executing-plans
Execute detailed plans in batches with review checkpoints
When & Why to Use This Skill
The 'Executing Plans' Claude skill is a high-reliability workflow designed for the systematic implementation of complex, multi-step projects. By utilizing a structured batch-processing approach with mandatory review checkpoints, it ensures that AI-driven tasks are executed with precision and human oversight. This skill minimizes errors by breaking down large implementation plans into manageable segments, performing rigorous verification at each stage, and maintaining a 'human-in-the-loop' feedback loop to guarantee alignment with project objectives.
Use Cases
- Incremental Software Development: Implementing a multi-file feature or architectural change by coding and testing in small, verifiable batches to ensure code quality and system stability.
- Complex System Migrations: Executing a step-by-step infrastructure or data migration plan where each phase requires validation and manual approval before proceeding to the next set of tasks.
- Large-scale Content or Code Refactoring: Performing systematic updates across extensive repositories, allowing for quality assurance reviews between batches to prevent the propagation of errors.
- Automated Workflow Orchestration: Managing long-running, multi-stage processes that require periodic synchronization with a human partner to refine the approach based on intermediate results.
| name | Executing Plans |
|---|---|
| description | Execute detailed plans in batches with review checkpoints |
| when_to_use | when partner provides a complete implementation plan to execute in controlled batches with review checkpoints |
| version | 2.2.0 |
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:
- Announce: "I'm using the Finishing a Development Branch skill to complete this work."
- Switch to skills/collaboration/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