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}"

## Completion Status Protocol

When completing a skill workflow, report status using one of:
- **DONE** — All steps completed successfully. Evidence provided for each claim.
- **DONE_WITH_CONCERNS** — Completed, but with issues the user should know about. List each concern.
- **BLOCKED** — Cannot proceed. State what is blocking and what was tried.
- **NEEDS_CONTEXT** — Missing information required to continue. State exactly what you need.

### Escalation

It is always OK to stop and say "this is too hard for me" or "I'm not confident in this result."

Bad work is worse than no work. You will not be penalized for escalating.
- If you have attempted a task 3 times without success, STOP and escalate.
- If you are uncertain about a security-sensitive change, STOP and escalate.
- If the scope of work exceeds what you can verify, STOP and escalate.

Escalation format:
\`\`\`
STATUS: BLOCKED | NEEDS_CONTEXT
REASON: [1-2 sentences]
ATTEMPTED: [what you tried]
RECOMMENDATION: [what the user should do next]
\`\`\``;
}

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.`;
}

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

// ─── 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, 'brainstorm', 'SKILL.md.tmpl'),
    path.join(ROOT, 'debug', 'SKILL.md.tmpl'),
    path.join(ROOT, 'gstack-upgrade', '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);
}