executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
When & Why to Use This Skill
The 'Executing Plans' skill is a specialized workflow designed to bridge the gap between planning and implementation. It enables Claude to systematically execute complex, multi-step technical plans by breaking them into manageable batches with mandatory review checkpoints. By prioritizing critical plan review, disciplined task execution, and integrated verification, this skill ensures high-quality outcomes and prevents error propagation in sophisticated software engineering or technical projects.
Use Cases
- Complex Feature Implementation: Executing a detailed technical design document by breaking down the development into verifiable batches, ensuring each component is tested before proceeding.
- Large-Scale Refactoring: Managing systematic code migrations or architectural updates where following a precise sequence of steps and running validation tests is critical to system stability.
- Structured Bug Resolution: Orchestrating the fix for intricate, multi-file issues that require sequential changes and progress reporting to a human reviewer at each stage.
- CI/CD Pipeline Setup: Following a multi-stage infrastructure plan to configure deployment pipelines, with checkpoints to verify environment readiness before moving to the next phase.
| name | executing-plans |
|---|---|
| description | Use when you have a written implementation plan to execute in a separate session with review checkpoints |
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."
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:
- Dispatch code-reviewer agent to review entire implementation
- Use requesting-code-review process
- Get git SHAs for base (start) and head (current)
- Review agent checks code quality, architecture, testing, requirements
- Fix any Critical or Important issues found
- Ready to merge
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