tasuku-9

Use when resuming work after chat loss, switching AI models, migrating context to a new agent or workspace, or maintaining long-running research and project memory across sessions. Manages roadmap, decision log, hypotheses, research evidence, and recovery checkpoints as separate canonical files so no single transcript becomes the source of truth. Also use when you want to ensure no insight, decision, or failed experiment is lost — structured accumulation makes the project knowledge base analysable over time: which hypotheses were tested, which decisions were made and why, which blockers recurred, and how confidence evolved. Trigger phrases: resume work, context lost, switch model, handoff brief, update project docs, classify decisions, audit memory, migrate context, log experiment, track hypothesis, what did we decide, why did we choose, manage paper, track literature, log figures, thesis management, publication-grade traceability.