agentleFS
GabrieleDattileGabrieleDattile/agent-superpowers/skills/frontend/hallmark/SKILL.md

hallmark

Skill1 starsChanged 15 days agoMITView on GitHub

Anti-AI-slop design engine and UI audit toolkit. Overrides generic LLM aesthetic defaults (purple gradients, predictable rounded cards, unopinionated typography) with 24 distinct visual material themes, purpose-driven layout verbs (build, audit, redesign, study), and automated sloplint verification.

29 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use review-animations, animate and 8 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.
  • arkanSkill

    review-animations

    Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

    Also in 3 projects that use this

  • delphi-aiSkill

    animate

    Animation patterns and best practices for Next.js/React applications. Use this skill when implementing animations, transitions, hover effects, page transitions, modals, or any motion in React components. Based on Emil Kowalski's "Animations on the Web" course.

    Also in 3 projects that use this

  • VercelSkill

    emil-design-eng

    This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

    Also in 3 projects that use this

  • dillonluiSkill

    design-review

    Review a view or flow for UX and UI issues. Provides severity-ranked, actionable findings grounded in established design heuristics. Use when the user asks for design feedback, UX review, or UI critique.

    Also in 3 projects that use this

  • AnasX7Skill

    design-taste-frontend

    Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

    Also in 3 projects that use this

  • GoogleSkill

    prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 28 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Hallmark enforces a hard floor against these defaults: Every page must look intentional, hand-crafted, and culturally distinct.

    line 33
  2. Distinctive:

    Define the Primary Action: Every screen is built around the ONE thing the visitor came to do (book, buy, search, read).

    line 40
  3. Very specific:

    Select a Material Theme: Do NOT invent colors on the fly.

    line 41
  4. Distinctive:

    Build the Hero First: Create and review the hero section cold before generating sub-sections.

    line 42
  5. Distinctive:

    When redesigning an existing page:

    line 52
  6. Distinctive:

    Before marking any UI task complete, run:

    line 78
  7. Very specific:

    If the Slop Score exceeds 25, refactor the layout using Hallmark theme tokens and re-run until the score returns 0 / 100 (CLEAN).

    line 87

“Common” is measured: kept by at least 6 in 10 of the 28 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

🎨 Skill: Hallmark (Anti-AI-Slop Design Engine)

1. When to Trigger (Routing)

  • TRIGGER WHEN:
    • The user asks to build a web page, landing page, app screen, or UI component.
    • The user says "don't make it look like AI generated it", "avoid generic AI design", or mentions "AI slop".
    • The user requests an aesthetic audit or wants to redesign an existing UI without breaking functionality.
    • The user asks to run sloplint or check against design anti-patterns.
  • DO NOT TRIGGER WHEN:
    • The task is purely backend, database querying, or non-visual terminal scripting.

2. The Anti-AI-Slop Manifesto

Large language models naturally converge on a predictable "slop attractor" due to statistical training defaults:

  1. The Purple/Indigo Linear Gradient: bg-gradient-to-r from-purple-600 to-indigo-600 on dark #0f172a.
  2. The Symmetrical 3-Card Feature Grid: 3 identical boxes with generic Lucide icons and placeholder buzzwords.
  3. The Unanchored Floating Blur Orb: Giant blur-3xl purple blobs dumped in the background to hide empty space.
  4. The Dual Primary Button Dilemma: Two filled bright buttons side-by-side causing visual decision fatigue.
  5. The Micro-Label Uppercase Disease: uppercase tracking-widest text-xs on every random paragraph.
  6. The Inter Font Monoculture: Zero typographic personality, identical weights, and no serif or display contrast.

Hallmark enforces a hard floor against these defaults. Every page must look intentional, hand-crafted, and culturally distinct.


3. The 4 Operational Verbs

🔨 build (Purpose-Driven Macrostructure)

  1. Define the Primary Action: Every screen is built around the ONE thing the visitor came to do (book, buy, search, read).
  2. Select a Material Theme: Do NOT invent colors on the fly. Pick a curated theme from references/themes.json (e.g. Atelier, Furrow, Cobalt, Studio, Midnight, Newsprint, Cyber-Nordic).
  3. Build the Hero First: Create and review the hero section cold before generating sub-sections.
  4. Vary Density: Break the 3-card pattern. Use asymmetrical bento boxes (2x1, 1x2), interactive calculators, full-bleed images, or typography-led lists.

🔍 audit (Sloplint Verification)

Runs the automated sloplint.py scanner over proposed or existing files to detect the 6 critical slop tells.

python skills/frontend/hallmark/scripts/sloplint.py <file-or-dir>

🔄 redesign (Visual Uplift with Zero Breakage)

When redesigning an existing page:

  • --kept Invariant: 100% of existing <form>, <input>, <a>, buttons, IDs, and event handlers MUST be preserved verbatim.
  • Upgrade typography, color palettes, spacing rhythm, and border-radius consistency while leaving functional DOM wires intact.

🔬 study (Style DNA Extraction)

Extracts typographic hierarchy, palette tokens, and border radii from external reference designs to assemble a custom theme.


4. Curated Hallmark Material Themes

ThemeMoodDisplay FontBody FontAccent ColorBorder Radius
AtelierEditorial, gallery warmthPlayfair DisplayPlus Jakarta Sans#c25e36 (Terracotta)4px
CobaltHigh-density engineeringSpace GroteskJetBrains Mono#00f0ff (Cyan)2px
FurrowGrounded agricultural-techFraunces (serif)IBM Plex Sans#dda15e (Gold)6px
StudioSwiss high-contrast minimalSyneInter Tight#ff3b00 (Vermillion)0px
MidnightDeep luxury obsidianCinzelGeist#d4af37 (Champagne)8px
NewsprintDense journalismNewsreaderLora#a63a24 (Crimson)0px
Cyber-NordicClean Scandinavian arcticCabinet GroteskManrope#38bdf8 (Ice Blue)4px
DoseSurgical bio-tech clarityDM SansIBM Plex Mono#14b8a6 (Teal)8px

5. Automated Sloplint Quality Gate

Before marking any UI task complete, run:

# Verify a single file
python skills/frontend/hallmark/scripts/sloplint.py src/components/Hero.tsx

# Or run via Agent Superpowers CLI
python cli/superpowers.py run sloplint src/

If the Slop Score exceeds 25, refactor the layout using Hallmark theme tokens and re-run until the score returns 0 / 100 (CLEAN).

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.