feat(curation): auto-curation after crawl + quality messaging

Automate curation:
- Add runPostCrawlCuration() to DB queries — runs after every
  full and incremental crawl (classify, dedup, category counts)
- No more need for manual curate.mjs runs after each crawl

Quality messaging:
- Homepage stats label: "Skills" → "Curated Skills" (en/fa)
- Add curation note: "deduplicated and quality-filtered from X+ repos"
- Update fallback counts from 172K to 16K across all touchpoints
  (BetaBanner, getting-started prompts, email templates)
- getting-started skill count query now uses browse-ready filter

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

apps/web/app/[locale]/docs/getting-started/page.tsx

@@ -14,10 +14,11 @@ async function getSkillCount(): Promise<string> {
     const db = createDb();
     const result = await db
       .select({ count: sql<number>`count(*)::int` })
-      .from(skills);
-    return formatPromptSkillCount(result[0]?.count ?? 170000);
+      .from(skills)
+      .where(sql`${skills.isDuplicate} = false AND (${skills.skillType} IS NULL OR ${skills.skillType} != 'aggregator')`);
+    return formatPromptSkillCount(result[0]?.count ?? 16000);
   } catch {
-    return '170,000+';
+    return '16,000+';
   }
 }