What problem does it solve? Turning a feature request, bug fix, or refactor intent into working code often skips planning and review, producing inconsistent or unverified changes. This Skill enforces a disciplined workflow that clarifies intent, writes a bounded implementation spec, dispatches implementation, and runs adversarial multi-layer code review before committing. ## Core Features & Use Cases - Spec-driven implementation: Clarifies intent, investigates the codebase, and writes a token-bounded spec file with a code map, tasks, and acceptance criteria before any code changes. - Adversarial review loop: Runs parallel review layers (blind hunter, edge-case hunter, verification-gap reviewer) over the diff, triages findings into intent gaps, spec fixes, patches, or deferred work, and loops back automatically. - Epic story support: Compiles focused epic context from planning artifacts and syncs sprint-status.yaml as stories move through in-progress, review, and done states. - Use Case: Ask it to add a new API endpoint; it drafts a spec for your approval, implements via a subagent, reviews the diff with three independent reviewers, fixes findings, and commits with a suggested review order. ## Quick Start Ask the assistant to implement a feature or fix a bug, for example: build a password reset endpoint following the project's existing patterns.
