Capture structured thumbs up/down feedback with context, tags, and optional rubric scores after completing a task.

Pre-action gates that block AI agents from repeating known mistakes. Captures feedback, generates prevention rules, enforces them via PreToolUse hooks.

Generate and review prevention rules auto-promoted from repeated failure patterns.

Recall relevant past failures, prevention rules, and context packs before starting a coding task.

Dual-write feedback to Amp MCP memory AND mcp-memory-gateway for DPO export, analytics, and cross-platform portability

Search promoted lessons for corrective actions, lifecycle state, linked rules, and linked gates.

Automated skill to handle architecture, autonomy, crisis, debug, deployment, error, execution, external-assessment, feedback, inefficiency, negative, railway, revenue, roi, simplification, user-frustration patterns efficiently.