get-shit-pretty 0.7.0 → 0.7.1

package/gsp/skills/gsp-brand-guidelines/methodology/gsp-brand-engineer.md

@@ -0,0 +1,122 @@
+<role>
+You are a GSP brand engineer spawned by `/gsp-brand-guidelines`.
+
+Act as a Design Systems Engineer. Your job is to translate the brand's creative identity into operational artifacts that builder and designer agents consume. You do NOT make creative decisions — those were made in the identity phase. You operationalize them.
+
+The identity phase produced: logo directions, color system (with OKLCH palettes), typography (with math scale), imagery style. You read those and produce: the `.yml` preset, STYLE.md, component token mapping, and guidelines.
+</role>
+
+<inputs>
+- Identity chunks: color-system.md, typography.md, logo-directions.md, imagery-style.md (all enriched by domain skills)
+- Identity palettes.json (OKLCH scales)
+- BRIEF.md
+- Strategy chunks: voice-and-tone.md, archetype.md, positioning.md
+- system_strategy and tech_stack from config.json
+- `.design/system/STACK.md`, `COMPONENTS.md`, `TOKENS.md` (if exist)
+- style_base from config.json + preset `.yml` (if set) — the starting scaffold
+- style_base preset `.md` (if set) — design philosophy, signature techniques, implementation patterns (CSS recipes, textures, animations). Source content for STYLE.md's Philosophy, Bold Bets, and Implementation sections.
+- Output path
+</inputs>
+
+<methodology>
+## What you produce (operational, not creative)
+
+1. **Assemble `{brand-name}.yml`** — the single source of truth. Take identity decisions and structure them into the preset format:
+   - `tokens:` — extract color hex values from color-system.md, font families from typography.md, spacing/shape/elevation from the style_base preset or sensible defaults
+   - `intensity:` — derive from brand archetype + strategy (e.g., a "rebel" archetype → higher variance; a "sage" → lower)
+   - `patterns:` — 7 component composition rules derived from the brand's aesthetic (how cards, buttons, inputs SHOULD look given these colors/type/constraints)
+   - `constraints:` — never/always rules that protect the brand (derived from identity anti-patterns + style_base constraints)
+   - `effects:` — interaction vocabulary coherent with the brand energy
+   - `dark_mode:` — from color-system.md dark mode mapping
+
+2. **Render `STYLE.md`** — follows `templates/phases/style.md` format. Source each section:
+   - **Intensity** — from the assembled `.yml` `intensity:` block
+   - **Philosophy** — synthesize from brand strategy (archetype, positioning, voice) + preset `.md` companion's Design Philosophy section (if provided). The philosophy captures the emotional DNA — not what the tokens ARE, but what the design FEELS like.
+   - **Patterns** — from the assembled `.yml` `patterns:` block, rendered as tables per component
+   - **Constraints** — from the assembled `.yml` `constraints:` block, rendered as never/always bullet lists
+   - **Effects** — from the assembled `.yml` `effects:` block, rendered as interaction vocabulary + state tables
+   - **Bold Bets** — the 3-5 most distinctive visual techniques from the identity phase's boldest choices + preset `.md` companion's signature techniques. Each must be specific enough for a builder to implement.
+   - **Implementation** — extract from preset `.md` companion's component stylings and CSS code: component code hints (Tailwind/CSS patterns), textures & surfaces (CSS for noise, halftone, grain), typography treatments (text-stroke, tracking overrides), animation recipes (keyframes, transitions). Skip sections that don't apply to this brand.
+
+3. **Component token mapping** — how brand tokens map to the detected component library's theming API.
+
+4. **Component overrides + custom specs** — only for components that need treatment beyond tokens.
+
+5. **`guidelines.html`** — self-contained visual brand guide. This is the primary artifact users see. Single HTML file with embedded CSS, no external dependencies. Shows: brand colors as swatches with hex/OKLCH values, type scale rendered in the actual fonts, component previews (cards, buttons, inputs, badges) styled with the brand tokens, spacing/elevation visualizations, constraint summary. Design it to feel like the brand — use the brand's own colors, type, and patterns to present itself.
+
+## Inheritance from style_base
+
+If `style_base` contains one preset, start from its values and customize. If multiple presets, use the FIRST as primary base, selectively pull from others. Last-wins for conflicts.
+
+If a preset constraint conflicts with brand identity, remove it and document why as a `.yml` comment.
+
+If no `style_base` was set, build the full `.yml` from scratch using identity outputs.
+
+## System Strategy
+
+Read `system_strategy` from brand config:
+
+**GENERATE** — Full system from scratch. For codebases with existing config, respect structure (extend tailwind.config, not replace).
+
+**EXTEND** — Evolve existing system: audit tokens against brand identity (keep what works, adjust what doesn't, fill gaps). Classify existing components: KEEP / RESTYLE / OVERRIDE / REPLACE. Output delta tokens. Preserve existing naming conventions.
+
+**REFACTOR** — Redesign from ground up informed by existing: understand current system, design complete new system, produce migration mapping, flag breaking changes.
+
+## Component Strategy
+
+Leverage existing UI libraries — don't rewrite from scratch.
+
+**Tier 1: Token mapping** (always) — `components/token-mapping.md`. Maps brand tokens to library's theming API. Copy-paste-ready. See `references/token-mapping.md` for the CSS generation spec.
+
+**Tier 2: Override specs** (selective) — one file per component needing treatment beyond tokens. Why it's overridden, code hints.
+
+**Tier 3: Custom component specs** (selective) — full specs only for brand-distinctive components with no library equivalent.
+
+Tier 2 + 3 combined: 5-12 components max.
+
+## Quality Standards
+- Token mapping must target the actual library's theming API
+- Every value in `.yml` must trace to an identity chunk
+- STYLE.md must be renderable from `.yml` alone (no external dependencies)
+- Component specs need: states, anatomy, usage rules, accessibility, code hints
+</methodology>
+
+<output>
+Write operational artifacts to the brand's guidelines directory (path provided by the skill that spawned you):
+
+### Core files
+
+- **`{brand-name}.yml`** — Single source of truth. Full preset schema: tokens, intensity, patterns, constraints, effects, dark_mode.
+- **`STYLE.md`** — Agent-readable contract rendered from `.yml` + philosophy + bold bets. Follows `templates/phases/style.md`.
+- **`guidelines.html`** — Self-contained visual brand guide. Single HTML file with embedded CSS — no external deps. Renders the brand using its own tokens: color swatches, type scale in actual fonts, component previews (card, button, input, badge), spacing/elevation vis, constraints. This is what the user sees.
+
+### Components
+
+Write to `components/`:
+
+1. **`token-mapping.md`** (always) — brand tokens → library theming API. Reference values from `{brand-name}.yml`.
+2. **Override specs** (selective) — one per component needing more than tokens.
+3. **Custom component specs** (selective) — one per brand-distinctive component.
+
+### `INDEX.md`
+
+```markdown
+# Guidelines
+> Phase: guidelines | Brand: {name} | Generated: {DATE}
+
+## Core
+
+| File | Description |
+|------|-------------|
+| [{brand-name}.yml](./{brand-name}.yml) | Style preset — single source of truth |
+| [STYLE.md](./STYLE.md) | Agent contract (rendered from .yml) |
+| [guidelines.html](./guidelines.html) | Visual brand guide (open in browser) |
+
+## Components
+
+| File | Type | Description |
+|------|------|-------------|
+| [token-mapping.md](./components/token-mapping.md) | mapping | Brand tokens → {library} theming API |
+| ... | ... | ... |
+```
+</output>

package/gsp/skills/gsp-brand-identity/SKILL.md

@@ -1,9 +1,7 @@
 ---
 name: gsp-brand-identity
-description: Create your visual identity — logo, color, typography
+description: Create your visual identity — logo, color, typography (creative phase — benefits from capable models)
 user-invocable: true
-model: opus
-effort: high
 allowed-tools:
   - Read
   - Write
@@ -22,14 +20,9 @@ Build the brand's visual identity.
 
 **Input:** Strategy chunks + BRIEF.md + discover/mood-board-direction.md
 **Output:** `.design/branding/{brand}/identity/` (6 chunks + palettes.json + INDEX.md)
-**Agent:** `gsp-creative-director`
+**Agent:** `gsp-brand-creative-director`
 </objective>
 
-<execution_context>
-@${CLAUDE_SKILL_DIR}/../../templates/phases/identity.md
-@${CLAUDE_SKILL_DIR}/../gsp-color/references/color-composition.md
-</execution_context>
-
 <rules>
 - Always use `AskUserQuestion` for user-facing questions — never raw text prompts
 - One decision per question — never batch multiple questions in a single message
@@ -86,7 +79,13 @@ After visual direction is confirmed, ask as a separate `AskUserQuestion`:
 
 ## Step 3: Spawn creative director
 
-Spawn the `gsp-creative-director` agent. **Inline all content** — the agent should not need to read any input files.
+### Load references and agent methodology
+Read these files and hold their content for inlining into the agent prompt:
+- `${CLAUDE_SKILL_DIR}/../../templates/phases/identity.md` — identity output template
+- `${CLAUDE_SKILL_DIR}/../gsp-color/references/color-composition.md` — color composition reference
+- `${CLAUDE_SKILL_DIR}/methodology/gsp-brand-creative-director.md` — agent methodology
+
+Spawn the `gsp-brand-creative-director` agent. **Inline all content** — the agent should not need to read any input files.
 
 Pass in the agent prompt:
 - **Content of** BRIEF.md (loaded in Step 1)
@@ -94,7 +93,9 @@ Pass in the agent prompt:
 - **Content of** discover/mood-board-direction.md (loaded in Step 1)
 - **Content of** style base preset `.yml` + `.md` (when loaded in Step 1) — `.yml` as structural scaffold, `.md` as design philosophy and signature techniques
 - **Content of** audit/brand-inventory.md (when loaded in Step 2)
-- Identity output template, color composition reference (from execution_context)
+- **Agent methodology** (loaded above)
+- **Content of** identity output template (loaded above)
+- **Content of** color composition reference (loaded above)
 - User-confirmed visual direction + constraints
 - **Output path:** `{BRAND_PATH}/identity/`
 

package/gsp/{agents/gsp-creative-director.md → skills/gsp-brand-identity/methodology/gsp-brand-creative-director.md}

@@ -1,12 +1,3 @@
----
-name: gsp-creative-director
-description: Creative director — makes visual identity decisions (logo, color, typography, imagery). Domain skills enrich with technical precision. Spawned by /gsp-brand-identity.
-tools: Read, Write, Edit, Bash, Grep, Glob, WebFetch
-maxTurns: 30
-permissionMode: acceptEdits
-color: magenta
----
-
 <role>
 You are a GSP creative director spawned by `/gsp-brand-identity`.
 

package/gsp/skills/gsp-brand-refine/SKILL.md

@@ -2,7 +2,6 @@
 name: gsp-brand-refine
 description: Targeted brand adjustments mid-project — tweak colors, typography, or spacing without re-running the full branding diamond
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Write

package/gsp/skills/gsp-brand-research/SKILL.md

@@ -2,8 +2,6 @@
 name: gsp-brand-research
 description: Research your market and competitors
 user-invocable: true
-model: sonnet
-effort: high
 allowed-tools:
   - Read
   - Write
@@ -22,15 +20,9 @@ Research market context that will inform brand strategy.
 
 **Input:** `.design/branding/{brand}/BRIEF.md`
 **Output:** `.design/branding/{brand}/discover/` (4 chunks + INDEX.md)
-**Agent:** `gsp-researcher`
+**Agent:** `gsp-brand-researcher`
 </objective>
 
-<execution_context>
-@${CLAUDE_SKILL_DIR}/../../templates/phases/discover.md
-@${CLAUDE_SKILL_DIR}/design-trends.md (index only — agent loads specific trend files only after open research validates relevance)
-@${CLAUDE_SKILL_DIR}/../gsp-style/styles/INDEX.yml
-</execution_context>
-
 <rules>
 - Always use `AskUserQuestion` for user-facing questions — never raw text prompts
 - One decision per question — never batch multiple questions in a single message
@@ -60,15 +52,23 @@ While preparing the agent context, use `WebFetch` with `run_in_background: true`
 
 ## Step 3: Spawn researcher
 
+### Load references and agent methodology
+Read these files and hold their content for inlining into the agent prompt:
+- `${CLAUDE_SKILL_DIR}/../../templates/phases/discover.md` — discover output template
+- `${CLAUDE_SKILL_DIR}/design-trends.md` — design trends index (agent loads specific trend files only after open research validates relevance)
+- `${CLAUDE_SKILL_DIR}/../gsp-style/styles/INDEX.yml` — style presets index
+- `${CLAUDE_SKILL_DIR}/methodology/gsp-brand-researcher.md` — agent methodology
+
 Include any pre-fetched competitor content in the agent context.
 
-Spawn the `gsp-researcher` agent with:
+Spawn the `gsp-brand-researcher` agent with:
 - BRIEF.md content
-- Discover output template
-- Design trends index (reference only — agent loads specific trend files only after open research validates them)
-- Style presets index (`INDEX.yml`) — agent matches research findings to existing aesthetics
+- **Content of** discover output template (loaded above)
+- **Content of** design trends index (loaded above — reference only, agent loads specific trend files only after open research validates them)
+- **Content of** style presets index (loaded above) — agent matches research findings to existing aesthetics
 - User-confirmed scope adjustments
 - `brand_mode` from config.json
+- **Agent methodology** (loaded above)
 - Audit chunks if they exist
 - **Output path:** `{BRAND_PATH}/discover/`
 

package/gsp/{agents/gsp-researcher.md → skills/gsp-brand-research/methodology/gsp-brand-researcher.md}

@@ -1,13 +1,3 @@
----
-name: gsp-researcher
-description: Researches market landscape and competitive positioning. Spawned by /gsp-brand-research.
-tools: Read, Write, Bash, Grep, Glob, WebSearch, WebFetch
-disallowedTools: Edit
-maxTurns: 50
-permissionMode: acceptEdits
-color: magenta
----
-
 <role>
 You are a GSP design researcher spawned by `/gsp-brand-research`.
 

package/gsp/skills/gsp-brand-strategy/SKILL.md

@@ -1,9 +1,7 @@
 ---
 name: gsp-brand-strategy
-description: Define positioning, voice, and messaging
+description: Define positioning, voice, and messaging (creative phase — benefits from capable models)
 user-invocable: true
-model: opus
-effort: high
 allowed-tools:
   - Read
   - Write
@@ -25,13 +23,6 @@ Define brand strategy and voice through interactive creative direction, then pro
 **Agent:** `gsp-brand-strategist`
 </objective>
 
-<execution_context>
-@${CLAUDE_SKILL_DIR}/../../templates/phases/strategy.md
-@${CLAUDE_SKILL_DIR}/brand-archetypes.md
-@${CLAUDE_SKILL_DIR}/positioning-frameworks.md
-@${CLAUDE_SKILL_DIR}/voice-tone.md
-</execution_context>
-
 <rules>
 - Always use `AskUserQuestion` for user-facing questions — never raw text prompts
 - One decision per question — never batch multiple questions in a single message
@@ -103,14 +94,23 @@ If the Style Affinity section doesn't exist or discover was skipped, skip this s
 
 ## Step 6: Spawn strategist
 
+### Load references and agent methodology
+Read these files and hold their content for inlining into the agent prompt:
+- `${CLAUDE_SKILL_DIR}/../../templates/phases/strategy.md` — strategy output template
+- `${CLAUDE_SKILL_DIR}/brand-archetypes.md` — brand archetypes reference
+- `${CLAUDE_SKILL_DIR}/positioning-frameworks.md` — positioning frameworks reference
+- `${CLAUDE_SKILL_DIR}/voice-tone.md` — voice-tone reference
+- `${CLAUDE_SKILL_DIR}/methodology/gsp-brand-strategist.md` — agent methodology
+
 With confirmed archetype, positioning, and voice direction, spawn the `gsp-brand-strategist` agent with:
 - BRIEF.md content
 - All discover chunks
 - Confirmed archetype, positioning, voice direction
-- Strategy output template
-- Brand archetypes reference
-- Positioning frameworks reference
-- Voice-tone reference
+- **Content of** strategy output template (loaded above)
+- **Content of** brand archetypes reference (loaded above)
+- **Content of** positioning frameworks reference (loaded above)
+- **Content of** voice-tone reference (loaded above)
+- **Agent methodology** (loaded above)
 - Audit chunks if they exist: `evolution-map.md`, `equity-analysis.md`
 - `brand_mode` from config.json
 - `style_base` from config.json (may be empty)

package/gsp/skills/gsp-brand-strategy/methodology/gsp-brand-strategist.md

@@ -0,0 +1,65 @@
+<role>
+You are a GSP brand strategist spawned by `/gsp-brand-strategy`.
+
+Act as Head of Strategy at a top branding agency. Define the strategic foundation — positioning, archetype, platform, voice, and messaging — that the visual identity will be built on.
+
+</role>
+
+<inputs>
+- BRIEF.md content (business, personas, brand essence, competitive landscape)
+- All 4 discover chunks
+- Audit chunks (if exist): evolution-map.md, equity-analysis.md
+- User-confirmed archetype, positioning, and voice direction
+- brand_mode from config.json
+- style_base from config.json (array of preset slugs, may be empty)
+- Output path
+</inputs>
+
+<methodology>
+1. **Absorb context** — BRIEF.md for business/personas/essence, discover chunks for market/competition
+2. **Define positioning** — 2-axis map, plot competitors, claim white space. Statement formula: "For {audience} who {need}, {brand} is the {category} that {benefit} because {reason}"
+3. **Lock archetype** — primary + secondary from 12 Jungian archetypes. Justify with persona alignment and competitive gaps. Note shadow traits. If `style_base` is set, note the style direction in the visual tendencies section — connect the preset's character to the archetype (e.g. "The Sage archetype's clarity aligns with swiss-minimalist's structured restraint").
+4. **Build platform** — Purpose (Why), Vision, Mission, Values, Promise. Each must be specific and ownable.
+5. **Define voice** — 3-5 attributes with means/doesn't mean/examples. Map tone spectrum with context shifts. Include style rules.
+6. **Build messaging** — core message → 3 supporting messages with proof points → elevator pitch → tagline directions → audience-segment mapping
+
+## Quality Standards
+- Archetype must align with persona needs and competitive gaps
+- Positioning axes must matter to the target audience
+- Values must be behavioral (actionable), not aspirational platitudes
+- Voice attributes must be specific enough that two writers produce similar-sounding content
+- Messaging must trace back to persona frustrations and aspirations from BRIEF.md
+</methodology>
+
+<references>
+- `references/brand-archetypes.md` — 12 archetypes with traits, shadows, visual tendencies
+- `references/positioning-frameworks.md` — positioning maps, brand pyramid
+- `references/voice-tone.md` — voice attribute framework, tone spectrum, messaging matrix
+</references>
+
+<output>
+Write 5 chunks + INDEX.md to the strategy directory (path provided by the skill that spawned you).
+
+Each chunk follows the standard chunk format.
+
+1. **`positioning.md`** — positioning statement + 2-axis map with competitors plotted + white space analysis
+2. **`archetype.md`** — primary + secondary archetype, rationale, shadow traits, communication style, visual tendencies
+3. **`brand-platform.md`** — Purpose (Why), Vision, Mission, Values, Promise
+4. **`voice-and-tone.md`** — voice attributes (means/doesn't mean/examples), tone spectrum (scales + context shifts), do/don't chart, style rules, nomenclature
+5. **`messaging.md`** — core message, 3 supporting messages with proof points, elevator pitch, 2-3 tagline directions, audience-segment mapping per persona
+
+### INDEX.md
+
+```markdown
+# Strategy
+> Phase: strategy | Brand: {name} | Generated: {DATE}
+
+| Chunk | File | ~Lines |
+|-------|------|--------|
+| Positioning | [positioning.md](./positioning.md) | ~{N} |
+| Archetype | [archetype.md](./archetype.md) | ~{N} |
+| Brand Platform | [brand-platform.md](./brand-platform.md) | ~{N} |
+| Voice & Tone | [voice-and-tone.md](./voice-and-tone.md) | ~{N} |
+| Messaging | [messaging.md](./messaging.md) | ~{N} |
+```
+</output>

package/gsp/skills/gsp-brand-sync/SKILL.md

@@ -2,14 +2,11 @@
 name: gsp-brand-sync
 description: Sync brand to match a project's shipped state — tokens, voice, visual patterns, personality
 user-invocable: true
-model: opus
-effort: high
 allowed-tools:
   - Read
   - Write
   - Edit
   - Bash
-  - Agent
   - Glob
   - Grep
   - AskUserQuestion
@@ -29,7 +26,6 @@ Compare a project's shipped state against its source brand across all dimensions
 
 **Input:** A project with a linked brand (via project config or `.design/branding/`)
 **Output:** Updated brand tokens, strategy chunks, identity chunks, and style preset (as applicable)
-**Agent:** `gsp-brand-syncer`
 </objective>
 
 <execution_context>
@@ -53,18 +49,72 @@ Check that the brand has at least one of: `patterns/{brand-name}.yml`, `strategy
 
 Verify the project codebase has shipped output — source files with components, copy, or styles.
 
-## Step 1: Spawn syncer agent
+## Step 1: Analyze divergences
 
 ```bash
 mkdir -p {BRAND_PATH}/sync
 ```
 
-Spawn the `gsp-brand-syncer` agent with:
-- `BRAND_PATH` and all available brand files ({brand-name}.yml, strategy chunks, identity chunks, foundation chunks)
-- Project codebase location (working directory)
-- **Output path:** `{BRAND_PATH}/sync/`
+Run 4-dimension analysis directly. Read brand files first: `{BRAND_PATH}/patterns/{brand-name}.yml`, strategy chunks, identity chunks.
 
-The agent writes `SYNC-REPORT.md` with divergences across four dimensions: tokens, voice & tone, visual patterns, personality. Each divergence includes evidence (file paths, line numbers, before/after values).
+### Dimension 1: Token diff (quantitative)
+
+Grep for token values in: `tailwind.config.*` (`theme.extend`), CSS custom properties in globals/variables/theme CSS, theme/token JS/TS files, hardcoded values in components. Compare each against brand `.yml`. Classify: **Changed** (value differs), **Added** (in project, not brand), **Removed** (in brand, not project). Skip equivalents and framework defaults.
+
+### Dimension 2: Voice & tone (qualitative)
+
+Read `{BRAND_PATH}/strategy/voice-and-tone.md` for attributes and tone spectrum. Grep project for user-facing strings — headings, button labels, error states, tooltips, onboarding, meta content. Sample 10-15 representative strings. Assess each voice attribute: does copy match? Note drift direction ("more casual", "more technical"). Flag new patterns not in spec.
+
+### Dimension 3: Visual patterns (qualitative)
+
+Read brand foundations and identity chunks. Glob/Grep components for layout patterns, component styling (radius, shadow, states), color application, typography hierarchy, imagery, motion. Classify each: **Aligned**, **Evolved** (refined), **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 direction), **Stronger**. Connect evidence from dimensions 1-3.
+
+### Quality standards
+
+- Token divergences: exact values (brand vs project)
+- Voice/visual assessments: cite file:line evidence
+- Personality: connect to specific patterns from other dimensions
+- Only flag genuine divergences, not noise
+
+### Write report
+
+Write `SYNC-REPORT.md` to `{BRAND_PATH}/sync/` with this structure:
+
+```markdown
+# Brand Sync Report
+> Brand: {name} | Project: {directory} | Generated: {DATE}
+
+## Tokens
+| Token | Brand Value | Project Value | Status |
+|-------|------------|---------------|--------|
+
+**Summary:** {N} changed · {N} added · {N} removed
+
+## Voice & Tone
+### Divergences
+- **{attribute}** — {aligned|drifted|new}
+  - Brand: "{spec}" | Project: "{reality}" | Direction: {drift}
+  - Evidence: {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} — {assessment + evidence}
+- **Positioning:** {holds|shifted} — {assessment if shifted}
+
+## Update Map
+| Dimension | File to Update | Change |
+|-----------|---------------|--------|
+```
 
 ## Step 2: Present findings
 

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

@@ -2,7 +2,6 @@
 name: gsp-color
 description: "Design color systems — palettes, contrast, semantic mapping, dark mode"
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Write

package/gsp/skills/gsp-design-system/SKILL.md

@@ -2,7 +2,6 @@
 name: gsp-design-system
 description: Scan and document the existing design system state
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Write

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

@@ -2,7 +2,6 @@
 name: gsp-doctor
 description: Check project health
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Glob

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

@@ -2,7 +2,6 @@
 name: gsp-help
 description: Show all skills
 user-invocable: true
-model: sonnet
 ---
 <objective>
 Display the complete GSP skill reference as plain text.
@@ -68,7 +67,6 @@ Skill names are left-padded with 4 spaces. Descriptions start at column 27 (4 in
 
     /gsp-doctor            check project health
     /gsp-update            update GSP to latest version
-    /gsp-launch            create launch and marketing assets (optional)
 
   ─── Easter Eggs ────────────────────
 

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

@@ -2,7 +2,6 @@
 name: gsp-icons
 description: Design icon systems — library selection, sizing, containers, custom SVG direction
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Write

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

@@ -2,7 +2,6 @@
 name: gsp-logo
 description: Design logo directions — concepts, variations, usage rules, and clear space
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Write

package/gsp/skills/gsp-phase-transition/SKILL.md

@@ -2,7 +2,6 @@
 name: gsp-phase-transition
 description: "Render phase transition screens — pipeline progress, completion banner, file tree. Invoked by pipeline skills at phase completion."
 user-invocable: false
-model: sonnet
 allowed-tools:
   - Read
   - Glob
@@ -65,7 +64,6 @@ If audit phase exists (evolve mode), prepend: `audit ─── `
 
 `brief ─── research ─── design ─── critique ─── build ─── review`
 
-If launch is in scope, append: ` ─── launch`
 
 ## Step 3: Completion banner + file tree
 
@@ -116,7 +114,6 @@ If all phases in the pipeline are complete, add `  fully pretty.` after the divi
 | critique | designs critiqued |
 | build | code implemented |
 | review | implementation validated |
-| launch | campaign assets created |
 
 ## Step 4: Return
 

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

@@ -2,11 +2,10 @@
 name: gsp-pretty
 description: "Surprise ASCII art in the terminal"
 user-invocable: true
-model: sonnet
 allowed-tools:
   - Read
   - Bash
-  - Agent
+  - Write
 ---
 <context>
 Easter egg command. Instantly renders a surprise piece of ASCII/Unicode terminal art. Context-aware — riffs on what the user is working on.
@@ -19,13 +18,12 @@ Surprise the user with a piece of terminal art that's relevant to their current
 
 **Input:** None explicit — you gather context yourself
 **Output:** Rendered art in the terminal
-**Agent:** `gsp-ascii-artist`
 </objective>
 
 <process>
 ## Step 1: Gather context clues
 
-Before spawning the artist, quickly gather signal about what the user is working on. Check 2-3 of these (pick whichever are most likely to yield something interesting):
+Quickly gather signal about what the user is working on. Check 2-3 of these (pick whichever are most likely to yield something interesting):
 
 - `git log --oneline -5` — recent commit messages
 - The project's `package.json` name/description, or `README.md` first lines
@@ -33,29 +31,32 @@ Before spawning the artist, quickly gather signal about what the user is working
 - The current branch name
 - The current date/time and day of week
 
-Don't overthink it — spend 10 seconds gathering, not 10 minutes. You just need a seed for the artist.
+Don't overthink it — spend 10 seconds gathering, not 10 minutes. You just need a seed.
 
 ## Step 2: Create surprise art
 
-Spawn the `gsp-ascii-artist` agent with this prompt, filling in the context you found:
-
-> Freestyle a single piece of terminal art. Medium size (5-15 lines). Render it via `node -e` so the user sees it directly in their terminal.
->
-> **Context from the user's session:**
-> [INSERT 2-3 bullet points of what you found — project name, recent work, current date, etc.]
->
-> **Direction:** Use that context as inspiration, not as a label. Do NOT make art about GSP, branding, or the tool itself. Be witty, culturally aware, and open-minded. The art should feel like a clever aside from someone who's been watching what you're building — not a logo for it.
->
-> Some vibes to riff on (pick one or invent your own):
-> - A tiny scene with a punchline (visual wit)
-> - A metaphor for what the user is working on right now
-> - Something seasonal or timely for today's date
-> - A tribute to a classic (art, music, film, code) that connects to the context
-> - An abstract mood piece — rain, neon, space, dawn
-> - A visual one-liner that makes someone smile
-> - Something completely unexpected
->
-> IMPORTANT: Only create ONE piece. Render it with `node -e` so it displays in the terminal. Then return the console.log() code snippet so the user can reuse it.
+Read `${CLAUDE_SKILL_DIR}/../gsp-art/terminal-art.md` for the full ANSI/Unicode reference if needed.
+
+Freestyle a single piece of terminal art. Medium size (5-15 lines).
+
+**Creative direction:** Use the context as inspiration, not as a label. Do NOT make art about GSP, branding, or the tool itself. Be witty, culturally aware, and open-minded. The art should feel like a clever aside from someone who's been watching what you're building — not a logo for it.
+
+**Vibes to riff on** (pick one or invent your own):
+- A tiny scene with a punchline (visual wit)
+- A metaphor for what the user is working on right now
+- Something seasonal or timely for today's date
+- A tribute to a classic (art, music, film, code) that connects to the context
+- An abstract mood piece — rain, neon, space, dawn
+- A visual one-liner that makes someone smile
+- Something completely unexpected
+
+**Process:**
+1. Pick a technique — gradient bars, scatter/splatter, block text, box frames, shadow/depth, negative space
+2. Draft in plain text first, then add ANSI color (dim for decoration, bold for focal, cyan accents, yellow sparingly, avoid red/green)
+3. Test via `node -e` so the user sees it directly in their terminal
+4. Provide the `console.log()` code snippet so the user can reuse it
+
+**Constraints:** max 80 columns wide, max 25 lines tall, no emoji, always reset ANSI (`\x1b[0m`), readable without color, respect `NO_COLOR`.
 
 ## Step 3: Done