executing-plans
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
When & Why to Use This Skill
The Executing Plans skill is a sophisticated orchestration framework designed to bridge the gap between high-level technical planning and systematic execution. It enables AI agents to implement complex features by breaking them down into controlled batches, incorporating critical review phases, and enforcing mandatory verification checkpoints. By prioritizing human-in-the-loop feedback and automated quality gates like linting and type-checking, it ensures high-reliability software development and minimizes the risk of runaway errors in autonomous workflows.
Use Cases
- Complex Feature Implementation: Executing multi-file technical designs in logical, testable increments to ensure architectural alignment at every stage.
- Systematic Code Refactoring: Managing large-scale architectural changes across a codebase with built-in safety checks and mandatory review points between batches.
- Automated Migration Tasks: Handling sensitive database or API migrations by following a structured plan with rigorous validation steps before proceeding to subsequent phases.
- Streamlined PR Preparation: Automating the transition from task completion to pull request creation by integrating linting, type-checking, and verification reporting into the execution flow.
| name | executing-plans |
|---|---|
| description | Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches |
Executing Plans
Overview
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."
The Process
Step 1: Load and Review Plan
- Read plan file
- Review critically - identify any questions or concerns about the plan
- If concerns: Raise them with your human partner before starting
- If no concerns: Create TodoWrite and proceed
Step 2: Execute Batch
Default: First 3 tasks
For each task:
- Mark as in_progress
- Follow each step exactly (plan has bite-sized steps)
- Run verifications as specified
- Mark as completed
Step 3: Report
When batch complete:
- Show what was implemented
- Show verification output
- Say: "Ready for feedback or commit changes?" or "Ready for next batch?"
Step 4: Continue
Based on feedback:
- Apply changes if needed
- Execute next batch
- Repeat until complete
If user wants to commit changes:
- Run linting and type checking
- Commit changes
- Ask user if they want to execute the next batch
Step 5: Complete Development
After all tasks complete and verified:
- Run linting and type checking
- Ask user if they want to create a pull request
When to Stop and Ask for Help
STOP executing immediately when:
- Hit a blocker mid-batch (missing dependency, test fails, instruction unclear)
- Plan has critical gaps preventing starting
- You don't understand an instruction
- Verification fails repeatedly
Ask for clarification rather than guessing.
When to Revisit Earlier Steps
Return to Review (Step 1) when:
- Partner updates the plan based on your feedback
- Fundamental approach needs rethinking
Don't force through blockers - stop and ask.
Remember
- Review plan critically first
- Follow plan steps exactly
- Don't skip verifications
- Reference skills when plan says to
- Between batches: just report and wait
- Stop when blocked, don't guess