create-pr
Create Pull Request
Draft a concise and descriptive title and a short paragraph for a PR. Explain the purpose of the changes, the problem they solve, and the general approach taken. When the changes involve clear runtime flows or state transitions, include Mermaid diagrams.
Step 1: Analyze Changes
If git is in a feature branch, examine all commit messages and the full diff to understand the overall changes. Analyze the diff for diagram opportunities (see Diagrams section below).
Step 2: Draft Title and Description
Run /github-voice to load writing style rules before drafting.
Draft a title and description, embedding any diagrams in the body. Output the drafted title and description as chat text so the user can review it.
Step 3: Confirm and Create
Use AskUserQuestion for confirmation only. Create the PR with gh pr create. Do not set --assignee unless the user explicitly asks to assign someone.
Diagrams
GitHub renders Mermaid natively in PR descriptions via ```mermaid code blocks. Include diagrams only when they add clarity a text description can't — skip for trivial changes or obvious flows.
Sequence Diagram
Include when the changes introduce or modify a clear runtime flow: API endpoints, event handlers, pipelines, multi-service interactions, webhook flows.
```mermaid
sequenceDiagram
Client->>API: POST /payments
API->>PaymentService: processPayment()
PaymentService->>StripeClient: charge()
StripeClient-->>PaymentService: confirmation
PaymentService->>DB: save()
```
State Diagram
Include when the changes add or modify entity states, status enums, workflow transitions, or lifecycle hooks.
```mermaid
stateDiagram-v2
[*] --> Draft
Draft --> Pending: submit()
Pending --> Approved: approve()
Pending --> Rejected: reject()
Approved --> [*]
```
Rules
- Only include when the diagram genuinely adds clarity
- Keep diagrams focused — max ~10 nodes/transitions
- Use descriptive labels on arrows (method names, HTTP verbs)
- Place diagrams after the summary paragraph under a
## Flowor## State Machineheading - One diagram per type max — don't include both unless the PR truly has both patterns
More from tobihagemann/turbo
find-dead-code
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to \"find dead code\", \"find unused code\", \"find unused exports\", \"find unreferenced functions\", \"clean up dead code\", or \"what code is unused\". Analysis-only — does not modify or delete code.
30simplify-code
Run a multi-agent review of changed files for reuse, quality, efficiency, and clarity issues followed by automated fixes. Use when the user asks to \"simplify code\", \"review changed code\", \"check for code reuse\", \"review code quality\", \"review efficiency\", \"simplify changes\", \"clean up code\", \"refactor changes\", or \"run simplify\".
23smoke-test
Launch the app and hands-on verify that it works by interacting with it. Use when the user asks to \"smoke test\", \"test it manually\", \"verify it works\", \"try it out\", \"run a smoke test\", \"check it in the browser\", or \"does it actually work\". Not for unit/integration tests.
22finalize
Run the post-implementation quality assurance workflow including tests, code polishing, review, and commit. Use when the user asks to \"finalize implementation\", \"finalize changes\", \"wrap up implementation\", \"finish up\", \"ready to commit\", or \"run QA workflow\".
22self-improve
Extract lessons from the current session and route them to the appropriate knowledge layer (project AGENTS.md, auto memory, existing skills, or new skills). Use when the user asks to \"self-improve\", \"distill this session\", \"save learnings\", \"update CLAUDE.md with what we learned\", \"capture session insights\", \"remember this for next time\", \"extract lessons\", \"update skills from session\", or \"what did we learn\".
22evaluate-findings
Critically assess external feedback (code reviews, AI reviewers, PR comments) and decide which suggestions to apply using adversarial verification. Use when the user asks to \"evaluate findings\", \"assess review comments\", \"triage review feedback\", \"evaluate review output\", or \"filter false positives\".
22