gstack/scripts/gen-skill-docs.ts

#!/usr/bin/env bun
/**
 * Generate SKILL.md files from .tmpl templates.
 *
 * Pipeline:
 *   read .tmpl → find {{PLACEHOLDERS}} → resolve from source → format → write .md
 *
 * Supports --dry-run: generate to memory, exit 1 if different from committed file.
 * Used by skill:check and CI freshness checks.
 */

import { COMMAND_DESCRIPTIONS } from '../browse/src/commands';
import { SNAPSHOT_FLAGS } from '../browse/src/snapshot';
import * as fs from 'fs';
import * as path from 'path';

const ROOT = path.resolve(import.meta.dir, '..');
const DRY_RUN = process.argv.includes('--dry-run');

// ─── Placeholder Resolvers ──────────────────────────────────

function generateCommandReference(): string {
  // Group commands by category
  const groups = new Map<string, Array<{ command: string; description: string; usage?: string }>>();
  for (const [cmd, meta] of Object.entries(COMMAND_DESCRIPTIONS)) {
    const list = groups.get(meta.category) || [];
    list.push({ command: cmd, description: meta.description, usage: meta.usage });
    groups.set(meta.category, list);
  }

  // Category display order
  const categoryOrder = [
    'Navigation', 'Reading', 'Interaction', 'Inspection',
    'Visual', 'Snapshot', 'Meta', 'Tabs', 'Server',
  ];

  const sections: string[] = [];
  for (const category of categoryOrder) {
    const commands = groups.get(category);
    if (!commands || commands.length === 0) continue;

    // Sort alphabetically within category
    commands.sort((a, b) => a.command.localeCompare(b.command));

    sections.push(`### ${category}`);
    sections.push('| Command | Description |');
    sections.push('|---------|-------------|');
    for (const cmd of commands) {
      const display = cmd.usage ? `\`${cmd.usage}\`` : `\`${cmd.command}\``;
      sections.push(`| ${display} | ${cmd.description} |`);
    }
    sections.push('');
  }

  return sections.join('\n').trimEnd();
}

function generateSnapshotFlags(): string {
  const lines: string[] = [
    'The snapshot is your primary tool for understanding and interacting with pages.',
    '',
    '```',
  ];

  for (const flag of SNAPSHOT_FLAGS) {
    const label = flag.valueHint ? `${flag.short} ${flag.valueHint}` : flag.short;
    lines.push(`${label.padEnd(10)}${flag.long.padEnd(24)}${flag.description}`);
  }

  lines.push('```');
  lines.push('');
  lines.push('All flags can be combined freely. `-o` only applies when `-a` is also used.');
  lines.push('Example: `$B snapshot -i -a -C -o /tmp/annotated.png`');
  lines.push('');
  lines.push('**Ref numbering:** @e refs are assigned sequentially (@e1, @e2, ...) in tree order.');
  lines.push('@c refs from `-C` are numbered separately (@c1, @c2, ...).');
  lines.push('');
  lines.push('After snapshot, use @refs as selectors in any command:');
  lines.push('```bash');
  lines.push('$B click @e3       $B fill @e4 "value"     $B hover @e1');
  lines.push('$B html @e2        $B css @e5 "color"      $B attrs @e6');
  lines.push('$B click @c1       # cursor-interactive ref (from -C)');
  lines.push('```');
  lines.push('');
  lines.push('**Output format:** indented accessibility tree with @ref IDs, one element per line.');
  lines.push('```');
  lines.push('  @e1 [heading] "Welcome" [level=1]');
  lines.push('  @e2 [textbox] "Email"');
  lines.push('  @e3 [button] "Submit"');
  lines.push('```');
  lines.push('');
  lines.push('Refs are invalidated on navigation — run `snapshot` again after `goto`.');

  return lines.join('\n');
}

function generatePreamble(): string {
  return `## Preamble (run first)

\`\`\`bash
_UPD=$(~/.claude/skills/gstack/bin/gstack-update-check 2>/dev/null || .claude/skills/gstack/bin/gstack-update-check 2>/dev/null || true)
[ -n "$_UPD" ] && echo "$_UPD" || true
mkdir -p ~/.gstack/sessions
touch ~/.gstack/sessions/"$PPID"
_SESSIONS=$(find ~/.gstack/sessions -mmin -120 -type f 2>/dev/null | wc -l | tr -d ' ')
find ~/.gstack/sessions -mmin +120 -type f -delete 2>/dev/null || true
_CONTRIB=$(~/.claude/skills/gstack/bin/gstack-config get gstack_contributor 2>/dev/null || true)
\`\`\`

If output shows \`UPGRADE_AVAILABLE <old> <new>\`: read \`~/.claude/skills/gstack/gstack-upgrade/SKILL.md\` and follow the "Inline upgrade flow" (auto-upgrade if configured, otherwise AskUserQuestion with 4 options, write snooze state if declined). If \`JUST_UPGRADED <from> <to>\`: tell user "Running gstack v{to} (just updated!)" and continue.

## AskUserQuestion Format

**ALWAYS follow this structure for every AskUserQuestion call:**
1. Context: project name, current branch, what we're working on (1-2 sentences)
2. The specific question or decision point
3. \`RECOMMENDATION: Choose [X] because [one-line reason]\`
4. Lettered options: \`A) ... B) ... C) ...\`

If \`_SESSIONS\` is 3 or more: the user is juggling multiple gstack sessions and context-switching heavily. **ELI16 mode** — they may not remember what this conversation is about. Every AskUserQuestion MUST re-ground them: state the project, the branch, the current plan/task, then the specific problem, THEN the recommendation and options. Be extra clear and self-contained — assume they haven't looked at this window in 20 minutes.

Per-skill instructions may add additional formatting rules on top of this baseline.

## Contributor Mode

If \`_CONTRIB\` is \`true\`: you are in **contributor mode**. When you hit friction with **gstack itself** (not the user's app), file a field report. Think: "hey, I was trying to do X with gstack and it didn't work / was confusing / was annoying. Here's what happened."

**gstack issues:** browse command fails/wrong output, snapshot missing elements, skill instructions unclear or misleading, binary crash/hang, unhelpful error message, any rough edge or annoyance — even minor stuff.
**NOT gstack issues:** user's app bugs, network errors to user's URL, auth failures on user's site.

**To file:** write \`~/.gstack/contributor-logs/{slug}.md\` with this structure:

\`\`\`
# {Title}

Hey gstack team — ran into this while using /{skill-name}:

**What I was trying to do:** {what the user/agent was attempting}
**What happened instead:** {what actually happened}
**How annoying (1-5):** {1=meh, 3=friction, 5=blocker}

## Steps to reproduce
1. {step}

## Raw output
(wrap any error messages or unexpected output in a markdown code block)

**Date:** {YYYY-MM-DD} | **Version:** {gstack version} | **Skill:** /{skill}
\`\`\`

Then run: \`mkdir -p ~/.gstack/contributor-logs && open ~/.gstack/contributor-logs/{slug}.md\`

Slug: lowercase, hyphens, max 60 chars (e.g. \`browse-snapshot-ref-gap\`). Skip if file already exists. Max 3 reports per session. File inline and continue — don't stop the workflow. Tell user: "Filed gstack field report: {title}"`;
}

function generateBrowseSetup(): string {
  return `## SETUP (run this check BEFORE any browse command)

\`\`\`bash
_ROOT=$(git rev-parse --show-toplevel 2>/dev/null)
B=""
[ -n "$_ROOT" ] && [ -x "$_ROOT/.claude/skills/gstack/browse/dist/browse" ] && B="$_ROOT/.claude/skills/gstack/browse/dist/browse"
[ -z "$B" ] && B=~/.claude/skills/gstack/browse/dist/browse
if [ -x "$B" ]; then
  echo "READY: $B"
else
  echo "NEEDS_SETUP"
fi
\`\`\`

If \`NEEDS_SETUP\`:
1. Tell the user: "gstack browse needs a one-time build (~10 seconds). OK to proceed?" Then STOP and wait.
2. Run: \`cd <SKILL_DIR> && ./setup\`
3. If \`bun\` is not installed: \`curl -fsSL https://bun.sh/install | bash\``;
}

function generateQAMethodology(): string {
  return `## Modes

### Diff-aware (automatic when on a feature branch with no URL)

This is the **primary mode** for developers verifying their work. When the user says \`/qa\` without a URL and the repo is on a feature branch, automatically:

1. **Analyze the branch diff** to understand what changed:
   \`\`\`bash
   git diff main...HEAD --name-only
   git log main..HEAD --oneline
   \`\`\`

2. **Identify affected pages/routes** from the changed files:
   - Controller/route files → which URL paths they serve
   - View/template/component files → which pages render them
   - Model/service files → which pages use those models (check controllers that reference them)
   - CSS/style files → which pages include those stylesheets
   - API endpoints → test them directly with \`$B js "await fetch('/api/...')"\`
   - Static pages (markdown, HTML) → navigate to them directly

3. **Detect the running app** — check common local dev ports:
   \`\`\`bash
   $B goto http://localhost:3000 2>/dev/null && echo "Found app on :3000" || \\
   $B goto http://localhost:4000 2>/dev/null && echo "Found app on :4000" || \\
   $B goto http://localhost:8080 2>/dev/null && echo "Found app on :8080"
   \`\`\`
   If no local app is found, check for a staging/preview URL in the PR or environment. If nothing works, ask the user for the URL.

4. **Test each affected page/route:**
   - Navigate to the page
   - Take a screenshot
   - Check console for errors
   - If the change was interactive (forms, buttons, flows), test the interaction end-to-end
   - Use \`snapshot -D\` before and after actions to verify the change had the expected effect

5. **Cross-reference with commit messages and PR description** to understand *intent* — what should the change do? Verify it actually does that.

6. **Check TODOS.md** (if it exists) for known bugs or issues related to the changed files. If a TODO describes a bug that this branch should fix, add it to your test plan. If you find a new bug during QA that isn't in TODOS.md, note it in the report.

7. **Report findings** scoped to the branch changes:
   - "Changes tested: N pages/routes affected by this branch"
   - For each: does it work? Screenshot evidence.
   - Any regressions on adjacent pages?

**If the user provides a URL with diff-aware mode:** Use that URL as the base but still scope testing to the changed files.

### Full (default when URL is provided)
Systematic exploration. Visit every reachable page. Document 5-10 well-evidenced issues. Produce health score. Takes 5-15 minutes depending on app size.

### Quick (\`--quick\`)
30-second smoke test. Visit homepage + top 5 navigation targets. Check: page loads? Console errors? Broken links? Produce health score. No detailed issue documentation.

### Regression (\`--regression <baseline>\`)
Run full mode, then load \`baseline.json\` from a previous run. Diff: which issues are fixed? Which are new? What's the score delta? Append regression section to report.

---

## Workflow

### Phase 1: Initialize

1. Find browse binary (see Setup above)
2. Create output directories
3. Copy report template from \`qa/templates/qa-report-template.md\` to output dir
4. Start timer for duration tracking

### Phase 2: Authenticate (if needed)

**If the user specified auth credentials:**

\`\`\`bash
$B goto <login-url>
$B snapshot -i                    # find the login form
$B fill @e3 "user@example.com"
$B fill @e4 "[REDACTED]"         # NEVER include real passwords in report
$B click @e5                      # submit
$B snapshot -D                    # verify login succeeded
\`\`\`

**If the user provided a cookie file:**

\`\`\`bash
$B cookie-import cookies.json
$B goto <target-url>
\`\`\`

**If 2FA/OTP is required:** Ask the user for the code and wait.

**If CAPTCHA blocks you:** Tell the user: "Please complete the CAPTCHA in the browser, then tell me to continue."

### Phase 3: Orient

Get a map of the application:

\`\`\`bash
$B goto <target-url>
$B snapshot -i -a -o "$REPORT_DIR/screenshots/initial.png"
$B links                          # map navigation structure
$B console --errors               # any errors on landing?
\`\`\`

**Detect framework** (note in report metadata):
- \`__next\` in HTML or \`_next/data\` requests → Next.js
- \`csrf-token\` meta tag → Rails
- \`wp-content\` in URLs → WordPress
- Client-side routing with no page reloads → SPA

**For SPAs:** The \`links\` command may return few results because navigation is client-side. Use \`snapshot -i\` to find nav elements (buttons, menu items) instead.

### Phase 4: Explore

Visit pages systematically. At each page:

\`\`\`bash
$B goto <page-url>
$B snapshot -i -a -o "$REPORT_DIR/screenshots/page-name.png"
$B console --errors
\`\`\`

Then follow the **per-page exploration checklist** (see \`qa/references/issue-taxonomy.md\`):

1. **Visual scan** — Look at the annotated screenshot for layout issues
2. **Interactive elements** — Click buttons, links, controls. Do they work?
3. **Forms** — Fill and submit. Test empty, invalid, edge cases
4. **Navigation** — Check all paths in and out
5. **States** — Empty state, loading, error, overflow
6. **Console** — Any new JS errors after interactions?
7. **Responsiveness** — Check mobile viewport if relevant:
   \`\`\`bash
   $B viewport 375x812
   $B screenshot "$REPORT_DIR/screenshots/page-mobile.png"
   $B viewport 1280x720
   \`\`\`

**Depth judgment:** Spend more time on core features (homepage, dashboard, checkout, search) and less on secondary pages (about, terms, privacy).

**Quick mode:** Only visit homepage + top 5 navigation targets from the Orient phase. Skip the per-page checklist — just check: loads? Console errors? Broken links visible?

### Phase 5: Document

Document each issue **immediately when found** — don't batch them.

**Two evidence tiers:**

**Interactive bugs** (broken flows, dead buttons, form failures):
1. Take a screenshot before the action
2. Perform the action
3. Take a screenshot showing the result
4. Use \`snapshot -D\` to show what changed
5. Write repro steps referencing screenshots

\`\`\`bash
$B screenshot "$REPORT_DIR/screenshots/issue-001-step-1.png"
$B click @e5
$B screenshot "$REPORT_DIR/screenshots/issue-001-result.png"
$B snapshot -D
\`\`\`

**Static bugs** (typos, layout issues, missing images):
1. Take a single annotated screenshot showing the problem
2. Describe what's wrong

\`\`\`bash
$B snapshot -i -a -o "$REPORT_DIR/screenshots/issue-002.png"
\`\`\`

**Write each issue to the report immediately** using the template format from \`qa/templates/qa-report-template.md\`.

### Phase 6: Wrap Up

1. **Compute health score** using the rubric below
2. **Write "Top 3 Things to Fix"** — the 3 highest-severity issues
3. **Write console health summary** — aggregate all console errors seen across pages
4. **Update severity counts** in the summary table
5. **Fill in report metadata** — date, duration, pages visited, screenshot count, framework
6. **Save baseline** — write \`baseline.json\` with:
   \`\`\`json
   {
     "date": "YYYY-MM-DD",
     "url": "<target>",
     "healthScore": N,
     "issues": [{ "id": "ISSUE-001", "title": "...", "severity": "...", "category": "..." }],
     "categoryScores": { "console": N, "links": N, ... }
   }
   \`\`\`

**Regression mode:** After writing the report, load the baseline file. Compare:
- Health score delta
- Issues fixed (in baseline but not current)
- New issues (in current but not baseline)
- Append the regression section to the report

---

## Health Score Rubric

Compute each category score (0-100), then take the weighted average.

### Console (weight: 15%)
- 0 errors → 100
- 1-3 errors → 70
- 4-10 errors → 40
- 10+ errors → 10

### Links (weight: 10%)
- 0 broken → 100
- Each broken link → -15 (minimum 0)

### Per-Category Scoring (Visual, Functional, UX, Content, Performance, Accessibility)
Each category starts at 100. Deduct per finding:
- Critical issue → -25
- High issue → -15
- Medium issue → -8
- Low issue → -3
Minimum 0 per category.

### Weights
| Category | Weight |
|----------|--------|
| Console | 15% |
| Links | 10% |
| Visual | 10% |
| Functional | 20% |
| UX | 15% |
| Performance | 10% |
| Content | 5% |
| Accessibility | 15% |

### Final Score
\`score = Σ (category_score × weight)\`

---

## Framework-Specific Guidance

### Next.js
- Check console for hydration errors (\`Hydration failed\`, \`Text content did not match\`)
- Monitor \`_next/data\` requests in network — 404s indicate broken data fetching
- Test client-side navigation (click links, don't just \`goto\`) — catches routing issues
- Check for CLS (Cumulative Layout Shift) on pages with dynamic content

### Rails
- Check for N+1 query warnings in console (if development mode)
- Verify CSRF token presence in forms
- Test Turbo/Stimulus integration — do page transitions work smoothly?
- Check for flash messages appearing and dismissing correctly

### WordPress
- Check for plugin conflicts (JS errors from different plugins)
- Verify admin bar visibility for logged-in users
- Test REST API endpoints (\`/wp-json/\`)
- Check for mixed content warnings (common with WP)

### General SPA (React, Vue, Angular)
- Use \`snapshot -i\` for navigation — \`links\` command misses client-side routes
- Check for stale state (navigate away and back — does data refresh?)
- Test browser back/forward — does the app handle history correctly?
- Check for memory leaks (monitor console after extended use)

---

## Important Rules

1. **Repro is everything.** Every issue needs at least one screenshot. No exceptions.
2. **Verify before documenting.** Retry the issue once to confirm it's reproducible, not a fluke.
3. **Never include credentials.** Write \`[REDACTED]\` for passwords in repro steps.
4. **Write incrementally.** Append each issue to the report as you find it. Don't batch.
5. **Never read source code.** Test as a user, not a developer.
6. **Check console after every interaction.** JS errors that don't surface visually are still bugs.
7. **Test like a user.** Use realistic data. Walk through complete workflows end-to-end.
8. **Depth over breadth.** 5-10 well-documented issues with evidence > 20 vague descriptions.
9. **Never delete output files.** Screenshots and reports accumulate — that's intentional.
10. **Use \`snapshot -C\` for tricky UIs.** Finds clickable divs that the accessibility tree misses.`;
}

function generateDesignMethodology(): string {
  return `## Modes

### Full (default)
Systematic review of all pages reachable from homepage. Visit 5-8 pages. Full checklist evaluation, responsive screenshots, interaction flow testing. Produces complete design audit report with letter grades.

### Quick (\`--quick\`)
Homepage + 2 key pages only. First Impression + Design System Extraction + abbreviated checklist. Fastest path to a design score.

### Deep (\`--deep\`)
Comprehensive review: 10-15 pages, every interaction flow, exhaustive checklist. For pre-launch audits or major redesigns.

### Diff-aware (automatic when on a feature branch with no URL)
When on a feature branch, scope to pages affected by the branch changes:
1. Analyze the branch diff: \`git diff main...HEAD --name-only\`
2. Map changed files to affected pages/routes
3. Detect running app on common local ports (3000, 4000, 8080)
4. Audit only affected pages, compare design quality before/after

### Regression (\`--regression\` or previous \`design-baseline.json\` found)
Run full audit, then load previous \`design-baseline.json\`. Compare: per-category grade deltas, new findings, resolved findings. Output regression table in report.

---

## Phase 1: First Impression

The most uniquely designer-like output. Form a gut reaction before analyzing anything.

1. Navigate to the target URL
2. Take a full-page desktop screenshot: \`$B screenshot "$REPORT_DIR/screenshots/first-impression.png"\`
3. Write the **First Impression** using this structured critique format:
   - "The site communicates **[what]**." (what it says at a glance — competence? playfulness? confusion?)
   - "I notice **[observation]**." (what stands out, positive or negative — be specific)
   - "The first 3 things my eye goes to are: **[1]**, **[2]**, **[3]**." (hierarchy check — are these intentional?)
   - "If I had to describe this in one word: **[word]**." (gut verdict)

This is the section users read first. Be opinionated. A designer doesn't hedge — they react.

---

## Phase 2: Design System Extraction

Extract the actual design system the site uses (not what a DESIGN.md says, but what's rendered):

\`\`\`bash
# Fonts in use (capped at 500 elements to avoid timeout)
$B js "JSON.stringify([...new Set([...document.querySelectorAll('*')].slice(0,500).map(e => getComputedStyle(e).fontFamily))])"

# Color palette in use
$B js "JSON.stringify([...new Set([...document.querySelectorAll('*')].slice(0,500).flatMap(e => [getComputedStyle(e).color, getComputedStyle(e).backgroundColor]).filter(c => c !== 'rgba(0, 0, 0, 0)'))])"

# Heading hierarchy
$B js "JSON.stringify([...document.querySelectorAll('h1,h2,h3,h4,h5,h6')].map(h => ({tag:h.tagName, text:h.textContent.trim().slice(0,50), size:getComputedStyle(h).fontSize, weight:getComputedStyle(h).fontWeight})))"

# Touch target audit (find undersized interactive elements)
$B js "JSON.stringify([...document.querySelectorAll('a,button,input,[role=button]')].filter(e => {const r=e.getBoundingClientRect(); return r.width>0 && (r.width<44||r.height<44)}).map(e => ({tag:e.tagName, text:(e.textContent||'').trim().slice(0,30), w:Math.round(e.getBoundingClientRect().width), h:Math.round(e.getBoundingClientRect().height)})).slice(0,20))"

# Performance baseline
$B perf
\`\`\`

Structure findings as an **Inferred Design System**:
- **Fonts:** list with usage counts. Flag if >3 distinct font families.
- **Colors:** palette extracted. Flag if >12 unique non-gray colors. Note warm/cool/mixed.
- **Heading Scale:** h1-h6 sizes. Flag skipped levels, non-systematic size jumps.
- **Spacing Patterns:** sample padding/margin values. Flag non-scale values.

After extraction, offer: *"Want me to save this as your DESIGN.md? I can lock in these observations as your project's design system baseline."*

---

## Phase 3: Page-by-Page Visual Audit

For each page in scope:

\`\`\`bash
$B goto <url>
$B snapshot -i -a -o "$REPORT_DIR/screenshots/{page}-annotated.png"
$B responsive "$REPORT_DIR/screenshots/{page}"
$B console --errors
$B perf
\`\`\`

### Auth Detection

After the first navigation, check if the URL changed to a login-like path:
\`\`\`bash
$B url
\`\`\`
If URL contains \`/login\`, \`/signin\`, \`/auth\`, or \`/sso\`: the site requires authentication. AskUserQuestion: "This site requires authentication. Want to import cookies from your browser? Run \`/setup-browser-cookies\` first if needed."

### Design Audit Checklist (10 categories, ~80 items)

Apply these at each page. Each finding gets an impact rating (high/medium/polish) and category.

**1. Visual Hierarchy & Composition** (8 items)
- Clear focal point? One primary CTA per view?
- Eye flows naturally top-left to bottom-right?
- Visual noise — competing elements fighting for attention?
- Information density appropriate for content type?
- Z-index clarity — nothing unexpectedly overlapping?
- Above-the-fold content communicates purpose in 3 seconds?
- Squint test: hierarchy still visible when blurred?
- White space is intentional, not leftover?

**2. Typography** (15 items)
- Font count <=3 (flag if more)
- Scale follows ratio (1.25 major third or 1.333 perfect fourth)
- Line-height: 1.5x body, 1.15-1.25x headings
- Measure: 45-75 chars per line (66 ideal)
- Heading hierarchy: no skipped levels (h1→h3 without h2)
- Weight contrast: >=2 weights used for hierarchy
- No blacklisted fonts (Papyrus, Comic Sans, Lobster, Impact, Jokerman)
- If primary font is Inter/Roboto/Open Sans/Poppins → flag as potentially generic
- \`text-wrap: balance\` or \`text-pretty\` on headings (check via \`$B css <heading> text-wrap\`)
- Curly quotes used, not straight quotes
- Ellipsis character (\`…\`) not three dots (\`...\`)
- \`font-variant-numeric: tabular-nums\` on number columns
- Body text >= 16px
- Caption/label >= 12px
- No letterspacing on lowercase text

**3. Color & Contrast** (10 items)
- Palette coherent (<=12 unique non-gray colors)
- WCAG AA: body text 4.5:1, large text (18px+) 3:1, UI components 3:1
- Semantic colors consistent (success=green, error=red, warning=yellow/amber)
- No color-only encoding (always add labels, icons, or patterns)
- Dark mode: surfaces use elevation, not just lightness inversion
- Dark mode: text off-white (~#E0E0E0), not pure white
- Primary accent desaturated 10-20% in dark mode
- \`color-scheme: dark\` on html element (if dark mode present)
- No red/green only combinations (8% of men have red-green deficiency)
- Neutral palette is warm or cool consistently — not mixed

**4. Spacing & Layout** (12 items)
- Grid consistent at all breakpoints
- Spacing uses a scale (4px or 8px base), not arbitrary values
- Alignment is consistent — nothing floats outside the grid
- Rhythm: related items closer together, distinct sections further apart
- Border-radius hierarchy (not uniform bubbly radius on everything)
- Inner radius = outer radius - gap (nested elements)
- No horizontal scroll on mobile
- Max content width set (no full-bleed body text)
- \`env(safe-area-inset-*)\` for notch devices
- URL reflects state (filters, tabs, pagination in query params)
- Flex/grid used for layout (not JS measurement)
- Breakpoints: mobile (375), tablet (768), desktop (1024), wide (1440)

**5. Interaction States** (10 items)
- Hover state on all interactive elements
- \`focus-visible\` ring present (never \`outline: none\` without replacement)
- Active/pressed state with depth effect or color shift
- Disabled state: reduced opacity + \`cursor: not-allowed\`
- Loading: skeleton shapes match real content layout
- Empty states: warm message + primary action + visual (not just "No items.")
- Error messages: specific + include fix/next step
- Success: confirmation animation or color, auto-dismiss
- Touch targets >= 44px on all interactive elements
- \`cursor: pointer\` on all clickable elements

**6. Responsive Design** (8 items)
- Mobile layout makes *design* sense (not just stacked desktop columns)
- Touch targets sufficient on mobile (>= 44px)
- No horizontal scroll on any viewport
- Images handle responsive (srcset, sizes, or CSS containment)
- Text readable without zooming on mobile (>= 16px body)
- Navigation collapses appropriately (hamburger, bottom nav, etc.)
- Forms usable on mobile (correct input types, no autoFocus on mobile)
- No \`user-scalable=no\` or \`maximum-scale=1\` in viewport meta

**7. Motion & Animation** (6 items)
- Easing: ease-out for entering, ease-in for exiting, ease-in-out for moving
- Duration: 50-700ms range (nothing slower unless page transition)
- Purpose: every animation communicates something (state change, attention, spatial relationship)
- \`prefers-reduced-motion\` respected (check: \`$B js "matchMedia('(prefers-reduced-motion: reduce)').matches"\`)
- No \`transition: all\` — properties listed explicitly
- Only \`transform\` and \`opacity\` animated (not layout properties like width, height, top, left)

**8. Content & Microcopy** (8 items)
- Empty states designed with warmth (message + action + illustration/icon)
- Error messages specific: what happened + why + what to do next
- Button labels specific ("Save API Key" not "Continue" or "Submit")
- No placeholder/lorem ipsum text visible in production
- Truncation handled (\`text-overflow: ellipsis\`, \`line-clamp\`, or \`break-words\`)
- Active voice ("Install the CLI" not "The CLI will be installed")
- Loading states end with \`…\` ("Saving…" not "Saving...")
- Destructive actions have confirmation modal or undo window

**9. AI Slop Detection** (10 anti-patterns — the blacklist)

The test: would a human designer at a respected studio ever ship this?

- Purple/violet/indigo gradient backgrounds or blue-to-purple color schemes
- **The 3-column feature grid:** icon-in-colored-circle + bold title + 2-line description, repeated 3x symmetrically. THE most recognizable AI layout.
- Icons in colored circles as section decoration (SaaS starter template look)
- Centered everything (\`text-align: center\` on all headings, descriptions, cards)
- Uniform bubbly border-radius on every element (same large radius on everything)
- Decorative blobs, floating circles, wavy SVG dividers (if a section feels empty, it needs better content, not decoration)
- Emoji as design elements (rockets in headings, emoji as bullet points)
- Colored left-border on cards (\`border-left: 3px solid <accent>\`)
- Generic hero copy ("Welcome to [X]", "Unlock the power of...", "Your all-in-one solution for...")
- Cookie-cutter section rhythm (hero → 3 features → testimonials → pricing → CTA, every section same height)

**10. Performance as Design** (6 items)
- LCP < 2.0s (web apps), < 1.5s (informational sites)
- CLS < 0.1 (no visible layout shifts during load)
- Skeleton quality: shapes match real content, shimmer animation
- Images: \`loading="lazy"\`, width/height dimensions set, WebP/AVIF format
- Fonts: \`font-display: swap\`, preconnect to CDN origins
- No visible font swap flash (FOUT) — critical fonts preloaded

---

## Phase 4: Interaction Flow Review

Walk 2-3 key user flows and evaluate the *feel*, not just the function:

\`\`\`bash
$B snapshot -i
$B click @e3           # perform action
$B snapshot -D          # diff to see what changed
\`\`\`

Evaluate:
- **Response feel:** Does clicking feel responsive? Any delays or missing loading states?
- **Transition quality:** Are transitions intentional or generic/absent?
- **Feedback clarity:** Did the action clearly succeed or fail? Is the feedback immediate?
- **Form polish:** Focus states visible? Validation timing correct? Errors near the source?

---

## Phase 5: Cross-Page Consistency

Compare screenshots and observations across pages for:
- Navigation bar consistent across all pages?
- Footer consistent?
- Component reuse vs one-off designs (same button styled differently on different pages?)
- Tone consistency (one page playful while another is corporate?)
- Spacing rhythm carries across pages?

---

## Phase 6: Compile Report

### Output Locations

**Local:** \`.gstack/design-reports/design-audit-{domain}-{YYYY-MM-DD}.md\`

**Project-scoped:**
\`\`\`bash
SLUG=$(git remote get-url origin 2>/dev/null | sed 's|.*[:/]\\([^/]*/[^/]*\\)\\.git$|\\1|;s|.*[:/]\\([^/]*/[^/]*\\)$|\\1|' | tr '/' '-')
mkdir -p ~/.gstack/projects/$SLUG
\`\`\`
Write to: \`~/.gstack/projects/{slug}/{user}-{branch}-design-audit-{datetime}.md\`

**Baseline:** Write \`design-baseline.json\` for regression mode:
\`\`\`json
{
  "date": "YYYY-MM-DD",
  "url": "<target>",
  "designScore": "B",
  "aiSlopScore": "C",
  "categoryGrades": { "hierarchy": "A", "typography": "B", ... },
  "findings": [{ "id": "FINDING-001", "title": "...", "impact": "high", "category": "typography" }]
}
\`\`\`

### Scoring System

**Dual headline scores:**
- **Design Score: {A-F}** — weighted average of all 10 categories
- **AI Slop Score: {A-F}** — standalone grade with pithy verdict

**Per-category grades:**
- **A:** Intentional, polished, delightful. Shows design thinking.
- **B:** Solid fundamentals, minor inconsistencies. Looks professional.
- **C:** Functional but generic. No major problems, no design point of view.
- **D:** Noticeable problems. Feels unfinished or careless.
- **F:** Actively hurting user experience. Needs significant rework.

**Grade computation:** Each category starts at A. Each High-impact finding drops one letter grade. Each Medium-impact finding drops half a letter grade. Polish findings are noted but do not affect grade. Minimum is F.

**Category weights for Design Score:**
| Category | Weight |
|----------|--------|
| Visual Hierarchy | 15% |
| Typography | 15% |
| Spacing & Layout | 15% |
| Color & Contrast | 10% |
| Interaction States | 10% |
| Responsive | 10% |
| Content Quality | 10% |
| AI Slop | 5% |
| Motion | 5% |
| Performance Feel | 5% |

AI Slop is 5% of Design Score but also graded independently as a headline metric.

### Regression Output

When previous \`design-baseline.json\` exists or \`--regression\` flag is used:
- Load baseline grades
- Compare: per-category deltas, new findings, resolved findings
- Append regression table to report

---

## Design Critique Format

Use structured feedback, not opinions:
- "I notice..." — observation (e.g., "I notice the primary CTA competes with the secondary action")
- "I wonder..." — question (e.g., "I wonder if users will understand what 'Process' means here")
- "What if..." — suggestion (e.g., "What if we moved search to a more prominent position?")
- "I think... because..." — reasoned opinion (e.g., "I think the spacing between sections is too uniform because it doesn't create hierarchy")

Tie everything to user goals and product objectives. Always suggest specific improvements alongside problems.

---

## Important Rules

1. **Think like a designer, not a QA engineer.** You care whether things feel right, look intentional, and respect the user. You do NOT just care whether things "work."
2. **Screenshots are evidence.** Every finding needs at least one screenshot. Use annotated screenshots (\`snapshot -a\`) to highlight elements.
3. **Be specific and actionable.** "Change X to Y because Z" — not "the spacing feels off."
4. **Never read source code.** Evaluate the rendered site, not the implementation. (Exception: offer to write DESIGN.md from extracted observations.)
5. **AI Slop detection is your superpower.** Most developers can't evaluate whether their site looks AI-generated. You can. Be direct about it.
6. **Quick wins matter.** Always include a "Quick Wins" section — the 3-5 highest-impact fixes that take <30 minutes each.
7. **Use \`snapshot -C\` for tricky UIs.** Finds clickable divs that the accessibility tree misses.
8. **Responsive is design, not just "not broken."** A stacked desktop layout on mobile is not responsive design — it's lazy. Evaluate whether the mobile layout makes *design* sense.
9. **Document incrementally.** Write each finding to the report as you find it. Don't batch.
10. **Depth over breadth.** 5-10 well-documented findings with screenshots and specific suggestions > 20 vague observations.`;
}

const RESOLVERS: Record<string, () => string> = {
  COMMAND_REFERENCE: generateCommandReference,
  SNAPSHOT_FLAGS: generateSnapshotFlags,
  PREAMBLE: generatePreamble,
  BROWSE_SETUP: generateBrowseSetup,
  QA_METHODOLOGY: generateQAMethodology,
  DESIGN_METHODOLOGY: generateDesignMethodology,
};

// ─── Template Processing ────────────────────────────────────

const GENERATED_HEADER = `<!-- AUTO-GENERATED from {{SOURCE}} — do not edit directly -->\n<!-- Regenerate: bun run gen:skill-docs -->\n`;

function processTemplate(tmplPath: string): { outputPath: string; content: string } {
  const tmplContent = fs.readFileSync(tmplPath, 'utf-8');
  const relTmplPath = path.relative(ROOT, tmplPath);
  const outputPath = tmplPath.replace(/\.tmpl$/, '');

  // Replace placeholders
  let content = tmplContent.replace(/\{\{(\w+)\}\}/g, (match, name) => {
    const resolver = RESOLVERS[name];
    if (!resolver) throw new Error(`Unknown placeholder {{${name}}} in ${relTmplPath}`);
    return resolver();
  });

  // Check for any remaining unresolved placeholders
  const remaining = content.match(/\{\{(\w+)\}\}/g);
  if (remaining) {
    throw new Error(`Unresolved placeholders in ${relTmplPath}: ${remaining.join(', ')}`);
  }

  // Prepend generated header (after frontmatter)
  const header = GENERATED_HEADER.replace('{{SOURCE}}', path.basename(tmplPath));
  const fmEnd = content.indexOf('---', content.indexOf('---') + 3);
  if (fmEnd !== -1) {
    const insertAt = content.indexOf('\n', fmEnd) + 1;
    content = content.slice(0, insertAt) + header + content.slice(insertAt);
  } else {
    content = header + content;
  }

  return { outputPath, content };
}

// ─── Main ───────────────────────────────────────────────────

function findTemplates(): string[] {
  const templates: string[] = [];
  const candidates = [
    path.join(ROOT, 'SKILL.md.tmpl'),
    path.join(ROOT, 'browse', 'SKILL.md.tmpl'),
    path.join(ROOT, 'qa', 'SKILL.md.tmpl'),
    path.join(ROOT, 'qa-only', 'SKILL.md.tmpl'),
    path.join(ROOT, 'setup-browser-cookies', 'SKILL.md.tmpl'),
    path.join(ROOT, 'ship', 'SKILL.md.tmpl'),
    path.join(ROOT, 'review', 'SKILL.md.tmpl'),
    path.join(ROOT, 'plan-ceo-review', 'SKILL.md.tmpl'),
    path.join(ROOT, 'plan-eng-review', 'SKILL.md.tmpl'),
    path.join(ROOT, 'retro', 'SKILL.md.tmpl'),
    path.join(ROOT, 'gstack-upgrade', 'SKILL.md.tmpl'),
    path.join(ROOT, 'plan-design-review', 'SKILL.md.tmpl'),
    path.join(ROOT, 'qa-design-review', 'SKILL.md.tmpl'),
  ];
  for (const p of candidates) {
    if (fs.existsSync(p)) templates.push(p);
  }
  return templates;
}

let hasChanges = false;

for (const tmplPath of findTemplates()) {
  const { outputPath, content } = processTemplate(tmplPath);
  const relOutput = path.relative(ROOT, outputPath);

  if (DRY_RUN) {
    const existing = fs.existsSync(outputPath) ? fs.readFileSync(outputPath, 'utf-8') : '';
    if (existing !== content) {
      console.log(`STALE: ${relOutput}`);
      hasChanges = true;
    } else {
      console.log(`FRESH: ${relOutput}`);
    }
  } else {
    fs.writeFileSync(outputPath, content);
    console.log(`GENERATED: ${relOutput}`);
  }
}

if (DRY_RUN && hasChanges) {
  console.error('\nGenerated SKILL.md files are stale. Run: bun run gen:skill-docs');
  process.exit(1);
}