rill-theme

Detailed instructions and examples for developing theme resources in Rill

Quality

58%

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-theme/SKILL.md

Quality

Content

63%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 — complete working YAML examples for every supported format plus a concrete, validated brand-adaptation workflow. Its weaknesses are token efficiency and structure: a fully enumerated 44-color example duplicated across light/dark modes and an inline schema dump bloat the file, and no reference files exist to split that material into.

Suggestions

Trim the recommended-structure example to a handful of representative entries per palette (e.g. color-qualitative-1 through -5 with a comment noting entries continue to -24), since the body already says all 24 are optional.

Move the full JSON schema into references/theme-schema.json (or .md) and reference it from a short 'Reference documentation' section, keeping only the description-level syntax inline.

Add a short feedback loop to the brand workflow for the contrast checkpoints (e.g. 'if contrast fails, nudge lightness until the 4.5:1 threshold passes').

Dimension	Reasoning	Score
Conciseness	The ~130-line example enumerating all 24 qualitative, 9 sequential, and 11 diverging hexes twice (light and dark) is padding Claude could generate — the body itself says 'You need not define all 24' — and the ~105-line JSON schema dump repeats already-explained syntax inline. This matches anchor 2 (noticeably verbose, padded sections) rather than 3, since the padding is substantial rather than incidental.	2 / 5
Actionability	Complete, copy-paste-ready YAML covers the common cases: full recommended structure, minimal brand-only theme, and the legacy format, plus concrete adaptation rules with specific thresholds ('Ensure fg-primary meets WCAG AA contrast (>= 4.5:1)') and concrete color-format examples. Anchor 5 fits; nothing is pseudocode or hand-wavy.	5 / 5
Workflow Clarity	The brand-matching process is a clearly sequenced 3-step workflow with explicit checkpoints ('Re-check contrast against the dark background, not the light one'). It falls short of anchor 5 because there are no error-recovery feedback loops (e.g. what to do when contrast fails), but checkpoints are explicit enough to exceed anchor 3.	4 / 5
Progressive Disclosure	Sections are well-organized with clear headers, but there are no bundle files at all and the full JSON schema reference (~105 lines) is inlined in SKILL.md when it clearly belongs in a references/ file. Anchor 3 fits (structure present, content that should be separate is inline); not 2 because navigation via headers is good, not 4 because the reference split is absent.	3 / 5
	Total	14 / 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 is short and names a specific domain, but it reads as a table-of-contents label rather than a trigger description. It lacks any 'when to use' guidance and enumerates only one generic action ('developing'), with filler phrasing ('Detailed instructions and examples') doing the work of real content.

Suggestions

Add an explicit trigger clause, e.g. 'Use when creating or editing Rill theme files, matching dashboard colors to a brand, or configuring light/dark mode palettes.'

Replace 'Detailed instructions and examples' with concrete actions: defining light/dark color palettes, setting qualitative/sequential/diverging chart colors, and referencing themes from rill.yaml or dashboards.

Include natural trigger keywords users would say — 'theme', 'colors', 'palette', 'brand colors', 'dark mode', 'Rill dashboard styling' — to improve discovery and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names the domain ('theme resources in Rill') and one action ('developing'), but 'Detailed instructions and examples' is padding rather than a capability. It is not a 2 because a concrete action is stated alongside the domain, and not a 4 because no multiple specific actions are enumerated.	3 / 5
Completeness	The 'what' is clear (developing theme resources in Rill) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot score 4 without any explicit 'when'.	3 / 5
Trigger Term Quality	'theme' and 'Rill' are natural terms users would say, but common variations like 'colors', 'palette', 'brand', 'styling', and 'dark mode' are missing. It matches anchor 3 (some relevant keywords, missing common variations) rather than 4, which requires fuller synonym coverage.	3 / 5
Distinctiveness Conflict Risk	Naming 'Rill' establishes a clear niche, but the description gives no distinct trigger phrases, so a generic theming/styling skill could still overlap on the word 'theme'. Anchor 4 fits better than 5, and better than 3 since the domain is genuinely specific.	4 / 5
	Total	13 / 20 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
Path: skills/rill-theme/SKILL.md
Commit: 1307e7f

Reviewed: 7 days 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.