get-shit-pretty 0.6.3 → 0.7.0

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

@@ -30,7 +30,7 @@ Design 3 distinct logo directions for a brand.
 </objective>
 
 <execution_context>
-@${CLAUDE_SKILL_DIR}/../../references/chunk-format.md
+@${CLAUDE_SKILL_DIR}/chunk-format.md
 </execution_context>
 
 <rules>
@@ -117,7 +117,7 @@ Resolve output path:
 - Within a project: `{PROJECT_PATH}/references/logo-directions.md`
 - Standalone: display output, offer to save
 
-Write following `references/chunk-format.md` format. Target: 100-140 lines.
+Write following `chunk-format.md` format. Target: 100-140 lines.
 
 Structure:
 ```markdown

package/gsp/skills/gsp-logo/chunk-format.md

@@ -0,0 +1,79 @@
+# Chunk Format Reference
+
+Standard format for all GSP phase output files. Chunks are the primary output — agents write chunks directly, not monoliths.
+
+## File Format
+
+Every chunk follows this structure:
+
+    # {Section/Component/Screen Name}
+
+    > Phase: {phase} | Brand/Project: {name} | Generated: {DATE}
+
+    ---
+
+    {Content for this chunk}
+
+    ---
+
+    ## Related
+
+    - [{Related chunk name}]({relative-path-to-related-chunk})
+
+## Naming Conventions
+
+- **Singular, kebab-case, lowercase:** "Buttons" → `button.md`, "Date Picker" → `date-picker.md`
+- **Screen files:** `screen-{NN}-{kebab-case-name}.md` (e.g., `screen-01-home.md`)
+
+## INDEX.md Format
+
+Each phase directory gets an INDEX.md manifest:
+
+    # {Phase Name}
+    > Phase: {phase} | Brand/Project: {name} | Generated: {DATE}
+
+    | Chunk | File | ~Lines |
+    |-------|------|--------|
+    | {Section} | [{filename}](./{filename}) | ~{N} |
+
+Lightweight — just a lookup table. No prose.
+
+## Rules
+
+- **Chunks are primary output** — agents write chunks directly to the phase directory
+- **No monoliths** — do not write a single large file then re-chunk it
+- **Size target:** 50-200 lines per chunk
+- **Self-contained:** each chunk must be understandable without loading other chunks
+- **Cross-references:** `## Related` section uses relative paths to related chunks
+- **Idempotent:** re-running a phase regenerates all chunks in that phase directory
+
+## Output Budgets
+
+Context is finite. Every line in a chunk is consumed by downstream agents. Budget accordingly.
+
+### Per-chunk budgets
+
+| Chunk type | Target | Hard max | Notes |
+|-----------|--------|----------|-------|
+| Phase chunk (design, research, etc.) | 50-150 lines | 200 lines | Self-contained, one concept per chunk |
+| INDEX.md | 10-30 lines | 50 lines | Lookup table only, no prose |
+| BUILD-LOG.md | 50-100 lines | 150 lines | Summary + tables, not narrative |
+| Component spec | 30-80 lines | 120 lines | Props, states, behavior — not full implementation |
+| Screen spec | 80-150 lines | 200 lines | Layout, components, interactions, states |
+
+### Per-phase budgets (total across all chunks)
+
+| Phase | Target total | Hard max | Typical chunks |
+|-------|-------------|----------|----------------|
+| Brief | 100-200 lines | 300 lines | 2-4 |
+| Research | 200-400 lines | 600 lines | 5-8 |
+| Design | 300-600 lines | 800 lines | 6-12 |
+| Critique | 100-200 lines | 300 lines | 2-4 |
+| Build log | 50-100 lines | 150 lines | 1 |
+| Review | 100-200 lines | 300 lines | 2-4 |
+
+### Terminal output (inline skills)
+
+- **Diagnostic** (doctor, progress): uncapped — user needs to see it, does not persist in agent context
+- **Greeting/status** (start): 20-40 lines
+- **Phase transitions**: 10-20 lines

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

@@ -0,0 +1,124 @@
+---
+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
+---
+<context>
+Rendering utility invoked by pipeline skills at phase completion. Produces the visual transition — pipeline progress line, completion banner, file tree of outputs — then returns control to the calling skill for routing.
+
+The calling skill provides phase name and output directory. This skill reads STATE.md, renders the transition, and returns. The calling skill handles routing (AskUserQuestion, E2E auto-invoke, etc.) after this skill completes.
+</context>
+
+<objective>
+Render a phase transition screen showing pipeline progress, the completed phase, and output file tree.
+
+**Input:** Phase name + output directory path from the invoking skill
+**Output:** Terminal output with pipeline progress, completion banner, and file tree
+**Agent:** None — inline rendering
+</objective>
+
+<process>
+## Step 0: Parse invocation context
+
+The invoking skill provides:
+- **Phase name** — which phase just completed (e.g., "discover", "strategy", "build")
+- **Output directory** — path to the phase's output files
+
+Look up the completion message from the defaults table. If the invoking skill provided a custom message, use that instead.
+
+## Step 1: Read STATE.md
+
+Determine context by reading the brand or project STATE.md:
+- Which pipeline (branding or project)?
+- Which phases are complete?
+- Brand/project name?
+
+Use Glob to find STATE.md: `.design/branding/*/STATE.md` or `.design/projects/*/STATE.md`.
+
+## Step 2: Pipeline progress line (conditional)
+
+Show the pipeline line **only when 2+ phases are complete**. If this is the first phase completed, skip the pipeline line.
+
+### Styling
+
+- `◆` for completed phases
+- `◈` for next phase
+- `◇` for pending phases
+- `───` connecting phases
+
+```
+  {brand-or-project-name}
+  ◆ discover ─── ◆ strategy ─── ◈ identity ─── ◇ guidelines
+```
+
+### Branding phases
+
+`discover ─── strategy ─── identity ─── guidelines`
+
+If audit phase exists (evolve mode), prepend: `audit ─── `
+
+### Project phases
+
+`brief ─── research ─── design ─── critique ─── build ─── review`
+
+If launch is in scope, append: ` ─── launch`
+
+## Step 3: Completion banner + file tree
+
+```
+  ◆ {phase} complete — {completion_message}
+
+    {phase_dir}/
+    ├── {file1}.md
+    ├── {file2}.md
+    └── INDEX.md
+
+  ──────────────────────────────
+```
+
+Read the actual output directory to list real files.
+
+### File tree rules
+
+- Root is the phase directory name followed by `/`
+- Files sorted alphabetically, directories first
+- INDEX.md always listed last
+- Use `├──` for all items except the last, which uses `└──`
+- Subdirectories show their contents with `│` continuation
+
+### Final phase
+
+If all phases in the pipeline are complete, add `  fully pretty.` after the divider.
+
+## Default completion messages
+
+### Branding
+
+| Phase | Message |
+|-------|---------|
+| audit | brand assessed |
+| discover | market landscape mapped |
+| strategy | brand platform defined |
+| identity | visual system designed |
+| guidelines | design system built |
+
+### Project
+
+| Phase | Message |
+|-------|---------|
+| brief | project scoped |
+| research | patterns and approaches researched |
+| design | screens designed |
+| critique | designs critiqued |
+| build | code implemented |
+| review | implementation validated |
+| launch | campaign assets created |
+
+## Step 4: Return
+
+Return control to the calling skill. Do NOT present routing options — the calling skill owns routing.
+</process>

package/gsp/skills/gsp-project-brief/SKILL.md

@@ -130,6 +130,6 @@ Update `{PROJECT_PATH}/STATE.md`:
 
 ## Step 5: Phase transition output
 
-Render phase transition (see `references/phase-transitions.md`).
+Invoke `/gsp-phase-transition` with phase `brief` and output directory `{PROJECT_PATH}/brief/`.
 </process>
 </output>

package/gsp/skills/gsp-project-build/SKILL.md

@@ -52,6 +52,11 @@ Implement designs as production-ready code in the codebase via phased pipeline w
 @${CLAUDE_SKILL_DIR}/../../templates/phases/build.md
 </execution_context>
 
+<rules>
+- Always use `AskUserQuestion` for user interaction — never prompt via plain text
+- One decision per question — never batch multiple questions in a single message
+</rules>
+
 <process>
 ## Step 0: Resolve project and brand
 
@@ -110,9 +115,9 @@ After scaffold completes, verify `{PROJECT_PATH}/build/SCAFFOLD-LOG.md` exists.
 
 ## Step 2.5: Load build references
 
-Read these reference files (relative to skill dir `${CLAUDE_SKILL_DIR}/../../references/`):
-- `visual-effects.md`
-- `block-patterns.md`
+Read these reference files:
+- `${CLAUDE_SKILL_DIR}/visual-effects.md`
+- `${CLAUDE_SKILL_DIR}/../gsp-project-design/block-patterns.md`
 
 Hold their content for inlining into agent prompts in Steps 3 and 5.
 
@@ -126,7 +131,7 @@ Spawn `gsp-builder` agent with **execution_mode: foundations**.
 
 | File | Purpose |
 |------|---------|
-| `{BRAND_PATH}/patterns/{brand-name}.yml` | Token values only — used with `references/token-mapping.md` to generate CSS variables. Do NOT re-read patterns/constraints/effects from here — those are in STYLE.md. |
+| `{BRAND_PATH}/patterns/{brand-name}.yml` | Token values only — used with `gsp-brand-guidelines/token-mapping.md` to generate CSS variables. Do NOT re-read patterns/constraints/effects from here — those are in STYLE.md. |
 | `{BRAND_PATH}/patterns/STYLE.md` | Design law — philosophy, patterns, constraints, effects, bold bets, implementation hints (if exists; fall back to `{brand-name}.md`) |
 | `{PROJECT_PATH}/brief/target-adaptations.md` | Component adaptations for target |
 | `.design/system/STACK.md` | Stack state |
@@ -348,7 +353,7 @@ Update `{PROJECT_PATH}/STATE.md`:
 
 ### Phase transition output
 
-Render phase transition (see `references/phase-transitions.md`). Include screen count and build status in the output.
+Invoke `/gsp-phase-transition` with phase `build` and output directory `{PROJECT_PATH}/build/`.
 
 ---
 

package/gsp/skills/gsp-project-critique/SKILL.md

@@ -70,9 +70,9 @@ Read `{PROJECT_PATH}/config.json` to get `implementation_target`, `design_scope`
 
 ## Step 1.8: Load critique references
 
-Read these reference files (relative to skill dir `${CLAUDE_SKILL_DIR}/../../references/`):
-- `wcag-checklist.md`
-- `color-composition.md`
+Read these reference files:
+- `${CLAUDE_SKILL_DIR}/../gsp-accessibility-audit/wcag-checklist.md`
+- `${CLAUDE_SKILL_DIR}/../gsp-color/references/color-composition.md`
 
 Hold their content for inlining into agent prompts in Step 2.
 
@@ -92,7 +92,7 @@ Hold their content for inlining into agent prompts in Step 2.
 - **Content of** BRIEF.md
 - **Content of** color composition reference (loaded in Step 1.8)
 - Critique output template (from execution_context)
-- `references_path`: `${CLAUDE_SKILL_DIR}/../../references/` — for supplementary Read access to visual-taste.md, anti-patterns.md
+- `references_path`: `${CLAUDE_SKILL_DIR}/` — for supplementary Read access to visual-taste.md, anti-patterns.md
 - Output path: `{PROJECT_PATH}/critique/`
 
 **Agent 2: gsp-accessibility-auditor** — Check if `{PROJECT_PATH}/critique/accessibility-audit.md` already exists from a prior `/gsp-accessibility` run. If yes, skip spawning the accessibility auditor — reuse the existing output. If no, pass in the agent prompt:
@@ -166,7 +166,7 @@ If verdict is **Fail**:
 
 ## Step 6: Phase transition output
 
-Render phase transition (see `references/phase-transitions.md`). This phase has pass/fail variants — the reference covers both.
+Invoke `/gsp-phase-transition` with phase `critique` and output directory `{PROJECT_PATH}/critique/`.
 
 If critique identified brand-level issues (palette contrast, typography weight, spacing scale), note: "Some issues are brand-level — run `/gsp-brand-refine` to adjust tokens without re-running identity."
 </process>

package/gsp/{references → skills/gsp-project-critique}/visual-taste.md

@@ -110,7 +110,7 @@ Does it feel like a $150k agency build? Score 1 if it looks AI-generated or temp
 
 ## How to Use
 
-This reference is loaded by the critique agent alongside `references/nielsen-heuristics.md`. During critique:
+This reference is loaded by the critique agent alongside `nielsen-heuristics.md`. During critique:
 
 1. Score each of the 15 taste items 1-5 with specific examples from the design
 2. Calculate total and map to sophistication level

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

@@ -155,6 +155,6 @@ Update `{PROJECT_PATH}/STATE.md`:
 
 ## Step 5: Phase transition output
 
-Render phase transition (see `references/phase-transitions.md`).
+Invoke `/gsp-phase-transition` with phase `design` and output directory `{PROJECT_PATH}/design/`.
 </process>
 </output>

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

@@ -132,6 +132,6 @@ Update `{PROJECT_PATH}/STATE.md`:
 
 ## Step 4: Phase transition output
 
-Render phase transition (see `references/phase-transitions.md`).
+Invoke `/gsp-phase-transition` with phase `research` and output directory `{PROJECT_PATH}/research/`.
 </process>
 </output>

package/gsp/skills/gsp-project-review/SKILL.md

@@ -171,7 +171,7 @@ If verdict is **Fail**:
 
 ## Step 6: Phase transition output
 
-Render phase transition (see `references/phase-transitions.md`). This phase has pass/fail variants — the reference covers both.
+Invoke `/gsp-phase-transition` with phase `review` and output directory `{PROJECT_PATH}/review/`.
 
 If review identified brand-level issues (token values that don't work in context), note: "Some issues are brand-level — run `/gsp-brand-refine` to adjust tokens without re-running identity."
 </process>

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

@@ -30,7 +30,7 @@ Through a sequential one-question-at-a-time conversation, gather a complete brie
 </objective>
 
 <execution_context>
-@${CLAUDE_SKILL_DIR}/../../references/questioning.md
+@${CLAUDE_SKILL_DIR}/questioning.md
 </execution_context>
 
 <rules>

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

@@ -29,15 +29,15 @@ Apply a named style preset to produce production-ready design tokens and foundat
 
 <execution_context>
 @${CLAUDE_SKILL_DIR}/styles/INDEX.yml
-@${CLAUDE_SKILL_DIR}/../../references/design-tokens.md
-@${CLAUDE_SKILL_DIR}/../../references/chunk-format.md
+@${CLAUDE_SKILL_DIR}/../gsp-brand-guidelines/design-tokens.md
+@${CLAUDE_SKILL_DIR}/chunk-format.md
 @${CLAUDE_SKILL_DIR}/../../templates/phases/patterns.md
 </execution_context>
 
 <rules>
 - Always use `AskUserQuestion` for user interaction — never prompt via plain text
 - One decision per question — never batch multiple questions in a single message
-- Token values in `.yml` presets follow W3C Design Tokens format from `references/design-tokens.md`
+- Token values in `.yml` presets follow W3C Design Tokens format from `gsp-brand-guidelines/design-tokens.md`
 - When mixing styles, later style values override earlier ones (last-wins precedence)
 - Never mix clashing styles — check the compatibility matrix first
 </rules>
@@ -128,7 +128,7 @@ Copy the preset `.yml` to the output path as the brand's style source:
 
 If a `.yml` already exists at the output path, use `AskUserQuestion`: "A style preset already exists — overwrite?" with options **Overwrite** and **Cancel**. If cancelled, skip and proceed.
 
-The `.yml` IS the token source of truth — no separate `tokens.json` needed. The builder generates CSS variables from it at build time using `references/token-mapping.md`.
+The `.yml` IS the token source of truth — no separate `tokens.json` needed. The builder generates CSS variables from it at build time using `gsp-brand-guidelines/token-mapping.md`.
 
 ## Step 7: Write STYLE.md
 

package/gsp/skills/gsp-style/chunk-format.md

@@ -0,0 +1,79 @@
+# Chunk Format Reference
+
+Standard format for all GSP phase output files. Chunks are the primary output — agents write chunks directly, not monoliths.
+
+## File Format
+
+Every chunk follows this structure:
+
+    # {Section/Component/Screen Name}
+
+    > Phase: {phase} | Brand/Project: {name} | Generated: {DATE}
+
+    ---
+
+    {Content for this chunk}
+
+    ---
+
+    ## Related
+
+    - [{Related chunk name}]({relative-path-to-related-chunk})
+
+## Naming Conventions
+
+- **Singular, kebab-case, lowercase:** "Buttons" → `button.md`, "Date Picker" → `date-picker.md`
+- **Screen files:** `screen-{NN}-{kebab-case-name}.md` (e.g., `screen-01-home.md`)
+
+## INDEX.md Format
+
+Each phase directory gets an INDEX.md manifest:
+
+    # {Phase Name}
+    > Phase: {phase} | Brand/Project: {name} | Generated: {DATE}
+
+    | Chunk | File | ~Lines |
+    |-------|------|--------|
+    | {Section} | [{filename}](./{filename}) | ~{N} |
+
+Lightweight — just a lookup table. No prose.
+
+## Rules
+
+- **Chunks are primary output** — agents write chunks directly to the phase directory
+- **No monoliths** — do not write a single large file then re-chunk it
+- **Size target:** 50-200 lines per chunk
+- **Self-contained:** each chunk must be understandable without loading other chunks
+- **Cross-references:** `## Related` section uses relative paths to related chunks
+- **Idempotent:** re-running a phase regenerates all chunks in that phase directory
+
+## Output Budgets
+
+Context is finite. Every line in a chunk is consumed by downstream agents. Budget accordingly.
+
+### Per-chunk budgets
+
+| Chunk type | Target | Hard max | Notes |
+|-----------|--------|----------|-------|
+| Phase chunk (design, research, etc.) | 50-150 lines | 200 lines | Self-contained, one concept per chunk |
+| INDEX.md | 10-30 lines | 50 lines | Lookup table only, no prose |
+| BUILD-LOG.md | 50-100 lines | 150 lines | Summary + tables, not narrative |
+| Component spec | 30-80 lines | 120 lines | Props, states, behavior — not full implementation |
+| Screen spec | 80-150 lines | 200 lines | Layout, components, interactions, states |
+
+### Per-phase budgets (total across all chunks)
+
+| Phase | Target total | Hard max | Typical chunks |
+|-------|-------------|----------|----------------|
+| Brief | 100-200 lines | 300 lines | 2-4 |
+| Research | 200-400 lines | 600 lines | 5-8 |
+| Design | 300-600 lines | 800 lines | 6-12 |
+| Critique | 100-200 lines | 300 lines | 2-4 |
+| Build log | 50-100 lines | 150 lines | 1 |
+| Review | 100-200 lines | 300 lines | 2-4 |
+
+### Terminal output (inline skills)
+
+- **Diagnostic** (doctor, progress): uncapped — user needs to see it, does not persist in agent context
+- **Greeting/status** (start): 20-40 lines
+- **Phase transitions**: 10-20 lines

package/gsp/skills/gsp-style/style-preset-schema.md

@@ -0,0 +1,124 @@
+# Style Preset YAML Schema
+
+Template for brand-derived style preset files (`{brand-name}.yml`). All token values must trace to foundation chunks. See any preset in `styles/` for a complete example.
+
+```yaml
+name: {brand-slug}
+description: {one-line brand aesthetic summary}
+tags: [5-8 fuzzy-match tags for style discovery]
+source: brand  # marks this as brand-derived, not a GSP preset
+
+tokens:
+  color:
+    primary: "{hex}"        # from identity/color-system.md
+    secondary: "{hex}"
+    accent: "{hex}"
+    background: "{hex}"
+    surface: "{hex}"
+    on-primary: "{hex}"
+    on-background: "{hex}"
+    error: "{hex}"
+    success: "{hex}"
+    warning: "{hex}"
+    info: "{hex}"
+    muted: "{hex}"
+
+  typography:
+    font-family-primary: "{font stack}"  # from identity/typography.md
+    font-family-mono: "{font stack}"
+    font-weight-heading: {number}
+    font-weight-body: {number}
+    font-size-base: "{px}"
+    line-height-base: {number}
+
+  shape:
+    border-radius-sm: "{px}"  # from patterns/component specs
+    border-radius-md: "{px}"
+    border-radius-lg: "{px}"
+    border-width: "{px}"
+    border-color: "{hex}"
+
+  elevation:
+    shadow-sm: "{value}"
+    shadow-md: "{value}"
+    shadow-lg: "{value}"
+    shadow-xl: "{value}"
+
+  spacing:
+    base: {number}
+    scale: [{values}]
+
+  motion:
+    duration-fast: "{ms}"
+    duration-normal: "{ms}"
+    easing: "{value}"
+
+dark_mode:
+  color:
+    background: "{hex}"
+    surface: "{hex}"
+    on-background: "{hex}"
+    border-color: "{hex}"
+    muted: "{hex}"
+
+intensity:
+  variance: {1-10}    # layout creativity — 1=strict grid, 10=experimental
+  motion: {1-10}      # animation energy — 1=instant/none, 10=cinematic
+  density: {1-10}     # content packing — 1=airy/spacious, 10=dense/compact
+
+patterns:
+  card:
+    border: "{spec}"
+    shadow: "{spec}"
+    radius: "{spec}"
+    background: "{spec}"
+    padding: "{spec}"
+  button-primary:
+    background: "{spec}"
+    border: "{spec}"
+    text: "{spec}"
+    radius: "{spec}"
+  button-secondary:
+    background: "{spec}"
+    border: "{spec}"
+    text: "{spec}"
+    radius: "{spec}"
+  input:
+    border: "{spec}"
+    radius: "{spec}"
+    background: "{spec}"
+    focus: "{spec}"
+  badge:
+    shape: "{spec}"
+    text: "{spec}"
+  nav:
+    style: "{spec}"
+    links: "{spec}"
+  layout:
+    archetype: "{name}"  # centered, asymmetric-grid, sidebar, dashboard, editorial
+    max-width: "{class}"
+    section-spacing: "{spec}"
+    grid-gap: "{spec}"
+    surfaces: "{spec}"   # background treatments (grid, dots, gradient, clean)
+    decoration: "{spec}" # decorative elements (shapes, lines, labels)
+
+constraints:
+  never:
+    - "{thing to never do — hard boundary}"
+  always:
+    - "{thing to always do — non-negotiable}"
+
+effects:
+  interaction-vocabulary: [{named-techniques}]
+  hover:
+    card: "{technique + spec}"
+    button: "{technique + spec}"
+  active:
+    button: "{technique + spec}"
+  focus:
+    general: "{technique + spec}"
+  transition: "{duration + easing spec}"
+
+compatibility: []  # leave empty for brand styles
+clashes: []        # leave empty for brand styles
+```