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

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>

plugins/linkedin-thought-leadership/agents/content-optimizer.md

@@ -210,11 +210,11 @@ When you receive content to optimize, analyze it through these lenses:
 **For carousels:**
 - Caption should be <500 chars
 - Focus on slide content separately
-- 12 slides optimal
+- 7 slides optimal (5-10 range)
 
 **For video scripts:**
 - Hook must grab in 3 seconds
-- 90 seconds optimal length
+- 60 seconds optimal length (30% completion rate minimum)
 - CTA at the end
 
 ## References

plugins/linkedin-thought-leadership/agents/content-repurposer.md

@@ -148,7 +148,7 @@ Old post → Updated post  Easy         High     Any 60+ day old post
 CAROUSEL CONVERSION BLUEPRINT
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
-Target: 10-12 slides (optimal engagement)
+Target: 5-8 slides (7 optimal for engagement)
 Design: Large text, mobile-readable (16px+ equivalent)
 
 SLIDE 1: HOOK
@@ -211,7 +211,7 @@ Design specifications:
 VIDEO SCRIPT CONVERSION BLUEPRINT
 ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
 
-Target length: 60-90 seconds (optimal for LinkedIn)
+Target length: 30-60 seconds (2026 optimal — 30% completion rate minimum)
 Style: Talking head with text overlays
 
 [0:00-0:03] HOOK — 3 seconds

plugins/linkedin-thought-leadership/agents/post-feedback-monitor.md

@@ -153,7 +153,7 @@ Check for these six anomaly patterns:
 - Video with <30s average watch time
 - Text post with very high impressions but low engagement
 **Likely cause:** Format choice didn't match the content or audience preference
-**Intervention:** Document for future posts. Consider repurposing the content in a different format. For carousels: check if slide count is optimal (12 slides). For video: check if captions are present (85% watch muted).
+**Intervention:** Document for future posts. Consider repurposing the content in a different format. For carousels: check if slide count is optimal (7 slides, 5-10 range). For video: check if captions are present (85% watch muted).
 
 ## Step 4: Real-Time Intervention Playbook
 

plugins/linkedin-thought-leadership/agents/video-scripter.md

@@ -66,10 +66,10 @@ Use AskUserQuestion:
 **How long should this video be?**
 1. **30 seconds** (75 words) — Single punchy insight or quick tip
 2. **60 seconds** (150 words) — Framework intro or single lesson
-3. **90 seconds** (225 words) — Complete framework or story with lesson (Recommended)
-4. **2 minutes** (300 words) — Detailed story or multi-step process
+3. **90 seconds** (225 words) — Extended format for complex frameworks (use sparingly)
+4. **2 minutes** (300 words) — Detailed story or multi-step process (retention drops significantly)
 
-Default recommendation: **90 seconds** — optimal balance of depth and retention on LinkedIn.
+Default recommendation: **60 seconds** — 2026 sweet spot. LinkedIn requires 30% minimum completion rate for distribution. Shorter videos achieve higher completion.
 
 ## Step 3: Topic and Angle Selection