awesome-design-md
Skill1 starsChanged 5 months agoMITView on GitHub
Access design system templates from 59 top companies (Claude, Anthropic, OpenAI, Cohere, ElevenLabs, Linear, Vercel, Framer, Figma, Stripe, Apple, BMW, Ferrari, etc.) as .md files. Use when the user asks for frontend design inspiration, wants to mimic a specific company's design language, needs typography/color/layout guidelines matching a reference brand, or wants to escape generic "AI slop" frontend. The templates are located at ~/Desktop/PROJETS_DEV/awesome-design-md/design-md/[company-name]/README.md.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- mithunyc/buildlooptheir own version, first seen Nov 1, 2026
- liushikuan63/Qoder-Optimizationtheir own version, first seen Nov 1, 2026
- YOSSII812001/claude-code-jarvistheir own version, first seen Oct 9, 2026
- Practice019/agent-skillstheir own version, first seen Sep 9, 2026
- miptah21/skillstheir own version, first seen May 26, 2026
- HK-hub/AgentSkillstheir own version, first seen Mar 2, 2026
Used with
Projects with it also use caveman.
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.
MicrosoftSkillcaveman
Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- HK-hub/AgentSkills★ 6same name
- liushikuan63/Qoder-Optimization★ 2same name
- miptah21/skills★ 2same name
- mithunyc/buildloop★ 1same name
- YOSSII812001/claude-code-jarvis★ 1same name
- Practice019/agent-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- anti-ai-detect-writingSkill
- audit-short-1v1Skill
- audit-short-ffaSkill
- claude-councilSkill
- deep-researchSkill
- design-mdSkill
- design-audit-paris-nuitSkill
- gemini-deep-researchSkill
- gemini-spriteSkill
- oracle-ampere-a1-setupSkill
- smart-routerSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
2
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
- Distinctive: line 24
Ask user (or infer from context) which brand aesthetic fits the project :
- Distinctive: line 54
Always start by reading the chosen .md file: before generating code
- Very specific: line 56
For {{USER_NAME}} specifically: : prefer Cohere, Claude, Linear for freelance offers (RAG, Chef de projet IA).
“Common” is measured: kept by at least 6 in 10 of the 4 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.
Files
Awesome Design MD — Reference Design Systems
Source
Repo cloned : ~/Desktop/PROJETS_DEV/awesome-design-md/
Upstream : https://github.com/VoltAgent/awesome-design-md (38K+ stars)
Available design systems (59 companies)
Anime, airbnb, airtable, apple, bmw, cal, claude, clay, clickhouse, cohere, coinbase, composio, cursor, elevenlabs, expo, ferrari, figma, framer, hashicorp, ibm, intercom, and many more.
List current templates :
ls ~/Desktop/PROJETS_DEV/awesome-design-md/design-md/How to use
Step 1 — Pick a reference design
Ask user (or infer from context) which brand aesthetic fits the project :
- Premium/enterprise SaaS → Claude, Linear, Vercel
- AI/dev tools → Cohere, Anthropic, ElevenLabs, Cursor
- Consumer-facing → Airbnb, Apple, Intercom
- Finance/trust → Coinbase, Stripe
- Auto/luxury → BMW, Ferrari
Step 2 — Read the template
cat ~/Desktop/PROJETS_DEV/awesome-design-md/design-md/[company]/README.mdEach template contains :
- Typography choices (no generic Inter/Roboto/Arial)
- Color palette with exact hex codes
- Spacing rules
- Button/component patterns
- Voice/tone guidelines
- Layout conventions (bentos, hero sections, pricing pages)
Step 3 — Apply to the target project
Inject the template content into the system prompt when generating the UI code. Example for a Next.js landing page :
Using the Cohere design system (see ~/Desktop/PROJETS_DEV/awesome-design-md/design-md/cohere/README.md),
build a landing page for [offer] with hero, 3-column features, pricing table, and footer.Rules
- Never use Inter/Roboto/Arial by default — each template specifies intentional typography
- Always start by reading the chosen .md file before generating code
- Mix templates when appropriate (e.g., Claude typography + Framer animations) but document the choice
- For {{USER_NAME}} specifically : prefer Cohere, Claude, Linear for freelance offers (RAG, Chef de projet IA). Airbnb/Intercom for landing pages consumer-facing.
Why this skill exists
Native frontend-design skill produces generic output. This repo provides 59 curated design systems with intentional choices, avoiding the "vibe-coded SaaS template" look that makes 95% of LLM-generated UIs feel identical.
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
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.

