What problem does it solve? AI coding agents often produce sloppy prose, unverified changes, and ad-hoc workflows. This Skill enforces a rigorous operating style for the agent: concise writing, deliberate subagent delegation, root-cause debugging, and evidence-backed verification before any work is declared done. ## Core Features & Use Cases - Playbook-driven execution: Routes tasks (bug fixes, features, refactors, investigations, perf work, PR babysitting, shipping, autonomous runs) to step-by-step playbooks with explicit verification gates. - Named engineering principles: Applies principles like Prove It Works, Fix Root Causes, Model the Domain, and Sequence Work into Verifiable Units to every code decision. - Subagent orchestration: Delegates code-writing to background subagents with per-role model selection, parallel fan-out, and swarm verification of merge-ready PRs. - Use Case: Ask the agent to fix a reported bug. It reproduces the defect on the real surface, binary-searches the root cause, delegates the fix, verifies the original repro passes, and opens a PR with a conventional-commit title. ## Quick Start Ask the agent to work in poteto mode on your next bug fix or feature and watch it follow the matching playbook end to end.
