gf-resume

Load greenfield progress files and write next-task.json with task details.

Updated Apr 4, 2026
One-click install
npx skills add https://github.com/ricky-yosh/agent-workflows --skill gf-resume
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gf-resume
Source: https://github.com/ricky-yosh/agent-workflows/tree/main/skills/greenfield/gf-resume
Command: npx skills add https://github.com/ricky-yosh/agent-workflows --skill gf-resume

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Reload session context for greenfield work by loading progress from .aw/greenfield-progress files. It summarizes where you left off by reading spec.xml, tasks.json, progress.txt, and recent git logs, enabling a seamless restart.

Core Features & Use Cases

  • Load context from greenfield-progress files to reestablish feature work state.
  • Read spec.xml, tasks.json, progress.txt, and git logs to summarize progress and identify the next task.
  • Write next-task.json with the next not-done task description and task metadata; gracefully handle the all-tasks-done scenario.

Quick Start

Run the gf-resume skill to load your previous greenfield progress and prepare the next task.

Frequently Asked Questions about gf-resume

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

FAQPage Schema
How do I resume greenfield feature work after losing my session context?

To resume greenfield feature work, this Skill reloads your session context by reading progress data from .aw/greenfield-progress files, spec.xml, tasks.json, and recent git logs to summarize where you left off.

What is the best way to track progress and determine the next task in greenfield development?

The best way to track progress is by reading tasks.json and progress.txt to identify incomplete items. This Skill extracts the next not-done task and writes its description, approach, and test requirements to next-task.json.

Does this progress tracking approach handle the scenario where all tasks are already done?

Yes, this progress tracking approach gracefully handles the all-tasks-done scenario. When tasks.json contains no incomplete items, the Skill recognizes the finished state and avoids writing invalid next-task data.

Can I use git log history to summarize where I left off in a new software project?

Yes, you can use recent git logs to summarize where you left off. This Skill reads recent git commit history alongside progress.txt to reestablish your feature work state and prepare the next task.

What file format does the next task data get written to?

The next task data is written to next-task.json. This file contains structured fields including task, description, approach, and needs_tests, which are derived directly from tasks.json data.

Why does next-task.json use default values when loading greenfield progress?

Next-task.json uses default values when tasks.json is missing required fields. This ensures the progress reload process continues smoothly, deriving available task metadata while applying defaults for any absent data.