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 provides a structured framework for Claude to execute complex implementation plans through controlled batch processing. It features a rigorous pre-execution review phase to identify risks and gaps, followed by iterative execution with mandatory checkpoints. This ensures high-quality results and seamless human-AI collaboration by allowing for feedback and verification between task batches, making it ideal for large-scale technical projects.
Use Cases
- Complex Software Feature Implementation: Systematically coding and testing new features in small, reviewable batches to maintain code quality and alignment with the original architecture.
- Systematic Code Refactoring: Executing multi-step architectural changes across a codebase with built-in verification steps at every milestone to prevent regressions.
- Multi-stage Technical Migrations: Managing sequential data or infrastructure migration tasks with mandatory pauses for manual approval and status reporting between phases.
- Automated Documentation Updates: Processing large-scale documentation changes in batches, ensuring each section is reviewed and verified before proceeding to the next.
| 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: Use question tool to raise them:
question({
questions: [
{
header: "Concerns",
question: "Plan review complete. Any concerns before proceeding?",
options: [
{
label: "No concerns (Recommended)",
description: "Plan looks good, execute batches",
},
{
label: "Has concerns",
description: "Need clarification before starting",
},
],
},
],
});
- Read plan and identify:
- What is the goal?
- What are the deliverables?
- What are the risks?
- Does the approach make sense?
- Are there missing pieces?
If no concerns: Create TodoWrite and proceed If concerns: Wait for human to decide and resubmit
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."
Step 4: Continue
Based on feedback:
- Apply changes if needed
- Execute next batch
- Repeat until complete
Step 5: Complete Development
After all tasks complete and verified:
- Announce: "I'm using finishing-a-development-branch skill to complete this work."
- REQUIRED SUB-SKILL: Use skill({ name: "finishing-a-development-branch" })
- Follow that skill to verify tests, present options, execute choice
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