executing-plans

Execute pre-written implementation plans in batches with human review checkpoints.

38|12|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill executing-plans-databrickslabs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: executing-plans
Source: https://github.com/databrickslabs/coding-agents-databricks-apps/tree/main/.claude/skills/executing-plans
Command: npx skills add https://github.com/databrickslabs/coding-agents-databricks-apps --skill executing-plans-databrickslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the risk of uncoordinated, error-prone implementation of pre-written plans by enforcing structured batch execution and mandatory review checkpoints between task sets, preventing costly rework from unchecked changes.

Core Features & Use Cases

  • Batch Task Execution: Breaks implementation plans into small, manageable batches (default 3 tasks per batch) to maintain progress visibility.
  • Mandatory Review Checkpoints: Requires reporting completed work and verification output to a human reviewer before proceeding to the next batch.
  • Use Case: When migrating a legacy monolithic application to a microservices architecture, use this Skill to implement the plan in small batches, get architect feedback after each batch, and adjust the approach if needed without wasting work on incorrect assumptions.

Quick Start

Use the executing-plans skill to implement the attached legacy application migration plan in batches with review checkpoints after each set of completed tasks.

Frequently Asked Questions about executing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce review checkpoints during a legacy migration implementation plan?

Batch task execution breaks implementation plans into manageable sets, defaulting to three tasks per batch, to maintain progress visibility. It requires reporting completed work and verification output to a human reviewer before proceeding to the next batch.

What is the best way to prevent unapproved changes in multi-repo refactoring workflows?

This approach handles iterative human feedback by requiring verification output and progress tracking after each task batch. If blockers arise, the workflow mandates escalation to a human reviewer, preventing incorrect assumptions from wasting further work.

How do I track progress when implementing a software development plan in batches?

You can track progress by executing software development plans in small batches and reporting completed work at mandatory review checkpoints. This provides continuous visibility and ensures verification compliance before advancing to subsequent tasks.

What happens if a blocker occurs during structured batch execution of an implementation plan?

If a blocker occurs during structured batch execution, the workflow mandates blocker escalation to a human reviewer. This prevents unapproved changes and ensures the implementation plan is adjusted without wasting work on incorrect assumptions.