Use when you have a written implementation plan to execute in a separate session with review checkpoints
npx skills add rapyuta-robotics/agent-ai --skill "executing-plans"
Install specific skill from multi-skill repository
# Description
Use when you have a written implementation plan to execute in a separate session with review checkpoints
# SKILL.md
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."
โ ๏ธ CRITICAL: Use Task Tracking and Parallel Agents
Always use task tracking to monitor progress:
| Platform | Task Tracking Tool |
|---|---|
| Claude Code | TodoWrite tool |
| VS Code Copilot | manage_todo_list |
| Codex | Built-in task tracking |
Create a todo item for each task in the plan and update status as you work.
When tasks are marked PARALLEL in the plan:
| Platform | Agent Dispatch Tool |
|---|---|
| Claude Code | Task tool |
| VS Code Copilot | runSubagent tool |
| Codex | dispatch_agent or equivalent |
- Dispatch multiple agents simultaneously
- Each agent works on an independent task
- Aggregate results before proceeding to dependent tasks
Why: Parallel execution dramatically speeds up independent work. Task tracking provides visibility into progress.
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 with ALL tasks from plan and proceed
Step 2: Execute Batch
Default: First 3 tasks
For each task:
1. Mark as in_progress
2. Follow each step exactly (plan has bite-sized steps)
3. Run verifications as specified
4. 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 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.
โ ๏ธ CRITICAL: No Linting, Commits, or Pushes During Execution
DO NOT run linting, commits, or pushes while executing tasks.
This will be handled in the linting and finalizing phase after all tasks are complete. See the verification-before-completion skill for linting workflow guidance.
Why:
- Linting interrupts implementation flow
- Commits mid-execution create messy history
- Pushes before verification risk broken code in remote
When to lint/commit/push: Only after ALL tasks complete and tests pass, during the finishing-a-development-branch skill phase.
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
- NO linting, commits, or pushes until finishing phase
# Supported AI Coding Agents
This skill is compatible with the SKILL.md standard and works with all major AI coding agents:
Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.