Neura Market Logo

AI Agent Helper

AI Agent 設定同優化助手 - Prompt Engineering、Task Decomposition、Agent Loop設計

Katrina-jpg

@katrina-jpg

What This Skill Does

Designs and optimizes AI agent configurations including system prompts, task decomposition, and agent loop patterns (ReAct, Chain-of-Thought). Provides structured templates and best practices for prompt engineering, tool selection, and error handling.

Replaces manual trial-and-error prompt tuning by offering reusable patterns for system prompts, few-shot examples, and output parsing.

When to Use It

  • Craft a high-quality system prompt for a new AI agent
  • Decompose a complex multi-step task into manageable subtasks
  • Design a ReAct or Chain-of-Thought loop for an agent
  • Optimize an existing agent's tool usage and output parsing
  • Add error handling and token efficiency patterns to an agent

Install

$ openclaw skills install @katrina-jpg/ai-agent-helper

AI Agent Helper

幫你setup同優化AI Agents既技能。

功能

  • 📝 Prompt Engineering - 整高質量system prompts
  • 🔄 Task Decomposition - 將複雜任務拆解
  • ⚙️ Agent Loop設計 - ReAct/ReAct/Chain-of-Thought
  • 🎯 Tool Selection - 最佳化agent既tool usage

使用場景

"帮我整prompt" / "點樣set AI agent" / "優化agent response"

技術

  • System Prompt優化
  • Few-shot examples
  • Output parsing (JSON/structured)
  • Error handling patterns
  • Token優化

範例

# Good prompt structure
system = """你係{role}。
目標：{goal}
限制：{constraints}
Output格式：{format}"""

Top skills in this category

self-improving agent

@pskoett

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea

4.0k477k

Skill Vetter

@spclaudehome

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

1.3k271k

Self-Improving + Proactive Agent

@ivangdavila

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

1.3k209k

Proactive Agent

@halthelobster

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

831175k

Agent Browser

@matrixy

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

459156k