5be9c8e47c
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>
134 lines
7.1 KiB
Markdown
134 lines
7.1 KiB
Markdown
# LinkedIn Thought Leadership Plugin — Roadmap
|
|
|
|
**Current version:** v1.1.0 (April 2026)
|
|
**Scope:** Planned improvements through Q4 2026
|
|
|
|
Items organized by quarter and track. Priority = Impact / Effort (High/Medium/Low). Items within each quarter ordered by priority.
|
|
|
|
---
|
|
|
|
## Q2 2026 (April-June)
|
|
|
|
### Onboarding & First-Run Experience
|
|
**Priority: High** | **Effort: Low**
|
|
|
|
- [x] First-run welcome flow in session-start hook
|
|
- [x] Condensed getting-started menu for zero-post users in `/linkedin` router
|
|
- [x] Readiness check in `/linkedin:post` and `/linkedin:quick` for unpersonalized state
|
|
- [x] Inline 5x5x5 engagement ritual explanation
|
|
- [x] `/linkedin:onboarding` — dedicated multi-step onboarding command that guides profile → setup → first-post as one flow
|
|
- [x] README Quick Start refinement — 5-minute getting-started path with single `/linkedin:onboarding` entry point
|
|
|
|
### Content Quality
|
|
**Priority: High** | **Effort: Medium**
|
|
|
|
- [x] Enhanced voice-trainer agent: automatic drift scoring on every post draft (compare against voice samples)
|
|
- [x] Content Matrix improvements: add industry-specific angle variants
|
|
- [x] Carousel post support: structured multi-slide content generation with visual layout guidance
|
|
- [x] `/linkedin:react` enhancement: multi-URL comparison posts (compare 2-3 articles)
|
|
|
|
### Analytics Pipeline
|
|
**Priority: Medium** | **Effort: Medium**
|
|
|
|
- [x] Automated week-rollover: session-start hook resets `posts_this_week` and updates `current_week` on week change
|
|
- [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)
|
|
|
|
### Claude Code Platform Integration
|
|
**Priority: High** | **Effort: Medium-High**
|
|
|
|
- [ ] Hook event expansion: leverage new Claude Code hook events as they become available for richer automation
|
|
- [ ] Subagent improvements: parallel content generation in `/linkedin:batch` using Claude Code's evolving subagent capabilities
|
|
- [ ] MCP server for analytics: expose analytics data as MCP resources for cross-plugin access
|
|
- *Blocked on:* Claude Code MCP server authoring stabilization
|
|
|
|
### Analytics & Intelligence
|
|
**Priority: High** | **Effort: Medium**
|
|
|
|
- [ ] Trend detection across 4+ weeks of imported data (analytics-interpreter agent)
|
|
- [ ] Benchmark database: anonymized performance baselines by niche and follower count
|
|
- [ ] A/B test auto-analysis: when experiment duration ends, surface winner with statistical confidence
|
|
- [ ] Content fatigue detection: alert when engagement drops on a recurring content pillar
|
|
|
|
### Content Strategy
|
|
**Priority: Medium** | **Effort: Medium**
|
|
|
|
- [ ] Video-first strategy: LinkedIn prioritizes native video — add video-specific hooks and scheduling guidance
|
|
- [ ] AI-generated image support via MCP image tools for post visuals and carousel slides
|
|
- [ ] Multi-language support: translate posts while preserving voice characteristics
|
|
- *Blocked on:* Voice profile internationalization design
|
|
|
|
---
|
|
|
|
## Q4 2026 (October-December)
|
|
|
|
### Advanced Content
|
|
**Priority: Medium** | **Effort: High**
|
|
|
|
- [ ] LinkedIn Newsletter integration: `/linkedin:newsletter` command for long-form content strategy (requires 5K+ followers gate)
|
|
- [ ] LinkedIn Article workflow: `/linkedin:article` with SEO optimization for LinkedIn's article platform
|
|
- [ ] Seasonal content library: pre-built content hooks for recurring Q1-Q4 events and industry moments
|
|
- [ ] Document/PDF carousel generation: create downloadable slide decks from post content
|
|
|
|
### Architecture & Reliability
|
|
**Priority: Medium** | **Effort: Medium**
|
|
|
|
- [ ] State file schema migration tool: handle breaking changes between plugin versions gracefully
|
|
- [ ] Hook performance audit: measure execution time per hook, identify bottlenecks
|
|
- [ ] E2E test suite for hooks: automated testing beyond the analytics pipeline
|
|
- [ ] Plugin self-update check: compare installed version against marketplace version
|
|
|
|
### Growth & Monetization
|
|
**Priority: Low** | **Effort: Medium**
|
|
|
|
- [ ] Competitor tracking persistence: store competitive analysis results for trend comparison over time
|
|
- [ ] Lead generation templates: content-to-DM pipeline for consulting/speaking inquiries
|
|
- [ ] Collaboration matching: suggest collaboration partners based on audience overlap analysis
|
|
|
|
---
|
|
|
|
## Deprioritized (Not in 2026 scope)
|
|
|
|
| Item | Reason |
|
|
|------|--------|
|
|
| LinkedIn API direct posting | No official posting API available; copy-paste workflow is intentional and avoids ToS issues |
|
|
| Multi-user / team support | Designed for individual thought leaders; team features would change the architecture fundamentally |
|
|
| Real-time analytics streaming | LinkedIn doesn't expose streaming data; CSV export is the only reliable data source |
|
|
| Automated engagement (auto-like, auto-comment) | Violates LinkedIn Terms of Service; plugin explicitly avoids this |
|
|
| OAuth login for LinkedIn data | LinkedIn's API access is restrictive; manual CSV export is more reliable and privacy-respecting |
|
|
|
|
---
|
|
|
|
## Dependencies on External Development
|
|
|
|
| Dependency | Impacts | Status |
|
|
|------------|---------|--------|
|
|
| Claude Code hook events (new event types) | Q3 automation improvements | Monitor Claude Code changelogs |
|
|
| Claude Code MCP server authoring | Q3 analytics MCP server | In development (as of April 2026) |
|
|
| Claude Code subagent API stability | Q3 batch generation | Available but evolving |
|
|
| LinkedIn CSV export format stability | All analytics features | Stable (no changes since Jan 2026) |
|
|
| MCP image generation tools | Q3 visual content | Available via mcp-image |
|
|
|
|
---
|
|
|
|
## How to Contribute Ideas
|
|
|
|
File an issue at the plugin's marketplace repository. Bug reports and feature requests are welcome.
|