finishing-a-development-branch
Finishing a Development Branch
Guard: Do NOT Use Mid-Epic
STOP. Before proceeding, check:
- Are you a subagent implementing a single task? -> This skill does NOT apply. Report your evidence and stop.
- Are there still open tasks in the epic? -> This skill does NOT apply. Only the orchestrator at COMPLETE state should invoke this.
- Is there an epic with a
completion:*label? -> Read it and execute automatically (see Step 3 Auto below). No prompting needed.
This skill is ONLY for: The final integration step after ALL work is done. If even one task remains open, do not invoke this skill.
The Process
Step 0: Check Epic Verification Tasks (If Applicable)
Skip if not working on a beads epic. Otherwise, run bd list --parent <epic-id> and check for verification tasks. Three outcomes: open verification tasks (STOP), no verification tasks/legacy (WARNING, proceed), all closed (proceed). See references/epic-verification.md.
Step 1: Verify Tests (Task-Tracked)
More from schlenks/superpowers-bd
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
10writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
9dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
9brainstorming
Use when starting any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
8epic-verifier
Use when all implementation tasks in an epic are closed, before calling finishing-a-development-branch
8rule-of-five-tests
Use when writing 50+ lines of test code, adding test suites, or before claiming test work complete - apply 5 focused passes (Draft, Coverage, Independence, Speed, Maintainability) to catch issues single-shot generation misses
8