A best practice for universal prompt engineering that complies with the AGENTS.md open specification.
- Organize
AGENTS.mdbest practices for different domains in separate folders skill/agents-md-best-practices/encapsulates allAGENTS.mdand uses workflow-generated SKILL for progressive disclosure
AGENTS.md-Best-Practices/
├── src/
│ ├── develop/ # Primary category
│ │ └── web-frontend-design/ # Secondary category
│ │ └── {author}/ # Author
│ │ ├── AGENTS.md # Main file (language-agnostic)
│ │ └── AGENTS_{xx-YY}.md # Optional multilingual version (e.g., zh-CN)
│ └── life/
└── skill/
└── agents-md-best-practices/ # Complete encapsulation (generated via workflow)
├── SKILL.md # Skill entry point
├── index.yaml # MD document index
└── md/ # All AGENTS.md
└── {primary-category}_{secondary-category}_{author}_AGENTS.md # AGENTS.md copy
Select the appropriate AGENTS.md file based on your needs and project description, download it to your project directory, and prompt the local Agent to load it after running.
Download and install the skill/agents-md-best-practices/ skill pack to the Agent's corresponding directory, then prompt the local Agent to load the skill after running.
No entries yet. Contributions are welcome.
Welcome to contribute in the following ways:
- Submit entries: Create corresponding
AGENTS.mdfiles in thesrc/directory according to the project structure requirements - Report issues: Submit Issues to report bugs or suggest improvements
- Improve documentation: Optimize existing documents or translate multilingual versions
- Develop features: Implement new features or optimize workflows
Please ensure you follow the project guidelines and maintain consistent code style.
This project is licensed under the MIT License
Copyright © 2026 JularDepick, see COPYRIGHT for details.