40986575b6
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>
2.5 KiB
LINKEDIN TOPIC ROTATION GATE: If the file being written/edited is LinkedIn content (a post draft, article, or content file — NOT config files, state files, scripts, documentation, JSON, or plan files), check topic diversity before proceeding.
Step 1: Read State
Read ~/.claude/linkedin-thought-leadership.local.md and extract:
last_post_topic— the pillar of the most recent postexpertise_areas— the user's 5 content pillars## Recent Postssection — post history with topic_area tags
Step 2: Identify Current Pillar Determine which expertise_area the current post best matches. Use semantic matching — the post doesn't need to use the exact pillar name, but its core topic should clearly map to one of the 5 expertise_areas.
Step 3: Run Checks
If fewer than 3 posts exist in the last 14 days, skip all checks (insufficient data for meaningful rotation analysis).
Check 1 — Back-to-back repetition:
If the current post's pillar matches last_post_topic, flag:
"TOPIC ROTATION WARNING: This post covers the same pillar ([pillar]) as your last post. Consider switching to an underrepresented pillar for better audience diversity and algorithmic reach."
Check 2 — 14-day balance:
Count posts per pillar from the ## Recent Posts section (last 14 days only). If any single pillar accounts for more than 50% of posts in that window, flag:
"PILLAR BALANCE WARNING: [pillar] has [X] of [Y] posts ([Z]%) in the last 14 days. LinkedIn's algorithm rewards topic consistency across your niche, but over-concentration on one pillar signals narrowing expertise."
Check 3 — Off-topic: If the current post does not match ANY of the 5 expertise_areas, flag:
"OFF-TOPIC WARNING: This post doesn't align with any of your 5 expertise areas. Off-pillar posts weaken your 360Brew topical authority signal. Consider reframing to connect with [closest pillar]."
Step 4: Suggest Alternatives If any check flagged, suggest 2-3 underrepresented pillars with context:
"Underrepresented pillars to consider:
- [Pillar A] — last posted [X] days ago ([N] posts in 14 days)
- [Pillar B] — last posted [Y] days ago ([M] posts in 14 days)
- [Pillar C] — last posted [Z] days ago ([P] posts in 14 days)"
This is a WARN-ONLY hook. Do not block content creation. Present the warning and let the user decide whether to adjust.
Skip this check if the file is a config file, state file (.local.md), script, hook, JSON, plan file, documentation, or any non-content file. Only apply to LinkedIn post drafts and articles.