Improve critique skill: sub-agents, scripts_path, browser overlays

- Add {{scripts_path}} build placeholder that resolves per-provider
  (${CLAUDE_PLUGIN_ROOT}/scripts for Claude Code, relative paths for others)
- Restructure critique into sub-agent architecture: LLM review and
  detector run independently to avoid bias, results synthesized at end
- Browser overlay is now a visual aid for the user only -- agent reads
  findings from console via [impeccable] prefix instead of scrolling
- Add scroll-to-top instruction before overlay injection
- Add allowed-tools frontmatter for detector bash commands
- Fix YAML parser to handle simple string arrays (not just - name: objects)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/lib/transformers/shared.js

@@ -36,6 +36,13 @@ export function transformProvider(config, skills, distDir, options = {}) {
     const frontmatter = generateYamlFrontmatter(frontmatterObj);
 
     let skillBody = replacePlaceholders(skill.body, provider, commandNames);
+
+    // Replace {{scripts_path}} with provider-aware path to skill's scripts directory
+    const scriptsPath = provider === 'claude-code'
+      ? '${CLAUDE_PLUGIN_ROOT}/scripts'
+      : `${configDir}/skills/${skillName}/scripts`;
+    skillBody = skillBody.replace(/\{\{scripts_path\}\}/g, scriptsPath);
+
     if (prefix) skillBody = prefixSkillReferences(skillBody, prefix, allSkillNames);
     if (transformBody) skillBody = transformBody(skillBody, skill);