video-skills-toolkit

In the author's own words, from each skill's SKILL.md.

• audio-to-subtitles

  Convert local audio/video files or public media URLs into subtitle files by uploading local files to Cloudflare R2 and calling Volcengine AI MediaKit ASR subtitles API. Also supports MiniMax text-to-speech generation from text or text files, with optional subtitle generation from the produced audio. Supports batch processing, SRT/VTT/JSON output, language selection, speaker labels, configurable M…

  skills/audio-to-subtitles/SKILL.md on GitHub (opens in a new tab)

• content-remix

  把已经完成八部分拆解的抖音视频、小红书图文或小红书视频，迁移成泊舟自己的小红书图文、抖音口播或小红书视频内部草稿。用户说“做二创”“按这个爆款做我的版本”“参考这个机制重新创作”“把这个拆解写成小红书/抖音”“不要照抄地借鉴”时使用；先提炼可迁移机制、删除不可照搬内容、映射泊舟真实经历/案例/判断，再按目标平台重新组织。不用于爆款判级、原文拆解、普通润色、自动发布或发布后复盘。

  skills/content-remix/SKILL.md on GitHub (opens in a new tab)

• douyin-cover

  生成抖音、视频号、小红书等短视频封面图、视频标题图和合集封面，也能诊断和改版已有封面。用户说做封面、生成封面、抖音封面、视频封面、标题图、合集封面、3:4、4:3、1:1、短视频首图、动态封面首帧、给这期视频做图、这封面为什么没人点、帮我改封面、封面点击率怎么提升、诊断封面时都应使用。小白学AI系列封面除外：遇到“小白学AI封面/小白学AI第N集封面”时优先使用 xiaobai-ai-cover skill（系统内置 imagegen + 固定角色参考图）。这个 skill 会根据每次标题重新设计简约大方、有点击理由的封面，保留泊舟 IP 人物识别特征，内置「信息密度 × 视觉锚点」方法论和冲突型/数字型/截图型/情绪型可选模板参数，支持 3:4 竖版、4:3 横版和 1:1 正方形，默认必须使用系统内置 `imagegen` skill / `image_gen` 工具直接生成带准确标…

  skills/douyin-cover/SKILL.md on GitHub (opens in a new tab)

• hook-writing

  为内容写钩子和开头，也可拆解爆款视频开头、逐字稿开头、文章、推文、小红书图文和短视频脚本里的钩子，并沉淀到钩子库。用于视频开头拆解、逐字稿开头分析、推文、文章、小红书图文、短视频脚本、标题和开头优化；当用户说“写个钩子”“开头不抓人”“第一句话怎么写”“标题不够抓人”“优化开头”“拆解这个视频开头”“拆解逐字稿开头”“拆解这个钩子”“把这个开头收进钩子库”时触发。

  skills/hook-writing/SKILL.md on GitHub (opens in a new tab)

• hyperframes-scene-animator

  接管 talking-head-hyperframes 的 READY_FOR_EXECUTION 交接，由主 Agent 完成字幕分镜与具体导演，先交付全镜头最终静态页审核，批准后再用快速子 Agent 协助实现互不冲突的镜头与动效，最后完成 HyperFrames proof、四遍审查与 preview-v1。适用于口播镜头、语义动效、转场、声音 cue 和整改；TEMPLATE_ONLY 或路径/hash/合同不完整时精确拒绝，不用于创建固定模板。

  skills/hyperframes-scene-animator/SKILL.md on GitHub (opens in a new tab)

• media-to-transcript

  Convert audio/video URLs or local media into corrected Markdown transcripts through Volcengine recording-file ASR 2.0. Reuses the existing video-transcript downloader for Bilibili, Douyin, Xiaohongshu, YouTube, extracts audio when input is video, uploads local audio to R2, splits media longer than 3 minutes into parallel AUC tasks, submits volc.seedasr.auc with compact source context, then perfor…

  skills/media-to-transcript/SKILL.md on GitHub (opens in a new tab)

• minimax-voice-director

  用 MiniMax 云端为视频制作可审批的声音导演稿，再生成、挑选和验收人声，最后以定稿音频产生字幕。用于用户明确选择 MiniMax 配音、继续已有 MiniMax 视频配音项目，或明确请求 MiniMax Voice ID/克隆/设计。泛指本地 TTS 或 IndexTTS 不使用本 skill；音乐、BGM、歌曲使用同级 music Skill。

  skills/minimax-voice-director/SKILL.md on GitHub (opens in a new tab)

• music

  Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata. For workspace video BGM, search the generated-music registry and reuse a suitable documented loop before spending credits o…

  skills/music/SKILL.md on GitHub (opens in a new tab)

• obsidian-bases

  Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

  skills/obsidian-bases/SKILL.md on GitHub (opens in a new tab)

• talking-head-hyperframes

  为 HyperFrames 口播或旁白项目创建、修复并验证固定舞台，锁定数字人 PIP 的区域、裁切、人物安全区和不透明背景，归档输入，生成 manifest 与 template handoff，并在就绪后按“字幕驱动的全镜头静态审核→动效”门禁路由到 hyperframes-scene-animator。适用于“新建 HyperFrames 口播模板”“准备或修复数字人/PIP”“导入音频字幕和制作资料”“检查模板能否开工”等请求；不负责镜头导演、内容场景、整片渲染或审片整改。

  skills/talking-head-hyperframes/SKILL.md on GitHub (opens in a new tab)

• video-script

  使用已经锁定的完整口播音频与带时间码字幕，把确认后的逐字稿转成管线无关的视频导演方案和 Beat Graph。适用于“根据最终配音做分镜”“按字幕设计整片画面”“规划 B-roll/证据/素材”“做 HyperFrames 或 Remotion 前的导演稿”等请求。面向短视频时，还要在镜头层承接上游已写入逐字稿的钩子、承诺、证据递进和结尾兑现，但不重新选题、改片头或重写正文。正式视频脚本必须发生在完整音频与字幕之后；只有逐字稿、草稿或试听音频时先回到上游，不凭预估语速编正式时间线。本 skill 负责导演规划，不写下游实现代码；导演稿确认后才进入制作规格和组件复用判断。

  skills/video-script/SKILL.md on GitHub (opens in a new tab)

• video-transcript

  Deprecated compatibility package. Do not use this skill for transcription. For any audio/video transcript, 逐字稿, 视频转文字, 音频转文字, 听写, or 提取视频文案 request, use media-to-transcript instead. The remaining scripts are kept only as downloader/probe helpers imported by media-to-transcript.

  skills/video-transcript/SKILL.md on GitHub (opens in a new tab)

• viral-video-benchmark

  判断、扫描、拆解并归档抖音视频、小红书图文或小红书视频。实时读取用户同平台粉丝数并划分主对标池/跨级灵感池，用已登录浏览器读取目标作品和作者主页公开指标，再用确定性代码判定普通、小爆、爆款、现象级并扫描作者近 20 条候选；只对用户选中的爆款和现象级先构建可追溯证据包，再调用子 Agent 拆解，经确认后写入爆款库并合并或创建选题。用于“判断是不是爆款”“看看这个账号近20条有没有爆款”“拆解对标内容”“筛选同阶段对标”“爆款入库”“从爆款生成选题”“把同题内容归到一个选题”等请求；不用于自动监控。

  skills/viral-video-benchmark/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• cangjie-skillby kangarooking 把书、长视频、播客等高价值内容蒸馏成可执行的 Agent Skills（Distill high-value content from books, long-form videos, podcasts, and more into executable Agent Skill… 11.4k stars · 21 skills
• superpowersby obra An agentic skills framework & software development methodology that works. 300k stars · 15 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 293k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill