dvy1987/agent-loom / .agents/skills/design-direction
design-direction
VerifiedSet a deliberate visual direction before any UI is built — the single biggest lever against generic AI output. Derives a posture from product-soul/PRD/specs, scores a curated archetype palette, then generates 2-3 GENUINELY DISTINCT directions and compares them side-by-side before committing to one. Load when the user asks to pick an aesthetic, choose a design direction, decide what a UI should feel like, explore visual options, says "what should this look like", "make it feel like [Linear/Apple/ Duolingo]", "give me design directions", "explore some looks", or when frontend-design routes here. Replaces design-archetype. Sub-skill of frontend-design.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.8 KB |
| references/archetypes/b2b-productivity.md | markdown | 3.2 KB |
| references/archetypes/brutalist-distinctive.md | markdown | 2.8 KB |
| references/archetypes/conversational-ai.md | markdown | 3.9 KB |
| references/archetypes/creative-tool.md | markdown | 3.5 KB |
| references/archetypes/dev-tool.md | markdown | 2.8 KB |
| references/archetypes/editorial.md | markdown | 2.8 KB |
| references/archetypes/enterprise-trust.md | markdown | 3.2 KB |
| references/archetypes/marketing-landing.md | markdown | 3.6 KB |
| references/archetypes/playful-consumer.md | markdown | 2.9 KB |
| references/archetypes/premium-consumer.md | markdown | 3.1 KB |
| references/archetypes/social-feed.md | markdown | 3.6 KB |
| references/archetypes/spatial-canvas.md | markdown | 3.7 KB |
| references/examples.md | markdown | 2.1 KB |
| references/exploration-method.md | markdown | 3.9 KB |
| references/selection-rubric.md | markdown | 4.1 KB |
| references/ux-context-checklist.md | markdown | 1.3 KB |
references/examples.md
View on GitHub# Design Direction — Full Session Examples
Read when you need a complete walkthrough beyond the inline teaser in SKILL.md.
---
## Example 1 — B2B settings page (3 distinct directions)
**Input:** "Design direction for our team billing settings — feels trustworthy, not playful"
**Agent actions:**
1. Read `docs/product-soul.md` + PRD — audience: finance admins, emotional goal: confidence.
2. Score archetypes — top seeds: `enterprise-trust`, `b2b-productivity`.
3. Posture: restrained, cool, classic, quiet, calm.
4. Generate 3 directions differing on type, layout, motion:
- **Ledger** — feels like Stripe Dashboard; tabular density, mono accents
- **Briefing** — feels like Linear; sidebar nav, generous whitespace
- **Vault** — feels like 1Password; card stacks, strong elevation
5. Side-by-side comparison table; owner non-technical → agent recommends **Ledger** with plain rationale.
6. Write `.design/billing-settings/DIRECTION.md`; handoff to `design-system`.
---
## Example 2 — Anti-skip (three palettes ≠ three directions)
**Input:** Agent proposes light/dark/blue variants of same layout
**Response:** Block — diverge on ≥3 dimensions (type, layout, motion) or it's one direction.
---
## Example 3 — No product docs
**Input:** "Make it look modern" (no PRD)
**Agent asks ONE question:** "What is this for, who is it for, and which product should it feel closest to?"
---
## Example 4 — Reference without posture
**Input:** "Make it like Linear"
**Output:** Reference sets fit; still state posture sentence + bold move per direction — never stop at the name drop.
---
## Example 5 — Orchestrator handoff
**Input:** `frontend-design` routes here for new dashboard shell
**Output:** DIRECTION.md committed; Impact Report lists handoff to `design-system` with chosen direction name and file path.
---
## Verification checklist (full session)
- [ ] Examples demonstrate SKILL.md hard rules, not generic chat
- [ ] Anti-skip or rationalization defense included where applicable
- [ ] Output artifacts or Impact Report shape is explicit
- [ ] Reader can trace input → concrete agent actions → outcome
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |