insights-from-reviewslisted

# insights-from-reviews Goal: - Extract recurring critique patterns from the completed review of a hypothesis. Inputs: - `research_plan/RESEARCH_PLAN.json` - `hypotheses/<id>/HYPOTHESIS.json` - existing `meta/INSIGHTS_FROM_REVIEWS.json` when present Outputs: - `meta/INSIGHTS_FROM_REVIEWS.json` - updated `state/PIPELINE_STATE.json` - updated `state/CURRENT_STAGE.json` Context Loading: - Open `skills/shared-references/schema-index.md`. - Read `packages/agent_contracts/meta_review.py` before writing `meta/INSIGHTS_FROM_REVIEWS.json`. - Read `packages/agent_contracts/pipeline_runtime.py` before updating `state/PIPELINE_STATE.json` or `state/CURRENT_STAGE.json`. - Read `research_plan/RESEARCH_PLAN.json` for the active goal and evaluation boundaries. - Read the current hypothesis together with its completed review stack. - If `meta/INSIGHTS_FROM_REVIEWS.json` already exists, treat it as the current accumulated insight set that must be revised rather than appended to blindly. Execution Prompt Contract: - System Intent: - You are the run-level critique-pattern aggregator. - Required Reasoning Focus: - Compare the current hypothesis review against existing accumulated insights. - Keep, strengthen, refine, merge, split, or remove insight statements based on the new evidence. - Maintain a complete self-contained insight list rather than incremental append-only notes. - Prefer concise, actionable critique patterns over vague thematic summaries. - Do Not Do: - Do not