agentleFS
Sign inStart free
F0rger123F0rger123/CLAUDE-DESIGN-GOD-MODE/skills/audit/SKILL.md

audit

Skill1 starsChanged 19 days agoMITView on GitHub

Use when asked to score, grade, critique or review the design of a website, app, landing page, dashboard or game UI. Returns a score out of 100 across eight categories, the generic "AI look" tells found, and a fix list ranked by points gained. Read-only; it changes nothing.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use delight, teach-impeccable and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • HK-hubSkill

    delight

    Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful. Use when the user asks to add polish, personality, animations, micro-interactions, delight, or make an interface feel fun or memorable.

    Also in 32 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 19 projects that use this

  • zwy123zwySkill

    normalize

    将用户随意输入的提示词规范化为结构清晰、便于大模型执行的标准化提示词。适用于需要整理、统一提示词格式时调用。

    Also in 19 projects that use this

  • SkillPilotCHSkill

    level-up

    Eine Automatisierung pro Woche finden, scopen, shippen. Output landet als proposed-Eintrag in cadence.md mit konkreten Implementations-Schritten.

    Also in 12 projects that use this

  • ww-w-aiSkill

    pm-discovery

    PM Agent Team - Automated product discovery, strategy, and PRD generation. Runs PM analysis workflow to produce comprehensive PRD before PDCA Plan phase.

    Also in 3 projects that use this

  • +7 more from HK-hub

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run node <skill-base-dir>/scripts/slop-scan.mjs <project-dir> for a fast static read (fonts, colours, radii, shadows, motion, emoji icons, …

    line 12
  2. Distinctive:

    Look at the rendered page if you can (desktop 1440px and phone 390px).

    line 13
  3. Distinctive:

    Every section centred, every section the same height, three identical cards in a row.

    line 33
  4. Distinctive:

    Keep it under 40 lines. Point to files.

    line 56

“Common” is measured: kept by at least 6 in 10 of the 175 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Design Audit

Score what is there, honestly. A generic but tidy page lands around 55-65. Reserve 90+ for work a senior designer would ship.

Steps

  1. Run node <skill-base-dir>/scripts/slop-scan.mjs <project-dir> for a fast static read (fonts, colours, radii, shadows, motion, emoji icons, focus styles).
  2. Look at the rendered page if you can (desktop 1440px and phone 390px). A screenshot beats reading 1,000 lines of CSS. If you cannot render it, score from code and mark visual categories "estimated".
  3. Score each category, then list fixes.

Categories (100 points)

#CategoryPtsFull marks means
1Hierarchy15One clear focal point per screen; the eye knows where to go next. Size, weight and space do the work, not colour alone.
2Typography15Deliberate typefaces (max 2), a real scale, body 16px+, line length 45-80 characters, tight headings, comfortable body leading.
3Colour124-6 named tokens, one accent used with discipline, neutrals tinted toward the brand, text contrast 4.5:1+.
4Layout and spacing15One spacing scale, consistent rhythm, alignment to a grid, variety in section shapes, no cramped or floating blocks.
5Identity13It looks like this product and no other. Imagery, motifs and copy come from the subject's world.
6Interaction and states10Hover, focus, active, disabled, loading, empty and error states exist and are designed.
7Responsive10Works at 390px with no sideways scroll, tap targets 44px+, nav that fits.
8Accessibility and performance10Visible focus, labels, alt text, reduced motion respected, no layout shift, fonts load without flash.

Generic "AI look" tells (each costs points in Identity or Hierarchy)

  • Purple-to-blue or pink gradient hero, gradient text on the main headline.
  • System default font or Inter/Roboto/Arial everywhere with no type decisions.
  • Every section centred, every section the same height, three identical cards in a row.
  • One border radius and one soft grey shadow on everything.
  • Emoji used as icons. Icon in a coloured circle above every card title.
  • Tracked-out ALL-CAPS eyebrow above every heading. "01 / 02 / 03" on things that are not steps.
  • Fade-and-slide-up on every section. transition: all.
  • Fake numbers ("10,000+ happy customers") and stock "Trusted by" logo rows.
  • Cream background with terracotta accent and serif headline; or near-black with one acid-green accent (both are current defaults, fine only when chosen on purpose).
  • Buttons ending in "→", vague CTAs ("Get started", "Learn more", "Submit").

Output format

Design score: 58/100  (Persuade mode)
Hierarchy 9/15 · Type 7/15 · Colour 8/12 · Layout 9/15 · Identity 4/13 · States 6/10 · Responsive 8/10 · A11y/Perf 7/10

Tells found: gradient hero, Inter only, 3 identical feature cards, emoji icons

Fixes, biggest gain first
1. (+8) Replace gradient hero with a product-led hero showing the real schedule view. — app/page.tsx
2. (+6) Set a type pair and scale in tokens. — globals.css
...

Keep it under 40 lines. Point to files. Each fix names what to do, not just what is wrong.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free