Generate Agent Instructions
Craft detailed, actionable instructions for other AI agents based on a given task or goal.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add generate-agent-instructions npx -- -y @trustedskills/generate-agent-instructions
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"generate-agent-instructions": {
"command": "npx",
"args": [
"-y",
"@trustedskills/generate-agent-instructions"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill generates detailed instructions for AI agents, specifying their roles, goals, and constraints. It helps define agent behavior clearly, ensuring they operate effectively within a defined scope. The generated instructions are designed to be easily understood by various AI platforms and frameworks.
When to use it
- Defining new agents: Quickly create clear operational guidelines for newly developed AI agents.
- Improving existing agent performance: Refine the behavior of current agents by providing more precise instructions.
- Standardizing agent workflows: Ensure consistency across multiple AI agents performing similar tasks.
- Facilitating collaboration between agents: Define interactions and responsibilities when multiple agents work together.
Key capabilities
- Role definition
- Goal specification
- Constraint setting
- Instruction generation
Example prompts
- "Generate instructions for an agent whose role is a customer service chatbot, with the goal of resolving user inquiries efficiently."
- "Create agent instructions for a data extraction tool that must only extract information from news articles and avoid opinion pieces."
- “Write instructions for an AI agent tasked with summarizing research papers, specifying it should focus on methodology and results.”
Tips & gotchas
The quality of the generated instructions depends heavily on the clarity and specificity of your initial prompt. Be as detailed as possible when describing the desired agent behavior to achieve optimal results.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.