gh:work

Automate software feature delivery from plan documents or prompts.

2|1|Updated Apr 17, 2026

Search Tags:#automation #planning #task-management #quality-checks #memory-context #work-execution

Ready to run

npx skills add https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI --skill gh-work

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: gh:work
Source: https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI/tree/main/plugins/galeharness-cli/skills/gh-work
Command: npx skills add https://github.com/wangrenzhu-ola/GaleHarnessCodingCLI --skill gh-work

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Automates work execution by transforming a plan document or a bare prompt into structured, trackable tasks and guided activities that yield a shipped feature.

Core Features & Use Cases

Plan-driven execution and task decomposition from a plan or prompt
Phase-based guardrails with memory-backed context retrieval
Integrated quality checks, testing, and incremental commits
Historical session awareness to reuse prior work patterns

Quick Start

Provide a plan document or bare prompt to begin executing work and shipping a complete feature.

Frequently Asked Questions about gh:work

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

FAQPage Schema

How do I automate software development workflows from a plan document?▼

You can automate work execution by providing a plan document or bare prompt to initiate task decomposition and phased planning. This process yields a shipped feature by applying memory-backed context retrieval, quality checks, and incremental commits.

What is task decomposition in software engineering?▼

Task decomposition is the process of breaking a plan document or bare prompt into structured, trackable tasks for guided activities. It enables phased planning, memory context retrieval, and quality checks across iterations and subagents.

Does memory-backed context retrieval help reuse prior work patterns?▼

Yes, memory-backed context retrieval provides historical session awareness to reuse prior work patterns during work execution. It maintains memory context across iterations and subagents to satisfy traceable task requirements and execution contracts.

Can I execute bare prompts to ship complete software features?▼

Yes, you can execute a bare prompt to ship complete features by transforming it into structured, trackable tasks. The automation applies phase-based guardrails, integrated quality checks, and incremental commits to yield the shipped feature.

What's the best way to ensure quality checks across development iterations?▼

The best way to ensure quality checks across iterations is to apply phase-based guardrails with memory-backed context retrieval during work execution. This integrates testing and incremental commits, satisfying verification criteria aligned with an established harness.

Do I need an established harness to apply traceable task execution contracts?▼

Yes, you need an established harness to apply traceable task execution contracts. The automation satisfies requirements for traceable tasks and verification criteria aligned with this harness to ship complete features successfully.