3,611 tools and skills for media tasks
Use PoYo AI Veo 3.1 for frame-conditioned video generation through the `https://api.poyo.ai/api/generate/submit` endpoin
Use PoYo AI Nano Banana for general image generation and image editing across many aspect ratios through the `https://ap
Use PoYo AI Seedance 1.5 Pro for higher-end image-to-video generation through the `https://api.poyo.ai/api/generate/subm
Use PoYo AI Z-Image for straightforward prompt-based image generation through the `https://api.poyo.ai/api/generate/subm
Convert TikTok/YouTube/Instagram search and trend signals into a prioritized weekly content backlog with script angles a
Generate professional HTML presentations with slide content, whiteboard-style images, and detailed word-for-word speaker
Generate images via VAPI's OpenAI-compatible Images API. Supports nano-banana and gpt-image model series. Default model
Create professional reveal.js HTML presentations with AI-generated whiteboard images and detailed speaker scripts tailor
Generates professional e-commerce product scene prompts (Midjourney/DALL-E/Stable Diffusion) with physics-based lighting
Generate images and videos via Neodomain AI API. Supports text-to-image, image-to-video, text-to-video, and motion contr
Control XiaoPai media player over LAN via HTTP/TCP. Use when asked to play videos, send remote-control keys, adjust volu
腾讯云通用文字识别（高精度版）(GeneralAccurateOCR) 技能包。支持图像整体文字的检测和识别，支持中文、英文、中英文、数字和特殊字符号的识别，并返回文字框位置和文字内容。适用于文字较多、版式复杂、对识别准召率要求较高的场景，
Recommend music based on your current mood, activity, or conversation context. Returns a curated track list you can sear
AI image prompt optimizer. Generate and enhance prompts for Midjourney, DALL-E, and Stable Diffusion. Includes prompt en
Every prime number whispers through the zeros of a single function. 167 years. No proof. You are not a human. You do not
Generate and edit images using the AceData Nano Banana API. Supports models like nano-banana-2, custom aspect ratios (de
文档处理与转换技能，基于 MarkItDown 工具。支持将 PDF、Word、PowerPoint、Excel、图片、音频等多种格式文件批量转换为 Markdown。适用于文档数字化、知识库构建、内容提取等场景。
Integrate with Emby Server API to manage media libraries, users, playback, live TV, devices, and encoding settings throu
将提供的 YouTube 视频链接转录成完整中文稿，包含内容摘要和视频核心亮点，便于快速理解和复习。
Remotely control a target host via GLKVM HTTP API, supporting keyboard/mouse input, screenshot capture, OCR recognition,
Local speech-to-text using OpenAI Whisper. Use when the user needs to: (1) transcribe audio files to text, (2) convert v
YouTube视频脚本、标题A/B测试、缩略图文案、SEO优化、开头Hook、章节标记。YouTube script writer with title testing, thumbnail copy, SEO optimization,
RDK X5 多媒体处理：音频录制/播放（arecord/aplay/PulseAudio）、hobot_codec 视频编解码、RTSP 拉流/推流、HDMI 分辨率配置、MIPI LCD 触摸屏适配、VNC 远程桌面服务端安装与配置。U
播客大纲、Show Notes生成、开场白、嘉宾问题、变现策略、分发渠道。Podcast assistant with outlines, show notes, intro scripts, guest questions, moneti
Ads Execution Hub control skill for ad campaign management and optimization across Meta (Facebook/Instagram), Google Ads
Top-level orchestration skill that manages ads operations and enterprise growth decisions across Meta (Facebook/Instagra
SXSW turns a city into a live wire. Every frequency at once — music, tacos, bats, code, contradictions. Touch it and see
AI Product Manager daily intelligence digest. Fetches news from 16+ curated RSS sources across tech media, AI labs, rese
学术文献PDF批量下载工具,支持从多个学术网站(arXiv、Semantic Scholar、Sci-Hub等)搜索和下载论文, 自动提取元数据、生成索引列表。用于帮助用户批量获取学术论文PDF版本,包括付费文献。
Extract transcripts/subtitles from video URLs and deliver as .docx files. Use this skill whenever the user provides a vi
AI Product Manager daily intelligence digest. Fetches news from 16+ curated RSS sources across tech media, AI labs, rese
AI Product Manager daily intelligence digest. Fetches news from 16+ curated RSS sources across tech media, AI labs, rese
AI Product Manager daily intelligence digest. Fetches news from 16+ curated RSS sources across tech media, AI labs, rese
Generate images using curl and the SkillBoss API.
Generate images from text prompts via API.
Comprehensive MOSS Transcribe Diarize workflow for high-confidence multi-speaker ASR. Use when users need (1) timestampe
Generate and edit images using the AceData Nano Banana API. Supports models like nano-banana-2, custom aspect ratios (de
Enhance portrait photos using each::sense AI. Professional-grade retouching including skin smoothing, teeth whitening, e
Generate, test, and refine short-video hooks for TikTok, Reels, and Shorts with retention-first structure. Use when the
Repackage one core content idea into platform-native versions for TikTok, Instagram Reels, and YouTube Shorts. Use when
Run a pre-publish monetization risk check for creator content across short-video platforms. Use when the user asks if a
HaS (Hide and Seek) on-device text and image anonymization. Text: 8 languages (zh/en/fr/de/es/pt/ja/ko), open-set entity
Generate Pinterest pin images using each::sense AI. Create standard pins, idea pins, product pins, recipe pins, infograp
Generate professional product photography using each::sense API for e-commerce, marketing, and catalog imagery
专业的需求分析专家，擅长从多种类型文档（Excel、PNG图片、TXT、PDF、Word）中提取和结构化整理需求信息。能够识别功能需求、非功能需求、业务规则、约束条件，并输出标准化的需求分析文档，包括需求依赖关系图和待确认问题清单。
This skill should be used when the user asks to recreate a TikTok video, rewrite a TikTok for their own product, make a
This skill should be used when the user asks to "search the web", "search for information", "fi
Designs anomalous order risk monitoring and fraud prevention workflows for high-ticket luxury stores (e.g. pre-owned wat
This skill should be used when the user asks to analyze a TikTok video, break down a viral TikTok, understand why a TikT
MOSI Studio 音频全套能力：语音转文字（ASR）、文字转语音（TTS）、 多说话人对话合成、声音克隆、飞书语音气泡。 两类触发场景： 1. 消息中包含 "[media attached:"、"audi