agentleFS
Sign inStart free
podopodo/design-agent-skills/skills/brand-design-md/SKILL.md

brand-design-md

Skill32 starsChanged 6 months agoMITView on GitHub

Looks up the design spec (a DESIGN.md of colors, type weights, letter-spacing, radii, shadows) for well-known brands such as Stripe, Linear, Apple, Figma, Notion and Nike from getdesign.md at runtime, then applies it to your project. The installed skill is written in Chinese but accepts English brand names.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    License: no LICENSE file <!-- das:install:end -->

    line 56
  2. Distinctive:

    When you need to develop a custom brand identity from scratch (this skill matches existing brands, not creates new ones)

    line 72
  3. Very specific:

    When none of the registry brands match your target (use design-consultation to build a bespoke system)

    line 73
  4. Distinctive:

    When brand token accuracy is legally or contractually sensitive (always verify tokens against official brand guidelines)

    line 74
  5. Very specific:

    When running an unpinned npx package at use time is not acceptable in your environment

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

brand-design-md

Catalogue stub — full skill: SpaceZephyr/brand-design-md

<!-- das:install:start — generated from stub.yaml by `npm run generate`; edit stub.yaml, not this block -->

Decision tree

  1. Is the full skill already installed?
    • Global: f=~/.agents/skills/brand-design-md/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • Project: f=.agents/skills/brand-design-md/SKILL.md; [ -f "$f" ] && ! grep -q "^das:" "$f" && echo "installed" || echo "pointer"
    • installed → the skill is installed as brand-design-md, invoke it and proceed
    • pointer → go to step 2

  2. Detect scope, then install:

    [ -e ~/.agents/skills/brand-design-md ] && echo "global" || echo "project"

    Global:

    npx skills add SpaceZephyr/brand-design-md --skill brand-design-md -g -y

    Project:

    npx skills add SpaceZephyr/brand-design-md --skill brand-design-md -y

    Claude Code: send a command as a chat message starting with ! to run it without leaving the conversation.

Heads-up

  • Requires: Node.js and network access at use time (the skill runs npx getdesign@latest add <brand>, which downloads and executes an unpinned third-party npm package)
  • License: no LICENSE file
<!-- das:install:end -->

Invoke after install

  • Skill name: brand-design-md
  • Trigger phrases: "brand tokens", "brand design", "match Stripe design", "62 brands", "brand-design-md"

What it does

Maps a brand name (Chinese or English, e.g. "做成 Stripe 的感觉", "make it feel like Linear") to a slug in its brand registry, runs npx getdesign@latest add <slug> in a temp directory to fetch that brand's DESIGN.md from getdesign.md, and then generates UI code that follows the exact values in it (colors, type scale, spacing, border-radius, shadows). It can blend several brands ("Notion colors + Linear typography"). Useful for demos, pitch material or brand-matched prototypes without manual research.

Two things to know before using it: the skill's own instructions are written in Chinese, and it executes an unpinned third-party npm package (getdesign@latest) at use time, so it needs Node.js and network access.

When NOT to use

  • When you need to develop a custom brand identity from scratch (this skill matches existing brands, not creates new ones)
  • When none of the registry brands match your target (use design-consultation to build a bespoke system)
  • When brand token accuracy is legally or contractually sensitive (always verify tokens against official brand guidelines)
  • When running an unpinned npx package at use time is not acceptable in your environment

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