发现优质的 AI Agent 技能

> Learn how to write effective Skills that Claude can discover and use successfully.

This skill enables Claude Code to deeply analyze empirical research papers, following a structured framework: Problem Statement → Core Empirical Challenges → Identification Strategy → Key Findings → Academic Contribution.

To build powerful frontend claude.ai artifacts, follow these steps: 1. Initialize the frontend repo using `scripts/init-artifact.sh` 2. Develop your artifact by editing the generated code 3. Bundle all code into a single HTML file using `scripts/bundle-artifact.sh` 4. Display artifact to user

> 本文件遵循 AGENTS.md 规范，供任意 AI Agent（OpenClaw、Claude、GPT、Gemini 等）直接学习并使用本 Skill。

> 本文件遵循 AGENTS.md 规范，供任意 AI Agent（OpenClaw、Claude、GPT、Gemini 等）直接学习并使用本 Skill。

本 Skill 的核心能力：**从对话中提取可复用的工作流，生成结构化的 Skill 文件， 让 Claude 在后续会话中能按照固定流程执行任务。**

- **Key:** claude-code - **Best for:** Code development, refactoring, debugging - **Capabilities:** dev, refactor, debug, docs - **Dispatch:** CLI via PowerShell (Windows native) or WSL - **Parallel:** Up to 3 instances

Orchestrates multi-step projects across multiple agents (Claude Code, Eva, others) using a state machine with JSON-based persistence. Each task has subtasks dispatched to agents, tracked via heartbeat, and reported through Discord.

Copy-paste these prompts directly to Claude Code to generate a digest.

OPENAI_API_KEY: OpenAI provider key GEMINI_API_KEY: Google Gemini provider key ANTHROPIC_API_KEY: Anthropic Claude provider key OLLAMA_BASE_URL: Ollama base URL (optional, defaults to http://localhost:11434) TWITTERAPI_IO_KEY: twitterapi.io API key (preferred)

Memory that carries across conversations. Automatically captures important knowledge during work and saves structured session summaries when you're done. Searches past context before new tasks.

HTTP MCP server that exposes OpenViking RAG capabilities as tools for Claude and other MCP clients.