// Use when you have a written implementation plan and need to execute it in Antigravity single-flow mode
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Use when executing implementation plans, handling multiple independent tasks, or doing structured task-by-task development with review gates in Antigravity.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
| name | executing-plans |
| description | Use when you have a written implementation plan and need to execute it in Antigravity single-flow mode |
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for architect review. Entrypoint principle: This is the standard execution entrypoint. Do not offer alternate execution modes.
Announce at start: "I'm using the executing-plans skill to implement this plan."
.agent/skills/single-flow-task-execution/SKILL.md<project-root>/docs/plans/task.md (table-only tracker) and proceedDefault: First 3 tasks
For each task:
When batch complete:
Based on feedback:
After all tasks complete and verified:
.agent/skills/finishing-a-development-branch/SKILL.mdSTOP executing immediately when:
Ask for clarification rather than guessing.
Return to Review (Step 1) when:
Don't force through blockers - stop and ask.
task_boundary for coding tasks; use browser_subagent only for browser tasksRequired workflow skills:
.agent/skills/using-git-worktrees/SKILL.md - REQUIRED: Set up isolated workspace before starting.agent/skills/writing-plans/SKILL.md - Creates the plan this skill executes.agent/skills/single-flow-task-execution/SKILL.md - REQUIRED: Enforce single-flow execution with two-stage review.agent/skills/finishing-a-development-branch/SKILL.md - Complete development after all tasks