Skill13 repo starsupdated yesterday

memoire-design-tooling

Memoire-design-tooling provides a local design evidence layer for UI and design system work by offering CLI commands to initialize design suites, run audits, synthesize research into specs, and maintain Atomic Design compliance. Use it when handling Figma integration, design-to-code workflows, component specifications, design system reviews, or research-backed design decisions to ensure changes align with established UX tenets and design documentation before implementation.

View source Repository: memi

Install in Claude Code

Copy

git clone --depth 1 https://github.com/sarveshsea/memi /tmp/memoire-design-tooling && cp -r /tmp/memoire-design-tooling/plugins/memoire/skills/memoire-design-tooling ~/.claude/skills/memoire-design-tooling

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# memi Design Tooling

Use memi as the local design evidence layer before making frontend changes.

## Commands
```bash
npm i -g @memi-design/cli
memi suite init --project .
memi daemon start --project . --port auto
memi daemon status --json
memi status
memi diagnose .
memi ux audit . --json
memi mcp start --no-figma
memi suite run design-audit --project . --json
memi suite run research-vibe-design --project . --json
memi research design --write-specs --mermaid-jam --json
memi mermaid-jam export --from research --json
memi compose "Create an Atomic Design implementation plan"
```

## Rules
- Inspect `.memoire/`, `memoire.agent.yaml`, specs, tokens, README/AGENTS instructions, and Figma state before changing UI.
- Prefer warmed daemon context and suite recipes when they exist; `memoire.agent.yaml` is the local contract for product memory, harnesses, skills, and recipes.
- For research-backed vibe design, preview with `research.design_package`, write only approved specs with `research.generate_specs`, and export FigJam source through `mermaid_jam.export`.
- Keep every component at an Atomic Design level.
- Prefer shadcn/ui and Tailwind.
- Treat UX Tenets and Traps as the review layer: protect clarity, feedback, control, consistency, accessibility, error recovery, progressive disclosure, workflow fit, trust, and state continuity.
- Use memi audits and specs as evidence in final responses.