Навыков: 28 269. Сортировка по числу звёзд.
Process videos using ffmpeg and gifsicle to edit videos. Use when working with .mp4, .avi, or .gif files, or sequences o...
Use when reviewing a local video visually with systematic timestamped frame sampling, contact sheets, selected full-dime...
Extract frames or short clips from videos using ffmpeg. Use when capturing screenshots from video, creating frame grids,...
使用 ffmpeg 从视频中提取帧或短片段。
Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference...
Hyperframes / Remotion 兼容的连续帧动画, 可自动播放
Turn a video or audio recording — a local file OR a URL (YouTube, TikTok, Instagram, ...) — into vault knowledge using t...
Merge multiple video files or all videos in a directory into a single output file using ffmpeg. Use when user wants to c...
This skill provides guidance for video analysis and processing tasks using computer vision techniques. It should be used...
Keep an AI video project, or any agent-built project, in a private GitHub repo, even when the person has never used git....
Craft effective prompts for VEO single-clip video generation - READ before any generate_video_clip call
从输入视频生成中文解说成片或原声剧情短片。用户提供 .mp4 / .mov / .mkv / .webm，并要求剪辑、添加旁白、 配音、总结、短剧/电视剧/电影/纪录片/科普解说时使用。负责编排 video-* 技能链：视频理解 → Age...
完整的视频二创工具，支持视频反推、素材生成(图片/音效/背景音乐/配音/字幕)、视频合成、文件下载的全流程，集成Coze Bot API进行视觉分析，使用Edge-TTS进行语音合成
识别视频中的敏感对话（涉黄/涉毒/暴力/色情/脏话/骂人/合规违禁词）并打哔消音；如画面有硬字幕且含敏感词，则擦除后重压干净字幕，输出可过审发布的成片。仅处理"音频敏感词打哔 + 硬字幕敏感词擦除并重压"两条主线。不处理画面人脸/车牌/lo...
Make short kinetic-type video reels (30 s to 3 min hype, explainer, pitch or event videos) from an HTML canvas project:...
按需把一部成片拆成可复用的制作参考：测镜头节奏与响度，标注段落与音轨分工，把原片事实与可迁移方法分开， 导出不含原片人名台词的 production_reference.json 供下次制作参考。不在默认生产路径上。 触发词：拆片、拆解成片...
Transforme une vidéo longue de {{COMPANY_NAME}} (webinar, podcast filmé, interview, live, conférence) en clips sociaux....
把一条视频重建成「只有画面和声音」的干净文件——**源片的元数据一概不搬**： GPS、设备型号、账号 ID、创建时间、章节、GoPro 的遥测轨，全部留在原地。 走的是白名单而不是黑名单：不列要删什么，只说带什么过去（画面一条流、声音一条...
Build and debug browser-based Zoom Video SDK for Web integrations using @zoom/videosdk. Use for custom video sessions, j...
Zoom Video SDK for Linux - C++ headless bots, raw audio/video capture/injection, Qt/GTK integration, Docker support
拉片：把一条成片拆成逐镜头的分析表——每个镜头的时长、景别、类别、运镜、画面。 分工刻在骨子里：**能量的都由代码量**（切点来自 ffmpeg 场景检测，时长是切点相减， 运动量是逐帧差分的中位数），模型只判断它真正该判断的那几件事（景别...
Makes the sound of any video: ElevenLabs voiceover (one file per line, static levelling, a transcript gate that must hea...
Ingest video monitoring sources and return raw segment/session metadata. Use when Codex needs to connect or normalize RT...
把拉片数据和原片合成一条**能直接看的视频**：一边是画面，一边是这一镜的分镜信息 （镜号、起止、时长、景别、类别、运镜、画面描述、台词），**镜头切了信息跟着切**， 镜头表自动滚动并高亮当前这一镜。 版式只看原片的宽高比：**横版 /...
Generate sound effects matched to a video using Sonilo — footsteps, impacts, ambience, foley — optionally scripted to sp...
Use when turning a long video (interview, podcast, talk, lecture, webinar) into short vertical clips for YouTube Shorts...
Generate music AND sound effects for a video in a single balanced, single-charge call using Sonilo. Use instead of calli...
Turn a video walkthrough, review, demo or bug report into Linear tickets backed by timestamped screenshots pulled from t...
Turn software or creative-workflow videos into evidence-grounded tutorials. Default visual mode uses local images and a...
Check the local toolchain required by the kit's video and animation skills before starting a render - Node.js, ffmpeg, P...
Batch Whisper transcription of video or audio (WAV, podcasts) with a re-runnable provenance record. Use to transcribe re...
Extract video transcripts: yt-dlp subtitles to clean paragraphs.
yt-dlp downloads: video, audio, subtitles, transcripts, clips, playlists.
Understand video content locally using ffmpeg frame extraction and Whisper transcription. No API keys needed. Use when:...
把带时间戳的 narration.json 合成为中文解说音频。使用 MiMo TTS（mimo-v2.5-tts）或 Fish Audio（s2.1-pro-free）或显式配置的通用 IndexTTS HTTP 服务逐段生成语音， 按时...
Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video...
Use viem for Celo development. Includes fee currency support, transaction signing, and Celo-specific configurations.
Reads blockchain data, sends transactions and calls smart contracts from TypeScript with Viem, the type-safe Ethereum li...
Viem with Celo chain configuration. Use when working with Celo blockchain interactions, public client setup, contract re...
Generates initial view components with mandatory unit tests. Creates HomeView.vue, PageNotFoundView.vue, and their .spec...
View a binary PCD pointcloud file with per-vertex RGB colors in a 3D matplotlib plot. Use when the user has a .pcd file...
Creates smooth animated transitions between views using the native View Transitions API. Use when building page transiti...
Implémente l'API View Transitions pour des transitions fluides entre pages et états. MANDATORY pour toutes navigations....
Specialist in ViewComponent implementation, component architecture, slots, previews, and method exposure patterns. Invok...
Investigate and optimize Blunder editor viewport performance: Skia present, CPU readback, zero-copy path, partial repain...
macOS-native self-supervising watchdog that monitors a project autonomously in the background. Launch it once and it kee...
Use when the user runs /vilya [start|ready|status|stop|log], or asks in plain words to "start the dev server", "serve th...