Content
55%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a concise, well-sectioned style direction with a distinctive and specific visual vocabulary, and its Avoid/Tuning-knobs sections are genuinely useful. Its main weaknesses are an entirely empty Workflow section, no concrete design tokens (colors, fonts, measurements) or examples that would make the guidance executable, and a verbatim-duplicated Use When line.
Suggestions
Fill in or remove the empty "## Workflow" section — give a rough application order (e.g., base surfaces and background framing → layout/module grid → typography and mono labeling → green accents and glow → motion) so the skill has an actual sequence.
Add concrete tokens or a small example snippet: hex values for the near-black surfaces and emerald accent, a sans/mono font pairing, and border/spacing values, so guidance is executable rather than purely descriptive.
Drop the "## Use When" section that repeats the frontmatter description verbatim (or fold it into Scope) to eliminate redundant tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Quotes: "Cards should look premium and modern: dark glass or matte shells, thin gradient borders, soft inner glow..." — the body is a lean list of terse directives with no explanation of concepts Claude already knows. Not 5 because tokens don't fully earn their place: the "## Use When" section repeats the frontmatter description verbatim, and the "## Workflow" section is completely empty. Not 3 because there is no padded or unnecessary explanation beyond those two structural redundancies. | 4 / 5 |
Actionability | Quotes: "Let green accents appear in status dots, progress fills, corner markers, subtle gradients, active borders, graph highlights" — placements are concretely enumerated, so guidance is more than high-level hints. However, no executable specifics are given: no color values (hex for the matte-black surfaces or emerald accent), no font pairings, no spacing/border measurements, no code snippets. This matches anchor 3 ("Some concrete guidance but incomplete... missing key details") rather than 4 ("mostly executable guidance with concrete code or commands"), and not 2 because the direction is far more specific than generic hints. | 3 / 5 |
Workflow Clarity | Quotes: "## Workflow" — the section dedicated to the process is empty; there are no steps and no sequence for applying the design system. The remaining sections (Scope → Visual target → Implementation guidance → Recommended patterns → Tuning knobs → Avoid) give a rough thematic order but many gaps, no checkpoints, and no validation of the visual result (e.g., contrast or glow checks). Matches anchor 2 ("Rough sequence present but many gaps; steps poorly defined") better than anchor 1 because the sections still imply an order of application; not 3 because a titled Workflow section exists with nothing in it. | 2 / 5 |
Progressive Disclosure | The body is under 50 lines with no bundle files (references/, scripts/, assets/ are absent) and no external references are needed, and content is organized into clearly labeled sections (Scope, Visual target, Implementation guidance, Recommended patterns, Tuning knobs, Avoid). Per the rubric's simple-skill guideline this can reach 5 with well-organized sections, but the empty "## Workflow" heading and the verbatim-duplicated "Use When" line are minor organization gaps, placing it at anchor 4 ("Good structure; most content is appropriately placed... minor organization gaps"). | 4 / 5 |
Total | 13 / 20 Passed |