← ClaudeAtlas

expert-councillisted

Dynamic Expert Council QA system. Selects domain-relevant expert personas to review deliverables before final delivery. 3 tiers with build/review mode toggle. Works with any AI assistant.
puretechnyc/purebrain-skills · ★ 0 · AI & Automation · score 78
Install: claude install-skill puretechnyc/purebrain-skills
# Dynamic Expert Council QA Run your work through a simulated expert review panel before publishing. Select domain-relevant expert personas, get scored feedback, and identify improvements you would have missed. ## Modes ### BUILD MODE (default) - Council is OFF - Fast iteration, no review gates - Creative freedom during design/development - Council only activates when explicitly triggered ### REVIEW MODE (triggered) - Activated by: "run it through the council" or "ready for review" or "final review" - Runs tiered QA on the deliverable - Returns scored feedback + recommendations - Deactivates after review completes (back to build mode) ## Tiers ### TIER 1 -- Quick Check (1 expert, ~30 seconds) - **Trigger**: Internal docs, messages, quick updates - **Expert**: Brand/product insider only - **Output**: Brand voice check, accuracy flag, go/no-go ### TIER 2 -- Standard Review (2-3 experts, ~1-2 min) - **Trigger**: Social posts, emails, blog drafts, content - **Experts**: 2 domain-relevant + brand insider - **Output**: Per-expert strengths/weaknesses/improvements, synthesis ### TIER 3 -- Full Council (5 experts + cross-review, ~3-5 min) - **Trigger**: Homepage launches, pricing pages, investor materials, major campaigns - **Experts**: 4 domain-relevant + brand insider - **Process**: Independent review > cross-review > chairman synthesis - **Output**: Full QA report, scored improvements, go/no-go with conditions ## Auto-Trigger Rules (optional) These deliverable types auto