diff --git a/ROADMAP.md b/ROADMAP.md deleted file mode 100644 index 17559c2..0000000 --- a/ROADMAP.md +++ /dev/null @@ -1,134 +0,0 @@ -# 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.