Media skills

Best practices for Remotion - Video creation in React

The English summary is being prepared. Showing the original description.

Master orchestrator that chains all Remotion video creation skills together in a single automated pipeline. Takes a creative brief and produces a complete, production-ready Remotion video project. Use when starting a new video from scratch, when asked to "create a video", "make a video", "build a complete video", or "video from idea to code".

The English summary is being prepared. Showing the original description.

Scaffolds Remotion project folder structure, base configuration files, and file organization. Focuses ONLY on directory creation, empty file templates, and Remotion configuration. Use when starting a new video project or when asked to "scaffold Remotion project", "create project structure", "setup Remotion folders".

The English summary is being prepared. Showing the original description.

Check and document Vibe's audio quality and conformance. Runs public conformance and torture corpora (IETF CELLAR FLAC files, ISO/IEC 14496-26 Layer III, FFmpeg FATE samples, McGill WAVE and AIFF samples, EBU BW64 tests, Chromium and Firefox media tests, TagLib test data) through the real decoders. Valid files must match their FLAC MD5 or reference decode within the ISO accuracy limits, decode to the length the handle states and seek exactly. Every file must finish with finite samples. Also regenerates docs/audio-quality.md's charts and its corpus results matrix. Use after changing a decoder, a parser, the file-open path or the resampler, before a release, when asked whether decoding is correct or conformant, or to update the audio quality page.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Use when the user asks to create a custom post type, build a portfolio, set up case studies, add team members, events, or podcast episodes, or says 'scaffold a CPT'. Creates the post type plus supporting taxonomies, an ACF field group, sample entries, and a builder-specific single template suggestion.

The English summary is being prepared. Showing the original description.

Use when the user says 'optimize my wordpress images with ai', 'compress and optimize all images', 'audit my media library', or 'improve image performance'. Downloads images, compresses, converts to WebP, resizes and renames locally, re-uploads, and updates every content reference.

The English summary is being prepared. Showing the original description.

HX Audio Player for music and sound playback. Use when implementing music playback, sound effects, HXMusic, HXSound, or audio in HXAudioPlayer. Library is in the hxaudio module.

The English summary is being prepared. Showing the original description.

将量化分析或已有 JPG/PNG、HTML、PDF 发布为 Quant Buddy 可分享活页或实时看板，并支持创建、更新、复用、验收和公开链接交付。适用于个股画像、估值财务、指数异动、多因子筛选、商品日报、模板、分享壳及卡片等页面。 用户提供 QuantBuddy 活页 URL 并要求解读时也使用。显式调用 /quant-buddy-view、/qbv、qbv 或 QBV，且请求并非纯咨询、代码维护或文档解释时，默认按可分享活页任务处理。 输入可唯一识别的 A 股名称、简称或代码，或简单要求单股综合分析（如“贵州茅台”“600519”“分析一下贵州茅台”）均默认请求个股快页；先通过 QBS 验证并回复完整个股分析，再同轮 new_asset_page，无需用户补说“生成页面”。 WebAgent 宿主要求金融问题统一交付问答与活页时，一次性行情、涨跌幅、估值、概念解释和口语近况问题也在 QBS 首答后交接本技能。无此宿主约定时一次性问题由 QBS 回答；复盘、监控、画图、回测、K线等操作仍默认有活页意图。明确不要网页或只回复文字时不建页。

The English summary is being prepared. Showing the original description.

Deterministic workflow to find and export full podcast transcripts as cleaned TXT files from YouTube URLs, episode webpages (including Xiaoyuzhou), Apple Podcasts title search, X/Twitter links, direct audio URLs, or plain episode titles. Use when users ask for 逐字稿/文字版/transcript/txt and want minimal trial-and-error.

The English summary is being prepared. Showing the original description.

Best practices for Remotion - Video creation in React

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

ALIGN for paper figures — draw a method-overview figure as an executable p5.js program that replays its own construction in named stages, exports SVG, and improves through pixel-only cross-model review whose gate is 'explain the method back from the figure alone, and is it worth looking at'. The method sets the relationships the figure must show, the chosen visual identity sets how its marks look, a composition source lends arrangements; the method may be the source's own (意临) or yours in its arrangement (风格迁移). Not for one-shot raster image generation.

The English summary is being prepared. Showing the original description.

ALIGN-video for Codex. 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.

The English summary is being prepared. Showing the original description.

ALIGN — Agentic Loop Image GeneratioN. Paint a subject in the craft of a reference artwork as executable p5.js, Canvas, SVG or another mark-based medium, replay that craft's real order of work, and improve it through pixel-only cross-model review. The reference fixes the craft; the subject may be the reference's own scene (千里江山图 → p5.js) or another (清明上河图 → 武汉). Not for one-shot raster image generation.

The English summary is being prepared. Showing the original description.

Size local blog images and add rendered dimensions to Markdown image URLs in jxck.io. Use when inserting article images, normalizing their displayed sizes, or invoking /img for a Markdown file.

The English summary is being prepared. Showing the original description.

Generates walkthrough videos from Stitch projects using Remotion. Downloads screenshots from Stitch screens, builds a Remotion composition with transitions and text overlays, and renders to MP4. Use with stitch-mcp-list-screens and stitch-mcp-get-screen for screen discovery.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Add, edit, generate, or organize image assets under src/jg/coop/images. Use for avatars, logos, posters, thumbnails, interest icons, project images, image formats, dimensions, cropping, or generated-image directories.

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Create and manage articles on the PANews platform. All operations require a valid user session. Triggers: write and publish new articles, view / edit / delete drafts, revise and resubmit rejected articles, upload images, search tags, apply for a column, polish or review article content.

The English summary is being prepared. Showing the original description.

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

The English summary is being prepared. Showing the original description.

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".

The English summary is being prepared. Showing the original description.

Create or revise repository-aware social preview images for GitHub, package pages, launch posts, and link cards. Use when an agent needs to inspect a project, sharpen its short positioning, generate a branded 2:1 raster preview, explore color variants, adapt a supplied visual reference without copying it, or validate and save a social-card image non-destructively.

The English summary is being prepared. Showing the original description.