What problem does it solve? Large features often exceed what a single agent pass can implement reliably, leading to incomplete changes, broken dependencies, and risky merges. This Skill structures the work as an RFC-driven pipeline so big changes are split into independently verifiable 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. - Quality Gates per Unit: Runs each unit through research, planning, implementation, tests, review, and a merge-ready report before integration. - Merge Queue & Recovery: Enforces rebase and integration-test rules on every queued merge, and recovers stalled units by snapshotting findings and regenerating narrowed scopes. - Use Case: When asked to add a new authentication subsystem touching schema, APIs, and UI, use this Skill to split the work into Tier 1-3 units, execute them against the dependency graph, and produce an integration risk summary. ## Quick Start Ask the agent to take this feature RFC and decompose it into dependency-ordered work units, then execute each unit through the quality pipeline with merge queue rules.
