How this skill is triggered — by the user, by Claude, or both
Slash command
/executing-plans:executing-plansThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
---
Execute plans in controlled batches with verification gates.
"I'm using the Executing Plans skill to implement this plan."
Load Plan → Review → Execute Batch → Report → Feedback → Next Batch
Default batch size: 3 tasks
For each task:
in_progresscompletedAfter each batch:
## Batch Complete
**Implemented:**
- Task 1: [summary]
- Task 2: [summary]
- Task 3: [summary]
**Verification:**
\`\`\`
[test output]
\`\`\`
Ready for feedback.
Based on feedback:
🛑 Stop immediately when:
Ask for clarification. Don't guess.
Before marking ANY task complete:
No "should work" or "looks good" - actual verification output.
### Batch N Complete
| Task | Status | Verification |
|------|--------|--------------|
| Task X | ✅ | 12/12 tests pass |
| Task Y | ✅ | Build successful |
| Task Z | ⚠️ | Needs review |
**Next batch:** Tasks A, B, C
Continue?
After all tasks:
finishing-branch skill if applicablenpx claudepluginhub a-ariff/ariff-claude-plugins --plugin executing-plansUse when you have a written implementation plan to execute in a separate session with review checkpoints
Executes written implementation plans in controlled batches with review checkpoints, verification, and feedback. Use when a plan exists needing strict adherence and regression prevention.
Executes written implementation plans in batched sessions: critically review plan, process first 3 tasks with verifications, report for feedback, repeat until complete with branch finishing. Use for structured dev with checkpoints.