.g. "Use when customizing dashboard colors, matching brand colors, or developing a Rill theme."

Surface concrete actions ("create, customize, and apply theme color palettes") instead of the generic "developing theme resources."

Include natural user phrasings like "brand colors", "dashboard styling", and "color palette" as keywords.

Dimension	Reasoning	Score
Specificity	"Detailed instructions and examples for developing theme resources in Rill" names the domain and a general action but does not enumerate multiple concrete actions (e.g., create, apply, customize), so it stops at 'names domain and some actions.'	2 / 3
Completeness	It states what the skill does (developing theme resources) but provides no "Use when..." clause or equivalent trigger for when to invoke it, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"theme resources" and "Rill" are relevant terms, but common natural phrasings a user would say ("dashboard colors", "brand colors", "color palette", "dashboard styling") are absent, leaving only partial keyword coverage.	2 / 3
Distinctiveness Conflict Risk	"theme resources in Rill" is a narrow, product-specific niche with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor rather than the generic overlap examples.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.