Agent skill
use-plan-execute
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Stars
163
Forks
31
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/use-plan-execute
SKILL.md
Load plan, review critically, execute tasks in batches, report for review between batches.
Core principle: Batch execution with checkpoints for review.
Announce at start: "I'm using the use-plan-execute skill to implement this plan."
The Process
1. Load and Review Plan
- Read plan file
- Review critically - identify any questions or concerns
- If concerns: Raise them before starting
- If no concerns: Create TodoWrite and proceed
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
3. Report
When batch complete:
- Show what was implemented
- Show verification output
- Say: "Ready for feedback."
4. Continue
Based on feedback:
- Apply changes if needed
- Execute next batch
- Repeat until complete
5. Complete Development
After all tasks complete and verified:
- Announce: "I'm using the use-branch-complete skill to complete this work."
- Use autonome:use-branch-complete
- Follow that skill to verify tests, present options, execute choice
When to Stop
STOP executing immediately when:
- Hit a blocker mid-batch (missing dependency, test fails, unclear instruction)
- 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.
Key Rules
- 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
Didn't find tool you were looking for?