Skill rating

Comprehensive CLI for Google NotebookLM including notebooks, sources, audio podcasts, reports, quizzes, flashcards, mind maps, slides, infographics, videos, and data tables. Use when working with Note

AI生视频工具（首尾帧/单图模式），根据原图和提示词生成视频，支持可选尾帧图控制结束画面。支持模型KLING可灵/WAN万相/SEED豆包/SEED_FAST/HAILUO海螺。用户说"生成视频"、"AI视频"、"图生视频"、"做个视频"、"video generation"、"generate video"、"图片转视频"、"动态视频"时触发。

Searches multiple online archives to find and recover deleted YouTube videos, metadata, and comments using a video ID.

播客生成器 — 根据用户描述，通过搜索引擎抓取最新资讯，生成口语化播客脚本，根据脚本语义自动匹配最合适的讯飞TTS声音，合成时长3分钟内的MP3音频并发送。触发词：生成播客、播客、podcast、帮我做一段音频、做一期节目。

Generate AI-powered notes from videos (document, outline, or graphic-text formats)

Using a fixed camera at home or in the office, the system analyzes daily videos of an individual (e.g., adult, adolescent) and detects anxiety-related behaviors: hand rubbing (repeated rubbing of both

B站视频发布。使用浏览器自动化在B站创作者平台发布视频。当用户说"发布视频到B站"、"发B站"、"投稿B站"时使用此技能。注意：B站审核转码较慢，建议最后发布。

Video analysis: object detection, scene classification, activity recognition, and summarization.

统一知识库入口技能（#kb）。当用户发送内容并标记 #kb 时触发。 自动完成：素材下载 → IMA 知识库存储 → workspace/kb 归档 → memory 记录。 支持：微信公众号文章、网页链接、YouTube 视频（字幕提取）、纯文本、文件路径。

抖音爆款标题生成器 | 自动生成吸引眼球的抖音视频标题，提高视频播放量和互动率。Generate viral Douyin titles to increase video views and engagement.

For transcript or subtitle requests involving podcast URLs, public audio URLs/files, or raw transcript cleanup. Generates audio + SRT + TXT artifacts and can optionally clean transcripts with episode-

Weave multiple maps, text and charts into a scroll-driven storytelling HTML page

使用 video_generate.py 脚本生成视频，需要提供文件名和 prompt，可选提供首帧图片（URL或本地路径）。

Search TikTok videos, collect creator videos, retrieve detail data and comments for one known video, and run product, trend, competitor, and content insights through Gecho Bridge MCP. Requires the Gec

Social Video Analytics is an AI analytics assistant for measuring how videos perform across social platforms and why some clips win. It helps teams read watch time, drop-off, hook strength, caption im

AI大模型专家｜TVC 广告片。帮助品牌市场、广告代理、创意策划、制片人与投放团队直接完成“TVC 广告片”：既可只输入文字从零生成，也可加入图片、视频或音频控制结果；通过 AI Hive 使用时，生成前自动上传所需素材，提交后自动保存任务、查询进度并下载成片。适用于 AI 广告、TVC、电商视频、产品展示、带货、种草、短剧、漫剧和社媒内容。 Use this skill for TVC 广告片,

Content repurposer — turn one blog post, video, or podcast into social posts, email newsletters, and threads. On-demand.

Render podcast episodes as 1080p art-slideshow MP4s and publish them to a YouTube Podcasts playlist: covers/thumbnails generated from your art, resumable batch upload, playlist ordering, retiring old

Transform YouTube videos into Telegraph Instant View articles with visual slides and timestamped summaries. Use this skill whenever a user shares a YouTube URL (youtube.com or youtu.be) and asks to su

A modern text-based browser. Renders web pages in the terminal using headless Firefox.

Turn user-provided text into a playable MP3 with AudioFlow TTS. Use when the user asks to read text aloud, speak or narrate a passage, or create playable speech from text. Skip account onboarding when

Upload videos to Bilibili (哔哩哔哩). Supports automatic login, title, description, tags, and partition selection.

AI大模型专家｜Seedream 5.0 Lite 图片生成与编辑。帮助设计师、电商运营、营销与广告团队、品牌方和内容创作者直接完成“Seedream 5.0 Lite 图片生成与编辑”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社

AI content brief, script, and outline generator for video, image, and audio production. Works as an AI research assistant that provides expert guidance on workflow design, model selection, parameter o

多场景分镜文生图制作助手。使用 BizyAir API 生成故事绘本分镜场景图，支持自动追加模特提示词、自定义图片比例和批量生成。当用户需要生成分镜图、故事场景图、绘本插图或提到"分镜"、"场景图"、"绘本"时必须使用此技能。

AI大模型专家｜Amazon 亚马逊 电商图片生成与编辑。帮助电商运营、商品摄影、品牌商品团队和直播带货团队直接完成“Amazon 亚马逊 电商图片生成与编辑”：既可从文字生成，也可加入参考图帮助控制主体、构图和视觉风格；通过 AI Hive 使用时，生成前自动上传参考图，提交后自动保存任务、查询进度并下载图片。适用于电商主图、商品详情页、广告 KV、海报、带货、种草、社媒配图、产品精修、换背景与

用户输入选题或工作流，自动生成完整短视频成片（文案、分镜、数字人口播与 AI 画面混剪）；调用 Chanjing Open API 与同仓库子技能脚本。

Create pinches (posts) on PinchBook — the social network for AI agents. Includes a persona system for developing emergent identity through social interaction.

A skill for interacting with the paip.ai social platform.

Edit PDFs with natural-language instructions using the nano-pdf CLI.

Generate, schedule, and publish posts to X and LinkedIn in your voice using AI. Browse viral content, manage preferences, and track billing.

免费文生图/文生视频：直连 Agnes、商汤 SenseNova、硅基流动 Kolors 等第三方免费模型，绕过混元 ImageGen、出图无水印。触发：打开免费生媒体 / 免费生图 / 免费生视频。 Free text-to-image & text-to-video: directly calls free third-party models (Agnes, SenseNova, Silic

Captures learnings, errors, and corrections to enable continuous improvement. And also 50+ models for image generation, video generation, text-to-speech, speech-to-text, music, chat, web search, docum

Pull a Facebook page's profile, posts, reels and photos, one post with its comments, a single reel/video with downloadable URLs, a public group and its posts, an event, and hashtag posts. 11 endpoints

将一个或多个本地视频转写为带每段开始和结束时间的整理版 TXT。当用户要求视频转文字、视频转写、提取视频文本或字幕、批量生成带时间戳 TXT、整理视频口述内容、统计视频处理耗时时使用。通过 uv、ffmpeg/ffprobe 和 openai-whisper 处理；中间文件写入系统临时目录并自动清理，永不删除源视频。

查询TikTok商品的关联带货视频数据，包括播放量、点赞、评论、分享、视频销量与GMV，分析商品的视频营销表现与达人内容效果。当用户提到TikTok商品视频、TikTok带货视频、商品关联视频、视频营销分析、达人视频表现、TikTok视频销量、TikTok video sales, product video analysis, influencer video performance, TikT

Meegle OpenAPI for work item attachment operations.

Forensic media triage with chain of custody. Use when receiving images, videos, audio, PDFs, or documents that need evidence-grade handling, integrity verification, and audit trails.

Webcam surveillance with AI analysis. Two modes: (1) One-shot analysis - answer specific questions about your space, (2) BOLO watch mode - continuous monitoring with motion detection and custom watchl

AI-powered YouTube video scoring. Scores videos 1-10 based on your learning goals and persona. Use when the user wants to evaluate YouTube videos, check their scored feed, manage tracked channels, or

Use when performing video/audio processing tasks including transcoding, filtering, streaming, metadata manipulation, or complex filtergraph operations with FFmpeg.

Using volcengine video_generate.py script to generate video, need to provide filename and prompt, optional provide first frame image (URL or local path).

Quick upload audio to AIOZ Stream API. Create audio objects with default or custom encoding configurations, upload the file, complete the upload, then return the audio link to the user.

Download YouTube videos in various formats and qualities. Use when you need to save videos for offline viewing, extract audio, download playlists, or get specific video formats.

Generate a narrated Remotion video from an Excalidraw (.excalidraw) diagram using text-to-speech (macOS say) and render to MP4. Use when creating explainer videos with pan/zoom + focus highlights over

Default video conferences via Meetling. Instant calls always use /m/ rooms + share payload for Claw default sending. Scheduled calls return link + email invite template. Secure contacts loading (no en

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing,

YouTube Search API via AIsa unified endpoint. Search YouTube videos, channels, and playlists with a single AIsa API key — no Google API key or OAuth required. Use this skill when users want to search

Use Renderful from OpenClaw for image/video/audio/3D creation with model discovery, quote-before-generate workflow, deterministic polling, and insufficient-funds/x402 fallback.

High-performance containerized web scraper (Docker + Crawlee + Playwright). Use when user mentions any of these: 爬虫, 爬取, 抓取, 采集, 数据采集, 爬数据, 抓数据, 获取数据, scrape, crawl, extract, fetch data, pull data, 亚马