open/ktg-plugin-marketplace
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity Actions

feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command

Browse source 
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Kjell Tore Guttormsen 2026-04-08 08:58:35 +02:00
commit 5be9c8e47c
27 changed files with 1723 additions and 73 deletions
Download patch file Download diff file Expand all files Collapse all files

59
plugins/linkedin-thought-leadership/references/algorithm-signals-reference.md
View file

@ -1,4 +1,4 @@
# LinkedIn Algorithm Signals Reference (January 2026)
# LinkedIn Algorithm Signals Reference (April 2026)
Quick reference for ranking signals, weights, and penalties. For detailed context, see SKILL.md.
@ -28,6 +28,7 @@ Quick reference for ranking signals, weights, and penalties. For detailed contex
| Signal | Weight | Notes |
|--------|--------|-------|
| Delayed engagement (24-72h) | 4-6x boost | Algorithm resurfaces quality content days after publication |
| Profile views from post | +10-15% | Interest signal, potential follower conversion |
| Click "see more" | +5-10% | Hook worked, engagement signal |
| Reactions (all types) | 0.2x | 5x less valuable than comments |
@ -38,7 +39,9 @@ Quick reference for ranking signals, weights, and penalties. For detailed contex
| Signal | Penalty | Notes |
|--------|---------|-------|
| 5+ hashtags | -68% | Spam signal, triggers AI classifier |
| AI-generated comments | -30% reach, -55% engagement | Detected and penalized - use human comments only |
| AI-generated comments | -30% reach, -55% engagement | Detected and penalized — use human comments only |
| Engagement pods | Shadow-ban | LinkedIn VP: goal to make pods "entirely ineffective". Comment velocity + account relationship analysis active |
| Third-party script comments | Removed | Comments via automation tools removed from "Most Relevant" feed |
| Off-topic for profile | -40-60% | 360Brew failure - profile doesn't validate expertise |
| External link in body | -25-40% | Platform retention focus - use first comment instead |
| Engagement bait phrases | -30-50% | "Comment YES if...", "Tag someone who...", "Type 1 for..." |
@ -66,10 +69,10 @@ Quick reference for ranking signals, weights, and penalties. For detailed contex
| Format | Reach Multiplier | Engagement Rate | Best For |
|--------|------------------|-----------------|----------|
| PDF/Carousel | 1.6x reach | 24.42% engagement | Frameworks, guides, step-by-step. 12 slides optimal, 25-50 words/slide |
| PDF/Carousel | 3.4x reach | 1.92% engagement | Frameworks, guides, step-by-step. 7 slides optimal (5-10 range), 25-50 words/slide. 35% click-through minimum or penalty |
| Multi-image | 1.3x reach | 6.60% engagement | Before/after, comparisons, processes. Best for 5K-10K follower accounts |
| Polls | 1.64x reach (declining) | 1.5-2% | Audience research only. Declining effectiveness in 2026 |
| Video (90s) | 1.4x reach | Variable | Personal connection. Always add captions (85% watch muted) |
| Video (60s) | 1.4x reach | Variable | Personal connection. Vertical 9:16 gets distribution boost. 30% completion rate minimum or zero reach. Always add captions (85% watch muted) |
| Text-only | 1.17x reach | 3-5% | Thought leadership, stories, opinions. Generates best comment quality |
| Link posts | -25-40% | <1% | Avoid if possible. Use first comment for links |
@ -80,13 +83,27 @@ Quick reference for ranking signals, weights, and penalties. For detailed contex
| Post length | 1,200-1,800 chars | <1,000 (-25%) or >2,500 (-32%) |
| Hook length | <140 chars | >140 truncated on mobile "see more" |
| Hashtags | 3-4 | 5+ triggers -68% penalty |
| Video length | 90 seconds | <30s low dwell, >3min high drop-off |
| Video length | 60 seconds | <30s low dwell, >90s retention drops. 30% completion gate |
| Posting frequency | 3-5x/week | <2x loses consistency, >2x/day can fatigue |
| Carousel slides | 12 slides | <8 too short, >15 completion drops |
| Carousel slides | 7 slides | <5 too short, >10 diminishing returns, >15 completion drops 40% |
| Caption (carousel) | <500 chars | Focus attention on slides |
| About section | 2,600 chars | Use all available space, front-load keywords |
| Headline | 220 chars | Include target audience + outcome |
## 2026 Reach Context
Overall organic reach declined significantly in 2026. This affects everyone — focus on relative performance (your posts vs your baseline), not absolute numbers.
| Metric | Change | Notes |
|--------|--------|-------|
| Total reach | -47% YoY | Platform-wide decline |
| Video content | -72% YoY | Poor video penalized harder, good video still rewarded |
| Text posts | -34% YoY | Most resilient format |
| Company pages | ~1.6% of followers | Personal profiles outperform company pages 8x |
| Posting cadence | 2-5x/week | Sweet spot unchanged despite reach decline |
**Implication:** The algorithm rewards precision over broadcast. Smaller, engaged audiences outperform large but passive ones. 1:1 connections are now more valuable than follower count.
## Posting Time Windows (CET/European Audience)
| Day | Peak Time | Notes |
@ -112,10 +129,28 @@ Quick reference for ranking signals, weights, and penalties. For detailed contex
| 1. Quality Classifier | 0-30s | AI spam/quality check + 360Brew profile validation | Ensure profile matches post topic |
| 2. Initial Test | 0-90min | 6-10% of connections see post | Stay active, respond to all comments |
| 3. Extended Distribution | 1-24h | 2nd/3rd degree if velocity good | Continue engagement, add value in comments |
| 4. Long-tail | 24-72h+ | Evergreen circulation, search/recommendations | Let compound effects work |
| 4. Long-tail | 24-72h+ | Evergreen circulation. Delayed engagement now yields 4-6x better performance. Algorithm resurfaces high-quality older content | Let compound effects work — high-dwell posts stay active up to 7 days |
**Stage 2 threshold:** 15+ engagements in first hour = unlock Stage 3.
## Depth Score (2026)
LinkedIn's primary content ranking metric. Measures actual engagement duration, not surface interactions. The feed now uses LLM-generated embeddings and transformer-based Generative Recommender models for semantic relevance scoring.
| Factor | Impact | Notes |
|--------|--------|-------|
| Time spent reading/watching | Primary signal | Replaced likes as #1 ranking factor |
| Slide completion (carousel) | High | Each slide click = engagement signal. 7 slides optimal for completion |
| Video watch percentage | High | 30% minimum completion or zero distribution |
| Scroll-back behavior | Medium | Re-reading = strong quality signal |
| Save after reading | Highest | Save + high dwell = maximum distribution boost |
**Distribution impact:**
- High-dwell posts: active in feeds up to **7 days**
- Low-dwell posts: dead after **24 hours**
- First-hour dwell time determines post lifecycle
- Minimalist carousel design: +12% completion rate vs complex backgrounds
## 360Brew Profile Validation (January 2026)
**The algorithm validates your profile BEFORE distributing content.**
@ -124,7 +159,7 @@ Quick reference for ranking signals, weights, and penalties. For detailed contex
|---------------------|----------------|----------------|
| About Section | Specific expertise claims, domain terminology | Rewrite with concrete expertise statements |
| Experience Section | Impact statements with metrics | Add quantified achievements |
| Content History | Previous posts on this topic, anecdotal evidence | Build topic consistency over 90+ days |
| Content History | Previous posts on this topic, anecdotal evidence | Requires 90 days of aligned posting for full expertise categorization. Topic mismatch limits reach directly |
| Network Quality | Connected to professionals in your field | Connect with relevant domain experts |
| Engagement Patterns | Do you comment on posts in your expertise area? | Daily: 3-5 thoughtful comments in your domain |
@ -165,17 +200,17 @@ Quick reference for ranking signals, weights, and penalties. For detailed contex
## Red Flags to Avoid
- Engagement pods (actively detected, shadow-ban risk)
- Engagement pods (LinkedIn VP: goal to make pods "entirely ineffective" — comment velocity analysis and account relationship patterns actively detect manufactured engagement)
- Pitch-slapping in DMs
- Posting same content as company page
- Random topics outside demonstrated expertise
- "Great post!" style generic comments
- "Great post!" style generic comments (harm reach even without pod involvement)
- Excessive self-promotion (>20% of content)
- Tagging unrelated people for reach
- Using AI-generated comments (55% engagement penalty)
---
*Last updated: January 2026*
*Last updated: April 2026*
*Sources: Research synthesis from Richard van der Blom (Algorithm Research 2025), Lara Acosta (SLAY Framework), 360Brew algorithm analysis, LinkedIn Engineering Blog, Buffer (2M+ post analysis), Sprout Social (2.5B engagements), Justin Welsh, Jasmin Alic, Sahil Bloom case studies*
*Sources: Research synthesis from Richard van der Blom (Algorithm Research 2025), Lara Acosta (SLAY Framework), 360Brew algorithm analysis, LinkedIn Engineering Blog, Buffer (2M+ post analysis), Sprout Social (2.5B engagements), Justin Welsh, Jasmin Alic, Sahil Bloom case studies. April 2026 update: ALM Corp (LLM architecture analysis), Botdog (360Brew deep dive), DesignACE (engagement signal weights), ContentIn (format strategy guide), UseVisuals (carousel statistics 2026), Visla (video format 2026)*

40
plugins/linkedin-thought-leadership/references/linkedin-formats.md
View file

@ -46,20 +46,21 @@ Choosing the right format isn't just about engagement rates—it's about underst
- Why it works: Encourages completion, maximizes dwell time
- Best for: Frameworks, step-by-step guides, data visualization
**2. Native documents (PDFs): 24.42% engagement rate**
**2. Native documents (PDFs): High engagement (historically 24.42%, likely inflated)**
- Note: The 24.42% figure is from 2025 studies that conflated PDF documents with multi-image carousels. Current carousel-specific data shows 1.92% engagement rate (still highest of all formats). PDF documents may still perform higher due to download value.
- Great for frameworks, step-by-step content, detailed insights
- Keeps users on platform (no external link penalty)
- Downloadable = high perceived value
- Significant increase in engagement rate in 2026
- Best for: Comprehensive guides, templates, detailed analyses
**3. Video posts: 5.60% engagement rate**
- Optimal length: 90 seconds for engagement
- Optimal length: 60 seconds (2026 sweet spot, down from 90s)
- **Critical:** 30% minimum completion rate or video gets zero distribution
- LinkedIn Live: 12-24x engagement vs standard posts
- 85% watch without sound (captions essential)
- Vertical 4:5 aspect ratio (1080x1350) preferred over square
- First 3 seconds determine 70% of retention
- Note: Videos under 90 seconds optimal for engagement and dwell time balance
- **Vertical 9:16 (1080×1920)** now gets distribution boost (3-4x watch duration vs landscape). 4:5 still acceptable but deprioritized
- First 3 seconds determine 70% of retention — 3-second hook is critical
- Note: Overall video reach down 72% YoY — but good video is rewarded more than ever
- Best for: Personal stories, quick insights, behind-the-scenes
- See "Video Content Deep Dive" section below for comprehensive guidance
@ -186,7 +187,7 @@ Algorithm prioritizes content that keeps users on platform longer.
- Content that makes people pause and think
**What doesn't improve dwell time despite engagement:**
- Videos under 90 seconds (balance engagement with dwell time)
- Videos under 60 seconds (balance engagement with completion rate)
- Very short posts (quick reaction, quick scroll)
- Polls (interaction but low time investment)
@ -287,7 +288,7 @@ Immediate engagement in first hour is critical for triggering subsequent waves.
**The Data Reality:**
- Video posts get high impression counts
- BUT: Engagement rates are often lower than text posts
- Videos under 90 seconds optimal for balancing engagement and dwell time
- Videos under 60 seconds optimal for balancing engagement and completion rate (30% minimum completion gate)
- Algorithm prioritizes dwell time over impressions
**What This Means:**
@ -472,9 +473,9 @@ Video isn't the silver bullet many creators think it is. Text-based thought lead
- Your comfort pace is usually 10-20% too slow
**5. Length Optimization**
- Ideal: 90 seconds (sweet spot for engagement vs dwell time)
- Acceptable: 60-120 seconds
- Avoid: <30 seconds (too shallow) or >2 minutes (retention drops)
- Ideal: 60 seconds (2026 sweet spot — maximizes completion rate)
- Acceptable: 30-90 seconds
- Avoid: >90 seconds (completion rate drops, 30% minimum required for any distribution)
**Editing tools by skill level:**
@ -532,13 +533,14 @@ Video isn't the silver bullet many creators think it is. Text-based thought lead
### Technical Specifications
**Video Format & Resolution:**
- **Aspect ratio:** Vertical 4:5 (1080x1350) preferred for mobile optimization
- Vertical 4:5: 1080x1350px (optimal for 2026)
- Square 1:1: 1080x1080px (acceptable)
- If using 16:9: 1920x1080px minimum
- **Aspect ratio:** Vertical 9:16 (1080x1920) now gets distribution boost in LinkedIn's immersive feed
- Vertical 9:16: 1080x1920px (optimal for 2026 — 3-4x watch duration vs landscape, 100% mobile viewport)
- Vertical 4:5: 1080x1350px (still acceptable)
- Square 1:1: 1080x1080px (deprioritized)
- If using 16:9: 1920x1080px minimum (only 25% of mobile viewport)
- **File format:** MP4 (H.264 codec)
- **Maximum file size:** 5GB
- **Maximum length:** 10 minutes (but aim for 45-90 seconds)
- **Maximum length:** 10 minutes (but aim for 30-60 seconds. 30% completion rate minimum or zero distribution)
- **Frame rate:** 30fps standard, 60fps for smooth motion
**Lighting:**
@ -639,11 +641,11 @@ Before posting any video, verify:
- [ ] Hook grabs attention in 3 seconds
- [ ] Clear value delivered (lesson/insight)
- [ ] Tight editing (no unnecessary seconds)
- [ ] Length: 90 seconds optimal
- [ ] Length: 60 seconds optimal (30% completion rate minimum)
- [ ] Ends with engagement-focused CTA
**Technical:**
- [ ] Vertical 4:5 format (1080x1350) for maximum reach
- [ ] Vertical 9:16 format (1080x1920) for maximum reach in immersive feed
- [ ] Professional captions added
- [ ] Audio quality clear and consistent
- [ ] Thumbnail captures attention
@ -657,7 +659,7 @@ Before posting any video, verify:
- [ ] Complements overall content strategy
- [ ] Doesn't include external links
**Bottom Line on Video:** Use strategically when it genuinely adds value beyond text. Prioritize authenticity over production quality. Focus on 90 second videos that deliver concentrated insights. Always optimize for mobile-first consumption with vertical 4:5 format, captions and strong hooks.
**Bottom Line on Video:** Use strategically when it genuinely adds value beyond text. Prioritize authenticity over production quality. Focus on 60-second videos that deliver concentrated insights. LinkedIn now requires 30% minimum completion rate for any distribution — shorter is safer. Always optimize for mobile-first consumption with vertical 9:16 format, captions, and 3-second hooks.
## Creator Mode Features (Available to All Users)

6
plugins/linkedin-thought-leadership/references/linkedin-growth-playbook-2025-2026.md
View file

@ -178,7 +178,7 @@ LinkedIn removed hashtag following, hashtag pages, and "Talks About" sections in
- 381 engagements vs 110 for text (247% increase)
**Optimal specifications:**
- 12 slides
- 7 slides (5-10 range, completion drops 40% beyond 15)
- 25-50 words per slide
- Caption under 500 characters
- Each slide swipe counts as engagement signal
@ -211,9 +211,9 @@ LinkedIn removed hashtag following, hashtag pages, and "Talks About" sections in
- Often deliver lower meaningful engagement than well-crafted text posts
**If using video:**
- Optimal length: 90 seconds for engagement and dwell time balance
- Optimal length: 60 seconds (2026 sweet spot — 30% completion rate minimum for any distribution)
- Always add captions (85% watch with sound off)
- Use vertical 4:5 format (1080x1350) for mobile optimization
- Use vertical 9:16 format (1080x1920) for immersive feed distribution boost
### Text-Only Posts

8
plugins/linkedin-thought-leadership/references/video-strategy-guide.md
View file

@ -286,9 +286,11 @@ LinkedIn's algorithm weights **completion rate** above all other video metrics.
| Length | Target Rate | Signal |
|--------|------------|--------|
| 30s | 70%+ | Strong — short enough for most viewers |
| 60s | 55%+ | Good — requires solid hook and pacing |
| 90s | 45%+ | Acceptable — sweet spot for depth vs retention |
| 2min | 35%+ | Challenging — only with compelling content |
| 60s | 55%+ | Good — 2026 sweet spot for depth vs completion |
| 90s | 45%+ | Risky — retention drops, only for complex frameworks |
| 2min | 35%+ | Dangerous — most viewers won't hit 30% completion gate |
**Critical (2026):** LinkedIn requires **30% minimum completion rate** or the video gets **zero distribution**. This makes shorter videos significantly safer. 60 seconds is the new recommended default.
**How to optimize:**
- Front-load the most interesting content (not chronological order)