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 designed to bridge the gap between planning and implementation by providing a structured framework for batch task execution. It solves the problem of AI agents 'going off the rails' during complex tasks by enforcing critical review checkpoints, mandatory verification steps, and a 'stop-and-ask' protocol for blockers, ensuring high-fidelity alignment with the original project roadmap.
Use Cases
- Software Development: Implementing a multi-file technical architecture where the agent codes specific modules in batches and waits for an architect's review before proceeding.
- Complex Data Migrations: Executing a step-by-step database migration plan with mandatory validation checks after each table or schema change to prevent data loss.
- Business Process Automation: Following a detailed SOP for onboarding or reporting where human approval is required at specific milestones before the next set of actions is triggered.
- Content Strategy Execution: Rolling out a multi-part marketing campaign plan, ensuring each piece of content meets brand guidelines and is verified 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:
- Run final verifications as specified in the plan
- Summarize completed work and verification output
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