chore(linkedin-studio): M0-13 — 4 D2 templates + scrub leak + scaffold fallback

2026-06-18 12:19:48 +02:00 · 2026-06-18 12:19:48 +02:00 · 3797eaf6b1
commit 3797eaf6b1
parent 29b139de11
7 changed files with 928 additions and 130 deletions
--- a/assets/audience-insights/demographics-template.md
+++ b/assets/audience-insights/demographics-template.md
@ -0,0 +1,211 @@
+# Audience Demographics
+
+Track WHO is actually engaging with your content. LinkedIn Analytics provides this data for free - use it to understand your real audience vs. your intended audience.
+
+## How to Access This Data
+
+1. Go to LinkedIn Analytics: https://www.linkedin.com/analytics/
+2. Click on any post
+3. Navigate to "Demographics" tab
+4. Review data monthly and update this file
+
+---
+
+## Current Demographics (Last Updated: [Date])
+
+### Industries (Top 10)
+
+Based on LinkedIn Analytics → Post Analytics → Demographics
+
+| Rank | Industry | % of Engagement | Trend |
+|------|----------|----------------|--------|
+| 1 | [Industry name] | [X]% | [↑/→/↓] |
+| 2 | [Industry name] | [X]% | [↑/→/↓] |
+| 3 | [Industry name] | [X]% | [↑/→/↓] |
+| 4 | [Industry name] | [X]% | [↑/→/↓] |
+| 5 | [Industry name] | [X]% | [↑/→/↓] |
+| 6 | [Industry name] | [X]% | [↑/→/↓] |
+| 7 | [Industry name] | [X]% | [↑/→/↓] |
+| 8 | [Industry name] | [X]% | [↑/→/↓] |
+| 9 | [Industry name] | [X]% | [↑/→/↓] |
+| 10 | [Industry name] | [X]% | [↑/→/↓] |
+
+**Key insights:**
+- [Observation 1 - e.g., "60% from government sector, higher than expected"]
+- [Observation 2 - e.g., "Tech companies underrepresented vs. my assumptions"]
+- [Implication - e.g., "Should increase public sector case studies"]
+
+---
+
+### Job Functions (Top 10)
+
+| Rank | Function | % of Engagement | Trend |
+|------|----------|----------------|--------|
+| 1 | [Function] | [X]% | [↑/→/↓] |
+| 2 | [Function] | [X]% | [↑/→/↓] |
+| 3 | [Function] | [X]% | [↑/→/↓] |
+| 4 | [Function] | [X]% | [↑/→/↓] |
+| 5 | [Function] | [X]% | [↑/→/↓] |
+| 6 | [Function] | [X]% | [↑/→/↓] |
+| 7 | [Function] | [X]% | [↑/→/↓] |
+| 8 | [Function] | [X]% | [↑/→/↓] |
+| 9 | [Function] | [X]% | [↑/→/↓] |
+| 10 | [Function] | [X]% | [↑/→/↓] |
+
+**Key insights:**
+- [Who is actually engaging]
+- [Implication for content framing]
+
+---
+
+### Seniority Levels
+
+| Level | % of Engagement | Change vs. Last Month |
+|-------|----------------|----------------------|
+| Entry level | [X]% | [+/-X%] |
+| Individual contributor | [X]% | [+/-X%] |
+| Manager | [X]% | [+/-X%] |
+| Director | [X]% | [+/-X%] |
+| VP | [X]% | [+/-X%] |
+| C-level | [X]% | [+/-X%] |
+| Owner/Partner | [X]% | [+/-X%] |
+
+**Key insights:**
+- **Dominant level:** [Which level engages most]
+- **Decision-maker presence:** [% at Director+ level]
+- **Content implication:** [How technical/strategic should content be?]
+
+---
+
+### Geographic Distribution (Top 10 Countries)
+
+| Rank | Country | % of Engagement | Trend |
+|------|---------|----------------|--------|
+| 1 | [Country] | [X]% | [↑/→/↓] |
+| 2 | [Country] | [X]% | [↑/→/↓] |
+| 3 | [Country] | [X]% | [↑/→/↓] |
+| 4 | [Country] | [X]% | [↑/→/↓] |
+| 5 | [Country] | [X]% | [↑/→/↓] |
+| 6 | [Country] | [X]% | [↑/→/↓] |
+| 7 | [Country] | [X]% | [↑/→/↓] |
+| 8 | [Country] | [X]% | [↑/→/↓] |
+| 9 | [Country] | [X]% | [↑/→/↓] |
+| 10 | [Country] | [X]% | [↑/→/↓] |
+
+**Key insights:**
+- **Primary market:** [Where most engagement comes from]
+- **Time zone implications:** [Optimal posting times]
+- **Regional context:** [Does content need localization?]
+
+---
+
+### Company Size (Of Engagers)
+
+| Size | % of Engagement | Trend |
+|------|----------------|--------|
+| 1-10 employees | [X]% | [↑/→/↓] |
+| 11-50 | [X]% | [↑/→/↓] |
+| 51-200 | [X]% | [↑/→/↓] |
+| 201-500 | [X]% | [↑/→/↓] |
+| 501-1000 | [X]% | [↑/→/↓] |
+| 1001-5000 | [X]% | [↑/→/↓] |
+| 5001-10000 | [X]% | [↑/→/↓] |
+| 10000+ | [X]% | [↑/→/↓] |
+
+**Key insights:**
+- **Dominant segment:** [Enterprise/Mid-market/SMB]
+- **Content implication:** [Scale of examples, budget assumptions]
+- **Opportunity:** [Underserved segment to target]
+
+---
+
+## Intended vs. Actual Audience
+
+### Who I Thought My Audience Was
+- **Industries:** [Your original assumptions]
+- **Roles:** [Your original assumptions]
+- **Seniority:** [Your original assumptions]
+- **Geography:** [Your original assumptions]
+
+### Who My Audience Actually Is
+- **Industries:** [Reality from data above]
+- **Roles:** [Reality from data above]
+- **Seniority:** [Reality from data above]
+- **Geography:** [Reality from data above]
+
+### Strategic Implications
+
+**Content adjustments needed:**
+1. [Adjustment 1 - e.g., "Increase public sector examples, decrease startup references"]
+2. [Adjustment 2 - e.g., "Frame for Director-level, not just technical ICs"]
+3. [Adjustment 3 - e.g., "Add European regulatory context"]
+
+**Opportunities identified:**
+1. [Opportunity 1 - e.g., "Large enterprise segment underserved by competitors"]
+2. [Opportunity 2 - e.g., "Growing Nordic audience interested in topic X"]
+
+---
+
+## Follower vs. Engager Analysis
+
+**Important distinction:** 
+- Your followers = who follows you
+- Your engagers = who actually interacts with content
+
+Often these are different groups. LinkedIn prioritizes showing your content to engagers, not just followers.
+
+### Follower Demographics
+[If you have LinkedIn Premium, note follower demographics here]
+- [Key differences from engager demographics]
+
+### Insight
+[What the difference between followers and engagers tells you]
+
+---
+
+## Competitive Audience Analysis
+
+How does your audience compare to key competitors/peers?
+
+| Peer | Their Primary Industry | Their Seniority Level | Difference from Mine |
+|------|----------------------|---------------------|---------------------|
+| [Name] | [Industry] | [Level] | [What's different] |
+| [Name] | [Industry] | [Level] | [What's different] |
+| [Name] | [Industry] | [Level] | [What's different] |
+
+**Content gap opportunity:**
+[Where your unique audience positioning creates content opportunities]
+
+---
+
+## Month-over-Month Trends
+
+### [Current Month] vs. [Previous Month]
+
+**Industry shifts:**
+- [What changed and why]
+
+**Seniority shifts:**
+- [What changed and why]
+
+**Geographic shifts:**
+- [What changed and why]
+
+**Analysis:**
+[What these trends indicate about content resonance and audience evolution]
+
+---
+
+## Update Schedule
+
+- **Monthly:** Update all demographics from LinkedIn Analytics
+- **Quarterly:** Deep analysis of trends and strategic implications
+- **Yearly:** Major review of intended vs. actual audience fit
+
+---
+
+## Update Log
+
+- **[Date]:** Initial demographics captured
+- **[Date]:** Observed [significant change] in [demographic category]
+- **[Date]:** Shifted content strategy based on [insight]
--- a/assets/audience-insights/engagement-patterns-template.md
+++ b/assets/audience-insights/engagement-patterns-template.md
@ -0,0 +1,267 @@
+# My Audience Engagement Patterns
+
+Track YOUR audience's specific behaviors and preferences here. This data is more valuable than generic "best practices" because it's based on YOUR actual results.
+
+## Update Frequency
+
+**Weekly (5 minutes):** Update posting times and add best-performing topic from the week
+**Monthly (15 minutes):** Deep dive into patterns, update demographics, analyze format performance
+
+---
+
+## Best Posting Times (Based on MY Data)
+
+**Important:** These should be YOUR times based on YOUR analytics, not generic advice. Track this in LinkedIn Analytics under "Post impressions by time of day."
+
+### Primary Posting Windows
+1. **[Day] at [Time]:** Avg. impressions: [X] | Avg. engagement: [Y]
+   - Why this works: [e.g., "My audience (public sector leaders) checks LinkedIn during lunch break"]
+
+2. **[Day] at [Time]:** Avg. impressions: [X] | Avg. engagement: [Y]
+   - Why this works: [Your analysis]
+
+3. **[Day] at [Time]:** Avg. impressions: [X] | Avg. engagement: [Y]
+   - Why this works: [Your analysis]
+
+### Worst Posting Times (To Avoid)
+- [Day/Time]: [Why it underperforms for YOUR audience]
+- [Day/Time]: [Why it underperforms for YOUR audience]
+
+**Update Log:**
+- [Date]: [Change observed - e.g., "Tuesday 2pm now outperforms Friday 8am"]
+
+---
+
+## Top-Performing Topics (Last 90 Days)
+
+Track which topics YOUR audience actually engages with, not what you think they should care about.
+
+1. **[Topic]:** Avg. engagement: [X] | Posts: [Y]
+   - Best-performing post example: [Brief description]
+   - Why it resonates: [Your analysis]
+
+2. **[Topic]:** Avg. engagement: [X] | Posts: [Y]
+   - Best-performing post example: [Brief description]
+   - Why it resonates: [Your analysis]
+
+3. **[Topic]:** Avg. engagement: [X] | Posts: [Y]
+   - Best-performing post example: [Brief description]
+   - Why it resonates: [Your analysis]
+
+### Topics That Surprisingly Underperformed
+- **[Topic]:** [Why you thought it would work] → [Why it didn't]
+- **[Topic]:** [Analysis]
+
+**Implication for content strategy:**
+[What you'll do differently based on this data]
+
+---
+
+## Format Performance (MY Audience)
+
+Based on YOUR analytics, not generic benchmarks. Track in LinkedIn Analytics and your own spreadsheet.
+
+### Format Rankings (By Engagement)
+1. **[Format - e.g., "Story-based posts"]:** 
+   - Avg. impressions: [X]
+   - Avg. engagement rate: [Y%]
+   - Best time to post: [When]
+   - Character sweet spot: [Range]
+
+2. **[Format - e.g., "Framework posts"]:**
+   - Avg. impressions: [X]
+   - Avg. engagement rate: [Y%]
+   - Best time to post: [When]
+   - Character sweet spot: [Range]
+
+3. **[Format - e.g., "Data/research posts"]:**
+   - [Same metrics]
+
+4. **[Format - e.g., "Case study posts"]:**
+   - [Same metrics]
+
+### Visual Content Performance
+- **Posts with images:** Avg. engagement: [X] vs text-only: [Y]
+- **Posts with documents:** Avg. engagement: [X]
+- **Posts with carousels:** Avg. engagement: [X]
+- **Video posts:** Avg. engagement: [X]
+
+**Your insights:**
+[What format performs best for YOUR audience and why]
+
+---
+
+## Hook Types That Work for ME
+
+Not all hook styles work for all audiences. Track which hooks YOUR audience responds to.
+
+### Top-Performing Hook Styles
+1. **[Hook type - e.g., "Counterintuitive stat"]**
+   - Example: [Actual hook you used]
+   - Avg. engagement: [X]
+   - Why it works for your audience: [Analysis]
+
+2. **[Hook type - e.g., "Bold contrarian statement"]**
+   - Example: [Actual hook]
+   - Avg. engagement: [X]
+   - Why it works: [Analysis]
+
+3. **[Hook type - e.g., "Personal story opening"]**
+   - Example: [Actual hook]
+   - Avg. engagement: [X]
+   - Why it works: [Analysis]
+
+### Hook Styles That Don't Work for YOUR Audience
+- **[Hook type]:** [Why it underperforms with your specific audience]
+- **[Hook type]:** [Why it underperforms]
+
+---
+
+## CTA Performance Analysis
+
+Which calls-to-action actually drive engagement from YOUR audience?
+
+### High-Performing CTAs
+1. **[CTA type - e.g., "Specific implementation question"]**
+   - Example: "Which stage is your organization in?"
+   - Avg. comments generated: [X]
+
+2. **[CTA type]**
+   - Example: [Actual CTA]
+   - Avg. comments generated: [X]
+
+### Low-Performing CTAs (To Avoid)
+- **[CTA type]:** [Why YOUR audience doesn't respond to this]
+
+---
+
+## Audience Demographics (Who Actually Engages)
+
+Based on LinkedIn Analytics → Analytics → Demographics of people who interacted with your posts
+
+### Industries (Top 5)
+1. [Industry]: [% of engagement]
+2. [Industry]: [% of engagement]
+3. [Industry]: [% of engagement]
+4. [Industry]: [% of engagement]
+5. [Industry]: [% of engagement]
+
+**Insight:** [What this means for content focus]
+
+### Job Functions (Top 5)
+1. [Function]: [% of engagement]
+2. [Function]: [% of engagement]
+3. [Function]: [% of engagement]
+4. [Function]: [% of engagement]
+5. [Function]: [% of engagement]
+
+**Insight:** [How this should shape your content]
+
+### Seniority Levels
+- C-level: [%]
+- VP/Director: [%]
+- Manager: [%]
+- Individual contributor: [%]
+- Entry level: [%]
+
+**Insight:** [Technical depth and framing implications]
+
+### Geographic Distribution (Top 5 Countries)
+1. [Country]: [%]
+2. [Country]: [%]
+3. [Country]: [%]
+4. [Country]: [%]
+5. [Country]: [%]
+
+**Insight:** [Time zone and regional context considerations]
+
+### Company Size (Of Engagers)
+- 1-10 employees: [%]
+- 11-50: [%]
+- 51-200: [%]
+- 201-500: [%]
+- 501-1000: [%]
+- 1001-5000: [%]
+- 5001-10000: [%]
+- 10000+: [%]
+
+**Insight:** [Scale and organizational context implications]
+
+---
+
+## Content Length Performance (YOUR Data)
+
+Track the optimal length for YOUR audience, not generic advice.
+
+- **800-1000 characters:** Avg. engagement: [X]
+- **1000-1200 characters:** Avg. engagement: [X]
+- **1200-1500 characters:** Avg. engagement: [X]
+- **1500-1900 characters:** Avg. engagement: [X]
+- **1900+ characters:** Avg. engagement: [X]
+
+**Your sweet spot:** [Range that consistently performs best]
+**Why:** [Your analysis of why this works for your audience]
+
+---
+
+## Engagement Velocity Patterns
+
+How quickly does YOUR content gain traction?
+
+### First Hour Performance
+- **Average engagement in first 60 minutes:** [X] likes, [Y] comments
+- **Threshold for algorithm boost:** [Based on your data, when does reach accelerate?]
+- **Your current hit rate:** [% of posts that hit the threshold]
+
+### 24-Hour Patterns
+- **Most engagement happens in:** [Time window - e.g., "First 3 hours"]
+- **Secondary surge times:** [If applicable]
+- **Typical engagement curve:** [Description of how your posts perform over 24 hours]
+
+---
+
+## Strategic Insights (The "So What")
+
+Based on all the data above, what should you do differently?
+
+### Content Strategy Adjustments
+1. **More of this:** [What data says you should double down on]
+2. **Less of this:** [What data says isn't working]
+3. **Test this:** [New hypotheses based on patterns]
+
+### Audience Alignment
+- **Who you thought your audience was:** [Original assumption]
+- **Who actually engages:** [Reality based on data]
+- **Strategic implication:** [How content should shift]
+
+### Competitive Edge Opportunities
+Based on YOUR unique audience makeup:
+- **Gap 1:** [Underserved need you could fill]
+- **Gap 2:** [Content angle competitors miss]
+- **Gap 3:** [Format opportunity]
+
+---
+
+## Monthly Comparison
+
+Track month-over-month to see if patterns are stable or shifting.
+
+### [Current Month]
+- Avg. impressions per post: [X]
+- Avg. engagement per post: [Y]
+- Follower growth: [+X]
+- Best-performing topic: [Topic]
+- Best-performing format: [Format]
+
+### [Previous Month]
+- [Same metrics for comparison]
+
+**Key changes:** [What's different and why]
+
+---
+
+## Update Log
+
+- **[Date]:** [Significant finding - e.g., "Discovered Thursday posts now outperform Tuesday"]
+- **[Date]:** [Pattern shift - e.g., "Framework posts have overtaken story posts in engagement"]
+- **[Date]:** [Audience insight - e.g., "Realize 60% of engagers are from enterprise, not SMB"]
--- a/assets/examples/high-engagement-posts-template.md
+++ b/assets/examples/high-engagement-posts-template.md
@ -0,0 +1,60 @@
+# High-Engagement Posts Collection
+
+Store your top-performing posts here for pattern analysis. Add 5-10 of your best posts to identify what consistently works for YOUR audience.
+
+> **Placeholder seed.** Your real, per-user collection lives in your external data
+> dir (`~/.claude/linkedin-studio/examples/high-engagement-posts.md`). Replace the
+> example structure below with your own posts.
+
+## How to Use This File
+
+After each successful post (high engagement relative to your baseline):
+
+1. Add a new `## Post N` section (where N is a number) per saved post
+2. Note engagement metrics and timing
+3. Analyze WHY it worked (hook, angle, timing, CTA)
+4. Document the replicable pattern
+
+Claude studies these to learn your successful patterns and apply them to new content.
+
+## Entry Format
+
+Each saved post is one `## Post N` section with these fields:
+
+- **Posted:** date, time, timezone
+- **Engagement:** likes / comments / shares
+- **Reach:** impressions and engagement rate
+- **The Post:** the full post text
+- **Why It Worked:** hook, angle, timing, CTA
+- **Pattern to Replicate:** the elements you want to reuse
+
+(Add your first `## Post N` section above this line once you have a high performer.)
+
+## Patterns Across All High-Performing Posts
+
+**Common Elements:**
+
+- [ ] [Element you notice across your best posts]
+- [ ] [Element 2]
+
+**Audience Preferences (What YOUR Audience Responds To):**
+
+- Format: [Your best-performing format]
+- Length: [Your best-performing length]
+- Tone: [Your best-performing tone]
+- CTAs: [What drives replies for you]
+
+**Topics That Resonate:**
+
+1. [Topic]
+2. [Topic]
+
+**Best Posting Times (Based on YOUR Data):**
+
+- Primary: [Time]
+- Secondary: [Time]
+- Avoid: [Time]
+
+## Update Log
+
+- [Date]: [What you added or learned]
--- a/assets/examples/high-engagement-posts.md
+++ b/assets/examples/high-engagement-posts.md
@ -2,157 +2,59 @@

 Store your top-performing posts here for pattern analysis. Add 5-10 of your best posts to identify what consistently works for YOUR audience.

+> **Placeholder seed.** Your real, per-user collection lives in your external data
+> dir (`~/.claude/linkedin-studio/examples/high-engagement-posts.md`). Replace the
+> example structure below with your own posts.
+
 ## How to Use This File

 After each successful post (high engagement relative to your baseline):
-1. Copy the full post text below
+
+1. Add a new `## Post N` section (where N is a number) per saved post
 2. Note engagement metrics and timing
 3. Analyze WHY it worked (hook, angle, timing, CTA)
 4. Document the replicable pattern

-Claude will study these to understand your successful patterns and apply them to new content.
+Claude studies these to learn your successful patterns and apply them to new content.

---
+## Entry Format

-## Post 1: Ralph Wiggum / Vibe Coding (BASELINE)
+Each saved post is one `## Post N` section with these fields:

-**Posted:** 2026-01-23, 23:13 CET (suboptimal timing)
-**Engagement:** Likes: 19 | Comments: 6 | Shares: 0
-**Reach:** 502 impressions
-**Engagement Rate:** 4.98%
-**Your Follower Count:** ~1,000
+- **Posted:** date, time, timezone
+- **Engagement:** likes / comments / shares
+- **Reach:** impressions and engagement rate
+- **The Post:** the full post text
+- **Why It Worked:** hook, angle, timing, CTA
+- **Pattern to Replicate:** the elements you want to reuse

-**The Post:**
-```
-𝗘𝗻 𝗱𝗮𝗴. 𝟭𝟬 𝟬𝟬𝟬 𝗹𝗶𝗻𝗷𝗲𝗿. 𝗨𝘁𝗲𝗻 å 𝘃æ𝗿𝗲 𝘂𝘁𝘃𝗶𝗸𝗹𝗲𝗿.
-
-Jeg er ikke utvikler. Jeg er KI-rådgiver. Jeg kan ikke skrive kode fra bunnen av.
-
-Men jeg kan kommunisere med Claude Code. Og det viser seg at det er nok.
-
-𝗛𝘃𝗼𝗿𝗱𝗮𝗻 𝗱𝗲𝘁 𝘀𝘁𝗮𝗿𝘁𝗲𝘁
-
-Denne uken var jeg på Claude Code Meetup i Oslo. 250+ deltakere. Arrangert av Aleksander Stensby og Mesh Oslo.
-
-Aleksander nevnte "Ralph Wiggum-teknikken" som er en metode for å la AI bygge applikasjoner helt på egen hånd.
-
-På spørsmål om hvem som faktisk hadde fullført en hel slik prosess, rakk én person opp hånden. Av 250.
-
-Den kvelden bestemte jeg meg: I morgen tester jeg dette.
-
-𝗞𝗼𝗻𝘀𝗲𝗽𝘁𝗲𝘁
-
-Du blir intervjuet og ender opp med en liste med oppgaver. Starter en prosess. Går og lager kaffe, eller sover.
-
-Når du kommer tilbake er applikasjonen bygget.
-
-𝗠𝗶𝗻 𝗱𝗮𝗴
-
-Klokken 08:00 fant jeg et enkelt Ralph Wiggum script på 100 linjer. Klokken 23:00 hadde jeg 10 000 linjer og et komplett rammeverk.
-
-Ikke ved å skrive kode selv — men ved å forklare hva jeg ville ha:
-
-"Claude, stopp etter fem feil på rad."
-"Claude, send meg Slack-melding når du er ferdig."
-"Claude, lag en AI som vurderer om ting ser bra ut visuelt."
-
-Claude foreslo løsninger. Jeg sa ja. Ferdig.
-
-𝗙ø𝗹𝗲𝗹𝘀𝗲𝗻
-
-Starte prosessen med 30 oppgaver. Gjør noe annet. Komme tilbake og se oppgavene tikke av. Én etter én.
-
-Å våkne til en Slack-melding: "🎉 Ferdig. Alle 30 oppgaver fullført."
-
-Å åpne mappen og se en fungerende app. Som jeg ikke skrev. Men som jeg 𝘥𝘦𝘧𝘪𝘯𝘦𝘳𝘵𝘦.
-
-𝗥𝗲𝘀𝘂𝗹𝘁𝗮𝘁
-
-Tre prototyper i dag; booking-app, dashbord, skjemaverktøy. Hver tok én time. Null linjer kode. Bare beskrivelser.
-
-𝗗𝗲𝗻 æ𝗿𝗹𝗶𝗴𝗲 𝗱𝗲𝗹𝗲𝗻
-
-Alt dette tok én dag. Og jeg skraper bare i overflaten.
-
-Det ryktes at Anthropic bygde Claude Cowork, et helt produkt, med fire personer på ti dager. Vi er i starten av noe stort.
-
-De som eksperimenterer nå kommer til å ha et forsprang. Det er ikke lenger AI som er begrensningen, det er deg og meg.
-
-𝗦å 𝗷𝗮. 𝗥𝗮𝗹𝗽𝗵 𝗪𝗶𝗴𝗴𝘂𝗺.
-
-Oppkalt etter Simpsons-karakteren som sier: "I'm learnding!"
-
-Det føles passende :-)
-
-—
-
-Jeg jobber med KI i offentlig sektor. Mer om dette og andre eksperimenter i kommende innlegg.
-
-𝗧𝗶𝗽𝘀: Claude Code Meetup i Oslo arrangeres jevnlig, sjekk [lenke]
-
-#AI #ClaudeCode #VibeCoding #OffentligSektor #Innovasjon
-```
-
-**Why It Worked (Despite Mistakes):**
- **Hook:** Strong - "En dag. 10 000 linjer. Uten å være utvikler." Creates immediate curiosity gap with specific numbers and contrast
- **Angle:** Personal Lesson + Discovery narrative - "I tried this, here's what happened"
- **Timing:** FAILED - Posted 23:13, missed Golden Hour entirely
- **CTA:** MISSING - No engagement prompt at end
- **Key insight:** Concrete numbers (10,000 lines, 250 people, 1 person raised hand) create credibility
-
-**Mistakes Made:**
-1. Posted at 23:13 (should be 08:00)
-2. Link in post body (should be in first comment)
-3. 5 hashtags (should be 3-4)
-4. No CTA (should ask question or invite discussion)
-5. Em dash used (should avoid)
-6. Post was in Norwegian (strategy says English)
-
-**Pattern to Replicate:**
- Hook with specific numbers + contrast works well
- "I'm not X, but I did Y" framing creates relatability
- Concrete timeline (08:00 to 23:00) adds credibility
- "Følelsen" section (emotional payoff) resonates
- Bold-formatted section headers improve readability
-
-**Audience Response Themes:**
- Interest in the technical process
- Questions about Ralph Wiggum technique
- Recognition from Claude Code community
-
-**What to Test Next:**
- Same quality content, but posted at 08:00
- With proper CTA
- Without link in body
- In English
-
---
+(Add your first `## Post N` section above this line once you have a high performer.)

 ## Patterns Across All High-Performing Posts

 **Common Elements:**
- [x] Specific numbers in hook (10,000 lines, 250 people)
- [x] Personal story structure (I did X, here's what happened)
- [x] Concrete timeline and details
- [ ] Strong CTA (not yet tested)
- [ ] Optimal timing (not yet tested)
+
+- [ ] [Element you notice across your best posts]
+- [ ] [Element 2]

 **Audience Preferences (What YOUR Audience Responds To):**
- Format: Story-based posts with concrete details
- Length: ~2,100 characters (slightly over optimal 1,800)
- Tone: Professional but personal, showing vulnerability ("I'm not a developer")
- CTAs: Unknown - need to test
+
+- Format: [Your best-performing format]
+- Length: [Your best-performing length]
+- Tone: [Your best-performing tone]
+- CTAs: [What drives replies for you]

 **Topics That Resonate:**
-1. AI-assisted coding / Vibe coding
-2. [More data needed]
-3. [More data needed]
+
+1. [Topic]
+2. [Topic]

 **Best Posting Times (Based on YOUR Data):**
- Primary: Unknown - need to test 08:00 CET
- Secondary: Unknown - need to test
- **Avoid:** After 21:00 (confirmed by Ralph Wiggum failure)
+
+- Primary: [Time]
+- Secondary: [Time]
+- Avoid: [Time]

 ## Update Log

- 2026-01-24: Added Ralph Wiggum post as baseline reference. Note: Post had good engagement rate (4.98%) despite multiple mistakes, suggesting content quality is strong. Focus on fixing timing, CTA, and link placement for next posts.
+- [Date]: [What you added or learned]
--- a/assets/templates/my-post-templates-template.md
+++ b/assets/templates/my-post-templates-template.md
@ -0,0 +1,249 @@
+# My Custom Post Templates
+
+Save your proven post structures here. When you find a format that works consistently, document it so Claude can replicate the pattern.
+
+---
+
+## Template 1: [Name - e.g., "My Framework Introduction Template"]
+
+**When to use:** [e.g., "When introducing a new framework or model I've developed"]
+
+**Structure:**
+
+```
+[HOOK - Counterintuitive stat or bold statement]
+(1-2 lines, <110 characters)
+
+[CONTEXT - The problem this framework solves]
+(2-3 lines explaining why people struggle)
+
+[FRAMEWORK INTRODUCTION]
+"I developed [Framework Name] to solve this."
+(Brief one-line description)
+
+[COMPONENT BREAKDOWN]
+Stage 1: [Name]
+→ [Key characteristic in one line]
+
+Stage 2: [Name]  
+→ [Key characteristic in one line]
+
+Stage 3: [Name]
+→ [Key characteristic in one line]
+
+[IMPLICATION]
+"Most organizations are stuck at Stage 1.
+Here's what moving to Stage 2 unlocks..."
+(2-3 lines on practical value)
+
+[CTA]
+"Which stage is your organization in?"
+```
+
+**Why this works for me:**
+- [Reason 1 - e.g., "My audience loves actionable frameworks"]
+- [Reason 2 - e.g., "The diagnostic question always generates 15+ comments"]
+
+**Example posts using this template:**
+- [Link to post 1]
+- [Link to post 2]
+
+**Average engagement:** [Metrics]
+
+---
+
+## Template 2: [Name - e.g., "My Before/After Transformation Story"]
+
+**When to use:** [e.g., "When sharing case study or project results"]
+
+**Structure:**
+
+```
+[HOOK - The transformation in numbers]
+"6 months ago: [painful metric]
+Today: [improved metric]"
+
+[THE BEFORE]
+[Organization] was struggling with [specific problem].
+(Paint picture of pain - 3-4 lines)
+
+[THE TURNING POINT]
+We decided to [key decision].
+Most teams choose [alternative]. Here's why we didn't...
+
+[THE APPROACH]
+"Three things mattered:
+• [Element 1]
+• [Element 2]  
+• [Element 3]"
+
+[THE AFTER]
+Results:
+→ [Metric 1]: [Before] → [After]
+→ [Metric 2]: [Before] → [After]
+→ [Metric 3]: [Before] → [After]
+
+[KEY LESSON]
+"The real breakthrough wasn't [expected thing].
+It was [non-obvious insight]."
+
+[CTA]
+"What's been YOUR biggest lesson in [topic]?"
+```
+
+**Why this works for me:**
+- [Reason 1]
+- [Reason 2]
+
+**Average engagement:** [Metrics]
+
+---
+
+## Template 3: [Name - e.g., "My Contrarian Take"]
+
+**When to use:** [e.g., "When challenging conventional wisdom in my field"]
+
+**Structure:**
+
+```
+[HOOK - Bold contrarian statement]
+"Everyone says [conventional wisdom].
+I think that's wrong."
+
+[THE CONVENTIONAL APPROACH]
+Most [target audience] believe [common belief].
+(Explain the mainstream view fairly - 2-3 lines)
+
+[WHY IT FAILS]
+But here's the problem...
+(2-3 specific reasons with examples)
+
+[THE ALTERNATIVE]
+Instead, try this:
+→ [Alternative approach 1]
+→ [Alternative approach 2]
+→ [Alternative approach 3]
+
+[EVIDENCE]
+"I've seen this play out across [X] projects:
+[Specific result/pattern you've observed]"
+
+[NUANCE]
+"To be clear: [conventional wisdom] works if [specific condition].
+But for [your context], [your approach] is better because..."
+
+[CTA]
+"What's your experience? Am I missing something?"
+```
+
+**Why this works for me:**
+- [Reason 1]
+- [Reason 2]
+
+**Average engagement:** [Metrics]
+
+---
+
+## Template 4: [Name - e.g., "My Failure Lesson Post"]
+
+**When to use:** [e.g., "When sharing what didn't work to build trust"]
+
+**Structure:**
+
+```
+[HOOK - Admission of failure]
+"[Approach] should have worked.
+It failed spectacularly."
+
+[SETUP]
+We were trying to [goal].
+The plan: [what you intended to do]
+On paper, perfect.
+
+[THE FAILURE]
+"Here's what actually happened..."
+(Specific description of what went wrong - 3-4 lines)
+
+[WHY IT FAILED]
+Looking back, three mistakes:
+1. [Mistake 1] - We assumed [wrong assumption]
+2. [Mistake 2] - We underestimated [factor]
+3. [Mistake 3] - We ignored [warning sign]
+
+[THE PIVOT]
+"So we tried [different approach] instead.
+That worked because..."
+
+[THE LEARNING]
+"Key lesson:
+[Non-obvious insight that only came from the failure]"
+
+[CTA]
+"Have you failed at [topic] too? What did you learn?"
+```
+
+**Why this works for me:**
+- [Reason 1]
+- [Reason 2]
+
+**Average engagement:** [Metrics]
+
+---
+
+## Template 5: [Name - Your custom template]
+
+**When to use:** [Context]
+
+**Structure:**
+[Your proven structure]
+
+**Why this works for me:**
+[Analysis]
+
+**Average engagement:** [Metrics]
+
+---
+
+## Template Performance Comparison
+
+| Template | Avg. Likes | Avg. Comments | Avg. Reach | Best Use Case |
+|----------|-----------|---------------|------------|---------------|
+| Framework Intro | [X] | [Y] | [Z] | [When] |
+| Before/After | [X] | [Y] | [Z] | [When] |
+| Contrarian | [X] | [Y] | [Z] | [When] |
+| Failure Lesson | [X] | [Y] | [Z] | [When] |
+
+**Insights:**
+[What these patterns tell you about your audience preferences]
+
+---
+
+## Template Selection Guide
+
+**Use Framework template when:**
+- Introducing new model/system
+- Teaching actionable process
+- Want high saves (reference value)
+
+**Use Before/After template when:**
+- Have strong results to share
+- Building credibility
+- Want case study authority
+
+**Use Contrarian template when:**
+- Challenging assumptions
+- Positioning unique POV
+- Want engagement/debate
+
+**Use Failure template when:**
+- Building trust/authenticity
+- Sharing hard-won lessons
+- Want vulnerable connection
+
+---
+
+## Update Log
+
+- [Date]: Created template 1 based on [successful posts]
+- [Date]: Refined template 2 after [pattern observation]
+- [Date]: Added template 3 for [new content type]
--- a/docs/m0/log.md
+++ b/docs/m0/log.md
@ -0,0 +1,59 @@
+# M0 — Implementation Log
+
+Running record of decisions, deviations, and out-of-scope follow-ups discovered
+during M0 execution. Plan: `docs/m0/plan.md` (18 steps). History → git; this file
+captures only what the commit messages cannot.
+
+## Session 3 — Steps 11–13 (2026-06-18)
+
+### Environment reality vs. plan assumptions
+
+The plan was authored assuming the operator's **real `.local.md` runtime data**
+sat in the plugin tree (227-line voice profile, analytics exports, draft queue).
+On this machine that data is **absent** — it is a clean clone:
+
+- `assets/voice-samples/`: only the PII-free placeholder `authentic-voice-samples.md`
+  (+ `.template.md`). No `.local.md` source.
+- `assets/drafts/`: only `.gitkeep`. `assets/analytics/`: only `README.md` + empty `ab-tests/`.
+- The 4 tracked D2 scaffold instances DO exist (`high-engagement-posts.md`,
+  `demographics.md`, `engagement-patterns.md`, `my-post-templates.md`).
+
+**Consequence for Step 12 (live migration):** every `MOVE_FILES` / `MOVE_DIRS`
+entry resolved to an absent source → clean no-op. Only the 4 `COPY_FILES`
+scaffolds were relocated. Result: `migrated — moved 0, copied 4, skipped 0`;
+`.migrated` marker written; idempotent re-run confirmed `already-migrated`.
+
+**Step 12 verify adapted:** the plan's literal check
+(`test -f .../voice-samples/authentic-voice-samples.md`) cannot pass without a
+`.local.md` source to move, so it was replaced with the achievable post-condition:
+`.migrated` marker present + 4 scaffolds external + `migrateData` wired into
+`session-start.mjs` + idempotency. The voice MOVE correctly no-op'd. (Operator
+pre-approved this adaptation before the run.)
+
+### OUT OF M0 SCOPE — git-history scrub of the leaked post (FOLLOW-UP)
+
+`assets/examples/high-engagement-posts.md` held the operator's **real** LinkedIn
+post at HEAD (the "Ralph Wiggum / vibe-coding" post — real names, real engagement
+metrics, real personal narrative). Step 13 scrubbed the **working-tree** content
+to a generic placeholder (0 `## Post N` sections → personalization score 0, no
+PII). **This does not remove the post from git history.** A history rewrite
+(`git filter-repo` / BFG) on `assets/examples/high-engagement-posts.md` is a
+separate, explicit operation — **deferred, not done here** (brief §13: out of M0
+scope). Track until the repo is published.
+
+### Note — external instance retains pre-scrub content (by design)
+
+The Step-12 migration copied `high-engagement-posts.md` to
+`~/.claude/linkedin-studio/examples/high-engagement-posts.md` **before** Step 13
+scrubbed the in-plugin file (B3 ordering). The external copy therefore still holds
+the migrated content. That is the operator's private data dir (outside any repo) —
+the operator may curate it; not an M0 concern.
+
+### D2 scaffolds completed
+
+All 6 scaffolds now have a read-only `*-template.*` seed: `case-study-template.md`
+and `framework-template.md` already shipped; Step 13 added the 4 missing ones
+(`high-engagement-posts-template.md`, `demographics-template.md`,
+`engagement-patterns-template.md`, `my-post-templates-template.md`). The 3
+already-generic instances seeded their templates verbatim; the high-engagement
+template is a freshly-authored generic seed (the old instance was the leak).
--- a/hooks/scripts/tests/personalization-score.test.mjs
+++ b/hooks/scripts/tests/personalization-score.test.mjs
@ -83,3 +83,53 @@ describe('calculateScore — reads external instance data (M0-7)', () => {
    assert.equal(score, 0);
  });
 });
+
+describe('calculateScore — scaffold categories read the external instance (M0-13)', () => {
+  let dataDir, pluginRoot;
+  const saved = { LINKEDIN_STUDIO_DATA: process.env.LINKEDIN_STUDIO_DATA };
+
+  afterEach(() => {
+    for (const d of [dataDir, pluginRoot]) {
+      if (d && existsSync(d)) rmSync(d, { recursive: true, force: true });
+    }
+    dataDir = pluginRoot = undefined;
+    if (saved.LINKEDIN_STUDIO_DATA === undefined) delete process.env.LINKEDIN_STUDIO_DATA;
+    else process.env.LINKEDIN_STUDIO_DATA = saved.LINKEDIN_STUDIO_DATA;
+  });
+
+  test('a populated external high-engagement-posts instance earns the 10 points', () => {
+    ({ dataDir, pluginRoot } = makeRoots());
+    process.env.LINKEDIN_STUDIO_DATA = dataDir;
+    mkdirSync(join(dataDir, 'examples'), { recursive: true });
+    const posts = ['## Post 1', '## Post 2', '## Post 3'].join('\n\n');
+    writeFileSync(join(dataDir, 'examples', 'high-engagement-posts.md'), `# Posts\n\n${posts}\n`, 'utf-8');
+
+    const { score, personalized } = calculateScore(pluginRoot);
+
+    assert.equal(score, 10, '3+ saved posts in the external instance earn the 10 points');
+    assert.equal(personalized, 1);
+  });
+
+  test('the generic placeholder seed (no line-leading ## Post N) scores 0 — no crash', () => {
+    ({ dataDir, pluginRoot } = makeRoots());
+    process.env.LINKEDIN_STUDIO_DATA = dataDir;
+    mkdirSync(join(dataDir, 'examples'), { recursive: true });
+    writeFileSync(join(dataDir, 'examples', 'high-engagement-posts.md'), `# Posts\n\nPlaceholder — add a ## Post N section per saved post.\n`, 'utf-8');
+
+    const { score, personalized } = calculateScore(pluginRoot);
+
+    assert.equal(score, 0, 'a placeholder with no ## Post [0-9] section scores 0');
+    assert.equal(personalized, 0);
+  });
+
+  test('scaffold absent at the external root → 0, no crash (graceful degradation)', () => {
+    ({ dataDir, pluginRoot } = makeRoots());
+    process.env.LINKEDIN_STUDIO_DATA = dataDir;
+    // examples/ dir never created — the category is simply skipped, never throws
+
+    const { score, personalized } = calculateScore(pluginRoot);
+
+    assert.equal(score, 0);
+    assert.equal(personalized, 0);
+  });
+});