skills.rest
jeremydhoover-blip
jeremydhoover-blipCOMMUNITY
Explore all skills by this author →
GitHub

designing-agent-instructions

Design unambiguous instructions defining agent purpose, behaviors, decision authority, output format, and error handling.

7|7|Updated Feb 20, 2026
Search Tags:#prompt engineering#llm#system prompt#agent#instruction design#ai behavior
One-click install
npx skills add https://github.com/jeremydhoover-blip/hoover-content-system --skill designing-agent-instructions
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: designing-agent-instructions
Source: https://github.com/jeremydhoover-blip/hoover-content-system/tree/main/skills/mcp-and-agents/designing-agent-instructions
Command: npx skills add https://github.com/jeremydhoover-blip/hoover-content-system --skill designing-agent-instructions

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you create clear, unambiguous instructions for AI agents, ensuring they behave as intended and avoid harmful or unhelpful actions.

Core Features & Use Cases

  • Define Agent Behavior: Specify what an agent MUST do and MUST NOT do.
  • Set Decision Boundaries: Clarify when an agent can act autonomously versus when it needs user confirmation.
  • Handle Errors and Edge Cases: Provide guidance for unexpected situations.
  • Use Case: You are building a customer support chatbot. Use this Skill to define its persona, its allowed actions (e.g., answering FAQs, troubleshooting), its prohibited actions (e.g., accessing payment info), and how it should handle errors or escalate complex issues.

Quick Start

Design agent instructions for a code review assistant that must check for bugs and style violations.

Frequently Asked Questions about designing-agent-instructions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write clear system prompts for LLM agents?▼

System prompts for LLM agents require defining purpose, core behaviors, decision authority, output format, and error handling to ensure reliable execution and avoid ambiguity or contradictions.

What are common pitfalls when designing AI agent instructions?▼

Common pitfalls when designing AI agent instructions include ambiguity, incompleteness, and contradictions, which cause unreliable execution. Addressing these ensures the agent behaves as intended within its operational constraints.

How do I set decision boundaries for an autonomous AI agent?▼

Set decision boundaries for an autonomous AI agent by explicitly specifying what it MUST do and MUST NOT do, clarifying when it can act autonomously versus when it needs user confirmation.

How should an LLM agent handle errors and unexpected edge cases?▼

LLM agent error handling requires providing explicit guidance for unexpected situations within the system prompt. This includes defining operational constraints for how the agent should respond to or escalate complex issues.

Can I use instruction design to restrict my chatbot from accessing certain data?▼

Yes, instruction design restricts chatbot actions by defining prohibited behaviors within the system prompt. You can explicitly specify that the agent MUST NOT access sensitive information like payment details.

Related Skills

Explore More Software Engineering Skills→
SSiertsemaSSiertsema

scope-statement-writing

Generate a complete project scope statement with boundaries and change protocol.

Community
Intermediate
erichowenserichowens
181

orchestrator

Coordinate specialized agents to decompose and execute multi-skill tasks.

Community
Advanced
TugoukezhangTugoukezhang
8

prompt-engineering-expert

Analyze and refine prompts for clarity, structure, and specificity.

Community
Advanced
theafhtheafh
38

ai_instruction_writing

Rewrites AI-consumed instructions to prioritize positive, actionable phrasing while retaining necessary catch-all negatives.

Community
Intermediate