agentleFS
Darcos-LoftDarcos-Loft/fluid/brandkit/SKILL.md

brandkit

Skill3 starsChanged 5 months agoMITView on GitHub

Generate premium brand reference images for a design system, covering logo concepts, color and type boards, and product mockups. Use when a brief needs visual references or a brand kit before or alongside building the UI. Tool-agnostic (works with Nano Banana / Gemini, Higgsfield, Midjourney, or any image model).

86 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use stitch-design-taste, design-taste-frontend-v1 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

    stitch-design-taste

    Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

    Also in 56 projects that use this

  • HK-hubSkill

    design-taste-frontend-v1

    The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.

    Also in 29 projects that use this

  • sanmidableSkill

    animate-expo

    Also in 6 projects that use this

  • sanmidableSkill

    ask-sonner

    Also in 6 projects that use this

  • wxyhgkSkill

    find-animation-opportunities

    Search a codebase or UI for places that don't animate but should, and reject everything that shouldn't. Read-only; it proposes motion with exact values, it does not implement it. Use when the user asks "what could be animated here?" or wants to "make this feel more alive". For fixing existing animations, use improve-animations or review-animations instead.

    Also in 12 projects that use this

  • cal1888Skill

    pick-ui-library

    Pick the right library for a given frontend task from a curated, opinionated list — numbers, OTP inputs, charts, command menus, virtualization, drag and drop, toasts, state, styling, and more. Only runs when explicitly invoked; it does not trigger on its own.

    Also in 9 projects that use this

  • +1 more from sanmidable

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 80 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Remove any model watermark before use (crop or a clean export).

    line 35

“Common” is measured: kept by at least 6 in 10 of the 80 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

Brandkit

Premium reference imagery for a brand: the visual north-star before code. Works with any image model. Pairs with the design-system skill, which provides the palette and type; this renders them.

What it produces

  • Logo concepts: a mark and a wordmark, on the brand palette.
  • A brand board: palette swatches, type specimens, the mood in one frame.
  • Product mockups: the site or app in context, premium product-photography style.
  • Optional hero: an "open and reveal" sequence (below).

Prompt formula (premium product photography)

[Subject + material and finish], centered in frame, 3/4 front angle.
Clean [brand background hex] background, soft studio lighting, subtle shadows.
[Detail specific to the brand]. Photorealistic, 16:9, catalog quality,
Apple-style product photography. No text, no logos, no other objects in frame.

The "open and reveal" hero (two-image to video)

A signature, attention-grabbing hero: an intact object that opens and whose contents spill out.

  1. Image A, closed: the object intact and clean.
  2. Image B, open: the same object, opened, contents floating around it. Golden rule: identical subject, angle, light, and background, only the state changes, or the animation will jump.
  3. Animate A to B with an image-to-video model (Higgsfield, Kling, Veo): set A as the start frame, B as the end frame, plus a motion prompt describing the opening. Fallback: animate image B alone with a floating motion.

Rules

  • The brand palette and type come from the design-system, not invented here. Render the system, do not redesign it.
  • Real material, premium light, no clutter. Generated does not mean cheap.
  • One consistent style across the whole kit.
  • Remove any model watermark before use (crop or a clean export).

Pairs with: design-system (the identity this renders).

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.