What problem does it solve? Large features often exceed what a single agent pass can implement reliably, leading to broken integrations and unverifiable changes. This Skill splits oversized work into independently verifiable units with explicit dependencies, quality gates, and rollback plans. ## Core Features & Use Cases - DAG Decomposition: Breaks an RFC into work units with id, depends_on, scope, acceptance_tests, risk_level, and rollback_plan fields. - Tiered Complexity Handling: Classifies units into three tiers from isolated file edits to schema, auth, performance, and security changes. - Merge Queue & Recovery: Enforces dependency checks, rebasing, and integration test re-runs, with stall recovery via scope narrowing and retry. - Use Case: When adding a booking system with schema changes, split it into migration, API, and UI units, validate each against acceptance tests, then merge through the queue with integration verification. ## Quick Start Use the ralphinho-rfc-pipeline skill to decompose this feature RFC into dependency-ordered work units with acceptance tests and a merge plan.