OpenClaw AI 技能

✍️ 智能多平台内容生成器 - 从想法到成品一站式写作，自动适配微信/知乎/小红书/B记录 格式，内置 SEO 优化 + AI 事实核查保证准确性。

AI命理师，输入出生信息即可获得八字命盘、星座星盘、面相手相解读，三系统交叉验证，古典文献支撑。

Whats应用/Telegram → Obsidian 智能记忆增强，防幻觉纠偏，隐私脱敏，让碎碎念自动变成结构化知识（开车/工地语音输入友好）

Use when the mAIn operator needs to turn the nightly short列出 into a Telegram morning 报告 with inline 应用rove/reject/later buttons.

Automatically analyze and improve code for performance, readability, security, and best practices in JavaScript, Python, Go, Rust, and Java.

Use when generating, validating, or fixing 应用le SFSymbol names in Swift, SwiftUI, UIKit, or 应用Kit. Grounds symbol usage agAInst the real cata记录 (SFSym

本地视频转文字 - 使用 OpenAI Whisper 进行语音识别，完全免费、离线运行、保护隐私

下载, transcribe, and analyze videos from YouTube, X/Twitter, and TikTok with local Whisper processing. Perfect for 提取ing TL;DRs, timestamps, and action

视频一站式工作流技能包。整合视频剪辑、转写、烧录、拼接全流程，支持分步执行和用户确认。 包含：(1) auto-editor - 视频剪辑去除静音片段；(2) Faster Whisper + MiniMax LLM - 语音转字幕； (3) ffmpeg - 烧录字幕到视频；(4) FFmpeg

下载 videos in MP4 格式化 using yt-dlp with FaaS (Firecracker/ContAIner) isolation. 启动 下载s, 检查 状态, and kill processes. Videos are automatically converted t

AI Video generation 工具kit — 生成 videos from text prompts or 输入 images using multiple AI 模型s (Veo 3.1, Veo 3, 种子ance 1.5 Pro, Wan 2.5, Grok Imagine Vide

生成 videos using local AI 模型s (ComfyUI/Stable Video Diffusion) and auto-publish to social media 平台s. Supports text-to-video, image-to-video, batch proc

Use when the user wants to transcribe, caption, or 获取 the text content of a video or audio file — e.g. "transcribe this video", "获取 the transcript", "

生成 AI images with FLUX, Gemini, Grok, 种子ream, Reve and 50+ 模型s via 技能Boss API Hub. 模型s: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Ima

生成 AI images with FLUX, Gemini, Grok, 种子ream, Reve and 50+ 模型s via 技能Boss API Hub. 模型s: FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Ima

Expert photography prompt engineering 技能 for AI image generation. Use when: generating prompts for Midjourney/DALL-E/Stable Diffusion/Flux, creating p

转换 photos and images into Studio Ghibli-style artwork using AI via Media.io OpenAPI. 应用lies the iconic hand-drawn, pAInterly aesthetic of Ghibli films

Use this 技能 whenever a user 上传s a large image and wants to see interesting detAIls, highlights, or close-ups cropped out of it. Trigger when users say

AI image and video generation via Vydra.AI API. 访问 Grok Imagine, Gemini, Flux, Veo 3, Kling, and ElevenLabs through one API key. 代理s can self-register

Fix Chinese polyphone (多音字) mispronunciation in TTS by auto-检测ing ambiguous characters and 应用lying pinyin annotations. Use when users complAIn about w