executing-plans

davila7's avatarfrom davila7

Use when you have a written implementation plan to execute in a separate session with review checkpoints

⭐14.5kstars🔀1.3kforks📁View on GitHub🕐Updated Jan 4, 2026⬇️1downloads

When & Why to Use This Skill

The 'Executing Plans' Claude skill is a specialized workflow agent designed to systematically implement complex, pre-written plans. It optimizes the execution process by breaking down tasks into manageable batches, performing critical pre-execution reviews, and enforcing mandatory checkpoints for human feedback. This ensures high-quality output, minimizes implementation errors, and maintains strict alignment with project architecture and goals.

Use Cases

  • Structured Software Development: Executing multi-step coding plans derived from technical design documents, ensuring each module is verified before proceeding.
  • Complex System Refactoring: Systematically updating legacy codebases following a detailed migration strategy with safety checkpoints to prevent regressions.
  • DevOps Infrastructure Deployment: Implementing Infrastructure-as-Code (IaC) plans in stages, with validation steps at each milestone to ensure environment stability.
  • Technical Documentation Updates: Managing large-scale documentation overhauls by processing content in batches and verifying technical accuracy at every stage.
  • Compliance and Security Auditing: Following a rigorous step-by-step audit plan to verify system configurations and security protocols with documented evidence.
nameexecuting-plans
descriptionUse 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

  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