LogoClawIndex
CasesSkillsAbout
LogoClawIndex

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.

prompt-engineering - Design structured system prompts for AI agents

Provides practices for creating and optimizing system prompts using XML structure, clear instructions, few-shot examples, and token-efficient formatting.

Tags

Updated: 2026-10-03

Capabilities

Typical Inputs

Typical Outputs

What this skill does

  • Structure prompts with XML tags
  • Define specific agent roles
  • Organize hierarchical instructions
  • Design few-shot examples
  • Specify output formats
  • Improve prompt clarity
  • Optimize token efficiency

Inputs

  • System prompt requirements
  • Agent role and domain
  • Few-shot examples
  • Output format requirements
  • Tool usage guidance

Outputs

  • Structured system prompts
  • Prompt templates
  • Few-shot prompt examples
  • Output format specifications

Requirements

    Source

    • Spec: SKILL.md
    prompt engineering
    system prompts
    XML prompts
    few-shot learning
    AI agents
    Structure prompts with XML tags
    Define specific agent roles
    Organize hierarchical instructions
    Design few-shot examples
    System prompt requirements
    Agent role and domain
    Few-shot examples
    Structured system prompts
    Prompt templates
    Few-shot prompt examples