Каталог навыков агентов

Takes an existing screen recording or demo video and adds professional zoom/pan effects synchronized to the narration. U...

Review and build video portfolio websites with mixed landscape and portrait media, strong visual direction, responsive i...

Post-process videos with FFmpeg for final output

Generate interactive HTML presentations for ANY video type (tutorials, comparisons, fact-checks, explainers, etc.). Crea...

Use when processing YouTube videos, extracting subtitles, parsing VTT files, analyzing video content, generating timesta...

Guide for video analysis and frame-level event detection tasks using OpenCV and similar libraries. This skill should be...

This skill provides guidance for video analysis and processing tasks using computer vision techniques. It should be used...

Download, transcribe, analyze, and clip video content — vertical shorts, captions, thumbnails

Trim, transcode, extract frames, add subtitles, and manipulate audio in video files using FFmpeg.

FFmpeg automation for cutting, trimming, concatenating videos. Audio mixing, timeline editing, transitions, effects. Exp...

Process video files for YouTube content creation and generate social media graphics - transcribe videos/clips into times...

Process videos by removing segments and concatenating remaining parts. Use when you need to remove detected pauses/openi...

Full YouTube video production pipeline using agent teams. Coordinates visual design, GIF search, and timeline building w...

End-to-end Remotion video production from natural language briefs. Orchestrates narrative structure, scene animation, vi...

Video Producer. Use for Phase 15 OpenMontage productions and Phase 19 video ads. Real titles: Video Producer, Motion Des...

Use this skill when creating, editing, or optimizing video content for YouTube and other platforms. Triggers on script w...

Use this skills whenever you are dealing with Remotion code to obtain the domain-specific knowledge.

Video downloading, stitching, title slides, and YouTube descriptions. Use this skill when downloading videos from Google...

Activate for video marketing strategy, script writing, video specifications for YouTube/TikTok/Instagram Reels/LinkedIn,...

Point d'entrée unique de toute demande vidéo pour {{COMPANY_NAME}} (Reel, Short, vidéo LinkedIn, explainer, vidéo produi...

Dựng video nhiều cảnh có kỷ luật cho SEOSONA — VO-first (đo giọng trước làm nhịp), style-anchor frame (1 keyframe neo pa...

Turn a video brief into a CapCut-ready production script by asking up to 8 high-signal clarification questions (one at a...

- taiyou-taiyo/content/creative/video/production-guide.md

Professional video production from planning to delivery. Use when creating video content, editing workflows, motion grap...

Generates video production plans including shot lists, scripts, B-roll suggestions, music mood, thumbnail concepts, and...

Video script writing and production methodology for MYCURE using Apple Keynote presentation principles and two-column AV...

Full video production sequence with script review, actual ingredient choices, controlled generation, editing, evidence-b...

Keep an AI video project, or any agent-built project, in a private GitHub repo, even when the person has never used git....

Write prompts for 20+ frontier AI video generators (Veo 3.1 + audio, Sora 2 + cameos, Kling 3.0, Runway Gen-4 / Aleph /...

Craft effective prompts for VEO single-clip video generation - READ before any generate_video_clip call

帮助用户编写专业级 AI 视频提示词，写完直接生成 MP4 视频。支持多种创作场景与问题诊断，确保提示词准确可执行。触发词：视频提示词、视频生成提示词、AI视频创作、写视频提示词、导演指令、文生视频提示词、视频脚本、生成视频

Use for diagnosis and revised prompt after a known defective result from approved user facts and assets; unlike $generat...

Viết prompt VIDEO có kỷ luật cho SEOSONA Flow lái Veo (và Sora/Kling) — cấu trúc 7 phần cố định: Subject·Action·Shot·Cam...

AI video/image prompt engineering expert. Triggered when users need to write or optimize prompts for AI video or image g...

Build video prototypes with AI simulation, image/video generation, scene planning, character chat, TTS, and speech-to-te...

Build a video understanding pipeline with scene segmentation, multi-vector indexing, temporal grounding, and timestamped...

Inspects a rendered video and reports problems with evidence, severity and a fix owner. Use after every render and after...

Analyzes video files using Google Gemini API and answers questions about content. Triggers on keywords: video query, ana...

Analyze a video file (mov, mp4, webm, etc.) or a YouTube video by extracting still frames with ffmpeg and reading them c...

Generate a Chinese-narration recap video from an input video, end to end. Use when the user gives a video file (.mp4 / ....

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...

Recreate or remix one supplied reference video with replacement characters, products, branding, props, or scenes. Use wh...

Comprehensive skill for programmatic video generation using the Remotion framework. Enables creating, scaffolding, and r...

Remove backgrounds from videos — video background removal API for transparent videos, alpha-channel clips, and green-scr...

Render videos using Remotion React-based video framework

Render an ace-web connect-videos program or a DDD connect-ddd-walkthrough to MP4 locally on a Mac, much faster than ace-...

Operate provider-neutral Hermes video work for Aries.

Execute provider-neutral Aries video render briefs through Hermes.

Generate a report about a video

Generate a report about a video

Generate a report about a video

Transforme une vidéo longue de {{COMPANY_NAME}} (webinar, podcast filmé, interview, live, conférence) en clips sociaux....

Take a published YouTube video URL, extract clips per the social calendar's Clip Release Schedule, write platform-native...

Research topics and gather content for video production

Analyze YouTube videos to generate viral video ideas and scripts. Use when given YouTube URLs to research, when asked to...

Find a model-specific video or motion skill and produce a decision workflow. Use for Claude Code, Opus 5.5, GPT-6 Astra,...

Write compelling video scripts with voiceover and visual directions

Generate formatted video scripts from transcripts, outlines, or topics with visual and audio columns

Create engaging video scripts for YouTube, TikTok, Instagram Reels, and podcasts

Draft a scene-by-scene video script with timing, visual direction, narration, and source attribution from upstream creat...

Write compelling video scripts — YouTube tutorials, explainers, ads, and documentary-style narratives with B-roll notes.

Write video scripts. Use when: creating YouTube, TikTok, Reels, LinkedIn, demo, or explainer video content.

Write creator video scripts for short-form, long-form, sponsored, educational, story, and product content. Use when Code...

Write a complete video script with hooks, B-roll notes, and CTAs. Use when Rick says write a script, create a video, or...

Video script yazma tarifi — platformlara özel, teleprompter'a hazır senaryo sistemi

Write the script for any video before anything is generated: what is said, shown and heard in every beat, sized to the c...

Write a timestamped Chinese narration script (解说词 / 旁白) for an already-analyzed video, then lint/validate it. Use after...

对已完成分析的视频进行导演与剪辑策划，再写带时间戳的中文解说并校验；也处理已有短片的 宣发标题、花字修订和外部文案回填。普通策划输入 work_dir 的 agent_narration_brief.md 与 vlm_analysis.js...

Write engaging video scripts for YouTube, TikTok, and other platforms. Creates complete scripts with hooks, main content...

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 or repair a guided or free-scroll video-scrub website deck with scrub-ready media, approved pause points, transiti...

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

Zoom Video SDK for Web - JavaScript/TypeScript integration for browser-based video sessions, real-time communication, sc...

Zoom Video SDK for Windows - C++ integration for video sessions, raw audio/video capture, screen sharing, recording, and...

Extract playable short video evidence clips around event times. Use when Codex has event_id, camera_id, raw_segment_uri,...

Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops. Defaults to Se...

Pro-camera HUD mockup template — full-viewport black canvas wrapping a real video with monospace overlays (corner bracke...

Create short clips from a YouTube URL or local long-form video with subtitles in one or more requested languages. Use wh...

Create cinematic product videos from shot recipe cards, a validated template, and code/audio assets (Remotion + real pag...

用镜头配方卡 + 已验收模板 + 代码/音频资产制作电影感产品视频（Remotion + 真实页面截图 + 2.5D 运镜 + 节奏卡点 + 声音设计）。当用户要求"用 video-shotcraft 做视频/宣传片"、点名 Ink Pre...

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...

Finds the right agent skill for an AI video, image, voice or music job on varg how to (varg.ai/how-to, 2,000+ checked sk...

Makes the sound of any video: ElevenLabs voiceover (one file per line, static levelling, a transcript gate that must hea...

Make the sound of any video so it feels real: AI voices that don't sound fake (cast from candidates a person picks, dire...

Use this skill for fast, traceable internet-source verification of claims from videos/articles (especially YouTube claim...

LLM-as-judge eval of the spec.yaml produced by /ace:video-spec-generate (or /ace:video-from-program-page, or hand-author...

Template-agnostic generator for ace-web video programs. Ingests a template's structured data (meta + intent + skeleton +...

Structural QA on the spec.yaml produced by /ace:video-from-program-page (or hand-authored) for an ace-web video program....

Use when a task involves turning a video brief into a shot-by-shot storyboard and timing plan before production to ident...

Create coherent video story sequences with AI-generated images and narrated audio. Combines image-generation and elevenl...

Ingest video monitoring sources and return raw segment/session metadata. Use when Codex needs to connect or normalize RT...

Video streaming expertise from Netflix - the world's largest streaming service. Master video encoding, adaptive bitrate...

Use when the user asks to create or edit videos end-to-end (script→video, auto-cut/jumpcut, captions/subtitles, polishin...

Starts and orchestrates any video - ads, launch and demo films, motion, title, end and CTA cards, UI walkthroughs, expla...

用 Kimi 拉片提取参考片的叙事、镜头、节奏和视觉语法，再适配到用户自己的内容与资产。