Media Claude Skills
3 032 media skills from 496 authors. They create and process images, video and sound. Half of them fit into 1 962 tokens or less — that is what one costs your context window when the agent loads it. 771 ship runnable scripts rather than instructions alone. 30 of them cannot work without an MCP server, most often rube. We also found 347 copies of these same skills sitting in other people's repositories — counted once here, not 347 times.
3 032 unique 496 authors 13 updated this month 173 from vendors
日本語翻訳：このファイルは manim-video 用の日本語翻訳が必要です
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。
Remotion のベストプラクティス - React で動画を作成する。3D、アニメーション、音声、字幕、チャート、トランジションなどをカバーするドメイン固有の29のルール。
AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.
Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
通过 fal.ai MCP 实现统一的媒体生成——图像、视频和音频。涵盖文本到图像（Nano Banana）、文本/图像到视频（Seedance、Kling、Veo 3）、文本到语音（CSM-1B），以及视频到音频（ThinkSound）。当用户想要使用 AI 生成图像、视频或音频时使用。
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, source-derived voice modeling, and channel-specific outreach across email, LinkedIn, and X. Use when the user wants to find, qualify, and reach high-value contacts.
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ecc video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
Best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts, transitions, and more.
Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.
AI辅助的视频编辑工作流程，用于剪辑、构建和增强实拍素材。涵盖从原始拍摄到FFmpeg、Remotion、ElevenLabs、fal.ai，再到Descript或CapCut最终润色的完整流程。适用于用户想要编辑视频、剪辑素材、制作vlog或构建视频内容的情况。
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.
为 OpenClaw AI Agent 锻造完整的龙虾灵魂方案。根据用户偏好或随机抽卡， 输出身份定位、灵魂描述(SOUL.md)、角色化底线规则、名字和头像生图提示词。 如当前环境提供已审核的生图 skill，可自动生成统一风格头像图片。 当用户需要创建、设计或定制 OpenClaw 龙虾灵魂时使用。 不适用于：微调已有 SOUL.md、非 OpenClaw 平台的角色设计、纯工具型无性格 Agent。 触发词：龙虾灵魂、虾魂、OpenClaw 灵魂、养虾灵魂、龙虾角色、龙虾定位、 龙虾剧本杀角色、龙虾游戏角色、龙虾 NPC、龙虾性格、龙虾背景故事、 lobster soul、lobster character、抽卡、随机龙虾、龙虾 SOUL、gacha。
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Replicate models, LumaAI, Runway, and FFmpeg editing.
| 视频生成 - AI视频生成与后期剪辑制作 职责：调用Vidu生成视频、模型选择、Prompt调优、视频拼接、质量检测
AI 视频生成全流程：通过 6 个阶段（剧本→角色/场景设计→分镜→参考图→视频生成→后期剪辑）将用户想法转化为完整视频。支持临时工作台（单独调用 LLM、VLM、文生图、图生图、视频生成）。触发词：视频生成、AI视频、AIGC、创作视频、制作视频、AI画图。
Automatic architecture video editing workflow with self-learning preferences
长文/测评文章 → 知识视觉笔记套图（3-5张）。自动提炼核心逻辑、规划分镜、生成高阶图像Prompt（4模块结构）。支持手写笔记/思维导图/架构图/对比矩阵四种风格。Use when: 文章转知识笔记、知识笔记图片、思维导图、视觉笔记、长文转图、知识卡片、文章可视化、article to infographic、knowledge note。Output: 中文摘要 + 纯英文生图Prompt。Pair with vectronode-image/relay-image-gen to generate final images.
Audio-to-video synchronization workflow: analyze audio (beats, tempo, emotion, mood), find/match video clips to match scene and feeling, sync cuts to music beats, generate beat-marked videos. Use when user wants to: (1) turn a song into a music video, (2) sync video clips to music beats, (3) create a video that matches audio mood/scene/rhythm, (4) do beat-matching video editing. Triggers: \"制作音乐视频\", \"音频转视频\", \"beat matching\", \"卡点视频\", \"音视频同步\", \"视频踩点\", \"music video creation\", \"sync video to audio\
Generates Xiaohongshu (Little Red Book) infographic series with 10 visual styles and 8 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
Build a complete brand identity for a solopreneur business from scratch or refresh an existing one. Covers brand personality, voice and tone, visual identity system (colors, typography, logo direction, imagery style), tagline crafting, and a brand guidelines document. Use when creating a new brand, rebranding, or needing to make brand decisions consistent. Trigger on "create my brand", "brand identity", "brand guidelines", "define my brand voice", "brand personality", "what should my brand look like", "brand strategy", "rebrand", "brand tone".
Enforce brand tone and style consistency across all content creation skills. Load brand profiles from workspace/brand/profiles/, apply tone rules (preferred and forbidden expressions), and validate written content against the selected voice. Use when the user mentions brand voice, tone consistency, style guide compliance, or needs to switch writing profiles via --voice.
AI视频生成质量增强引擎。解决AI视频角色僵硬、表情空白、动作机械的问题。通过高级prompt工程+角色卡+运镜指令+表情库，让AI视频角色活起来。触发词：视频质量、角色僵硬、灵动、表情、动作、cinematic video、视频生成增强、MV视频、角色动画
> 最强免费生图方案：用前端代码(HTML/CSS/JS/Canvas/SVG)设计画面，通过 Playwright 渲染为任意分辨率高清 PNG。 零API成本、无限分辨率、中文100%准确、代码可复用、Git可追踪。 配合 frontend-design / canvas-design / frontend-design-ultimate 产出 HTML 设计稿后调用。
> 文章配图决策 skill：根据文章内容判断该配什么图、图从哪里来、什么时候该用 Telegram 真实对话截图，什么时候该用工具界面图、官网图、生成插图或流程图。 适用于公众号、小红书长图文、知识星球、掘金、博客等内容配图。触发词包括：'配图'、'插图'、'素材图'、'这篇文章该配什么图'、'截图进素材库'、'给这篇稿子补图'、'根据内容选图'。
Turn one piece of content into 10+ formats. Transform blog posts, podcasts, videos, or talks into tweets, LinkedIn posts, newsletters, carousels, and more.
Use for concise Chinese X/Twitter posts in Daniel's first-person voice, mixing human tension, numerical evidence, explicit decision rules, and a sharp reflective ending.
Digital human video generation via Qingyun API — avatar-based talking head videos
获取抖音热榜/热搜榜数据，包含热门视频、挑战赛、音乐等多领域热门内容，并输出标题、热度值、跳转链接及封面图（如有）。
抖音图文/视频发布（OpenClaw Browser 自动化）：登录检测→内容校验→上传页导航→填标题/正文→上传封面+素材→暂存离开。
抖音创作者平台智能发布（视频/图文）：内容适配→上传→填描述/#话题→封面→存草稿→截图回传确认。默认只存草稿；只有在 Daniel 明确确认后才允许点击发布。覆盖标题(≤55字)、描述(建议≤200字)、#话题标签(3-5个)、封面设置、定时发布、可见性、合拍/下载开关。Playwright 自动化。触发：'发抖音'、'抖音发布'、'douyin publish'、'抖音图文'、'抖音视频'、'发布短视频'。
抖音账号视频批量采集与文案分析工作流。当用户提供抖音账号主页链接、要求抓取最新 N 条视频链接、提取视频文案（语音转文字）、或对视频内容进行总结归纳时，激活此 skill。依赖 browser 工具（抓取视频列表）和 mcporter + douyin-mcp（文案提取）。
Generate FFmpeg commands from natural language video editing requests - cut, trim, convert, compress, change aspect ratio, extract audio, and more.
Create AI digital human videos with HeyGen API. Free starter guide.
Scrape and download all images from a given URL. Takes a URL, extracts image URLs from the page, and downloads them. Uses python3/curl as primary method, falls back to browser automation if needed. Use when user provides a URL and wants to download images from that page.
Image analysis using multimodal vision models. Use when user needs to: (1) Describe what's in an image, (2) Extract text from images (OCR), (3) Analyze visual content, (4) Compare images, (5) Answer questions about images. Supports JPG, PNG, GIF, WebP formats.
即梦AI数字人视频生成全流程自动化。通过浏览器自动化操控 jimeng.jianying.com 数字人界面，完成角色上传、音色选择、台词填入、视频生成和下载。触发场景：用户需要生成数字人视频、即梦数字人、AI数字人口播视频、数字人视频制作。依赖 jimeng-login skill 处理登录。
将口播视频剧本拆解为即梦AI数字人平台的分镜头脚本。输出格式为每个镜头的角色说（台词）和动作描述（镜头语言/数字人动作），适配即梦 jimeng.jianying.com 数字人视频生成界面。触发场景：用户需要生成口播视频分镜、数字人视频剧本拆解、即梦分镜脚本、短视频口播脚本分镜、数字人台词加动作拆分。
> 看相分析技能。通过用户上传的人体部位图片，识别图片类型（面相/手相/体相/骨相），调用相应的相术规则知识库，结合图片内容进行专业分析。支持面相（五官、三庭、十二宫）、手相（掌线、指形、掌丘）、骨相（头骨、体骨、九骨）、体相（体型、体态、气质）的综合分析。基于《麻衣神相》《柳庄相法》《神相全编》《水镜神相》《冰鉴》等经典相书整理。
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, source-derived voice modeling, and channel-specific outreach across email, LinkedIn, and X. Use when the user wants to find, qualify, and reach high-value contacts.
MediaClaw内容生产的核心配图skill。当有长篇文章需要转化为可传播的视觉笔记时调用。 长文知识提取转图Skill。将深度长文降维提取核心逻辑，生成3-5张高真实感、含密集中文文字信息的视觉笔记图。 使用qingyun-api的gemini-3-pro-image模型生成。 (3) 独立的长文转图任务 (4) Claude vs Codex等测评文章配套素材。
歌词-视频精准匹配引擎。将MP3中的歌词片段按时间轴精准匹配到对应视频clip，支持歌词提取、时间轴对齐、情绪映射、字幕烧录、音频分段混合。触发词：歌词匹配、lyrics sync、歌词卡点、音频对齐、字幕视频、lyrics video、歌词视频、音乐视频字幕
Text-to-speech synthesis via MiniMax WebSocket API
多模态内容生成（图片、视频）。当用户需要生成图片、生成图像、生成视频、AI绘画、AI作图、画一张图、做个视频、文生图、文生视频时使用此技能。自动调用 multimodal-agent 进行生成。
MediaClaw 内置的音乐视频端到端生成技能。 End-to-end MV (music video) generation pipeline for virtual singers. Audio analysis → Scene timeline → Frame generation → Video generation → Final merge.
MV production standard — end-to-end music video creation workflow
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.