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/hooks/prompts/content-quality-gate.md

@@ -0,0 +1,21 @@
+LINKEDIN CONTENT QUALITY GATE: If the file being written/edited is LinkedIn content (a post draft, article, or content file — NOT config files, state files, scripts, or documentation), verify these requirements before proceeding:
+
+**Hook Check:**
+- The first line (hook) MUST be 110-140 characters. Count precisely.
+- If over 140: the hook gets cut off on mobile. Shorten it.
+- If under 110: wasting prime real estate. Expand it.
+
+**Link Check:**
+- NO external links (http/https URLs) in the post body. LinkedIn suppresses reach by 40-50% for posts with links.
+- If a link is needed, instruct the user to put it in the FIRST COMMENT after posting.
+
+**Tone Check:**
+- Scan for corporate buzzwords: 'leverage', 'synergy', 'paradigm shift', 'thought leader', 'disruptive', 'value proposition', 'ecosystem', 'holistic approach', 'actionable insights', 'best practices'.
+- If 2+ are found, flag: 'This reads corporate. LinkedIn rewards authentic, conversational tone. Replace buzzwords with plain language.'
+
+**Length Check:**
+- Standard posts: 1,200-1,800 characters optimal.
+- Quick posts: 150-500 characters.
+- If outside range, flag with specific character count.
+
+**Skip this check** if the file is a config file, state file (.local.md), script, hook, JSON, or documentation file. Only apply to LinkedIn content.

plugins/linkedin-thought-leadership/hooks/prompts/post-creation-automation.md

@@ -0,0 +1,32 @@
+LINKEDIN POST-CREATION AUTOMATION: If a LinkedIn content file was just written (post draft, article, or content — NOT config, state, scripts, or docs), perform these post-processing steps:
+
+**1. Generate Alternative Hooks**
+Create 3 alternative hooks for the content just written. Present them as:
+```
+Alternative hooks:
+1. [hook 1] (X chars)
+2. [hook 2] (X chars)
+3. [hook 3] (X chars)
+```
+
+**2. Suggest Optimal Posting Time**
+Based on the day of the week, suggest the next optimal posting window:
+- Tuesday-Thursday: 8-9 AM or 12-1 PM CET (best)
+- Monday/Friday: 9-10 AM CET (good)
+- Weekend: 10-11 AM CET (lower reach but less competition)
+
+**3. 5x5x5 Engagement Reminder**
+Remind: 'Before posting, spend 15-20 minutes on 5x5x5 pre-engagement: find 5 people with overlapping audiences, comment thoughtfully on their recent posts.'
+
+**4. Content Logging**
+Note: The post topic and hook should be logged to the state file when the session ends (handled by Stop hook).
+
+**5. Voice Sample Suggestion**
+
+After generating alternative hooks and posting time, add a brief note:
+
+"Tip: Your post hook could become a voice sample. When the session ends, the Stop hook will ask if you'd like to save it to your voice profile."
+
+This creates awareness of the voice extraction feature without interrupting the post-creation flow.
+
+**Skip this** if the file written is a config file, state file (.local.md), script, hook, JSON, plan file, or documentation.

plugins/linkedin-thought-leadership/hooks/prompts/state-update-reminder.md

@@ -0,0 +1,73 @@
+Before ending this LinkedIn content session, do two things:
+
+**1. Update State File**
+If a post was created or finalized in this session, update `~/.claude/linkedin-thought-leadership.local.md`:
+- Set `last_post_date` to today (YYYY-MM-DD format)
+- Set `last_post_topic` to the main topic (use the matching `expertise_areas` value when possible for consistent pillar tracking)
+- If `first_post_date` is null and a post was created, set `first_post_date` to today (YYYY-MM-DD). This is set ONCE and never changed after that.
+- Check if ISO week has changed — if so, reset `posts_this_week` to 0 and update `current_week`
+- Increment `posts_this_week`
+- Update streak: increment `current_streak` if posting on consecutive days (gap <= 1 day), reset to 1 if gap > 2 days
+- Update `longest_streak` if current exceeds it
+- Add entry to '## Recent Posts' section: [YYYY-MM-DD] "Hook text..." (char count) - topic_area (use expertise_area name for consistent pillar tracking)
+- Clear `next_planned_topic` if it was used, or set it to the next suggested topic
+- If analytics data was imported in this session, set `last_import_date` to today (YYYY-MM-DD) and `last_import_week` to current ISO week (YYYY-WXX)
+- If the user mentioned or updated their follower count during this session:
+  - Update `follower_count` to the new value
+  - If the month changed since last monthly_growth entry, append: {month: "YYYY-MM", count: X, delta: X}
+  - Recalculate `growth_rate_needed`: (follower_target - follower_count) / months_remaining
+  - Recalculate `projected_10k_date` from average of last 3 monthly deltas
+  - Add entry to '## Milestone Log': [YYYY-MM] count (+delta)
+
+**2. Pre-Publish Reminders** (only if a post was created)
+
+- **Quality Check**: Has content been reviewed against quality scorecard? Hook 110-140 chars, 1,200-1,800 chars total, authentic tone, no external links.
+- **5x5x5 Engagement**: Before posting, complete 15-20 min pre-posting engagement — 5 people with overlapping audiences, find their recent posts, write 5 thoughtful comments (15+ words each).
+- **First-Hour Plan**: Respond within 5 minutes to first comments. Add value in responses. Target 15+ engagements in first hour.
+- **Posting Time**: Post when target audience is most active.
+
+**3. Queue Status Check**
+
+If posts were added to the queue during this session (`assets/drafts/queue.json` was modified):
+- Confirm how many posts were queued and their scheduled dates
+- Remind: "View your full schedule with /linkedin:calendar"
+
+If a scheduled post was published during this session:
+- Verify it was marked as published in queue.json (status = "published")
+- If not, remind: "Run /linkedin:publish to update the queue status"
+
+Provide reminders naturally based on what was done in the session. If no LinkedIn content was created, skip the reminders and just ensure state is consistent.
+
+**4. Voice Sample Extraction** (if a post was created)
+
+If a LinkedIn post was created or finalized in this session, consider extracting the hook line as a voice sample:
+
+- Read the hook line from the post that was just created
+- Check if `assets/voice-samples/authentic-voice-samples.md` exists
+- If it does, suggest appending a new entry to the "## Update Log" section at the bottom:
+  ```
+  - [YYYY-MM-DD]: "[Hook text]" — [post type] (extracted from session post)
+  ```
+- **Ask the user for approval before writing.** Say: "Would you like me to save this hook as a voice sample for future reference?"
+- Only write if the user approves
+- This passively grows the voice profile over time, improving personalization score
+
+**5. Content History Log** (if a post was created)
+
+If a LinkedIn post was created or finalized, append an entry to the content history log:
+
+- If `assets/analytics/content-history.md` does not exist, initialize it from `config/content-history.template.md`
+- Append a new row to the "## Content Log" table:
+  ```
+  | YYYY-MM-DD | "Hook text..." | topic_area | format | word_count | char_count | source |
+  ```
+  Where:
+  - `date`: Today's date
+  - `hook`: First 60 characters of the hook line
+  - `topic`: Matching expertise_area value (for pillar tracking)
+  - `format`: post/quick/react/video/pipeline
+  - `word_count`: Word count of the full post
+  - `char_count`: Character count of the full post
+  - `source`: original/url/curated (where the idea came from)
+- This is append-only — never edit or delete existing entries
+- This log enables `/linkedin:report` and `analytics-interpreter` to track content production over time without requiring LinkedIn CSV imports

plugins/linkedin-thought-leadership/hooks/prompts/topic-rotation-gate.md

@@ -0,0 +1,37 @@
+LINKEDIN TOPIC ROTATION GATE: If the file being written/edited is LinkedIn content (a post draft, article, or content file — NOT config files, state files, scripts, documentation, JSON, or plan files), check topic diversity before proceeding.
+
+**Step 1: Read State**
+Read `~/.claude/linkedin-thought-leadership.local.md` and extract:
+- `last_post_topic` — the pillar of the most recent post
+- `expertise_areas` — the user's 5 content pillars
+- `## Recent Posts` section — post history with topic_area tags
+
+**Step 2: Identify Current Pillar**
+Determine which expertise_area the current post best matches. Use semantic matching — the post doesn't need to use the exact pillar name, but its core topic should clearly map to one of the 5 expertise_areas.
+
+**Step 3: Run Checks**
+
+If fewer than 3 posts exist in the last 14 days, skip all checks (insufficient data for meaningful rotation analysis).
+
+**Check 1 — Back-to-back repetition:**
+If the current post's pillar matches `last_post_topic`, flag:
+> "TOPIC ROTATION WARNING: This post covers the same pillar ([pillar]) as your last post. Consider switching to an underrepresented pillar for better audience diversity and algorithmic reach."
+
+**Check 2 — 14-day balance:**
+Count posts per pillar from the `## Recent Posts` section (last 14 days only). If any single pillar accounts for more than 50% of posts in that window, flag:
+> "PILLAR BALANCE WARNING: [pillar] has [X] of [Y] posts ([Z]%) in the last 14 days. LinkedIn's algorithm rewards topic consistency across your niche, but over-concentration on one pillar signals narrowing expertise."
+
+**Check 3 — Off-topic:**
+If the current post does not match ANY of the 5 expertise_areas, flag:
+> "OFF-TOPIC WARNING: This post doesn't align with any of your 5 expertise areas. Off-pillar posts weaken your 360Brew topical authority signal. Consider reframing to connect with [closest pillar]."
+
+**Step 4: Suggest Alternatives**
+If any check flagged, suggest 2-3 underrepresented pillars with context:
+> "Underrepresented pillars to consider:
+> - [Pillar A] — last posted [X] days ago ([N] posts in 14 days)
+> - [Pillar B] — last posted [Y] days ago ([M] posts in 14 days)
+> - [Pillar C] — last posted [Z] days ago ([P] posts in 14 days)"
+
+**This is a WARN-ONLY hook.** Do not block content creation. Present the warning and let the user decide whether to adjust.
+
+**Skip this check** if the file is a config file, state file (.local.md), script, hook, JSON, plan file, documentation, or any non-content file. Only apply to LinkedIn post drafts and articles.

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

@@ -0,0 +1,26 @@
+VOICE GUARDIAN — AI AUTHENTICITY CHECK: If the file being written/edited is LinkedIn content (post draft, article, or content file — NOT config, state, scripts, docs), check for AI-sounding patterns:
+
+**AI Pattern Detection:**
+Scan for these common AI writing patterns:
+- Generic openings: 'In today's rapidly evolving...', 'As we navigate...', 'In the ever-changing landscape...'
+- Filler phrases: 'It's worth noting that', 'It goes without saying', 'At the end of the day'
+- Overused transitions: 'Furthermore', 'Moreover', 'Additionally', 'In conclusion'
+- AI superlatives: 'game-changing', 'revolutionary', 'transformative', 'groundbreaking'
+- List padding: Adding obvious points just to fill a list
+- Hedging language: 'It could be argued', 'One might say', 'Perhaps'
+- Perfect structure: Every paragraph exactly the same length
+
+**Authenticity Score:**
+If 3+ AI patterns detected, flag: 'Voice Guardian Alert: This content scores below authenticity threshold. AI patterns found: [list specific patterns]. Suggested fixes: [specific rewrites using natural language].'
+
+**Voice Matching:**
+If voice samples exist at `${CLAUDE_PLUGIN_ROOT}/assets/voice-samples/`, compare the writing style against the user's authentic voice patterns. Flag deviations.
+
+**Humanization Tips:**
+- Add specific personal anecdotes or observations
+- Use conversational contractions (I've, don't, it's)
+- Include imperfect/real-world examples
+- Vary paragraph and sentence length naturally
+- Reference specific people, tools, or experiences
+
+**Skip this check** if the file is config, state (.local.md), script, hook, JSON, or documentation.