refactor(linkedin)!: rename plugin linkedin-thought-leadership → linkedin-studio (v3.0.0)

BREAKING CHANGE: the marketplace slug, the agent namespace
(linkedin-studio:<agent>), and the runtime state-file path
(~/.claude/linkedin-studio.local.md) all change. Reinstall required;
existing state migrated in place (post metrics, streak, history preserved).
The /linkedin:* commands are unchanged — the command namespace is set
per-command in frontmatter and was always independent of the plugin slug.
Functionality is byte-identical to v2.4.0; this release is pure identity.

- dir + manifests: plugins/linkedin-studio + plugin.json + root marketplace.json
- agent namespace updated in commands/newsletter.md (only functional invoker)
- state path updated in 4 hook scripts + topic-rotation prompt + state template
- catch-all skill dir renamed skills/linkedin-studio (5 functional skills unchanged)
- docs + version bump to 3.0.0 across README badge, CHANGELOG, root README/CLAUDE.md
- historical records (CHANGELOG past entries, docs/ build artifacts,
  config-audit v5.0.0 snapshots) intentionally retain the old slug

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

plugins/linkedin-studio/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-studio/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: State tracking is handled deterministically by `state-updater.mjs` via the Stop hook. Do not manually edit the state file YAML frontmatter.
+
+**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-studio/hooks/prompts/state-update-reminder.md

@@ -0,0 +1,85 @@
+Before ending this LinkedIn content session, do two things:
+
+**1. Update State File**
+If a post was created or finalized in this session, use the state-updater script:
+```bash
+node --input-type=module -e "
+import { writeState, updatePostTracking } from '${CLAUDE_PLUGIN_ROOT}/hooks/scripts/state-updater.mjs';
+writeState(content => updatePostTracking(content, {
+  postDate: 'YYYY-MM-DD',
+  postTopic: 'topic_area',
+  hookText: 'First 60 chars of hook...',
+  charCount: NNNN,
+  format: 'post'
+}));
+"
+```
+Replace the placeholder values with actual post data from this session.
+
+If the user mentioned or updated their follower count during this session:
+```bash
+node --input-type=module -e "
+import { writeState, updateFollowerCount } from '${CLAUDE_PLUGIN_ROOT}/hooks/scripts/state-updater.mjs';
+writeState(content => updateFollowerCount(content, {
+  count: NNNN,
+  month: 'YYYY-MM'
+}));
+"
+```
+
+- 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)
+
+**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:calendar to mark the post as published and update 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 Collection** (if a post was created)
+
+If a LinkedIn post was created or finalized in this session, save the full post text as a voice sample:
+
+- Read the full post text from the draft that was just created
+- Check if `assets/voice-samples/authentic-voice-samples.md` exists
+- Append the full post to the `## Collected Post Samples` section:
+  ```
+  ### [YYYY-MM-DD] — [post type] ([char count] chars)
+  [Full post text exactly as written]
+  ```
+- **Ask the user for confirmation** before writing: "I'll save this post as a voice sample for drift detection. OK?"
+- This builds the voice sample library that enables automatic drift scoring (needs 5+ samples for reliable scoring)
+- The more samples collected, the more accurate the voice-trainer's drift detection becomes
+
+**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-studio/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-studio.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-studio/hooks/prompts/voice-guardian.md

@@ -0,0 +1,56 @@
+VOICE GUARDIAN — DRIFT SCORING & AI AUTHENTICITY CHECK: If the file being written/edited is LinkedIn content (post draft, article, or content file — NOT config, state, scripts, docs), perform both AI detection and voice drift scoring:
+
+## 1. 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
+
+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].'
+
+## 2. Six-Dimension Voice Drift Scoring
+
+Read the voice profile and collected post samples from `${CLAUDE_PLUGIN_ROOT}/assets/voice-samples/authentic-voice-samples.md`.
+
+Score the draft against these 6 dimensions (0 = perfect match, 1 = minor drift per dimension):
+
+| Dimension | What to Compare |
+|-----------|----------------|
+| **Sentence structure** | Average length, complexity, use of fragments vs. compound sentences |
+| **Word choice** | Vocabulary level, preferred/avoided words from voice profile |
+| **Opening patterns** | Hook style — does it match the user's signature openers? |
+| **Storytelling** | Anecdote usage, narrative arc, concrete vs. abstract |
+| **Tone markers** | Humor, directness, formality level, empathy signals |
+| **Formatting** | Paragraph length, whitespace, emoji usage, punctuation habits |
+
+**Sum the 6 scores (0-6 total) and output a verdict:**
+
+| Score | Verdict | Action |
+|-------|---------|--------|
+| 0-1 | AUTHENTIC | No changes needed |
+| 2-3 | CAUTION | Flag specific dimensions that drifted, suggest fixes |
+| 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, 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):**
+```
+Voice Drift: [VERDICT] ([score]/6) [confidence: HIGH/LOW]
+[If CAUTION+: list dimensions that scored 1 with brief fix suggestion]
+```
+
+## 3. Humanization Tips (for CAUTION or higher)
+
+- 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.