Use when you have a written implementation plan to execute in a separate session with review checkpoints. Do NOT use when running as an Agent Teams teammate — the Lead manages the shared task list with checkpoints natively.
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers-agent-teams:executing-plansThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Load plan, review critically, execute tasks in batches, report for review between batches.
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review.
Announce at start: "I'm using the executing-plans skill to implement this plan."
Agent Teams: Do NOT use this skill when Claude Code Agent Teams is active. Agent Teams replaces this skill — the Lead manages a shared task list with checkpoints instead. Using both creates nested orchestration. See
docs/agent-teams-integration-guide.md.
Default: First 3 tasks
For each task:
When batch complete:
Based on feedback:
After all tasks complete and verified:
STOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers - stop and ask.
Required workflow skills:
npx claudepluginhub datar-tech/superpowersCreates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.