Agent Instructions
VoltAgent supports three approaches for defining agent instructions. Each approach addresses different requirements around flexibility, team collaboration, and deployment workflows.
Explore
15,060 skills indexed with the new KISS metadata standard.
VoltAgent supports three approaches for defining agent instructions. Each approach addresses different requirements around flexibility, team collaboration, and deployment workflows.
This document provides a comprehensive collection of effective prompts for using the WpfToAvalonia MCP Server with AI agents like Claude, GitHub Copilot, and other LLM-based assistants.
If you want to rebuild this project from scratch, you can follow these sequential prompts:
This guide provides natural language examples for querying your FOCUS cost data through Claude Desktop, Gemini CLI, or other MCP-compatible agents.
How to manage prompts effectively.
- **Difficulty**: Intermediate
**Name**: FrenchToxicityPrompts
generic skill
"Ganapati and Scribe, I need to [describe your goal]. Help me identify the critical path - what are the real obstacles versus imagined ones? Scribe, capture the pattern we discover."
https://arxiv.org/abs/2210.03629
This document describes the comprehensive prompt engineering system implemented to avoid "AI slop" and ensure high-quality, professional UI designs.
AI image generation with structured prompts
Erfahren Sie, wie Sie effektive Prompts für Adobe GenStudio for Performance Marketing schreiben.
Saiba como escrever prompts efetivos para o Adobe GenStudio for Performance Marketing.
You are an intelligent workflow planner for a dynamic task execution system.
Choose from our preset templates or create your own prompt to control how your agent handles conversations with callers.
A list of suggested prompt data object based on the current prompt.
- [System Prompts Leaks](https://github.com/asgeirtj/system_prompts_leaks)
generic skill
发布时间:2024年04月03日
发布时间:2024年06月12日
Analiza el funcionamiento de todo mi codigo y y genera un readme explicando como funciona
**Tasks**
**Denoise**