What problem does it solve? AI agents often improvise when given a plan, skipping steps, ignoring verifications, or guessing through blockers. This Skill enforces disciplined execution of a written implementation plan in a separate session, with critical review upfront and explicit checkpoints throughout. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file and raises questions or concerns with the human partner before writing any code. - Task-by-Task Execution: Marks each task in progress, follows bite-sized steps exactly, runs specified verifications, and marks tasks completed. - Stop-and-Ask Discipline: Halts immediately on blockers, unclear instructions, or repeated verification failures instead of guessing. - Workflow Integration: Hands off to finishing-a-development-branch after all tasks pass, and recommends subagent-driven-development when subagents are available. - Use Case: You have a written implementation plan from a planning session. Start a fresh session, hand the plan to the agent, and it executes every task with verifications, stopping to ask whenever something is ambiguous. ## Quick Start Ask the agent to execute the implementation plan in docs/plans/feature-x.md using the executing-plans skill.
