# Repository Instructions

This repo is the public design-agent discovery layer.

## Scope

- Curate high-signal design skills, rubrics, examples, and rankings for AI coding/design agents.
- Own broad UI quality, anti-slop design, brand-system discovery, design audits, and before/after examples.
- Defer motion-specific rankings to `awesome-motion-design-agent-skills`.
- Defer owned brand doctrine to `starlight-design-intelligence`.

## Quality Bar

- Rank by demonstrated usefulness to shipped design quality, not by stars alone.
- Prefer resources that improve hierarchy, spacing, typography, density, accessibility, visual system coherence, and interaction polish.
- Avoid broad prompt dumps, generic inspiration lists, and resources with no visible output quality bar.

## Safety

- Keep public-safe. Do not include private brand strategy, client work, credentials, or internal-only visual systems.
- Link to official sources and active repos when possible.

## Verification

- Scan for broken links, stale dates, placeholders, and private paths before handoff.

## Design Taste Kernel

For any site, app, landing page, dashboard, visual identity, brand, motion, media, social, or frontend task, apply the shared Design Taste Kernel before handoff:

- ../design-agent-standards/DESIGN_TASTE.md
- ../design-agent-standards/WEB_EXPERIENCE_STANDARD.md
- ../design-agent-standards/MOTION_TASTE_RUBRIC.md
- ../design-agent-standards/MULTI_AGENT_DESIGN_COUNCIL.md
- ../design-agent-standards/VISUAL_QA_GATE.md

When motion, scroll, generated media, GIF/video, or premium polish matters, route through the Motion Design Studio plugin/skills and verify the result visually.

## Generated Asset Curation Gate

When adding or ranking resources for image generation, logo agents, motion agents, UI builders, or design QA, evaluate them with:

- `rubrics/premium-generation-gate.md`
- `../design-agent-standards/OUTCOMES.md`
- `../design-agent-standards/AGENTIC_DESIGN_LOOP.md`

Prefer resources that create measurable loops: research, direction board, output inspection, scoring, iteration, and handoff evidence.