OpenClaw AI 技能

钉钉 流 模式连接 OpenClaw AI 对话。通过钉钉机器人接收用户消息，调用 OpenClaw HTTP API 获取 AI 回复，再用 网页hook 发回钉钉。用于实现"钉钉 AI 助手"场景。

Convert a scientific paper into a presentation deck (PPTX). 生成s structured Chinese or bilingual slides for journal clubs, group meetings, or conferenc

Full-流水线 Nature-series journal writing 助手. Covers journal selection, literature review, manuscript drafting, figure generation, citation verification,

下载 videos from 1800+ 网页sites and 生成 subtitles using Faster Whisper AI. Use when user wants to 下载 videos from YouTube, Bilibili, Twitter, TikTok, Faceb

创建 concise 60-90 second videos for career coaches showcasing their unique job 搜索 methods, 命令行工具ent 成功es, and practical interview coaching tips.

提取 YouTube video URL into 提取ed audio 追踪 with this 技能. Works with MP4, MOV, 网页M, AVI files up to 500MB. content 创建器s use it for 提取in...

获取 清理 audio video ready to post, without touching a single slider. 上传 your video with audio (MP4, MOV, AVI, 网页M, up to 500MB), say something like "移除

获取 re-audioed MP4 ready to post, without touching a single slider. 上传 your video with audio (MP4, MOV, AVI, 网页M, up to 500MB), say something like "rep

Transcribe audio and video files into text using OpenAI's Whisper API. Use this 技能 whenever a user wants to convert any audio or video file to text —

Post, 搜索, interact, and manage Molttwit (Mastodon) content, media, polls, followers, and 通知 via Molttwit API.

Visual image 搜索 using Google Lens via SerpAPI. Identify objects, landmarks, products, plants, animals, artwork, 记录os, or any visual entity from an ima

When the user wants to 优化 images for 搜索 engines and performance. Also use when the user mentions "image SEO," "alt text," "image captions," "figcap...

跨平台图片压缩工具，基于 sharp 实现高效压缩（节省 60-80% 体积）。支持单图/批量压缩、格式转换 (JPG/PNG/网页P/AVIF/HEIC)、画质调节、尺寸缩放。当用户需要压缩图片体积、转换格式、缩小尺寸、批量处理图片、优化图片用于微信/邮件/网页上传时使用此技能。触发词："压缩"、

压缩 JPG, PNG, 网页P, and GIF images to reduce file size 签名ificantly while preserving visual 质量 with bulk 压缩ion support.

生成 images using the internal Google Antigravity API (Gemini 3 Pro Image). High 质量, native generation without browser 自动化.

生成 comprehensive 30-40 page academic re搜索 papers with full citations. Trigger: deep re搜索, 生成 re搜索 paper, academic paper, literature review, re搜索 报告, 3

Transcribe audio files to text using local Whisper (Docker). Use when receiving voice messages, audio files (.mp3, .m4a, .ogg, .wav, .网页m), or when as

Auto-play TTS voice files with wake word 检测ion. Only plays audio when user message contAIns wake words like "语音", "念出来", "voice", etc. Perfect for 网页c

Text-to-speech conversion using UniSound's TTS 网页Socket API for generating high-质量 Chinese Mandarin audio from text. Supports multiple voices, adjusta

Speech-to-text transcription via Crazy路由r API (OpenAI Whisper). Transcribe audio/video files to text. Supports mp3, mp4, wav, m4a, 网页m. Use when user