Media AI Skills

Use when directing FLUX 3 audio, dialogue, or voiceover. Covers ambience, effects, music, silence, and timing.

Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM incrementally builds and maintains interlinked markdown pages from raw sources.…

去除AI味道，让文字读起来像人写的。触发词：去AI味、AI味太重、帮我改改、润色一下、写得像人、humanize、重写一下、帮我润色

Fetch a YouTube transcript and generate an executive summary, key points, and timestamped topic list as a polished HTML report. Activate on YouTube URLs or requests like "summarize this video",…

把一段 15–60 秒的中文口播做成某种画风的动画视频（1920×1080、30 帧/秒的 mp4，带口播和字幕，能直接拖进剪映）。画面全部由 Claude 用 HTML/Canvas 代码画、无头 Chrome 逐帧截图合成，不用生图模型。自带 7…

Play a local audio file through the system's default speakers using Sonilo's MCP server. Use after generating a track with Sonilo (or for any local WAV/MP3/M4A/AAC/OGG/FLAC file) when the user wants…

This skill should be used when the user wants a "blob store" or "object storage", names "S3" or an S3-compatible store, needs to "store images / video / files", asks about "multipart upload" or…

Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you…

ffmpeg 自动拼接成片：一条命令把 storyboard.json（商品图/视频片段 + 口播稿）渲染成带配音、字幕花字、转场、BGM 自动闪避、响度标准化的 9:16 MP4，纯本地运行。Use when the user wants to assemble/edit/render a product video, 自动剪辑, 一键成片, 拼接视频, 图片转视频, Ken Burns,…

竖屏视频字幕位置与参数配置 skill。适用于 9:16 或其他竖屏视频的字幕烧录、ASS 样式调整、安全区控制、替换或压住原视频自带字幕，以及“字幕别挡脸/别压底部按钮/盖住原字幕/字体太小/字幕超宽/字幕变成三行”这类字幕排版请求。当前版本只优化字幕参数，不处理遮罩、底板、背景条或毛玻璃效果。只要用户提到竖屏字幕位置、字号、边距、换行、盖住原字幕，都应优先使用这个 skill。

把用户的一句话想法/选题/素材，写成能直接开口录的自媒体口播逐字稿（含3个开头候选、标题封面、录制提示、自检），并把纯口播文案（.txt）和执行方案（.md）分别保存到本地项目文件夹作为交付结果。适用抖音、视频号、快手、小红书视频、B站、YouTube/Shorts…

Generate cinematic motion graphics videos using ByteDance Seedance 2.0 via Fal AI. Covers image-to-video, reference-to-video, text-to-video, liquid glass prompting, App Store screenshot scraping, and…

Generate high-CTR YouTube thumbnails for a mascot-driven channel using parallel gpt-image-2 jobs via the Codex CLI. Use whenever the user asks for a thumbnail, cover, or thumbnail alternatives for a…

Local Vercel AI SDK documentation reference (latest). Use for AI chat interfaces, text generation, structured output, tool calling, agents, MCP, streaming, embeddings, and multi-provider support.

Render music videos from audio files and lyrics using Remotion. Accepts audio + LRC/JSON lyrics + title to produce MP4 videos with waveform visualization and synced lyrics display. Use when users…

中文网文人物设定。当用户要设计主角、反派、配角、CP，做人设卡、人物小传、角色弧光、人物关系网，或人物"立不住/脸谱化/前后不一"时使用。产出有记忆点、有成长弧、服务爽感的人设卡。

一句话生成一条完整的口播视频：写稿 → 生成口播数字人（即梦 CLI / Seedance 2.5，本人照片 + 本人声音）→ 做 B-roll（截图、本人素材、代码动画）→ HyperFrames 合成 → 分段渲染 → 抽帧检查 → 按平台出版本。用户说“帮我做一条口播视频”“一句话出片”“按我的风格做期教程视频”“把这期做成成片”时使用。

Use when the user wants to turn a static scene, character images, aerial map, drawn path, or route-control image into an immersive first-person FPV AI video prompt, especially…

The Klik production method — takes a user from prompt to COMPLETE animated video (motion graphics + typography) in Remotion. Runs a fixed discovery questioning sequence into a single source of truth,…

Generates images with Codex (OpenAI's coding agent and its built-in image tool, included in a ChatGPT plan) - YouTube thumbnails, covers, B-roll stills, board images, profile pictures - one Codex job…

Turn anything hard to picture into a 3D world people can watch or play with - an operation or system (airport, data center, port, factory, hospital), an event spreading over real land (wildfire,…

Strict guidelines for the Milimo Video React 18/TypeScript frontend, specifically regarding the 7-slice Zustand God Store architecture, the SSE listener loops, and the "Magnetic V1" CSS-based timeline…

This skill should be used when the user needs to transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration.

AI 视频工厂，用于完整测试和执行 LaborAny 的多模态视频生产链路。 适用于： (1) 用户给一个爆款视频，要求拆解脚本、分镜、动作、配乐、镜头语言并复刻或改写； (2) 用户给一个想法，要求规划完整短视频、生成角色一致的关键帧图片、调用视频生成模型生成分段视频； (3) 用户要求把多个 15s 视频片段剪辑合成为最终成片； (4)…

Use when creating or editing Remotion videos, programmatic explainers, motion graphics, MP4 renders, GIF renders, social cutdowns, or React-authored video templates.

Extract and parse content from URLs. Triggers on: user provides a URL to extract content from, another skill needs to parse source material, "parse this URL", "extract content", "解析链接", "提取内容".

Diretor de edição de vídeo curto (Reels, TikTok, Shorts, YouTube, LinkedIn) — edita os takes que você gravou (corte por palavra, jump cut, rosto + tela, textos e imagens aparecendo em cima de quem…

Zoom Contact Center SDK for Android. Use for native Android chat/video/ZVA/scheduled callback integrations, campaign mode, service lifecycle, and rejoin handling.

Compares two podcasts or YouTube shows side by side: size, latest episode, what each talks about, what both cover, and shared sponsors. Uses arcmira.

Photoshop layer checks for commercial 2D motion deliverables.

白板火柴人拆书短视频工作流。用于把一本书或一段长内容做成 60-90 秒竖屏(9:16)白板手绘信息图风格的拆书口播短视频，并用 HyperFrames 在本地渲染无平台水印的最终成片。覆盖：拆书脚本与分镜表生成、白板火柴人信息图分镜图生成、口播配音生成(可选男声/女声)、背景音乐生成(可选活泼/沉稳/其他风格)、每个阶段与用户确认、HyperFrames…

将中文剧本同时加工为影视分镜、人物情绪表演和 Seedance 视频提示词或中文 HTML 分镜网页。Use when the user asks for 分镜、镜头表、视频提示词、Seedance提示词、分镜网页、人物表情、微表演、情绪弧线，或要求把 chuanzhang-fenjing 与 chuanzhangbiaoqing…

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

面向科普/讲解的自动视频流水线：调研→撰稿→PPT截图→TTS→逐段合成→整片输出。用户给主题/要求/关键词即可生成 1080p 知识讲解视频。

This skill should be used when the user names Charmbracelet VHS, asks to use the `vhs` CLI, wants a terminal recording, terminal GIF, terminal MP4/WebM, `.tape` file, scripted terminal demo, or a…

本地版（逐步确认式 · 纯提示词）。从故事创意到成片的 3D 动画短片：简报→大纲→角色卡/场景卡(只给生图提示词+等用户返回图像)→镜头表→分镜→批次化视频提示词(调用 h3-video-prompt-cn skill，以返回图像为参考图；每批次一份文件)→BGM(先问云端)→剪辑思路。不硬编码任何生图/视频工具路径，不依赖 MiniMax Hub。

品牌宣传短片 —— 宣传片线方向之一：新品发布、官网展示与社交推广用的品牌宣传短片。

한국어 모션그래픽 영상(이력서용 쇼릴·홍보 영상·프로필 영상·티저·브랜드 필름·행사 홍보·제품 소개·교육 영상·메이킹 필름)을 콘셉트부터 납품까지 만드는 스킬. 정해 둔 무드나 템플릿을 고르지 않는다. 요청마다 콘셉트 후보를 여러 개 세워 가장 강한 것을 고르고, 구간마다 아트 디렉션을 새로 정해 코드(DOM·캔버스·WebGL 셰이더·3D)로 화면을 만든…

Find, transcribe, summarize, and organize all Apple Voice Memos into a searchable archive. Batch processes hundreds of recordings locally using whisper.cpp — no API keys needed. Use when the user…

独立口播剪辑试用版。用授权本地视频、现成时间戳逐字稿或 SRT、审核后的源区间，产出自有可编辑 JSON 工程、MP4、同步 SRT 和媒体校验报告。仅在用户明确说独立口播剪辑、ah-talking-head-edit、不依赖旧引擎剪片，或明确选择本项目时使用。普通剪映剪辑、剪映原生草稿、写口播稿、ASR 转写和封面制作不自动触发本 Skill。

广告创意素材搜索助手。通过 api.admapix.com 搜索竞品广告素材。触发关键词：找素材、搜广告、广告视频、创意素材、竞品广告、ad creative、search ads、find creatives、competitor ads、ad spy。

MUST USE when user wants to 调研/research/搜索/search/查/找/look up anything on the internet — e.g. 全网调研 X / 查一下 X / 看看大家怎么评价 X。 Also MUST USE when user mentions any platform or shares any URL/链接:…

Audit and fix HTML accessibility issues including ARIA labels, keyboard navigation, focus management, color contrast, and form errors. Use when adding interactive controls, forms, dialogs, or…

Convert MP3/WAV/FLAC audio files to MIDI (.mid) and MusicXML (.musicxml) with full music analysis. Two engines: Basic Pitch (general-purpose polyphonic) and Piano Model (high-accuracy piano, 96.7%…

Build multi-step AI content creation pipelines combining image, video, audio, and text. Workflow examples: generate image -> animate -> add voiceover -> merge with music. Tools: FLUX, Veo, Kokoro TTS,…

Generate AI videos from text prompts using multiple provider gateways. Use when: (1) Generating videos from text descriptions, (2) Creating AI-generated video clips for content production, (3)…

Find animation and video references on 1human, consult a human-agent shared library, and contribute public creations only with prior owner permission.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction,…

Retrieve and analyze Screenpipe CLI backend logs and desktop app logs for debugging

Create an annotated MP4 tutorial from a workflow demonstrated in the owner's actual application. Use when asked for a tutorial video, not merely to watch an action live.

视频提示词规范 — 根据分镜段落内容生成按时间分段、段内可切镜的视频生成提示词