ss-score

Name: ss-score
Author: bitjaru

156installs73forks

How to install ss-score?

bitjaru/styleseed/ss-score

$npx -y skills add bitjaru/styleseed --skill ss-score

Installs into the current project.

Summary

Score a visual artifact's implementation quality 0-100 against its composed StyleSeed rule set — category breakdown, evidence, and prioritized fixes.

Files · 1

View on GitHub

SKILL.md

1	# Design Score
2
3	`/ss-review` tells you what's wrong. `/ss-score` tells you *how good it is
4	overall* and what to fix first — a single number plus a category breakdown, so
5	you can track UI quality like you track test coverage.
6
7	## When NOT to use
8
9	- For a quick pass/fail before committing → use `/ss-lint`
10	- For a full prose audit with fixes → use `/ss-review`
11	- For logic/config with no visual artifact — scoring is meaningless
12
13	## Step 0 — Resolve the effective rule set
14
15	Before scoring, read `PRODUCT-PRINCIPLES.md`, `RULESETS.md`, `ADAPTERS.md`, `PRESETS.md`, and `STYLESEED.md`.
16	If the lock selects `reference:<slug>`, read its project-local `RULESET.md` and evidence/checks.
17
18	Score in authority order: core invariants first, then the exact output grammar, domain/page,
19	optional aesthetic profile, and bounded lock values. The lock cannot waive an invariant.
20	Unknown values fall back to the nearest built-in grammar; do not invent an exception.
21
22	The output must name the effective rule set, for example:
23
24	```text
25	Rule set: operations-console × SaaS × dashboard × swiss
26	```
27
28	## What to score
29
30	Score the file (or each file in a directory) on eight weighted categories that
31	map to the design language. Total = 100.
32
33	\| Category \| Weight \| Reads from \|
34	\|---\|---\|---\|
35	\| Color discipline \| 16 \| DESIGN-LANGUAGE §1, §18, §72 + VISUAL-CRAFT §C4 \|
36	\| Hierarchy & typography \| 16 \| §2, §3, §4, §16 + Font Size table + VISUAL-CRAFT §C2 \|
37	\| Layout & rhythm \| 12 \| §13, §14, §15, §61 + VISUAL-CRAFT §C1 \|
38	\| Cards & elevation \| 10 \| §7, §8, §12, §1 + VISUAL-CRAFT §C3 \|
39	\| States & a11y \| 18 \| §11, §70, §71, §72 + VISUAL-CRAFT §C3 \|
40	\| Motion & interaction \| 6 \| §24, §59 + `engine/motion` \|
41	\| Coherence \| 12 \| VISUAL-CRAFT §C0 (one choice per axis) \|
42	\| Distinctiveness \| 10 \| Golden Rules 14–16 + VISUAL-CRAFT §CC-9b (not generic/default/template) \|
43
44	## How to score each category
45
46	For each category, start at full marks and subtract for violations you find by
47	reading the code. Be specific and evidence-based — cite the line.
48
49	Color discipline (16) — deduct for: accidental `#000`/`text-black` outside a profile or
50	grammar contract that explicitly uses hard black structurally (−4 each, cap −8); competing
51	decorative emphasis hues (−5); emoji used as UI icons (−5); a normal/OK/"보통" state shown in a status color instead of
52	neutral grey (−4); status color on most/every row (no severity hierarchy) (−4);
53	decorative hues (gold stars, rainbow category dots) instead of accent/grey (−3);
54	hardcoded hex where a semantic token exists (−2 each, cap −6); status conveyed by color
55	alone (−4); the unlocked default indigo (`#5E6AD2`/`#4F46E5`) used as the accent instead of
56	a chosen domain-fit color (−4).
57
58	Distinctiveness (10) — a coherent screen can still read "AI-generated." Deduct for: the
59	icon-chip cliché — a generic Lucide line-icon in an identical pale-tinted rounded-square,
60	repeated for every feature/step (−4, §CC-9b); the StyleSeed demo layout copied verbatim
61	(hero+chat / 3-step / feature-grid / pricing) with no product-specific identity (−4); **no focal
62	point** — an all-even grid of same-weight, centered, evenly-spaced cards (−3); the hero shows a
63	stock/placeholder visual instead of this product (−3); the escape hatch as a new uniform
64	(§CC-9c) — ghost 01/02/03 index numbers on every section, or identical uppercase-overline +
65	big-number cards repeated with no variation (−2); distinctive-but-dated (§CC-9d) — full
66	beige/paper page base, serif body text on a product surface, dark-heavy blocks that read
67	"brochure" not "2026 product" (−3). Cap −10.
68
69	Hierarchy & typography (16) — deduct for: number/unit not ~2:1 (−4); font
70	sizes off the Font Size table / `text-[var(--…)]` for size (−5); everything the
71	same weight, no clear primary (−5); cramped or wrong line-height on body (−3);
72	body < 16px on a desktop/web B2B surface (tight mobile scale on a wide screen) (−4 —
73	but dense-data chrome is exempt: chart ticks, mono SHAs/timestamps, table metadata at
74	12–13px are correct; and dashboard app-chrome h1 at 22–24px is correct, not a violation
75	of the marketing 40–56px headline scale).
76
77	Layout & rhythm (12) — deduct for: grouping that contradicts the selected grammar (−6):
78	`operations-console` needs explicit functional groups, while `editorial-reading` should not be
79	forced into cards; arbitrary off-scale spacing (−3); same section type repeated without purpose
80	(−4); no discernible proximity rhythm (−3).
81
82	Cards & elevation (10) — deduct for mixed or task-inappropriate surface language. Hairlines,
83	flat grouping, tonal ramps, or restrained shadows are valid only when the selected grammar/profile
84	uses them c

People who liked this also viewed

6 picks

Type

web-design-guidelinesReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".SkillsJul 2026483k29k
lark-slides飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到 WebFetch；路由依据是 URL 路径模式和 token，而不是域名。不负责：云文档内容编辑（走 SkillsJul 2026332k16k
design-taste-frontendTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop SkillsJul 2026280k66k
ui-ux-pro-maxUI/UX design intelligence for web and mobile. Searchable local database with 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presSkillsJul 2026280k109k
caveman-helpQuick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".SkillsJul 2026249k92k
codebase-designShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-nSkillsJul 2026225k182k

ss-score

156installs73forks

View on GitHub

How to install ss-score?

bitjaru/styleseed/ss-score

$npx -y skills add bitjaru/styleseed --skill ss-score

Installs into the current project.

Summary

Score a visual artifact's implementation quality 0-100 against its composed StyleSeed rule set — category breakdown, evidence, and prioritized fixes.

Files · 1

View on GitHub

SKILL.md

1	# Design Score
2
3	`/ss-review` tells you what's wrong. `/ss-score` tells you *how good it is
4	overall* and what to fix first — a single number plus a category breakdown, so
5	you can track UI quality like you track test coverage.
6
7	## When NOT to use
8
9	- For a quick pass/fail before committing → use `/ss-lint`
10	- For a full prose audit with fixes → use `/ss-review`
11	- For logic/config with no visual artifact — scoring is meaningless
12
13	## Step 0 — Resolve the effective rule set
14
15	Before scoring, read `PRODUCT-PRINCIPLES.md`, `RULESETS.md`, `ADAPTERS.md`, `PRESETS.md`, and `STYLESEED.md`.
16	If the lock selects `reference:<slug>`, read its project-local `RULESET.md` and evidence/checks.
17
18	Score in authority order: core invariants first, then the exact output grammar, domain/page,
19	optional aesthetic profile, and bounded lock values. The lock cannot waive an invariant.
20	Unknown values fall back to the nearest built-in grammar; do not invent an exception.
21
22	The output must name the effective rule set, for example:
23
24	```text
25	Rule set: operations-console × SaaS × dashboard × swiss
26	```
27
28	## What to score
29
30	Score the file (or each file in a directory) on eight weighted categories that
31	map to the design language. Total = 100.
32
33	\| Category \| Weight \| Reads from \|
34	\|---\|---\|---\|
35	\| Color discipline \| 16 \| DESIGN-LANGUAGE §1, §18, §72 + VISUAL-CRAFT §C4 \|
36	\| Hierarchy & typography \| 16 \| §2, §3, §4, §16 + Font Size table + VISUAL-CRAFT §C2 \|
37	\| Layout & rhythm \| 12 \| §13, §14, §15, §61 + VISUAL-CRAFT §C1 \|
38	\| Cards & elevation \| 10 \| §7, §8, §12, §1 + VISUAL-CRAFT §C3 \|
39	\| States & a11y \| 18 \| §11, §70, §71, §72 + VISUAL-CRAFT §C3 \|
40	\| Motion & interaction \| 6 \| §24, §59 + `engine/motion` \|
41	\| Coherence \| 12 \| VISUAL-CRAFT §C0 (one choice per axis) \|
42	\| Distinctiveness \| 10 \| Golden Rules 14–16 + VISUAL-CRAFT §CC-9b (not generic/default/template) \|
43
44	## How to score each category
45
46	For each category, start at full marks and subtract for violations you find by
47	reading the code. Be specific and evidence-based — cite the line.
48
49	Color discipline (16) — deduct for: accidental `#000`/`text-black` outside a profile or
50	grammar contract that explicitly uses hard black structurally (−4 each, cap −8); competing
51	decorative emphasis hues (−5); emoji used as UI icons (−5); a normal/OK/"보통" state shown in a status color instead of
52	neutral grey (−4); status color on most/every row (no severity hierarchy) (−4);
53	decorative hues (gold stars, rainbow category dots) instead of accent/grey (−3);
54	hardcoded hex where a semantic token exists (−2 each, cap −6); status conveyed by color
55	alone (−4); the unlocked default indigo (`#5E6AD2`/`#4F46E5`) used as the accent instead of
56	a chosen domain-fit color (−4).
57
58	Distinctiveness (10) — a coherent screen can still read "AI-generated." Deduct for: the
59	icon-chip cliché — a generic Lucide line-icon in an identical pale-tinted rounded-square,
60	repeated for every feature/step (−4, §CC-9b); the StyleSeed demo layout copied verbatim
61	(hero+chat / 3-step / feature-grid / pricing) with no product-specific identity (−4); **no focal
62	point** — an all-even grid of same-weight, centered, evenly-spaced cards (−3); the hero shows a
63	stock/placeholder visual instead of this product (−3); the escape hatch as a new uniform
64	(§CC-9c) — ghost 01/02/03 index numbers on every section, or identical uppercase-overline +
65	big-number cards repeated with no variation (−2); distinctive-but-dated (§CC-9d) — full
66	beige/paper page base, serif body text on a product surface, dark-heavy blocks that read
67	"brochure" not "2026 product" (−3). Cap −10.
68
69	Hierarchy & typography (16) — deduct for: number/unit not ~2:1 (−4); font
70	sizes off the Font Size table / `text-[var(--…)]` for size (−5); everything the
71	same weight, no clear primary (−5); cramped or wrong line-height on body (−3);
72	body < 16px on a desktop/web B2B surface (tight mobile scale on a wide screen) (−4 —
73	but dense-data chrome is exempt: chart ticks, mono SHAs/timestamps, table metadata at
74	12–13px are correct; and dashboard app-chrome h1 at 22–24px is correct, not a violation
75	of the marketing 40–56px headline scale).
76
77	Layout & rhythm (12) — deduct for: grouping that contradicts the selected grammar (−6):
78	`operations-console` needs explicit functional groups, while `editorial-reading` should not be
79	forced into cards; arbitrary off-scale spacing (−3); same section type repeated without purpose
80	(−4); no discernible proximity rhythm (−3).
81
82	Cards & elevation (10) — deduct for mixed or task-inappropriate surface language. Hairlines,
83	flat grouping, tonal ramps, or restrained shadows are valid only when the selected grammar/profile
84	uses them c

People who liked this also viewed

6 picks

Type