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

14
plugins/linkedin-thought-leadership/ROADMAP.md
View file

@ -34,6 +34,20 @@ Items organized by quarter and track. Priority = Impact / Effort (High/Medium/Lo
- [x] Post-level heatmap generation: day-of-week performance matrix from imported CSV data (time-of-day not available in CSV export)
- [x] `/linkedin:report` month-over-month comparison view
### Algorithm Reference Update (April 2026)
**Priority: High** | **Effort: Low-Medium**
LinkedIn's 2026 algorithm introduced significant changes since the January 360Brew update. The plugin's reference documents and commands need updating to reflect current data.
- [x] Carousel optimal slide count: update from 12 to 7 slides (18% better performance). Updated `algorithm-signals-reference.md`, `carousel-templates.md`, `carousel.md` quality checklist
- [x] Carousel reach multiplier: update from 1.6x to 3.4x vs single-image. Clarified engagement rate (24.42% was PDF-specific, carousel-specific is 1.92%). Added 35% click-through threshold penalty
- [x] Video format overhaul: vertical 9:16 gets distribution boost (3-4x watch duration vs landscape). Updated recommended max from 90s to 60s. Added 30% completion rate gate. Updated 12 files
- [x] Depth Score concept: added new section to `algorithm-signals-reference.md` — LinkedIn's primary ranking metric measuring actual engagement duration
- [x] Delayed engagement boost: added 4-6x boost for 24-72h post-publication engagement. Updated distribution model
- [x] 90-day topic alignment requirement: updated 360Brew validation section with 90-day categorization requirement
- [x] Organic reach decline context: added "2026 Reach Context" section (-47% YoY overall, -72% video, -34% text)
- [x] Engagement pod detection hardened: strengthened negative signals and red flags with LinkedIn VP statement and detection mechanisms
---
## Q3 2026 (July-September)