動画・画像・音声のスキル

ALIGN-video for Claude Code with independent Codex adversarial review. Create or revise a video through agent-authored code, rendering, editing and fresh-context audiovisual review, without image, video or music generation models. Use for reference-led animation, procedural films, motion design, explainers, construction replays, and continuing an existing coded-video project. Carries the work from reference study and animatic through a finished, reproducible film; supports explicitly requested self-review when appropriate.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user wants Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.

日本語の概要は準備中です。原文の説明を表示しています。

Google Imagen image generation via Vertex AI — text-to-image, image editing, inpainting, and upscaling using ImageGenerationModel

日本語の概要は準備中です。原文の説明を表示しています。

视频逆向复刻 — 分析参考视频(FFmpeg帧提取+Vision LLM) + 生成复刻Seedance 2.0 Prompt + 4种素材替换模式。支持单个和批量。Use when: '复刻这个视频', '分析爆款视频', 'replicate this video', '视频逆向', '反编译视频', '批量分析视频'. Do NOT use for creating from scratch — use fashion-video-creator instead.

日本語の概要は準備中です。原文の説明を表示しています。

Xiaohongshu (Little Red Book) infographic series generator with multiple style options. Breaks down content into 1-10 cartoon-style infographics. Use when user asks to create "小红书图片", "XHS images", or "RedNote infographics".

日本語の概要は準備中です。原文の説明を表示しています。

Improve how interfaces use photos, screenshots, icons, illustrations, and user-uploaded media so visuals support clarity instead of undermining it. Use when the user mentions images, screenshots, background photos, hero images, icon sizing, user-uploaded media, crops, overlays, or image readability.

日本語の概要は準備中です。原文の説明を表示しています。

Image optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, and CLS prevention. Use when user says "image optimization", "alt text", "image SEO", "image size", or "image audit".

日本語の概要は準備中です。原文の説明を表示しています。

This skill should be used when the user asks to "make an ASCII animation", "build a terminal/CLI intro or loader", "convert an image or video to ASCII art", "add an ASCII shader/post-effect to a canvas or Three.js scene", "create retro/hacker text-character motion", or "animate text characters with a brightness ramp". Covers generative ASCII fields, image/video/3D-to-ASCII, and animated character art for both web and terminal.

日本語の概要は準備中です。原文の説明を表示しています。

Extract transcript and key slides from a local video file, then create a vault-formatted lecture note. Use this skill whenever a user provides a local video file (.mp4, .mov, .mkv, .avi, .webm) and wants notes from it. Triggers on "lecture", "take notes", "I have a recording of", "class video", "transcribe this presentation", "process this video for notes", or /lecture. Works with any language — auto-detects transcript language.

日本語の概要は準備中です。原文の説明を表示しています。

Analyze a YouTube video and create a vault note from its transcript. Use this skill whenever a YouTube URL is pasted — even with casual commentary like "check this out" or "interesting talk." Also triggers on "youtube", "take notes from this video", "summarize this video", or any YouTube link (youtube.com, youtu.be) regardless of surrounding context.

日本語の概要は準備中です。原文の説明を表示しています。

Create or refine custom icon assets as native or traced SVGs and transparent PNG/WebP files. Use when the user asks for a bespoke icon or cohesive icon set, wants an image traced into a clean vector, or needs a detailed or 3D icon with transparency.

日本語の概要は準備中です。原文の説明を表示しています。

Vets whether to build a feature from scratch, use an existing free/open-source solution, or pay for a third-party API/service. Use this whenever the user asks Claude to implement, add, integrate, or write code for a feature or capability, especially one that sounds like it could already be a solved problem (auth, payments, scraping, animation, comment/DM automation, video/image generation, search, notifications, etc.), even if the user doesn't explicitly ask "should I build or buy this." Make sure to trigger this before writing non-trivial implementation code for any feature-level capability, not just when the user asks about libraries directly.

日本語の概要は準備中です。原文の説明を表示しています。

Generate a polished release video for a tbh-meter release in the Claude-Code motion style (recreated animated UI + real game sprites + synth soundtrack), to post with a launch. Primary input is a GitHub release LINK — the skill turns it into a video named after that release, covering ONLY the features that shipped in that release, version stamped on the intro. Use when asked to make/update a release video, showcase clip, feature trailer, or promo video for a meter release, or "make the video for <release link>".

日本語の概要は準備中です。原文の説明を表示しています。

動画・画像のフレーム抽出、Remotion レンダリング、仕様チェック、目視検証を行う汎用ビデオツールキット。 ffmpeg / ffprobe / remotion still / remotion render を統一シェルスクリプト (video-tool.sh) で操作し、 Read ツール（マルチモーダル対応）で実際の見た目を確認して品質レポートを出す。 Use when: 動画のフレームを確認したい、レンダリング結果を検証したい、 画像の品質を目視チェックしたい、Remotion プロジェクトを MP4 に出力したい、 動画の仕様（解像度・fps・長さ）をチェックしたい。 Triggers: "フレーム確認", "フレーム検証", "動画チェック", "frame inspect", "フレーム抽出", "動画の中身を見たい", "レンダリング確認", "動画検証", "MP4 確認", "動画のスクショ", "frame check", "動画を出力", "Remotion render", "動画レンダリング", "仕様チェック", "spec check", "video render"

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"

Render a deterministic 15-second vertical promo video from real Simulator screenshots with a three-beat viewer challenge and no Remotion initialization. Use in a twelve-minute parallel launch lane, as a reliable fallback to a richer Claude Design animation, or whenever ffmpeg and ImageMagick are available.

日本語の概要は準備中です。原文の説明を表示しています。

Capture reproducible screenshots from the currently booted iOS Simulator and turn them into three App Store marketing cards with validated dimensions and concise copy. Use after a successful Simulator build, during the two-minute proof lane, or when replacing prototype images with real app captures.

日本語の概要は準備中です。原文の説明を表示しています。

Timebox and coordinate a live three-lane iOS launch sprint from audience idea to tested SwiftUI app, landing page, ASO copy, screenshots, promo video, and privacy report. Use for a 50-minute talk, demo rehearsal, fallback drill, or any request to finish a tiny local iOS product under a hard deadline.

日本語の概要は準備中です。原文の説明を表示しています。

Summarize videos, audio files, and podcasts into key takeaways. Give it a YouTube/podcast URL or a local audio/video file — it transcribes locally (cached; repeat requests reuse the transcript) and distills the transcript into key points, summaries, or translations. Use when the user asks to summarize, get key points from, translate, or TL;DR any audio or video content.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the deliverable is spoken words to be performed on camera or into a mic: video and podcast scripts, hooks, and CTAs for short-form (TikTok, Reels, Shorts), YouTube long-form, or podcast episodes. Triggers: "write me a reel about X", "I need a hook for my video", "script a 60-second video", "draft a podcast episode", "turn this idea into a script". For motion/timing/shot specs rather than the words, use motion-picture.

日本語の概要は準備中です。原文の説明を表示しています。

Redact rendered visual artifacts — Mermaid diagrams, SVGs, and HTML dashboards — before public disclosure, using an ordered longest-first mapping table (specific label, then namespace label, then catch-all placeholder) that swaps sensitive identifiers for descriptive stand-ins while preserving structure, node ids, and teaching value. Covers whole-word identifier replacement, node-label-vs-node-id discrimination, re-rendering the derived image from the redacted source, and verifying the result through the redaction gate. Use when a diagram or dashboard built from internal findings must ship to a public mirror without leaking the names behind it.

日本語の概要は準備中です。原文の説明を表示しています。

Implement a generative diffusion model (DDPM or score-based) with noise scheduling, U-Net architecture, training loop, and sampling procedures including DDIM acceleration. Use when building a generative model for image, audio, or molecular synthesis; implementing DDPM from a research paper; adding a custom noise schedule or conditioning mechanism; replacing a GAN-based generator with a diffusion alternative; or prototyping before scaling with production frameworks like diffusers.

日本語の概要は準備中です。原文の説明を表示しています。

Compose 2D graphics programmatically using SVG generation, diagram layout algorithms, image compositing, and batch processing workflows. Use when generating diagrams, flowcharts, or infographics programmatically, creating reproducible scientific figures, automating production of badges or visual assets, building custom chart types not in standard libraries, or batch generating graphics with parameter variations.

日本語の概要は準備中です。原文の説明を表示しています。

This skill should be used when analyzing market breadth charts, specifically the S&P 500 Breadth Index (200-Day MA based) and the US Stock Market Uptrend Stock Ratio charts. Use this skill when the user provides breadth chart images for analysis, requests market breadth assessment, positioning strategy recommendations, or wants to understand medium-term strategic and short-term tactical market outlook based on breadth indicators. All analysis and output are conducted in English.

日本語の概要は準備中です。原文の説明を表示しています。