dev-github-workflow

Git Workflow Automation

Handles commits, branches, pull requests, and merges. Works in two modes: automatic (called during plan execution after each approved phase) and manual (user invokes directly to commit changes).

For Git concepts and educational content, see github-for-designers.md.

Interaction Method

If AskUserQuestion is available, use it for all prompts below.

If not, present each question as a numbered list and wait for a reply before proceeding. For multiSelect questions, accept comma-separated numbers (e.g. 1, 3). Never skip or auto-answer without explicit user consent.

---

Step 0: Before starting

1. Announce your execution plan: Before doing anything, state what you will do in this activity: "Here's what I'm going to do: 1) check the current git state and branch, 2) determine what to include in the commit, 3) generate a commit message following Conventional Commits format, 4) commit and push after your approval." This is a commitment device – harder to skip steps you just announced.

2. Conditional teaching: Ask the user if they are familiar with Git basics – commits, branches, and pull requests. If yes, give a one-sentence refresher on the Conventional Commits format used here. If no, explain it in simple terms: Git tracks every change you make so you can go back if something breaks – commits are save points, branches are parallel versions, and PRs are how you merge work back together. Refer to github-for-designers.md for a deeper walkthrough.

   Required: ALWAYS ask the question, ALWAYS give the refresher when the user says yes. Never skip this step because the user "is a designer" or "already demonstrated familiarity earlier." Users want a memory refresh on every activity, including ones they know. Phrases like "I'll skip the explainer (you're a designer)" are forbidden — they signal the model has decided ON BEHALF OF the user that a refresher isn't needed. The user, not the model, decides what's redundant. The refresher takes one sentence; the cost is trivial; the value to a tired user mid-session is high.