rework

Append implementation steps to a Ralph spec GitHub issue and re-queue it.

1|4|Updated Oct 27, 2014
One-click install
npx skills add https://github.com/rjernst/dotfiles --skill rework
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rework
Source: https://github.com/rjernst/dotfiles/tree/main/claude/skills/rework
Command: npx skills add https://github.com/rjernst/dotfiles --skill rework

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Rework helps you take review outcomes from a Ralph spec issue and convert them into concrete implementation steps, then re-queue the spec for another execution cycle.

Core Features & Use Cases

  • Append new implementation steps: Adds new tasks to the existing spec issue using the same step numbering and formatting as the current issue body.
  • Transition the spec to re-execution: Updates issue labels to move the spec back into a status:ready state so it can run again.
  • Review-context driven step creation: When invoked after a review, it translates Critical and Suggestions findings into new implementation steps, optionally filtered by referenced finding numbers.

Quick Start

Ask the assistant to rework the spec by replying to the appropriate issue context, for example: run /rework with an issue number or with the review findings you want to address.

Frequently Asked Questions about rework

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

FAQPage Schema
How do I append new tasks to a GitHub issue after a code review?

To append new tasks to a GitHub issue after a code review, use a workflow automation tool to derive implementation steps from Critical and Suggestions findings, generate formatted numbered steps, and append them to the existing spec issue body.

How do I automate re-queuing a GitHub spec issue for execution?

Automating the re-queuing of a GitHub spec issue involves appending newly generated implementation tasks to the issue body and transitioning its labels back to a status:ready state using GitHub CLI with repository-scoped --repo handling.

Can I generate implementation steps from specific review findings on a GitHub issue?

Yes, you can generate implementation steps from specific review findings by providing natural-language instructions that reference Critical and Suggestions finding numbers from a prior review, optionally filtering the new task generation by those referenced numbers.

Do I need to manually approve new tasks before a GitHub issue is updated?

Yes, a mandatory user approval review gate is required before any GitHub issue edits occur, ensuring you review and approve the correctly formatted new numbered steps generated from the review findings before they are appended.

How does label management work when reworking a spec issue?

Label management during spec rework uses GitHub CLI to transition issue labels to status:ready, moving the updated spec back into an execution queue after the new implementation tasks are appended and approved.

What is the best way to update a Ralph spec issue with new workflow automation tasks?

The best way to update a Ralph spec issue with new tasks is initiating a rework command with an issue number or review instructions, generating matching numbered steps, passing an approval gate, and applying label transitions for re-execution.