Start Work

Start Work

Create a feature branch from a GitHub issue and prepare the working context.

Configuration

Read cloudstack.json from the project root at the start of execution. Extract relevant fields:

• REPO_OWNER / REPO_NAME = repository.owner / repository.name (default: detect from git remote -v)

If cloudstack.json does not exist, auto-detect by parsing the GitHub remote URL:

git remote get-url origin | sed -E 's|.*github\.com[:/]([^/]+)/([^/.]+).*|\1 \2|'

Arguments

• {issue} -- GitHub issue number (required). Pass as argument: /start-work 42

Process

1. Fetch issue details -- Read the issue title and body to understand the scope.
2. Ensure clean working tree -- Check git status for uncommitted changes. Warn the user if the tree is dirty.
3. Pull latest main -- Ensure the branch starts from the latest main.
4. Create and checkout branch -- Use the naming convention below.
5. Report -- Show the branch name and a summary of the issue tasks.

Branch Naming Convention

{username}/{issue-number}-{short-slug}

Derive {username} from the git config user.name (lowercase, no spaces). Derive {short-slug} from the issue title (lowercase, hyphens, max 50 chars, no special characters).

Examples:

• jdoe/42-user-group-assignments
• jdoe/15-order-versioning-api

Commands

Fetch the issue using MCP for structured data:

mcp__github-mcp-server__get_issue(owner: "{REPO_OWNER}", repo: "{REPO_NAME}", issue_number: {issue})

This returns structured JSON with title, body, labels, and state -- no CLI parsing needed.

# Check working tree
git status --short

# Update main and create branch
git fetch origin main
git checkout -b {branch-name} origin/main

After Starting -- Automatic Implementation

Once the branch is created, do not stop. Immediately continue with implementation:

1. Analyze the issue -- Parse acceptance criteria, identify affected services, and determine which layers need changes (Domain, Application, Infrastructure, Endpoints, Frontend, Tests).
2. Create a task list -- Use TodoWrite to track each implementation step derived from the issue.
3. Implement -- Follow the layer order: Domain -> Application -> Infrastructure -> Endpoints -> Frontend -> Tests. Use the appropriate scaffolding skills (/add-entity, /add-command, /add-query, /add-event-handler, /add-migration, /add-feature) where they apply. Commit logically after each meaningful change.
4. Verify as you go -- Run tests and architecture checks between steps. Fix issues before moving on.
5. When done -- Run /complete-task to go through the full completion workflow (build, lint, tests, review, PR).

Do not ask the user what to do next. Read the issue, plan the work, and start building. Only ask clarifying questions if the issue has genuine ambiguity that blocks implementation.

Output

After branch creation, report:

## Ready to Work

- Branch: `{branch-name}`
- Issue: #{issue} -- {title}
- Labels: {labels}

### Acceptance Criteria
{parsed AC from issue}

### Implementation Plan
{task list derived from issue analysis}

Starting implementation...

Error Handling

• Dirty working tree: List the uncommitted files and ask the user to commit or stash before proceeding.
• Issue not found: Verify the issue number and repo. Suggest checking with gh issue view {number}.
• Branch already exists: Ask the user if they want to check it out instead of creating a new one.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: makigjuro
• Source: makigjuro/cloudstack-ai-plugins
• License: MIT
• Homepage: https://github.com/makigjuro/cloudstack-ai-plugins#quick-start

Install and usage instructions live in the source repository linked above.