Agentic Workflows
awesome-gpt-image-2-prompts
我们收录了 GPT-Image-2 在人像、海报、角色设计、UI 原型及社区实验等场景下的高质量提示词与图像案例。**
Understanding Hermes Supervisor through the Evolution of Anthropic's Harness
Understanding Hermes Supervisor through the Evolution of Anthropic's Harness
Harness design for long-running application development
Written by Prithvi Rajasekaran, a member of our [Labs](https://www.anthropic.com/news/introducing-anthropic-labs) team.*
How to 10x your Claude Skills (using Karpathy's autoresearch method)
How to 10x your Claude Skills (using Karpathy's autoresearch method)
Karpathy's 10 Actionable Insights for Working with AI Agents
Karpathy's 10 Actionable Insights for Working with AI Agents
Harness Engineering Is Cybernetics
Harness Engineering Is Cybernetics
Harness Engineering is Cybernetics
Harness Engineering is Cybernetics
Collection of Excellent Design Skills
Another summary of the design skills currently available on the market:
Don't Build a Thousand Agents: How Ramp Handles Financial Automation with One Agent
Don't Build a Thousand Agents: How Ramp Handles Financial Automation with One Agent
Don't Understand These Files? No Wonder Your OpenClaw is Dumb and Clueless
Don't Understand These Files? No Wonder Your OpenClaw is Dumb and Clueless
Five Steps to Create an OpenClaw Multi-Agent Telegram Group Chat! Includes Advanced Hacks! (Practical Guide + You'll Get It or I'm to Blame)
Five Steps to Create an OpenClaw Multi-Agent Telegram Group Chat! Includes Advanced Hacks! (Practical Guide + You'll Get It or I'm to Blame)
A Labor of Love, My Gift to You Lobsters: OpenClaw Agent System Prompt Architecture Explained (9 Layers)
A labor of love, my gift to you lobsters: A detailed breakdown of the OpenClaw Agent's complete System Prompt structure.
From 0 to 1: Replicating an Agent Like Claude Code
From 0 to 1: Replicating an Agent Like Claude Code
Building an OpenClaw Multi-Role Team from 0 to 1
A complete guide to building an OpenClaw multi-role team from scratch
The OpenClaw Chronicles: From Zero to Hero! Must-Read After Installation (40 Days of Hands-On Experience + Character Prompts)
The OpenClaw Chronicles: From Zero to Hero! Must-Read After Installation (40 Days of Hands-On Experience + Character Prompts)
Step-by-Step Guide to Configuring OpenClaw Multi-Agent × Telegram Group Automation System (Includes Easter Egg)
🦞 A step-by-step guide to configuring the OpenClaw multi-agent × Telegram group automation system, includes an easter egg.
The File System Is the New Database: How I Built a Personal OS for AI Agents
The File System Is the New Database: How I Built a Personal OS for AI Agents
From Vibe Coding to Agentic Engineering: The Developer Role is Being Rewritten
From Vibe Coding to Agentic Engineering: The Developer Role is Being Rewritten
How to set up OpenClaw Agents that actually get better Over Time (My exact stack after 40 Days)
How to set up OpenClaw Agents that actually get better Over Time (My exact stack after 40 Days)
The Hidden Layer in OpenClaw Swarms: Make Them Disagree, See Who Survives
The Hidden Layer in OpenClaw Swarms: Make Them Disagree, See Who Survives
Agent Skill Best Practices
Agent Skill Best Practices
Andrej Karpathy on X: CLIs are super exciting precisely
Andrej Karpathy (@karpathy)
Implementing the ReAct Pattern
Reasoning and Acting: The foundational pattern that allows LLMs to interact with external tools.
Building a Self-Reflecting Agent
Enhance agent reliability by implementing a critique-and-refine loop.