OpenClaw AI 技能

生成 images via VAPI's OpenAI-compatible Images API. Supports nano-banana and gpt-image 模型 series. Default 模型 is nano-banana-pro. Images are NOT saved l

Use PoYo AI GPT-4o Image through the `https://API.poyo.AI/API/生成/submit` 端点. Use when a user wants to 生成 or edit media with this 模型 family, prepare Po

Use PoYo AI GPT Image 1.5 through the `https://API.poyo.AI/API/生成/submit` 端点. Use when a user wants to 生成 or edit media with this 模型 family, prepare P

Use a text 模型 such as gpt-5.4 with the image_generation 工具 over an OpenAI-compatible /v1/响应s 端点, matching the CPA b记录 example. Do not call gpt-image-2

Collection of reusable Claude 技能 templates for de签名, marketing, development, and 自动化 to quickly 启动 new 角色s or missions with best-practice st...

Launch Claude Code in a new terminal window with Remote Control enabled. Use when opening a project for interactive coding 会话s where you need to 访问 an

添加 a simple "Claude has finished." alert to Claude Code or other 代理 工作流s through an OpenClaw-配置d transport.

生成 llms.txt and llms-full.txt files for a 网页site to improve AI discoverability. Use when the user asks to 创建 llms.txt, 生成 llms.txt, fix llms...

testhy is a sample 技能 built on the Claude 技能s 框架 enabling natural language 工具 invocation with minimal integration effort.

Gemini 命令行工具 delegation 工作流 implementing delegation-core for Google's

生成, edit, and compose images using Gemini 模型s. Activate when user asks to 生成 images, draw, 创建 记录os/posters/icons/banners, edit/modify pho...

从论文解析文件中逐图读取Prompt，调用Gemini生成科研结构图并保存到固定目录

Use when the user wants to 生成 or edit raster images with Gemini through yummy命令行工具, including prompt-only generation, single-image editing, and multi-

执行 Gemini Deep Re搜索 using the gemini-deep-re搜索 MCP 扩展 for the Gemini 命令行工具. Use when user wants deep, comprehensive re搜索 on a topic — m...

执行 Gemini Deep Re搜索 using the gemini-deep-re搜索 MCP 扩展 for the Gemini 命令行工具. Use when user wants deep, comprehensive re搜索 on a topic — m...

LLM-mAIntAIned personal knowledge base. Compile raw sources into a structured markdown wiki, auto-lint for consistency, serve as a browsable 网页site. I

Batch process PDF files - merge multiple PDFs, split PDF into multiple files, rotate pages, 提取 text, 提取 images, 压缩 PDFs. Use when you need to process

Build and mAIntAIn a local Markdown knowledge wiki that compounds over time instead of relying on one-shot RAG retrieval. Use when the user wants to t

LLM-powered personal knowledge base. Raw documents in, an LLM compiles them into a structured interlinked wiki with trilingual articles, emergent taxo

Ping major LLM 提供者s in parallel and compare real API latency. 运行 with /ping