Contributing to AI Workflow
January 16, 2026 ยท View on GitHub
First off, thanks for taking the time to contribute! ๐
How Can I Contribute?
๐ Reporting Bugs
- Check if the bug has already been reported in Issues
- If not, create a new issue using the bug report template
- Include as much detail as possible
๐ก Suggesting New Skills or Workflows
- Open an issue with the "feature request" template
- Describe the use case and target users
- List the skills you think should be included
๐ง Submitting Pull Requests
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-skill) - Make your changes
- Test your skills with Claude Code or other supported tools
- Commit your changes (
git commit -m 'Add amazing-skill') - Push to the branch (
git push origin feature/amazing-skill) - Open a Pull Request
Creating New Skills
Skill Structure
skill-name/
โโโ SKILL.md # Required: Skill definition
โโโ references/ # Optional: Reference documents
โ โโโ guide.md
โโโ assets/ # Optional: Templates, examples
โโโ template.md
SKILL.md Format
---
name: skill-name
description: Brief description of what this skill does and when to use it
---
# Skill Name
## Overview
Detailed description of the skill.
## When to Use
- Trigger condition 1
- Trigger condition 2
## Workflow
Step-by-step instructions for the AI.
## Output Format
Expected output format.
Best Practices
- Clear trigger conditions - Make it easy for AI to know when to use the skill
- Specific instructions - Be detailed about what the AI should do
- Examples - Include example inputs and outputs
- References - Add supporting documents for complex skills
Creating New Workflows
Workflow Structure
workflow-name/
โโโ .claude/skills/ # Claude Code skills
โโโ README.md # English documentation
โโโ README_cn.md # Chinese documentation
โโโ AGENTS.md # Agent routing guide
Checklist
- At least 10 skills included
- README.md with clear target users
- README_cn.md for Chinese users
- AGENTS.md for AI routing
- Symlinks for multi-AI tool support
Code of Conduct
Please read our Code of Conduct before contributing.
Questions?
Feel free to open an issue with your question!