m2ai-skills-pack

Run an After-Action Review on an agent dispatch run, build execution, or multi-step orchestrated operation. Gathers forensics across the orchestrator DB, A2A endpoints, pm2 logs, git history, and queue files; classifies failure modes; captures benchmarks; produces a structured AAR. Use when the user says "aar", "after action review", "let's review what happened", "review this run", or after any dispatch that produced mixed results worth learning from.

Interview the user about their agent usage patterns and risk tolerance, then generate a tiered action-class policy document. Each tier gets classification criteria, required approvals, rollback procedures, and monitoring expectations. Use when someone says "/action-class-policy", "define action classes", "agent permissions policy", "what actions can my agent take unsupervised", or wants a governance framework for agent autonomy.

Structured post-mortem for the failure mode where an agent executed the correct mechanical action but produced the wrong outcome — the action succeeded, the goal failed. Walks through what semantic context was missing, where to add it, and how to prevent recurrence. Use when an agent did exactly what it was told but the result was wrong, or the user says "/action-outcome-postmortem", "right action wrong result", "agent succeeded but outcome was bad", "mechanical success semantic failure".

Set up and run a two-AI coding workflow where a primary assistant handles planning and code generation while an adversarial auditor stress-tests the plan, catches edge cases, and reviews output before shipping. Use when the user wants complementary AI tool pairing, a structured code review gate, an adversarial planning loop, or a background audit running in parallel with active development.

Evaluate an agent codebase against 12 infrastructure primitives (permission model, token budget, crash recovery, tool assembly, streaming events, state machine, provenance, stop reasons, boot sequence, verification harness, memory decay, health checks) and return a severity-ranked gap analysis with prioritized upgrade path. Use when auditing agent architecture, reviewing agent readiness, or planning what infrastructure to build next.