feat: SKILL.md template system, 3-tier testing, DX tools (v0.3.3) (#41)

* refactor: extract command registry to commands.ts, add SNAPSHOT_FLAGS metadata - NEW: browse/src/commands.ts — command sets + COMMAND_DESCRIPTIONS + load-time validation (zero side effects) - server.ts imports from commands.ts instead of declaring sets inline - snapshot.ts: SNAPSHOT_FLAGS array drives parseSnapshotArgs (metadata-driven, no duplication) - All 186 existing tests pass * feat: SKILL.md template system with auto-generated command references - SKILL.md.tmpl + browse/SKILL.md.tmpl with {{COMMAND_REFERENCE}} and {{SNAPSHOT_FLAGS}} placeholders - scripts/gen-skill-docs.ts generates SKILL.md from templates (supports --dry-run) - Build pipeline runs gen:skill-docs before binary compilation - Generated files have AUTO-GENERATED header, committed to git * test: Tier 1 static validation — 34 tests for SKILL.md command correctness - test/helpers/skill-parser.ts: extracts $B commands from code blocks, validates against registry - test/skill-parser.test.ts: 13 parser/validator unit tests - test/skill-validation.test.ts: 13 tests validating all SKILL.md files + registry consistency - test/gen-skill-docs.test.ts: 8 generator tests (categories, sorting, freshness) * feat: DX tools (skill:check, dev:skill) + Tier 2 E2E test scaffolding - scripts/skill-check.ts: health summary for all SKILL.md files (commands, templates, freshness) - scripts/dev-skill.ts: watch mode for template development - test/helpers/session-runner.ts: Agent SDK wrapper for E2E skill tests - test/skill-e2e.test.ts: 2 E2E tests + 3 stubs (auto-skip inside Claude Code sessions) - E2E tests must run from plain terminal: SKILL_E2E=1 bun test test/skill-e2e.test.ts * ci: SKILL.md freshness check on push/PR + TODO updates - .github/workflows/skill-docs.yml: fails if generated SKILL.md files are stale - TODO.md: add E2E cost tracking and model pinning to future ideas * fix: restore rich descriptions lost in auto-generation - Snapshot flags: add back value hints (-d <N>, -s <sel>, -o <path>) - Snapshot flags: restore parenthetical context (@e refs, @c refs, etc.) - Commands: is → includes valid states enum - Commands: console → notes --errors filter behavior - Commands: press → lists common keys (Enter, Tab, Escape) - Commands: cookie-import-browser → describes picker UI - Commands: dialog-accept → specifies alert/confirm/prompt - Tips: restore → arrow (was downgraded to ->) * test: quality evals for generated SKILL.md descriptions Catches the exact regressions we shipped and caught in review: - Snapshot flags must include value hints (-d <N>, -s <sel>, -o <path>) - is command must list all valid states (visible/hidden/enabled/...) - press command must list example keys (Enter, Tab, Escape) - console command must describe --errors behavior - Snapshot -i must mention @e refs, -C must mention @c refs - All descriptions must be >= 8 chars (no empty stubs) - Tips section must use → not -> * feat: LLM-as-judge evals for SKILL.md documentation quality 4 eval tests using Anthropic API (claude-haiku, ~$0.01-0.03/run): - Command reference table: clarity/completeness/actionability >= 4/5 - Snapshot flags section: same thresholds - browse/SKILL.md overall quality - Regression: generated version must score >= hand-maintained baseline Requires ANTHROPIC_API_KEY. Auto-skips without it. Run: bun run test:eval (or ANTHROPIC_API_KEY=sk-... bun test test/skill-llm-eval.test.ts) * chore: bump version to 0.3.3, update changelog Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: add ARCHITECTURE.md, update CLAUDE.md and CONTRIBUTING.md Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: conductor.json lifecycle hooks + .env propagation across worktrees bin/dev-setup now copies .env from main worktree so API keys carry over to Conductor workspaces automatically. conductor.json wires up setup and archive hooks. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: complete CHANGELOG for v0.3.3 (architecture, conductor, .env) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-05-02 03:35:09 +02:00 · 2026-03-13 21:08:12 -07:00
parent ea0c0dad5e
commit 5205070299
29 changed files with 2479 additions and 135 deletions
@@ -0,0 +1,107 @@
+/**
+ * Command registry — single source of truth for all browse commands.
+ *
+ * Dependency graph:
+ *   commands.ts ──▶ server.ts (runtime dispatch)
+ *                ──▶ gen-skill-docs.ts (doc generation)
+ *                ──▶ skill-parser.ts (validation)
+ *                ──▶ skill-check.ts (health reporting)
+ *
+ * Zero side effects. Safe to import from build scripts and tests.
+ */
+
+export const READ_COMMANDS = new Set([
+  'text', 'html', 'links', 'forms', 'accessibility',
+  'js', 'eval', 'css', 'attrs',
+  'console', 'network', 'cookies', 'storage', 'perf',
+  'dialog', 'is',
+]);
+
+export const WRITE_COMMANDS = new Set([
+  'goto', 'back', 'forward', 'reload',
+  'click', 'fill', 'select', 'hover', 'type', 'press', 'scroll', 'wait',
+  'viewport', 'cookie', 'cookie-import', 'cookie-import-browser', 'header', 'useragent',
+  'upload', 'dialog-accept', 'dialog-dismiss',
+]);
+
+export const META_COMMANDS = new Set([
+  'tabs', 'tab', 'newtab', 'closetab',
+  'status', 'stop', 'restart',
+  'screenshot', 'pdf', 'responsive',
+  'chain', 'diff',
+  'url', 'snapshot',
+]);
+
+export const ALL_COMMANDS = new Set([...READ_COMMANDS, ...WRITE_COMMANDS, ...META_COMMANDS]);
+
+export const COMMAND_DESCRIPTIONS: Record<string, { category: string; description: string; usage?: string }> = {
+  // Navigation
+  'goto':    { category: 'Navigation', description: 'Navigate to URL', usage: 'goto <url>' },
+  'back':    { category: 'Navigation', description: 'History back' },
+  'forward': { category: 'Navigation', description: 'History forward' },
+  'reload':  { category: 'Navigation', description: 'Reload page' },
+  'url':     { category: 'Navigation', description: 'Print current URL' },
+  // Reading
+  'text':    { category: 'Reading', description: 'Cleaned page text' },
+  'html':    { category: 'Reading', description: 'innerHTML', usage: 'html [selector]' },
+  'links':   { category: 'Reading', description: 'All links as "text → href"' },
+  'forms':   { category: 'Reading', description: 'Form fields as JSON' },
+  'accessibility': { category: 'Reading', description: 'Full ARIA tree' },
+  // Inspection
+  'js':      { category: 'Inspection', description: 'Run JavaScript', usage: 'js <expr>' },
+  'eval':    { category: 'Inspection', description: 'Run JS file', usage: 'eval <file>' },
+  'css':     { category: 'Inspection', description: 'Computed CSS value', usage: 'css <sel> <prop>' },
+  'attrs':   { category: 'Inspection', description: 'Element attributes as JSON', usage: 'attrs <sel|@ref>' },
+  'is':      { category: 'Inspection', description: 'State check (visible/hidden/enabled/disabled/checked/editable/focused)', usage: 'is <prop> <sel>' },
+  'console': { category: 'Inspection', description: 'Console messages (--errors filters to error/warning)', usage: 'console [--clear|--errors]' },
+  'network': { category: 'Inspection', description: 'Network requests', usage: 'network [--clear]' },
+  'dialog':  { category: 'Inspection', description: 'Dialog messages', usage: 'dialog [--clear]' },
+  'cookies': { category: 'Inspection', description: 'All cookies as JSON' },
+  'storage': { category: 'Inspection', description: 'localStorage + sessionStorage', usage: 'storage [set k v]' },
+  'perf':    { category: 'Inspection', description: 'Page load timings' },
+  // Interaction
+  'click':   { category: 'Interaction', description: 'Click element', usage: 'click <sel>' },
+  'fill':    { category: 'Interaction', description: 'Fill input', usage: 'fill <sel> <val>' },
+  'select':  { category: 'Interaction', description: 'Select dropdown option', usage: 'select <sel> <val>' },
+  'hover':   { category: 'Interaction', description: 'Hover element', usage: 'hover <sel>' },
+  'type':    { category: 'Interaction', description: 'Type into focused element', usage: 'type <text>' },
+  'press':   { category: 'Interaction', description: 'Press key (Enter, Tab, Escape, etc.)', usage: 'press <key>' },
+  'scroll':  { category: 'Interaction', description: 'Scroll element into view', usage: 'scroll [sel]' },
+  'wait':    { category: 'Interaction', description: 'Wait for element/condition', usage: 'wait <sel|--networkidle|--load>' },
+  'upload':  { category: 'Interaction', description: 'Upload file(s)', usage: 'upload <sel> <file...>' },
+  'viewport':{ category: 'Interaction', description: 'Set viewport size', usage: 'viewport <WxH>' },
+  'cookie':  { category: 'Interaction', description: 'Set cookie' },
+  'cookie-import': { category: 'Interaction', description: 'Import cookies from JSON file', usage: 'cookie-import <json>' },
+  'cookie-import-browser': { category: 'Interaction', description: 'Import cookies from real browser (opens picker UI, or direct with --domain)', usage: 'cookie-import-browser [browser] [--domain d]' },
+  'header':  { category: 'Interaction', description: 'Set custom request header', usage: 'header <name> <value>' },
+  'useragent': { category: 'Interaction', description: 'Set user agent', usage: 'useragent <string>' },
+  'dialog-accept': { category: 'Interaction', description: 'Auto-accept next alert/confirm/prompt', usage: 'dialog-accept [text]' },
+  'dialog-dismiss': { category: 'Interaction', description: 'Auto-dismiss next dialog' },
+  // Visual
+  'screenshot': { category: 'Visual', description: 'Save screenshot', usage: 'screenshot [path]' },
+  'pdf':     { category: 'Visual', description: 'Save as PDF', usage: 'pdf [path]' },
+  'responsive': { category: 'Visual', description: 'Mobile/tablet/desktop screenshots', usage: 'responsive [prefix]' },
+  'diff':    { category: 'Visual', description: 'Text diff between pages', usage: 'diff <url1> <url2>' },
+  // Tabs
+  'tabs':    { category: 'Tabs', description: 'List open tabs' },
+  'tab':     { category: 'Tabs', description: 'Switch to tab', usage: 'tab <id>' },
+  'newtab':  { category: 'Tabs', description: 'Open new tab', usage: 'newtab [url]' },
+  'closetab':{ category: 'Tabs', description: 'Close tab', usage: 'closetab [id]' },
+  // Server
+  'status':  { category: 'Server', description: 'Health check' },
+  'stop':    { category: 'Server', description: 'Shutdown server' },
+  'restart': { category: 'Server', description: 'Restart server' },
+  // Meta
+  'snapshot':{ category: 'Snapshot', description: 'Accessibility tree with @refs', usage: 'snapshot [flags]' },
+  'chain':   { category: 'Meta', description: 'Multi-command from JSON stdin' },
+};
+
+// Load-time validation: descriptions must cover exactly the command sets
+const allCmds = new Set([...READ_COMMANDS, ...WRITE_COMMANDS, ...META_COMMANDS]);
+const descKeys = new Set(Object.keys(COMMAND_DESCRIPTIONS));
+for (const cmd of allCmds) {
+  if (!descKeys.has(cmd)) throw new Error(`COMMAND_DESCRIPTIONS missing entry for: ${cmd}`);
+}
+for (const key of descKeys) {
+  if (!allCmds.has(key)) throw new Error(`COMMAND_DESCRIPTIONS has unknown command: ${key}`);
+}
@@ -110,28 +110,9 @@ const idleCheckInterval = setInterval(() => {
  }
 }, 60_000);

-// ─── Command Sets (exported for chain command) ──────────────────
-export const READ_COMMANDS = new Set([
-  'text', 'html', 'links', 'forms', 'accessibility',
-  'js', 'eval', 'css', 'attrs',
-  'console', 'network', 'cookies', 'storage', 'perf',
-  'dialog', 'is',
-]);
-
-export const WRITE_COMMANDS = new Set([
-  'goto', 'back', 'forward', 'reload',
-  'click', 'fill', 'select', 'hover', 'type', 'press', 'scroll', 'wait',
-  'viewport', 'cookie', 'cookie-import', 'cookie-import-browser', 'header', 'useragent',
-  'upload', 'dialog-accept', 'dialog-dismiss',
-]);
-
-export const META_COMMANDS = new Set([
-  'tabs', 'tab', 'newtab', 'closetab',
-  'status', 'stop', 'restart',
-  'screenshot', 'pdf', 'responsive',
-  'chain', 'diff',
-  'url', 'snapshot',
-]);
+// ─── Command Sets (from commands.ts — single source of truth) ───
+import { READ_COMMANDS, WRITE_COMMANDS, META_COMMANDS } from './commands';
+export { READ_COMMANDS, WRITE_COMMANDS, META_COMMANDS };

 // ─── Server ────────────────────────────────────────────────────
 const browserManager = new BrowserManager();
@@ -40,6 +40,31 @@ interface SnapshotOptions {
  cursorInteractive?: boolean; // -C / --cursor-interactive: scan cursor:pointer etc.
 }

+/**
+ * Snapshot flag metadata — single source of truth for CLI parsing and doc generation.
+ *
+ * Imported by:
+ *   - gen-skill-docs.ts (generates {{SNAPSHOT_FLAGS}} tables)
+ *   - skill-parser.ts (validates flags in SKILL.md examples)
+ */
+export const SNAPSHOT_FLAGS: Array<{
+  short: string;
+  long: string;
+  description: string;
+  takesValue?: boolean;
+  valueHint?: string;
+  optionKey: keyof SnapshotOptions;
+}> = [
+  { short: '-i', long: '--interactive', description: 'Interactive elements only (buttons, links, inputs) with @e refs', optionKey: 'interactive' },
+  { short: '-c', long: '--compact', description: 'Compact (no empty structural nodes)', optionKey: 'compact' },
+  { short: '-d', long: '--depth', description: 'Limit depth', takesValue: true, valueHint: '<N>', optionKey: 'depth' },
+  { short: '-s', long: '--selector', description: 'Scope to CSS selector', takesValue: true, valueHint: '<sel>', optionKey: 'selector' },
+  { short: '-D', long: '--diff', description: 'Diff against previous snapshot (what changed?)', optionKey: 'diff' },
+  { short: '-a', long: '--annotate', description: 'Annotated screenshot with ref labels', optionKey: 'annotate' },
+  { short: '-o', long: '--output', description: 'Output path for screenshot', takesValue: true, valueHint: '<path>', optionKey: 'outputPath' },
+  { short: '-C', long: '--cursor-interactive', description: 'Cursor-interactive elements (@c refs — divs with pointer, onclick)', optionKey: 'cursorInteractive' },
+];
+
 interface ParsedNode {
  indent: number;
  role: string;
@@ -50,49 +75,24 @@ interface ParsedNode {
 }

 /**
- * Parse CLI args into SnapshotOptions
+ * Parse CLI args into SnapshotOptions — driven by SNAPSHOT_FLAGS metadata.
 */
 export function parseSnapshotArgs(args: string[]): SnapshotOptions {
  const opts: SnapshotOptions = {};
  for (let i = 0; i < args.length; i++) {
-    switch (args[i]) {
-      case '-i':
-      case '--interactive':
-        opts.interactive = true;
-        break;
-      case '-c':
-      case '--compact':
-        opts.compact = true;
-        break;
-      case '-d':
-      case '--depth':
-        opts.depth = parseInt(args[++i], 10);
+    const flag = SNAPSHOT_FLAGS.find(f => f.short === args[i] || f.long === args[i]);
+    if (!flag) throw new Error(`Unknown snapshot flag: ${args[i]}`);
+    if (flag.takesValue) {
+      const value = args[++i];
+      if (!value) throw new Error(`Usage: snapshot ${flag.short} <value>`);
+      if (flag.optionKey === 'depth') {
+        (opts as any)[flag.optionKey] = parseInt(value, 10);
        if (isNaN(opts.depth!)) throw new Error('Usage: snapshot -d <number>');
-        break;
-      case '-s':
-      case '--selector':
-        opts.selector = args[++i];
-        if (!opts.selector) throw new Error('Usage: snapshot -s <selector>');
-        break;
-      case '-D':
-      case '--diff':
-        opts.diff = true;
-        break;
-      case '-a':
-      case '--annotate':
-        opts.annotate = true;
-        break;
-      case '-o':
-      case '--output':
-        opts.outputPath = args[++i];
-        if (!opts.outputPath) throw new Error('Usage: snapshot -o <path>');
-        break;
-      case '-C':
-      case '--cursor-interactive':
-        opts.cursorInteractive = true;
-        break;
-      default:
-        throw new Error(`Unknown snapshot flag: ${args[i]}`);
+      } else {
+        (opts as any)[flag.optionKey] = value;
+      }
+    } else {
+      (opts as any)[flag.optionKey] = true;
    }
  }
  return opts;