246 个 · 按相关度排序
Turn a GitHub pull request into a video explaining a feature, fix, refactor, or changelog. The workflow uses actual diffs, commits, and files to plan the story, show code excerpts, and produce an MP4.
中文简介正在准备中。当前显示英语简介。
Create navigable HyperFrames presentations with step-by-step reveals, clickable branches, and speaker notes. You can also turn an existing page into a deck while preserving its visual design, motion, and interactive behavior.
中文简介正在准备中。当前显示英语简介。
Capture cmux windows as screenshots or video clips from the CLI. Create visual evidence for pull requests and bug reports, with region selection and captions to explain drags, animations, or layout changes.
中文简介正在准备中。当前显示英语简介。
Render landscape videos with KrillinAI CLI, combining original footage with bilingual subtitles or prepared dubbed footage with target-language subtitles. Optionally replace audio, adjust subtitle styling, and verify the output video and subtitle placement.
中文简介正在准备中。当前显示英语简介。
Render portrait videos with KrillinAI CLI using short bilingual subtitles or prepared dubbed footage with target-language subtitles. Add titles and check the resulting video for readable captions, working audio, and correctly displayed text.
中文简介正在准备中。当前显示英语简介。
Retrieve video subtitles and turn them into a clean paragraph, with optional timestamps and bracketed cues. Download video, audio, or subtitle files, inspect available formats, and choose a language or specific download format.
中文简介正在准备中。当前显示英语简介。
Publish videos to Douyin, search posts, manage comments, and check visible performance data. The skill reuses existing signed-in accounts and records drafts, task outcomes, and supporting evidence in the operations panel.
中文简介正在准备中。当前显示英语简介。
Create live HTML product demos that show an app’s workflow inside a Mac-style window. Reproduce real interface text and results, animate a scripted pointer, and support step navigation, scrubbing, and consistent frozen frames.
中文简介正在准备中。当前显示英语简介。
Turn a topic or script into a finished short explainer video with images, narration, subtitles, and optional music. Coordinate the production steps, use supplied assets or generated visuals, and retain intermediate files for later replacement.
中文简介正在准备中。当前显示英语简介。
Calibrates pre-recorded `cam_*.mp4` datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to `amc-run-rtsp-calibration`.
中文简介正在准备中。当前显示原文说明。
口播视频成片 Skill。把文章/口播稿/SRT、剪后视频和 HTML/图片素材串成分镜稿、时间线预览和最终 MP4；成片比例和动画风格从用户配置读取，动画默认使用小黑风格。触发词：口播成片、做分镜稿、时间线预览、合成口播视频、导出竖屏MP4
中文简介正在准备中。当前显示原文说明。
Fix silent video/media processing failures caused by URL extraction code that filters on file extensions (.mp4, .webm, .webp). Use when: (1) Media moderation, transcoding, or analysis silently skips files from Blossom or content-addressed storage servers, (2) URL extraction from Nostr event tags (imeta, r tags) drops URLs without recognized extensions, (3) CDN fallback URLs append .mp4 but the actual server uses extensionless content-addressed paths like /{sha256}. Common in Nostr video events (kind 34236) where different clients use different URL formats.
中文简介正在准备中。当前显示原文说明。
Use this skill whenever the user asks for an HTML-first visual design deliverable or design judgment: interactive prototype, slide deck, motion demo, infographic, dashboard, landing page, whitepaper, changelog, business card, social cover, brand system, design critique, multi-variant exploration, or export to MP4, GIF, PPTX, PDF, or SVG. It is optimized to make AI agents do the routing, template selection, verification, and export prep so humans spend less time prompt-engineering. Do not use for production web apps, SEO sites, backend systems, or pure copy edits.
中文简介正在准备中。当前显示原文说明。
Use when the user wants a 王建硕-style WeChat article (article.md) turned into a narrated short MP4 video — TTS voiceover via 火山引擎 Volcano TTS, HyperFrames CSS/GSAP animation per scene, subtle SFX, abstract watercolor background, full pipeline rendering to 1080×1920 portrait MP4 (30-90s). Triggers — "把这篇文章做成视频", "做一个解说视频", "讲解视频", "/wjs-converting-text-to-video".
中文简介正在准备中。当前显示原文说明。
Motion design — produce HTML animations and export MP4/GIF with optional BGM. Use when asked to "animate this", "create a motion design", "make an intro animation", "product launch animation", "promo video", "export MP4", "export GIF", "60fps animation", "animated logo", or "motion graphics". Delivers a self-contained HTML animation plus rendered video exports. Not for micro-interactions in production code — use /prism-ui for that.
中文简介正在准备中。当前显示原文说明。
HyperFrames (HTML + GSAP → MP4) でアプリのプロモ動画を決定論的に生成するスキル。 HyperFrames 公式スキル（19本）を土台として前提にし、素材の橋渡し・検証ゲート・ 納品仕様・誇張表現の禁止という「公式が扱わない層」だけを担当する。 SNS リール、LP ヒーロー動画、リリース告知、機能デモが対象。 Use when: プロモ動画を作りたい、告知動画を作りたい、HTML から動画を作りたい、 HyperFrames で動画を作りたい、リリース動画を作りたい、SNS 用の縦動画を作りたい。 Triggers: "HyperFrames", "hyperframes", "プロモ動画", "告知動画", "宣伝動画", "HTML から動画", "html to video", "リリース動画", "SNS動画", "縦動画", "リール"
中文简介正在准备中。当前显示原文说明。
Programmatic React video best practices for Remotion. Use this skill whenever the user is writing, debugging, or rendering Remotion code — compositions, useCurrentFrame animations, interpolate, spring, Sequence timing, <Img>/<Video>/<Audio> from @remotion/media, staticFile, calculateMetadata, the Studio preview, `npx remotion render`, captions, subtitles, voiceover, audio visualization, ffmpeg, transitions, light leaks, transparent video, Lottie, 3D scenes, Mapbox flyovers. Triggers especially on HtmlInCanvas / "html in canvas" requests, CRT terminal effects, glitch effects, video shaders, WebGL video, and any request to scaffold a new programmatic React video. Owns `remotion render` and everything about Remotion code. Do NOT trigger for finished MP4 ad assembly from existing slides (that is `/video-content`) or for the inspiration-to-MP4 reference-video pipeline (that is `/cmo-video`).
中文简介正在准备中。当前显示原文说明。
Use this skill whenever the user asks for an HTML-first visual design deliverable or design judgment: interactive prototype, slide deck, motion demo, infographic, dashboard, landing page, whitepaper, changelog, business card, social cover, brand system, design critique, multi-variant exploration, or export to MP4, GIF, PPTX, PDF, or SVG. It is optimized to make AI agents do the routing, template selection, verification, and export prep so humans spend less time prompt-engineering. Do not use for production web apps, SEO sites, backend systems, or pure copy edits.
中文简介正在准备中。当前显示原文说明。
Agent-native design engine that makes AI do more useful work: route the prompt, fork a template, weave IFQ ambient craft, verify the artifact, and only install export tooling when requested. One prompt -> shippable HTML, with optional MP4 / GIF / PPTX / PDF / SVG. Triggers include prototype, hi-fi mockup, slide deck, motion demo, infographic, dashboard, whitepaper, changelog, business card, social cover, brand from scratch, design critique, mp4/gif export, 60fps, keynote, PPTX, A-vs-B benchmark. Do not use for production web apps, SEO-critical sites, backend systems, or pure copy edits.
中文简介正在准备中。当前显示原文说明。
host / 辅助段优化模块（L3）：把**非 DiT、非解码段**的固定开销落成可复验的优化—— ① 交付与搬运（mp4/图片编码、worker→API 通路、落盘、异步化）； ② 装载与预热（权重加载、编译与图下发预热、镜像/容器预热）。 当用户说“mp4 编码/传输/落盘慢”“交付这段占了不少时间”“模型加载慢”“首启编译太久” “固定开销占比高”“每个请求都要重新编码/重新写盘”时使用。 **入口条件**：占比已达门限（瓶颈标签 `非DiT-host段`；标签枚举、门限与测点口径的单一真源在 model-auto-optimization/references/bottleneck-labels.md，本技能只消费不定义）。 near-miss（看似相关但不属本技能）： - **并发 / 吞吐 / 批处理调度 / 队列深度与限流** → **不属本技能**（会改变所有性能口径与 SLO 语义， 未来独立立项；本技能只在**不改变请求并发模型**的前提下压固定开销）； - VAE/TAE 解码段（计算或通信）→ `vae-opt`；DiT 计算 → `dit-perf-opt`； 多卡并行 / 通信掩盖 → `dit-parallel-opt`； - **装库 / 下载权重 / 构建镜像 / 创建容器** → `env-install`（本技能只优化装载与预热**过程本身**）； - 编译与图下发的**机制本体**（pattern / Inductor / NPUGraph / 图 pool / 缓存条目）→ `pattern-dev` / `aclgraph-dev`（本技能不另做一套缓存）； - 产物一致性与精度判据 → `accuracy-gate`；收益口径 → `perf-gate`； - 瓶颈未定位 / 没有占比锚点 → `model-auto-optimization`。
中文简介正在准备中。当前显示原文说明。
Premiere Pro 動画編集ワークフローを Claude Code で自動化するスキル集。/cut は Premiere Pro XML の無音・雑音区間をジェットカット、/srt は WAV+Premiere XML から日本語テロップ用 SRT を並列Whisper→LLM意味区切り→全体アライメントSRT の3ステップ(v6)で生成、/srt-fast は改行工程まで3チャンク並列化した高速版、/telop-check は書き出し済みMP4を全編スキャンしてテロップの数字表記・誤字脱字・い抜き・ら抜き・固有名詞ミスを検出する。faster-whisper / ffmpeg / Premiere Pro を要するローカル実行型。日本語トーク動画のショート / ロング編集向け。
中文简介正在准备中。当前显示原文说明。
[Document Processing] Use when a workflow step or the user asks for HTML page, deck, mockup or animation export to PNG, vector PDF, MP4 or GIF. --to={png|pdf|mp4|gif}.
中文简介正在准备中。当前显示原文说明。
動画/音声ファイルをタイムスタンプ付きで文字起こしし、要約まで行うスキル。「動画を文字起こしして」「この音声を要約して」「会議の録画をまとめて」「mp4を文字起こしして要約して」「インタビュー音声から議事録作って」などのリクエストで使用する。OpenAI Whisper（ローカル）でタイムスタンプ付き全文mdを生成し、Claude自身がその全文を読んで要約mdを別ファイルで書き出す。出力先はプロジェクトルート直下（`TRANSCRIPT_OUTPUT_PATH` で変更可）。
中文简介正在准备中。当前显示原文说明。
窓際族物語の2Dゲームを新規作成し、Seedance（CapCut）で制作した動画をオープニング/イベントのカットシーンとして組み込むワークフロー。ユーザーから2Dゲームの制作を頼まれたとき、添付動画（mp4）をゲームに組み込む・差し替えるよう頼まれたとき、カットシーンの追加・修正を頼まれたときに必ず使用する。
中文简介正在准备中。当前显示原文说明。