home / skills / hxk622 / tokendance / executing-plans
This skill loads a written plan, reviews it critically, executes tasks in batches with checkpoints, and reports outcomes for architect review.
npx playbooks add skill hxk622/tokendance --skill executing-plansReview the files below or copy the command above to add this skill to your agents.
---
name: executing-plans
display_name: 执行计划
version: 1.0.0
author: system
description: "当有书面实施计划需要执行时使用,在单独会话中执行并设置审查检查点。Use when you have a written implementation plan to execute in a separate session with review checkpoints. Batch execution with checkpoints for architect review."
tags: [execute, plan, implementation, execution, 执行, 计划, 实施, checkpoint, 检查点, review, 审查]
allowed_tools: []
max_iterations: 30
timeout: 600
enabled: true
match_threshold: 0.65
priority: 7
---
# 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
1. Read plan file
2. Review critically - identify any questions or concerns about the plan
3. If concerns: Raise them with your human partner before starting
4. If no concerns: Create TodoWrite 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 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
This skill executes a written implementation plan in controlled batches with review checkpoints. It emphasizes critical plan review, exact step-by-step execution, and reporting between batches for architect feedback. It is designed to stop on blockers and escalate for clarification rather than guessing.
The skill first loads and critically reviews the plan to surface questions or gaps before any work begins. It then executes tasks in batches (default: first three tasks), marking tasks in_progress, following steps exactly, running specified verifications, and marking tasks completed. After each batch it reports what was implemented and verification results, then waits for feedback before continuing. On full completion it delegates finalization to the finishing-a-development-branch sub-skill.
What if I find problems in the plan during review?
Raise the concerns with your human partner and do not start executing until issues are resolved or clarified.
How large should each batch be?
Default is three tasks, but adjust batch size for complexity; keep batches small enough for meaningful review and verification.