executing-plans
💡 Summary
A skill for AI agents to execute pre-written implementation plans in batches with human review checkpoints.
🎯 Target Audience
🤖 AI Roast: “It's a glorified to-do list manager that finally teaches AI agents to ask for directions instead of confidently driving into a ditch.”
The skill orchestrates execution of arbitrary tasks from a plan file, which is a high-risk operation. It likely invokes other skills/tools (e.g., shell, file ops) without intrinsic validation of the plan's commands. Mitigation: Implement a plan validation and sanitization step (e.g., allow-list of permitted operations) before any execution.
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:
- Announce: "I'm using the finishing-a-development-branch skill to complete this work."
- REQUIRED SUB-SKILL: Use superpowers: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
Pros
- Enforces structured, reviewable execution reducing errors.
- Promotes safe batching and clear human-AI collaboration.
- Improves reliability by mandating verification steps.
Cons
- Heavily dependent on quality of the pre-written plan.
- Rigid batch size (3 tasks) may not suit all contexts.
- Adds overhead for simple or well-understood tasks.
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author obra.