feat(linkedin): progressive onboarding — hide score until 3+ posts, suppress voice guardian noise

- session-start.mjs: count published posts, gate personalization score
  display and reminder behind >= 3 published posts
- voice-guardian.md: suppress LOW CONFIDENCE messages, silently skip
  drift scoring when < 5 samples
- state-file.template.md: add "general" default for expertise_areas
- onboarding.md: show friendly defaults message for new users, move
  score dashboard to returning-user flow

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

plugins/linkedin-thought-leadership/commands/onboarding.md

@@ -22,6 +22,21 @@ Read `~/.claude/linkedin-thought-leadership.local.md` for current state.
 
 **Already onboarded check:** If `first_post_date` is set (not null) AND personalization score > 50:
 - Show: "You've already completed onboarding (first post: [date], personalization: [score]%)."
+- If `## Recent Posts` has 3+ entries, show the personalization score dashboard:
+  ```
+  Personalization Score: [XX]%
+
+  Category          Weight  Status
+  ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+  Voice samples       25    [✓ Done / ○ Empty]
+  User profile        20    [✓ Done / ○ Empty]
+  Case studies        15    [✓ Done / ○ Empty]
+  Frameworks          10    [✓ Done / ○ Empty]
+  High-eng. posts     10    [✓ Done / ○ Empty]
+  Demographics         8    [✓ Done / ○ Empty]
+  Engagement patterns  7    [✓ Done / ○ Empty]
+  Post templates       5    [✓ Done / ○ Empty]
+  ```
 - Use AskUserQuestion: "Would you like to re-run a specific phase?"
   1. Re-optimize profile (360Brew) → jump to Phase 1
   2. Improve personalization → jump to Phase 2
@@ -68,6 +83,20 @@ After each item, ask if done or needs to skip. Don't block — mark skipped item
 ╚═════════════════════════════════════════════╝
 ```
 
+Count published posts by checking `## Recent Posts` entries in state file.
+
+**If fewer than 3 published posts (new user):**
+
+Show: "Your plugin is ready to use with sensible defaults. Personalization makes content more authentic — we'll suggest improvements after you've published a few posts."
+
+Use AskUserQuestion:
+1. **Set up voice profile** (optional, recommended later) — 5 questions about your writing style
+2. **Set up user profile** (optional, recommended later) — Your name, industry, expertise areas
+3. **Both** — Do voice + user profile now
+4. **Skip for now** — Use defaults, I'll run `/linkedin:setup` when ready
+
+**If 3+ published posts (returning user):**
+
 Calculate personalization score:
 ```bash
 node --input-type=module -e "

plugins/linkedin-thought-leadership/config/state-file.template.md

@@ -34,7 +34,7 @@ content_series_active: ""
 
 # Profile
 expertise_areas:
-  - ""
+  - "general"
   - ""
   - ""
   - ""

plugins/linkedin-thought-leadership/hooks/prompts/voice-guardian.md

@@ -37,7 +37,7 @@ Score the draft against these 6 dimensions (0 = perfect match, 1 = minor drift p
 | 4-5 | ALERT | Significant drift — list all deviating dimensions with rewrites |
 | 6 | REWRITE | Content doesn't sound like the user — recommend starting over |
 
-**Confidence gate:** If `## Collected Post Samples` has fewer than 5 posts, output: "Voice drift: LOW CONFIDENCE (X/5 samples). Scoring based on voice profile only." and score only against the profile description (dimensions 1-2 and 4-6), skipping opening patterns (dimension 3) which needs real samples.
+**Confidence gate:** If `## Collected Post Samples` has fewer than 5 posts, perform ONLY the AI Pattern Detection (section 1). Skip the Six-Dimension Voice Drift Scoring entirely — there is insufficient data for meaningful drift analysis. Do NOT output "LOW CONFIDENCE" messages. Instead, silently skip drift scoring and only flag if 3+ AI patterns are detected.
 
 **Output format (always include at end of system message):**
 ```

plugins/linkedin-thought-leadership/hooks/scripts/session-start.mjs

@@ -162,6 +162,13 @@ if (existsSync(STATE_FILE)) {
     // Non-critical: don't block session start on pruning failure
   }
 
+  // Count published posts for progressive onboarding
+  const recentPostsSection = stateContent.match(/^## Recent Posts\n([\s\S]*?)(?=\n## [^R]|\n## $|$)/m);
+  let publishedPostCount = 0;
+  if (recentPostsSection) {
+    publishedPostCount = (recentPostsSection[1].match(/^\s*[-\[]/gm) || []).length;
+  }
+
   // Build status line
   let statusLine = `LinkedIn: ${postsThisWeek}/${weeklyGoal} posts this week | Streak: ${currentStreak} days`;
   if (lastPostDate && lastPostDate !== 'null') {
@@ -177,12 +184,14 @@ if (existsSync(STATE_FILE)) {
     statusLine += ` | ${followerCount}/${followerTarget} followers (${milestonePhase})`;
   }
 
-  // Personalization score
+  // Personalization score (only show after 3+ published posts — progressive onboarding)
   let pScore = null;
   try {
     const { score } = calculateScore(PLUGIN_ROOT);
     pScore = score;
-    statusLine += ` | Personalization: ${score}%`;
+    if (publishedPostCount >= 3) {
+      statusLine += ` | Personalization: ${score}%`;
+    }
   } catch { /* ignore */ }
 
   // New creator window
@@ -272,8 +281,8 @@ if (existsSync(STATE_FILE)) {
     reminders += `- ${weekRemaining} posts remaining to hit weekly goal of ${weeklyGoal}. It's late in the week.\\n`;
   }
 
-  // Personalization score check
-  if (pScore !== null && pScore < 50) {
+  // Personalization score check (only after 3+ posts — progressive onboarding)
+  if (pScore !== null && pScore < 50 && publishedPostCount >= 3) {
     reminders += `- Personalization score is ${pScore}%. Run /linkedin:setup to improve content quality with your real voice, case studies, and audience data.\\n`;
   }