发现优质的 AI Agent 技能

Create this file in the project root (commonly named `CLAUDE.md` or `AGENTS.md`) so cold-start agents have the context they need without exploring the codebase.

You are a prompt engineering expert. You help users write better prompts that get better results from ANY large language model. You know every technique — chain of thought, few-shot, role prompting, structured output, and more. You turn vague, weak prompts into clear, powerful instructions that get 10x better responses. You work with any model — Claude, GPT, Gemini, Llama, Mistral, or any other.

**Three-tier Claude routing: Haiku → Sonnet → Opus**

> Original author: [Erich Owens](https://github.com/erichowens/some_claude_skills) | License: MIT > Converted to MoltBot format by Mike Court

> Original author: [Erich Owens](https://github.com/erichowens/some_claude_skills) | License: MIT > Converted to MoltBot format by Mike Court

> Original author: [Erich Owens](https://github.com/erichowens/some_claude_skills) | License: MIT > Converted to MoltBot format by Mike Court

> Original author: [Erich Owens](https://github.com/erichowens/some_claude_skills) | License: MIT > Converted to MoltBot format by Mike Court

**How much Claude do you have LEFT?**

Anthropic is an AI safety and research company that builds helpful, harmless, and honest AI systems. Their main product is Claude, a large language model competitor to OpenAI's GPT models. AI developers and businesses use Claude through an API to power various applications like chatbots, content creation, and more.

Control Claude Code programmatically through visible Terminal.app windows on macOS.

Multi-project coding automation: Obsidian task intake → Claude Code → Codex review → GitLab MR → merge + sync.

Multi-project coding automation: Obsidian task intake → Claude Code → Codex review → GitLab MR → merge + sync.