Prompt
**Practical Examples:**
> * **v0 & ChatGPT:** Use Markdown headings extensively (e.g., `## General Instructions`, `# Tools`, `## Refusals`).
*[Source: v0/v0.md](https://github.com/dontriskit/awesome-ai-system-prompts/blob/main/v0/v0.md)*
> * **same.new:** Employs custom XML-like tags to encapsulate rule sets (e.g., `<tool_calling>`, `<making_code_changes>`).
*[Source: same.new/same.new.md](https://github.com/dontriskit/awesome-ai-system-prompts/blob/main/same.new/same.new.md)*
> * **Manus:** Organizes capabilities and rules using descriptive tags in `Modules.md` (e.g., `<system_capability>`, `<agent_loop>`, `<tool_use_rules>`).
*[Source: Manus/Modules.md](https://github.com/dontriskit/awesome-ai-system-prompts/blob/main/Manus/Modules.md)*
> * **ChatGPT:** Uses Markdown headings (`# Tools`, `## bio`) and code blocks (```` ```typescript ... ``` ````) to define tool schemas and policies.
*[Source: ChatGPT/4-5.md](https://github.com/dontriskit/awesome-ai-system-prompts/blob/main/ChatGPT/4-5.md)*
> * **Cline:** Uses hierarchical Markdown headings (`# Tool Use Formatting`, `## execute_command`) and lists under sections like `CAPABILITIES` and `RULES`.
*[Source: Cline/system.ts](https://github.com/dontriskit/awesome-ai-system-prompts/blob/main/Cline/system.ts)*