What problem does it solve? Large features often exceed what a single agent pass can implement reliably, leading to incomplete work, broken dependencies, and risky merges. This Skill provides a structured pipeline for splitting big features into independently verifiable work units with quality gates. ## Core Features & Use Cases - DAG Decomposition: Breaks an RFC into work units with explicit depends_on relationships, scope, acceptance tests, risk levels, and rollback plans. - Tiered Complexity Handling: Classifies units into three tiers, from isolated file edits to schema, auth, performance, and security changes. - Merge Queue & Recovery: Enforces merge rules such as rebasing on the integration branch and re-running integration tests, plus a recovery loop that evicts stalled units, snapshots findings, and retries with narrowed scope. - Use Case: When asked to build a multi-module authentication overhaul, use this Skill to produce an RFC execution log, unit scorecards, a dependency graph snapshot, and an integration risk summary. ## Quick Start Ask the agent to decompose your large feature RFC into dependency-ordered work units and execute them through the pipeline with quality gates.
