calibratelisted

# Calibrate -- Teach Your Clone How You Think Interactive scenario-based calibration sessions that extract your decision heuristics, values, and reasoning patterns. Each session takes 5-10 minutes and significantly improves how well the clone models your thinking. ## How It Works 1. **Gap Analysis** -- Check which domains of your thinking are under-modeled 2. **Scenario Presentation** -- Present a realistic scenario that forces a judgment call 3. **Adaptive Follow-ups** -- Probe deeper based on your initial response 4. **Disagreement Probes** -- Challenge your answer to surface nuance and exceptions 5. **Knowledge Storage** -- Extract and store decision patterns and values at high confidence ## Backend tools (use these, don't improvise) - **`calibration_status`** (`mcp__nomos-think__calibration_status`) -- the real gap analysis (per-domain coverage from the documented `patterns*0.6 + values*0.4` formula). Use for `/calibrate status` and to pick the focus domain. - **`calibration_next_scenario`** (`mcp__nomos-think__calibration_next_scenario`) -- returns the next scenario (from the curated library) targeting the biggest gap. Pass `completedIds` for scenarios already shown this session. Present the scenario it returns; do not invent your own. ## Commands - `/calibrate` -- Start a calibration session (auto-picks the least-covered domain) - `/calibrate status` -- Show calibration coverage and gaps - `/calibrate <domain>` -- Focus on a specific domain ### Available