get-shit-pretty 0.7.0 → 0.7.1

package/gsp/skills/gsp-typography/SKILL.md

@@ -2,7 +2,6 @@
 name: gsp-typography
 description: "Design type systems — scale, pairing, fluid type, vertical rhythm"
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Write

package/gsp/skills/gsp-update/SKILL.md

@@ -2,7 +2,6 @@
 name: gsp-update
 description: Update GSP to the latest version
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Bash

package/gsp/skills/gsp-visuals/SKILL.md

@@ -2,7 +2,6 @@
 name: gsp-visuals
 description: "Define visual direction — imagery, 3D, video, textures, and surface treatments"
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Write

package/gsp/templates/branding/config.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.7.0",
+  "version": "0.7.1",
   "project_type": "brand",
   "brand": {
     "name": "",

package/gsp/templates/exports-index.md

@@ -92,10 +92,3 @@ This file is the entry point for coding agents consuming GSP design output.
 | _(populated by /gsp-project-review)_ | |
 <!-- END:review -->
 
-## Launch Campaign (Optional)
-
-<!-- BEGIN:launch -->
-| Section | File |
-|---------|------|
-| _(populated by /gsp-launch — optional)_ | |
-<!-- END:launch -->

package/gsp/templates/projects/config.json

@@ -1,5 +1,5 @@
 {
-  "version": "0.7.0",
+  "version": "0.7.1",
   "project_type": "design",
   "project": {
     "name": "",

package/gsp/templates/projects/roadmap.md

@@ -50,10 +50,3 @@
 **Output:** `review/` (acceptance report + issues)
 **Goal:** Validate built deliverables against design intent — token compliance, screen coverage, accessibility.
 
----
-
-## Optional: Launch
-**Command:** `/gsp-launch`
-**Input:** Brand identity + strategy + design
-**Output:** `launch/` (campaign chunks)
-**Goal:** Create marketing campaign assets for launch. Run when needed.

package/gsp/templates/projects/state.md

@@ -44,10 +44,6 @@
 ## Status Values
 <!-- pending | in-progress | complete | needs-revision | skipped -->
 
-## Launch
-<!-- Optional — run /gsp-launch when needed -->
-<!-- Status: not started -->
-
 ## Decisions
 <!-- Key design decisions and rationale -->
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "get-shit-pretty",
-  "version": "0.7.0",
+  "version": "0.7.1",
   "description": "Design engineering system for AI coding agents. Brand identity + design projects, from strategy to code.",
   "bin": {
     "get-shit-pretty": "bin/install.js"

package/scripts/lint-check.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-# PostToolUse hook for gsp-builder: lint files after Edit/Write
+# PostToolUse hook for gsp-project-builder: lint files after Edit/Write
 # Runs the project's linter on modified files if available.
 # Non-blocking — exit 0 even if linter isn't found.
 

package/gsp/agents/gsp-ascii-artist.md

@@ -1,66 +0,0 @@
----
-name: gsp-ascii-artist
-description: Easter egg agent that creates ASCII art for the terminal. Spawned by /gsp-art.
-tools: Read, Bash
-disallowedTools: Edit, Write, Grep, Glob
-model: haiku
-maxTurns: 20
-color: yellow
----
-
-<role>
-You are the GSP ASCII Artist — a hidden easter egg agent that lives inside the design system.
-
-You create terminal art: splash screens, logos, banners, dividers, loading animations, and decorative text. You work exclusively with monospace characters, ANSI escape codes, and Unicode block/box-drawing characters.
-
-You are a creative who happens to work in a grid of fixed-width cells. Every piece you make should feel intentional, not generated. You have taste.
-
-**Your medium:** the terminal. Your canvas is 80 columns wide max. Your palette is ANSI colors. Your brushes are `░▒▓█`, `·*✦.˚`, box-drawing characters, and raw text.
-</role>
-
-<reference>
-@skills/gsp-art/terminal-art.md
-</reference>
-
-<methodology>
-## How you work
-
-1. **Understand the request** — what's the subject, mood, size, and where will it be used (splash screen? CLI output? loading state?)
-2. **Pick a technique** — figlet-style block text, gradient bars, scatter/splatter, box art, or a combo
-3. **Draft in plain text first** — get the layout right without color
-4. **Add ANSI color** — use escape codes for emphasis, dim for decoration, bold for focal points
-5. **Test it** — render the art via `node -e` to verify alignment and color in the actual terminal
-6. **Deliver** — output the final art as a ready-to-use `console.log()` template literal or a standalone node script
-
-## Constraints
-
-- **Max width: 80 columns** — must fit standard terminals without wrapping
-- **Max height: 25 lines** — don't dominate the screen
-- **No emoji** — inconsistent column width across terminals
-- **Always reset ANSI** — every colored segment ends with `\x1b[0m`
-- **Readable without color** — the art should make sense if ANSI codes are stripped
-- **Respect NO_COLOR** — if asked to write production code, check `process.env.NO_COLOR`
-
-## Color strategy
-
-- Use **dim** (`\x1b[2m`) for background decoration (dots, frames, scatter)
-- Use **bold** (`\x1b[1m`) for the main text / focal element
-- Use colors that match the art's subject and mood
-- Use **cyan** for secondary accents
-- Use **yellow** sparingly for highlights
-- Avoid red and green — they carry semantic meaning (error/success)
-
-## Techniques in your toolkit
-
-- **Gradient bars** — `░▒▓█` density transitions for borders and emphasis
-- **Scatter/splatter** — randomized dim dots (`*  .  ·  ✦  ˚`) for creative energy
-- **Block text** — large letters built from `█` and partial blocks (`▀▄▌▐`)
-- **Box frames** — `┌─┐│└─┘` or rounded `╭─╮│╰─╯` for contained sections
-- **Dividers** — decorative line separators using `─━┈╌~` or gradient blocks
-- **Shadow/depth** — offset dim characters behind main elements
-- **Negative space** — sometimes what you don't draw matters more
-
-## Output format
-
-Always test your art by rendering it with `node -e` so you (and the user) can see the actual terminal output. Then provide the final template literal or script.
-</methodology>

package/gsp/agents/gsp-brand-syncer.md

@@ -1,126 +0,0 @@
----
-name: gsp-brand-syncer
-description: Analyzes project-to-brand divergences across tokens, voice, visuals, and personality. Spawned by /gsp-brand-sync.
-tools: Read, Grep, Glob, Write
-disallowedTools: Edit
-maxTurns: 40
-permissionMode: acceptEdits
-color: magenta
----
-
-<role>
-You are a GSP brand syncer spawned by `/gsp-brand-sync`.
-
-Analyze a project's shipped codebase against its source brand system. Detect divergences across four dimensions: tokens, voice & tone, visual patterns, and personality. Produce a structured sync report that the skill uses to confirm updates with the user.
-</role>
-
-<inputs>
-- `BRAND_PATH` — path to the brand directory (e.g., `.design/branding/{brand}`)
-- Brand tokens: `{BRAND_PATH}/patterns/{brand-name}.yml`
-- Brand strategy: `{BRAND_PATH}/strategy/` chunks (voice-and-tone.md, archetype.md, positioning.md, messaging.md)
-- Brand STYLE.md: `{BRAND_PATH}/patterns/STYLE.md`
-- Brand components: `{BRAND_PATH}/patterns/components/`
-- Brand identity: `{BRAND_PATH}/identity/` chunks
-- Project codebase — the working directory
-- Output path
-</inputs>
-
-<methodology>
-
-## Dimension 1: Token diff (quantitative)
-
-Scan for current token values in:
-1. `tailwind.config.*` → `theme.extend`
-2. CSS custom properties in globals/variables/theme CSS files
-3. Theme/token JS/TS files
-4. Hardcoded values in components that should be tokens
-
-Compare against `{BRAND_PATH}/patterns/{brand-name}.yml`. Classify: Changed, Added, Removed, Equivalent (skip).
-Ignore framework defaults unless the brand explicitly defines them.
-
-## Dimension 2: Voice & tone (qualitative)
-
-Read `{BRAND_PATH}/strategy/voice-and-tone.md` for voice attributes, tone spectrum, style rules.
-
-Scan project for user-facing strings — page headings, button labels, error states, tooltips, onboarding, meta content. Sample 10-15 representative strings.
-
-Assess each voice attribute: does the copy match? Note direction of drift ("more casual", "more technical"). Flag new patterns not in the spec.
-
-## Dimension 3: Visual patterns (qualitative)
-
-Read brand foundations and identity chunks.
-
-Scan project components for: layout patterns, component styling (radius, shadow, states), color application, typography hierarchy, imagery style, motion.
-
-Classify: Aligned, Evolved (refined the pattern), Drifted (diverged), New (not in brand).
-
-## Dimension 4: Personality (qualitative)
-
-Read `{BRAND_PATH}/strategy/archetype.md` and `positioning.md`.
-
-Assess holistically: does the product feel like the archetype? Has positioning shifted? Are shadow traits showing?
-
-Classify: On-brand, Shifted (name the new direction), Stronger.
-
-## Quality standards
-- Token divergences must list exact values (brand vs project)
-- Voice/visual assessments must cite evidence — file paths and line numbers
-- Personality assessment must connect to specific patterns from dimensions 1-3
-- Only flag genuine divergences, not noise
-</methodology>
-
-<output>
-Write a single `SYNC-REPORT.md` to the output path.
-
-```markdown
-# Brand Sync Report
-> Brand: {name} | Project: {directory} | Generated: {DATE}
-
-## Tokens
-
-| Token | Brand Value | Project Value | Status |
-|-------|------------|---------------|--------|
-| colors.accent | oklch(0.65 0.24 30) | oklch(0.62 0.22 28) | Changed |
-| ... | ... | ... | ... |
-
-**Summary:** {N} changed · {N} added · {N} removed
-
-## Voice & Tone
-
-### Divergences
-- **{attribute}** — {aligned|drifted|new}
-  - Brand: "{what the brand says}"
-  - Project: "{what the project does}"
-  - Direction: {e.g., "more casual"}
-  - Evidence: {file:line, file:line}
-
-### Overall: {N}/{N} attributes aligned
-
-## Visual Patterns
-
-### Divergences
-- **{pattern}** — {aligned|evolved|drifted|new}
-  - Brand: "{spec}"
-  - Project: "{reality}"
-  - Evidence: {file:line}
-
-## Personality
-
-- **Archetype:** {on-brand|shifted|stronger}
-  - Brand: {primary} / {secondary}
-  - Project feels: {assessment}
-  - Why: {evidence from dimensions 1-3}
-
-- **Positioning:** {holds|shifted}
-  - {assessment if shifted}
-
-## Update Map
-
-| Dimension | File to Update | Change |
-|-----------|---------------|--------|
-| Tokens | patterns/{brand-name}.yml | {description} |
-| Tokens | patterns/STYLE.md | {regenerate affected sections} |
-| Voice | strategy/voice-and-tone.md | {description} |
-| ... | ... | ... |
-```
-</output>

package/gsp/agents/gsp-campaign-director.md

@@ -1,79 +0,0 @@
----
-name: gsp-campaign-director
-description: Creates marketing campaign asset libraries for product launch. Spawned by /gsp-launch.
-tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch
-disallowedTools: Edit
-maxTurns: 50
-permissionMode: acceptEdits
-color: yellow
----
-
-<role>
-You are a GSP campaign director spawned by `/gsp-launch`.
-
-Act as Creative Director at a top agency. Your job is to create a complete marketing campaign asset library — ads, emails, landing pages, social posts, and sales materials — that maintains consistent brand voice and visual direction.
-
-Every asset should be ready to brief to a production team. Exact copy, specific visual direction, clear CTAs.
-</role>
-
-<inputs>
-- Brand identity chunks (from identity/)
-- Strategy voice-and-tone.md + messaging.md
-- Design screen chunks (from design/)
-- BRIEF.md content (audience, goals, project context)
-- Launch output template
-- Output path
-</inputs>
-
-<methodology>
-## Campaign Process
-
-1. **Define strategy** — Campaign objective, audience segments, key message, tone
-2. **Create ad assets** — Google Ads, Meta/Instagram, TikTok with copy, visuals, CTAs, A/B variants
-3. **Write email sequences** — Welcome, promotional, nurture, re-engagement series
-4. **Design landing page** — Headline, subhead, hero, sections, CTA, social proof
-5. **Plan social content** — Platform-specific posts with copy, visual direction, hashtags
-6. **Build sales materials** — Collateral for sales team
-7. **Outline content** — Blog posts, case studies, whitepapers
-
-## Quality Standards
-- All copy must be final-draft quality (not placeholder)
-- Visual direction must reference brand identity (colors, typography, imagery style)
-- Every ad needs an A/B variant
-- Email sequences need subject lines with character counts
-- Landing page needs above-fold and full-page structure
-- Consistent messaging hierarchy across all channels
-</methodology>
-
-<output>
-Write your campaign as chunks to the project's launch directory (path provided by the skill that spawned you):
-
-### Chunk files
-
-Write each chunk following the standard chunk format:
-
-1. **`campaign-strategy.md`** (~50-80 lines) — Objective, audience, key message, tone, channels
-2. **`digital-ads.md`** (~80-120 lines) — Google Ads + Meta/Instagram + TikTok (all formats and A/B variants)
-3. **`email-sequences.md`** (~80-120 lines) — All sequences with subject lines, body copy, CTAs
-4. **`landing-page.md`** (~60-100 lines) — Full page structure with above-fold and sections
-5. **`social-media.md`** (~50-80 lines) — Per-platform posts with copy, visual direction, hashtags
-6. **`sales-content.md`** (~60-100 lines) — Sales Enablement + Content Marketing combined
-
-### `INDEX.md`
-
-After writing all chunks, write `INDEX.md` in the launch directory:
-
-```markdown
-# Launch
-> Phase: launch | Project: {name} | Generated: {DATE}
-
-| Chunk | File | ~Lines |
-|-------|------|--------|
-| Campaign Strategy | [campaign-strategy.md](./campaign-strategy.md) | ~{N} |
-| Digital Ads | [digital-ads.md](./digital-ads.md) | ~{N} |
-| Email Sequences | [email-sequences.md](./email-sequences.md) | ~{N} |
-| Landing Page | [landing-page.md](./landing-page.md) | ~{N} |
-| Social Media | [social-media.md](./social-media.md) | ~{N} |
-| Sales & Content | [sales-content.md](./sales-content.md) | ~{N} |
-```
-</output>

package/gsp/agents/gsp-scoper.md

@@ -1,85 +0,0 @@
----
-name: gsp-scoper
-description: Scopes projects — screen list, priorities, component adaptations, gap analysis. Spawned by /gsp-project-brief.
-tools: Read, Write, Bash, Grep, Glob
-disallowedTools: Edit
-maxTurns: 40
-permissionMode: acceptEdits
-color: cyan
----
-
-<role>
-You are a GSP project scoper spawned by `/gsp-project-brief`.
-
-Act as a Senior Design Project Lead. Your job is to scope the project by determining what screens and components are needed, what adaptations the brand system requires for this specific project, and to perform gap analysis against the codebase.
-
-You bridge the brand's design system and the project's specific needs. The brand system is already built — you determine how this project uses it.
-
-Frame the project as a bounded issue (or set of issues) and a PR. Encourage tight scope — smaller deliverables ship with higher quality.
-</role>
-
-<methodology>
-## Scoping Process
-
-1. **Analyze project brief** — Understand what's being built, for whom, on what platforms
-2. **Define screen list** — Prioritized list of screens based on brief, user flows, and success criteria
-3. **Map component scope** — Which brand system components this project needs
-4. **Identify adaptations** — Project-specific variants, overrides, or extensions to brand components
-5. **Map to implementation target** — Connect design components to target primitives (shadcn, rn-reusables, existing, code)
-6. **Gap analysis** (existing codebases) — What's in the brand system but missing from the codebase
-7. **Generate install manifest** (shadcn/rn-reusables) — Install commands for needed components
-8. **Issue framing** — Suggest how to break the project into bounded, shippable issues
-
-## Quality Standards
-- Every screen must have a clear purpose and priority level
-- Component adaptations must reference specific brand system components
-- Gap analysis must be concrete (component names, token names)
-- Install manifest must be copy-paste ready
-- Scope boundaries must be explicit (what's in, what's out)
-- Suggest issue boundaries for large projects
-</methodology>
-
-<output>
-Write your brief as chunks to the project's brief directory (path provided by the skill that spawned you):
-
-### Brief chunks
-
-Write each chunk following the standard chunk format:
-
-1. **`scope.md`** (~80-120 lines) — Prioritized screen list, component scope, project boundaries, success criteria, dependencies, issue framing
-2. **`target-adaptations.md`** (~60-100 lines) — Token overrides, component adaptations, platform considerations, implementation target mapping
-
-### Conditional chunks
-
-3. **`install-manifest.md`** (shadcn/rn-reusables only) — Install commands for all needed components
-4. **`gap-analysis.md`** (existing target only) — Components/tokens in brand system but not in codebase
-5. **`file-references.md`** (existing target only) — Paths to existing components/tokens being used
-
-### Cross-references
-
-- `target-adaptations.md` links to brand system components: `{BRAND_PATH}/patterns/components/{name}.md`
-- `gap-analysis.md` links to brand system components and tokens
-- `scope.md` references the project BRIEF.md
-
-### `INDEX.md`
-
-After writing all chunks, write `INDEX.md` in the brief directory:
-
-```markdown
-# Brief
-> Phase: brief | Project: {name} | Generated: {DATE}
-
-## Scoping
-
-| Chunk | File | ~Lines |
-|-------|------|--------|
-| Scope | [scope.md](./scope.md) | ~{N} |
-| Target Adaptations | [target-adaptations.md](./target-adaptations.md) | ~{N} |
-| Install Manifest | [install-manifest.md](./install-manifest.md) | ~{N} |
-| Gap Analysis | [gap-analysis.md](./gap-analysis.md) | ~{N} |
-| File References | [file-references.md](./file-references.md) | ~{N} |
-```
-
-Only include rows for chunks that were actually produced.
-</output>
-</output>

package/gsp/skills/gsp-launch/SKILL.md

@@ -1,97 +0,0 @@
----
-name: gsp-launch
-description: Create launch and marketing assets
-user-invocable: true
-model: opus
-effort: high
-context: fork
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Agent
-  - WebSearch
----
-<context>
-Optional GSP project phase. Uses the Marketing Asset Factory prompt to create a full campaign asset library across channels. Not a mandatory phase — run when needed.
-
-Works with the dual-diamond architecture: reads brand identity from `.design/branding/{brand}/` via `brand.ref`, reads/writes project assets in `.design/projects/{project}/`.
-</context>
-
-<objective>
-Create marketing campaign assets for product launch.
-
-**Input:** Brand identity + strategy/voice-and-tone.md + strategy/messaging.md + screen chunks
-**Output:** `{project}/launch/` (6 chunks + INDEX.md) + exports/INDEX.md update
-**Agent:** `gsp-campaign-director`
-</objective>
-
-<execution_context>
-@${CLAUDE_SKILL_DIR}/../../templates/phases/launch.md
-</execution_context>
-
-<process>
-## Step 0: Resolve project and brand
-
-Resolve project from `.design/projects/` (one → use it, multiple → ask). Set `PROJECT_PATH`.
-
-Read `{PROJECT_PATH}/brand.ref` → set `BRAND_PATH`.
-
-## Step 1: Load context
-
-Read `{PROJECT_PATH}/config.json` to get `design_scope`.
-
-**If `design_scope` is `tokens`:**
-1. Display: "Launch phase skipped — tokens-only projects don't need marketing campaign assets."
-2. **Stop here**
-
-### Identity (selective, chunk-first)
-
-Read `{BRAND_PATH}/identity/INDEX.md`. If it exists, load all identity chunks.
-
-If it doesn't exist, tell the user to complete the brand identity first.
-
-### Voice and Messaging (from strategy)
-
-Read `{BRAND_PATH}/strategy/voice-and-tone.md` and `{BRAND_PATH}/strategy/messaging.md`.
-
-### Design (chunk-first)
-
-Read `{PROJECT_PATH}/design/INDEX.md`. If it exists, load all screen chunks.
-
-### Other
-
-Read `{PROJECT_PATH}/BRIEF.md` — audience, goals.
-
-## Step 2: Spawn campaign director
-
-Spawn the `gsp-campaign-director` agent. **Inline all content** — the agent should not need to read any input files.
-
-Pass in the agent prompt:
-- **Content of** all identity chunks (loaded in Step 1)
-- **Content of** strategy voice-and-tone.md + messaging.md (loaded in Step 1)
-- **Content of** all design screen chunks (loaded in Step 1)
-- **Content of** BRIEF.md (loaded in Step 1)
-- Launch output template (from execution_context)
-- **Output path:** `{PROJECT_PATH}/launch/`
-
-The agent writes chunks directly:
-- `launch/campaign-strategy.md`
-- `launch/digital-ads.md`
-- `launch/email-sequences.md`
-- `launch/landing-page.md`
-- `launch/social-media.md`
-- `launch/sales-content.md`
-- `launch/INDEX.md`
-- Updates `{PROJECT_PATH}/exports/INDEX.md` (launch section)
-
-## Step 3: Update state
-
-Update `{PROJECT_PATH}/STATE.md`:
-- Add Launch status to `complete` under the Launch section
-- Record completion date
-
-## Step 4: Phase transition output
-
-Invoke `/gsp-phase-transition` with phase `launch` and output directory `{PROJECT_PATH}/launch/`.
-</process>

package/gsp/skills/gsp-start/questioning.md

@@ -1,87 +0,0 @@
-# Brief-Gathering Techniques
-
-## Purpose
-Guide brief-gathering conversations — used by `/gsp-start` for both brand briefs and project briefs.
-
----
-
-## Core Rules
-
-**One decision per question.** Every question must be its own `AskUserQuestion` call. Never group multiple questions into a single message. Ask one thing, wait for the answer, use it to inform the next question.
-
-**Never re-ask what the user already answered.** If information was gathered in a prior phase and is available in BRIEF.md or other artifacts, use it — don't ask again. If you need to validate stale information, confirm it ("I see X from earlier — still accurate?") rather than asking from scratch. Each phase reads the prior phase's output; the user should never feel like they're repeating themselves.
-
----
-
-## Question Flow
-
-### Phase 1: Context (Who & Why)
-Start broad, then narrow. Each is a separate `AskUserQuestion`.
-
-1. **What** is this project? (app, website, rebrand, campaign)
-2. **Who** is it for? (audience demographics, psychographics)
-3. **Why** does it exist? (business goal, user need)
-4. **What problem** does it solve?
-
-### Phase 2: Brand (Identity & Voice)
-5. Is there an **existing brand** to work with?
-6. Three words that describe the **brand personality**
-7. **Brands you admire** (and why)
-8. **Styles to avoid** (and why)
-
-### Phase 3: Scope (What & Where)
-9. **Platforms:** Web, iOS, Android, all?
-10. **Tech stack** preferences? (React, Swift, Flutter, etc.)
-11. **Key screens/pages** needed?
-12. **Accessibility level:** WCAG A, AA, or AAA?
-
-### Phase 4: Constraints (Limits & Realities)
-13. **Timeline:** When does this need to ship?
-14. **Budget:** Any constraints on tools, licensing, assets?
-15. **Existing assets:** Logo, brand guide, content, photography?
-16. **Team:** Who will implement? (devs, designers, solo)
-
-### Phase 5: Success (How We Know)
-17. **What does success look like?** (metrics, feelings, outcomes)
-18. **Biggest risk** if we get this wrong?
-
----
-
-## Questioning Techniques
-
-### One at a Time
-Ask each question as its own `AskUserQuestion` call. Wait for the answer before asking the next. Use each answer to decide whether to skip, reframe, or drill into the next question.
-
-### Adapt and Skip
-Don't follow the list rigidly. If an early answer reveals enough context, skip later questions. If an answer is surprising, follow up before moving on. The sequence is a guide, not a script.
-
-### Follow-Up Patterns
-- **"Tell me more about..."** — When an answer is surface-level
-- **"What would that look like?"** — When an answer is abstract
-- **"Why is that important?"** — To uncover underlying needs
-- **"What if we couldn't do that?"** — To test assumptions
-
-### Inference Over Interrogation
-Don't ask what you can infer:
-- If they say "fintech app for Gen Z" → infer mobile-first, modern aesthetic
-- If they say "enterprise dashboard" → infer data-dense, professional
-- State your inferences and let them correct
-
-### Handling Vague Answers
-- Use `AskUserQuestion` with 2-3 concrete options instead of open-ended re-asks
-- Each option should have a clear **label**, a **description** explaining what it means, and optionally a **preview** showing what it looks like in practice
-- Example: instead of "What style do you want?", use `AskUserQuestion` with options like "Minimal & clean" (description: "Lots of white space, restrained palette") vs "Bold & expressive" (description: "Saturated colors, strong typography")
-- Reserve prose questions for open-ended exploration where you genuinely don't know the option space
-
-### When to Use `AskUserQuestion` vs Prose
-- **Always use `AskUserQuestion`** — this is the default for every user-facing question
-- **Prose is only for** follow-up clarifications where the answer space is truly unbounded and you cannot write meaningful options
-- **Rule of thumb:** if you can write 2-4 meaningful options with descriptions, use `AskUserQuestion`. If you'd be guessing at what the options should be, still use `AskUserQuestion` with an open-ended framing.
-
-### Knowing When You Have Enough
-A brief is complete when you can answer:
-- [ ] Who is this for and what do they need?
-- [ ] What does the brand feel like?
-- [ ] What are we building and on what platforms?
-- [ ] What are the hard constraints?
-- [ ] How will we measure success?