skill-ai-escape-mrc
by oxydavid-maxx
Use when reviewing AI harness, agent, CI, or browser/API automation flows that reported success but may have missed verification, renamed entrypoints, plugin links, generated docs, tests, runtime artifacts, delivery artifacts, or other escape paths. Triggers on AI automation escape review, harness escape, automation-flow escape, missed verification, false completion, non-detection, recurrence prevention, corrective action, proof of action, and managerial root cause. LangGraph FSM-driven with research, IS/IS-NOT scoping, four-quadrant TRC/MRC analysis, corrective/prevention matrices, proof-of-action verification, report/plan generation, and email delivery.