auto-pr
Auto PR - Automated PR Submission Assistant
Overview
This skill helps you automate the complete Pull Request process, including code review, documentation generation, and PR creation.
Core Functions
- Update Base Branch - Sync remote main/master branch
- Code Review Analysis - Compare differences between current and base branch
- PR Template Discovery - Automatically scan for PR templates in the project
- English Documentation Generation - Generate English PR description, waiting for user confirmation
- Automatic PR Submission - Create PR using English description after user approval
- Cleanup Process - Offer to remove temporary PR description files after submission
Usage
/auto-pr [base-branch]
base-branch: Optional, defaults tomain
Workflow
Please execute the following workflows in sequence:
- Branch Preparation ⭐⭐⭐
- Code Review ⭐⭐⭐
- Documentation Generation ⭐⭐⭐
- PR Submission ⭐⭐⭐
Key Interaction Points
During the documentation generation phase, the process will pause to wait for user confirmation:
Branch Preparation → Code Review → Generate English Documentation → [Wait for User Confirmation] → Submit PR → [Clean Up Temporary Files]
User Confirmation Points:
- After English documentation is generated, wait for user review and confirmation
- After PR is submitted, confirm deletion of temporary description files (PR_DESCRIPTION.md, etc.)
Prerequisites
Environment Check
Before executing the skill, run the check script:
node ./scripts/check-prerequisites.js
Dependency Requirements
| Dependency | Required | Installation Method |
|---|---|---|
| Git | Yes | System built-in or brew install git |
| GitHub CLI | Yes | brew install gh |
| Node.js | Yes | brew install node |
GitHub CLI Authentication
Complete authentication for first use:
gh auth login
Select as prompted:
- GitHub.com
- HTTPS
- Use browser for authentication
After authentication, verify:
gh auth status
Project Requirements
- Git repository initialized
- Remote repository configured
- Current branch is not main/master
- Unpushed commits exist
Script Tools
This skill includes the following scripts:
| Script | Description |
|---|---|
scripts/check-prerequisites.js |
Prerequisites check |
scripts/create-pr.js |
Automatic PR creation |
Quick Start
node ./scripts/create-pr.js \
--title "feat: feature description" \
--body-file ./PR_DESCRIPTION.md
Notes
- Ensure all changes are committed before execution
- PR descriptions will automatically search for templates in the project
- Supports GitHub (requires gh CLI installation)
- Temporary description files will be offered for deletion after PR submission
More from qwenlm/qwen-code-examples
weixin-channel-setup
帮助用户快速配置和使用微信通道功能。当用户想要"配置微信"、"连接微信"、"设置微信机器人"、"weixin setup"、"wechat channel"时使用此技能。
84dashboard-builder
Build full-stack dashboard applications using React/Next.js + shadcn/ui + Tailwind CSS + Recharts + Express with customizable data sources. Use when creating data visualization dashboards, business intelligence interfaces, monitoring systems, KPI displays, analytics platforms, or any project requiring data visualization with modern UI components and dynamic effects.
72image-generation
Image generation skill based on Alibaba Cloud DashScope, supporting the creation of high-quality hand-drawn or standard images from user descriptions.
26youtube transcript extractor
Extracts timestamped transcripts from YouTube videos for translation, summarization, and content creation.
12oss-styles
|
3codegraph-qa
Use CodeScope to analyze any indexed codebase via its graph database (neug) and vector index (zvec). Supports Python, JavaScript/TypeScript, C, and Java (including Hadoop-scale repositories). Covers call graphs, dependency analysis, dead code detection, hotspots, module coupling, architectural layering, commit history, change attribution, semantic code search, impact analysis, full architecture reports, and bug root cause analysis from GitHub issues. Use this skill whenever the user asks about code structure, code dependencies, who calls what, why something changed, finding similar functions, generating architecture reports, understanding module boundaries, analyzing GitHub issues/bugs, finding bug root causes, understanding why a project has many bugs, tracing bugs to code, indexing Java projects, or any question that benefits from a code knowledge graph — even if they don't mention "CodeScope" by name. If a `.codegraph` or similar index directory exists in the workspace, this skill applies.
2