design-system-builder
Skill2 starsChanged 42 days agoApache-2.0View on GitHub
Guides and executes the from-scratch construction of an agentic design system for any team — component architecture, tokens, governance, and audit — with explicit human confirmation before every structural decision.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- yesith0106/Skillstheir own version, first seen Nov 1, 2026
- zebbern/claude-code-guidetheir own version, first seen Oct 30, 2026
- mattiazi/skillstheir own version, first seen Oct 20, 2026
- signerlabs/design-system-builder-skillstheir own version, first seen Oct 20, 2026
- thewyattbrocato/design-and-copy-skillstheir own version, first seen Oct 17, 2026
- Geruyang/skillstheir own version, first seen Oct 15, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- zebbern/claude-code-guide★ 4.7ksame name
- signerlabs/design-system-builder-skills★ 8same name
- Uwayxt/agent-skills★ 4same name
- Geruyang/skills★ 2same name
- thewyattbrocato/design-and-copy-skills★ 2same name
- yesith0106/Skills★ 2same name
- mattiazi/skills★ 1same name
- novatic-cu/nova-skills★ 1same 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-component-metadataSkill
- ai-ds-composerSkill
- codebase-indexSkill
- documentSkill
- post-change-pipelineSkill
- quality-gateSkill
- ux-pattern-reviewSkill
- ai-component-metadataSkill
- ai-ds-composerSkill
- codebase-indexSkill
- documentSkill
- post-change-pipelineSkill
- quality-gateSkill
- ux-pattern-reviewSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
0
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
- Very specific: line 43
Every action this skill takes respects references/non-negotiable-foundation.md without exception.
“Common” is measured: kept by at least 6 in 10 of the 7 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
Design System Builder
This skill is not passive documentation to read. It is an execution flow that an agent follows, together with a human, to build an agentic design system from scratch in a target project.
Before doing anything else, read
execution/05-human-gates-checklist.md. It lists every point across the phases below where this skill stops and waits for explicit human confirmation. See the stop points before seeing the first action.
What this skill produces
A design system foundation with:
- A component architecture decision, recorded rather than assumed
- A three-layer token structure (primitive → semantic → component)
- A non-negotiable governance foundation (
GOVERNANCE.md) in the target project - Accessibility, hard-coded-style, and primitive-token audits wired into the build
- Agent instructions with explicit, unambiguous trigger conditions
Structure
master-skill/
├── SKILL.md ← this file
├── execution/
│ ├── 00-component-architecture.md ← Web Components (default) vs a documented deviation
│ ├── 01-governance-setup.md ← writing GOVERNANCE.md in the target project
│ ├── 02-token-architecture.md ← primitive → semantic → component
│ ├── 03-audit-setup.md ← accessibility, hard-coded style, primitive tokens
│ ├── 04-agent-instructions.md ← trigger conditions, agent-alone vs human-required
│ └── 05-human-gates-checklist.md ← every stop point, consolidated
└── references/
└── non-negotiable-foundation.md ← generated from GOVERNANCE.md, never edited by handExecution flow
Run the phases in execution/ in order, 00 through 04. Each phase depends on the previous one being confirmed by the human — do not skip ahead because a later phase seems obvious or low-risk. Each phase file states its own stop point; 05-human-gates-checklist.md is the cross-cutting summary of all of them.
Non-negotiable foundation
Every action this skill takes respects references/non-negotiable-foundation.md without exception. See that file for the four rules and why each one exists.
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.