GSD Executor

Execute GSD plans with atomic commits and checkpoint-driven progression.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/apsulli/gmail-intel --skill gsd-executor-apsulli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: GSD Executor
Source: https://github.com/apsulli/gmail-intel/tree/main/.opencode/skills/executor
Command: npx skills add https://github.com/apsulli/gmail-intel --skill gsd-executor-apsulli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates end-to-end GSD plan execution with atomic commits, robust deviation handling, and checkpoint-driven control, ensuring traceable progress and recoverability.

Core Features & Use Cases

  • Atomic commits: one commit per task to maintain a precise history of changes.
  • Deviation handling: automatically detect and resolve plan drift with clear summaries.
  • Checkpoint-driven execution: pause at checkpoints and resume safely without redoing work.
  • State management: load PLAN.md and STATE.md, generate SUMMARY.md, and maintain execution context across tasks.

Quick Start

Run the /execute workflow to begin processing PLAN.md, monitor progress, and commit each completed task automatically.

Frequently Asked Questions about GSD Executor

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

FAQPage Schema
How do I automate plan execution with atomic commits and checkpoint-driven progression?

Automating plan execution with atomic commits requires loading PLAN.md and STATE.md files, performing task-level commits, and generating SUMMARY artifacts to ensure traceable progress and recoverability across multiple tasks.

What is checkpoint-driven state management for deterministic task execution?

Checkpoint-driven state management for deterministic task execution pauses progress at defined checkpoints, allowing you to resume safely without redoing work while maintaining execution context across tasks via STATE.md tracking.

How do I handle plan drift and deviations during automated task execution?

Handling plan drift during automated task execution involves detecting deviations from the original plan, automatically resolving them, and capturing clear summaries in the generated SUMMARY.md artifact for full traceability.

Can I use GSD Executor for rollback and state tracking across multiple tasks?

Yes, GSD Executor supports rollback and state tracking across multiple tasks by applying one atomic commit per task, maintaining a precise history of changes, and generating STATE artifacts to recover previous execution contexts.

What do I need to set up before running automated plan execution workflows?

To run automated plan execution workflows, you need a defined PLAN.md file outlining tasks and a STATE.md file for tracking progress, ensuring the executor can apply atomic commits and capture deviations from the start.

When should I not use atomic commits for plan-driven automation scenarios?

Atomic commits for plan-driven automation are not ideal for scenarios requiring non-deterministic task execution, as the executor relies on checkpoint-driven progression, strict state tracking, and rollback capabilities to maintain traceable history.