feat(linkedin-thought-leadership): v1.0.0 — initial open-source import

Build LinkedIn thought leadership with algorithmic understanding,
strategic consistency, and AI-assisted content creation. Updated for
the January 2026 360Brew algorithm change.

16 agents, 25 commands, 6 skills, 9 hooks, 24 reference docs.

Personal data sanitized: voice samples generalized to template,
high-engagement posts cleared, region-specific references replaced
with placeholders.

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

plugins/linkedin-thought-leadership/references/poll-strategy-guide.md

@@ -0,0 +1,221 @@
+# Poll Strategy Guide
+
+LinkedIn polls generate high impressions but their effectiveness is declining in 2026 due to overuse. Strategic polls still work — generic ones don't. This guide covers when polls are worth it, how to design them, and what to do with the results.
+
+## Poll Effectiveness (2026 Status)
+
+**Reach multiplier:** 1.64x average (down from 2.1x in 2024)
+**Trend:** Declining. LinkedIn is reducing poll distribution to combat low-quality engagement farming.
+**Verdict:** Use sparingly (1-2 per month maximum). Make every poll count.
+
+**Why polls still work when done right:**
+- They create a low-friction engagement action (one click)
+- Results generate curiosity and return visits
+- Follow-up posts based on poll data perform well
+- They provide genuine audience research data
+
+**Why most polls fail:**
+- Generic questions that don't teach anything
+- No follow-up content using the results
+- Overuse (more than 2 per month gets penalized)
+- Options that are obviously "right answer" bait
+
+## When to Use Polls (and When Not To)
+
+### Use a Poll When:
+- You genuinely want audience data to inform future content
+- The question reveals a surprising split in your audience
+- You're testing a hypothesis before writing about it
+- You want to start a conversation about a controversial topic
+- You plan to create follow-up content from the results
+
+### Don't Use a Poll When:
+- You just want easy engagement (engagement farming)
+- The answer is obvious (everyone will pick the same option)
+- You have no plan for the results
+- You've posted a poll in the last 2 weeks
+- The topic doesn't relate to your expertise areas
+
+**Test:** Before posting a poll, ask: "Would I write a follow-up post about these results regardless of the outcome?" If no, skip the poll.
+
+## Poll Design Principles
+
+### Question Types That Work
+
+**1. Industry Trend Poll**
+**Pattern:** "Where is [industry topic] heading?"
+**Works because:** People want to see if their prediction matches the crowd.
+```
+What will be the biggest AI adoption barrier in 2026?
+
+○ Data quality and governance
+○ Talent and skills gap
+○ Integration with legacy systems
+○ Organizational resistance to change
+```
+
+**2. Experience-Based Poll**
+**Pattern:** "What has been your experience with [specific thing]?"
+**Works because:** People engage with questions about their own reality.
+```
+How is your team using AI assistants today?
+
+○ Daily — integrated into workflow
+○ Weekly — specific tasks only
+○ Experimenting — no clear process yet
+○ Not using — waiting to see
+```
+
+**3. Contrarian Poll**
+**Pattern:** "Unpopular opinion check: [bold claim]"
+**Works because:** People love proving they agree or disagree with bold takes.
+```
+Hot take: Most "AI strategies" are just PowerPoint decks.
+
+○ Agree — execution is the gap
+○ Disagree — strategy matters first
+○ Partially — both are needed
+○ It depends on the organization
+```
+
+**4. Decision-Point Poll**
+**Pattern:** "If you had to choose between [A] and [B]..."
+**Works because:** Forces a choice, which triggers emotional engagement.
+```
+If you could only invest in ONE AI capability this year:
+
+○ Copilot for productivity
+○ Custom AI agents
+○ Data platform modernization
+○ AI literacy training for all staff
+```
+
+**5. Knowledge-Test Poll**
+**Pattern:** "What percentage of [thing] do you think [outcome]?"
+**Works because:** People want to test their knowledge against reality.
+```
+What % of enterprise AI projects make it to production?
+
+○ Less than 20%
+○ 20-40%
+○ 40-60%
+○ More than 60%
+```
+
+### Question Types to Avoid
+
+- **"Do you agree?"** — Too simple, no conversation value
+- **"What's your favorite X?"** — Fun but no professional insight
+- **"Yes/No/Maybe"** — Binary polls generate no discussion
+- **"Rate X on a scale"** — Not how polls work on LinkedIn
+- **"Which is better: [obvious winner] or [obvious loser]?"** — No real debate
+
+## Poll Configuration
+
+### Duration
+- **1 day:** Creates urgency, good for time-sensitive topics
+- **3 days:** Sweet spot for most polls — enough time for reach, short enough for relevance
+- **1 week:** Only for broad audience research questions
+- **2 weeks:** Too long — results feel stale, engagement drops off
+
+**Recommendation:** Default to 3 days. Use 1 day for breaking news or controversial takes.
+
+### Number of Options
+- **2 options:** Only for true binary choices (rare)
+- **3 options:** Good for clear categories
+- **4 options:** Best default — covers the spectrum without overwhelming
+
+**Tip:** Always include one option that's slightly unexpected or provocative. This drives comments.
+
+## Caption Strategy
+
+The caption is more important than the poll itself. A poll without context is engagement farming. A poll with a strong caption is audience research.
+
+### Caption Structure
+```
+[1-2 sentences of context: why you're asking this]
+
+[The insight or observation that led to the question]
+
+Vote below, and I'll share what I'm seeing in [your context] in the comments.
+
+#[topic] #[niche]
+```
+
+### Caption Template
+```
+I've been talking to [N] [audience members] about [topic] this month.
+
+The split in perspectives is surprising. [Brief observation about what you're seeing.]
+
+Curious if LinkedIn reflects the same pattern:
+
+[Poll renders here]
+
+I'll share what the data shows from my conversations once the poll closes.
+```
+
+### Caption Rules
+- **300-400 characters** (not too long — the poll takes visual space)
+- **Always provide context** for why you're asking
+- **Promise a follow-up** to incentivize voting
+- **Don't reveal your own answer** in the caption (kills curiosity)
+
+## Follow-Up Strategy
+
+The real value of a poll is what you do after it closes. Plan your follow-up before you post the poll.
+
+### Follow-Up Post Template (24 hours after poll closes)
+```
+[N] people voted on my poll about [topic].
+
+The results: [brief summary]
+
+What surprised me: [unexpected finding]
+
+Here's what this means:
+[3-5 insights based on the results + your expertise]
+
+The bigger lesson: [connect to your thought leadership angle]
+
+What do you think — did the results match your expectation?
+```
+
+### Follow-Up Actions
+
+| Result Pattern | Follow-Up Action |
+|---------------|-----------------|
+| Clear winner (70%+) | Post about why the consensus is right (or wrong) |
+| Even split (40/60) | Write about why this divide exists |
+| Surprising result | Share context that explains the unexpected outcome |
+| Low engagement | Don't follow up — the topic didn't resonate |
+
+### Follow-Up Timeline
+1. **During poll:** Reply to commenters, add your own perspective in comments
+2. **Poll closes:** Screenshot the results
+3. **Next day:** Post follow-up with analysis and insights
+4. **Week after:** Reference the poll data in related content ("Last week, 68% of you said...")
+
+## Poll Frequency Rules
+
+| Frequency | Effect |
+|-----------|--------|
+| 1 per month | Optimal — each poll feels intentional |
+| 2 per month | Acceptable — space them 2+ weeks apart |
+| 1 per week | Too much — reach penalty, audience fatigue |
+| Multiple per week | Algorithm suppression, looks like engagement farming |
+
+**Calendar rule:** Never post polls in consecutive weeks. Alternate with text, carousel, and story posts.
+
+## Quality Checklist
+
+Before posting a poll, verify:
+
+- [ ] The question relates to your expertise areas
+- [ ] No obvious "right answer" among the options
+- [ ] You have a follow-up post planned
+- [ ] Caption provides context (not just the question)
+- [ ] Duration is set (default: 3 days)
+- [ ] You haven't posted a poll in the last 2 weeks
+- [ ] At least one option is slightly provocative or unexpected
+- [ ] The results will be genuinely useful for your audience