Video editing, thumbnails, comics, and audio (3.2K skills)
Generate an image from a brief — provider-agnostic blueprint then provider-specific translation, with ref-image/seed reuse for consistency. Use when generating/creating an image.
The English summary is being prepared. Showing the original description.
Edit an existing image — inpaint, background swap, variation — via providers that support it. Use when editing/modifying/inpainting an image or making variations.
The English summary is being prepared. Showing the original description.
Use to generate a character image to spec — max-fidelity reproducible prompt from a Canon Spec, anchors-first, provider/governance-gated. Triggers 'generate this character', 'render to spec'.
The English summary is being prepared. Showing the original description.
Use to analyse a character image down to the smallest mole and diff against a canon — per-feature spec, OCR-reads tattoo text, flags drift. Triggers 'analyse this image', 'match the canon'.
The English summary is being prepared. Showing the original description.
Wire up DevContainers / GitHub Codespaces — `devcontainer.json`, container images, secrets, VS Code features, port forwarding. NOT for tuning Copilot itself (use `copilot-config`).
The English summary is being prepared. Showing the original description.
Use when a character must stay visually identical across AI video scenes — locks identity tokens (silhouette, palette, wardrobe, prop) in JSON. Triggers 'character lock', 'same character'.
The English summary is being prepared. Showing the original description.
Generate brand assets — banners, social cards, CIP elements — with brand-token injection + provider routing. Use when generating a banner / social image / branded asset.
The English summary is being prepared. Showing the original description.
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
The English summary is being prepared. Showing the original description.
JMComic3 APK 逆向修改：输入 APK 文件，自动解包→去广告→移除游戏/电影板块。支持 AI 可执行的意图解析+自定义组合。基于 v2.0.29 实战经验。触发词：JMComic去广告、APK修改、去除游戏电影、jmcomic mod
The English summary is being prepared. Showing the original description.
OCR scanned PDFs and image files into searchable text using pdftoppm + tesseract (or ocrmypdf if available). Load when about to OCR a scanned PDF or image, or when extracted PDF text is empty/garbled.
The English summary is being prepared. Showing the original description.
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community detection, and query/path/explain tools.
The English summary is being prepared. Showing the original description.
[User-Invoked] Use when creating, updating, or previewing Remotion videos.
The English summary is being prepared. Showing the original description.
- End-to-end workflow to establish where and when a photo or video was captured and whether it is authentic — evidentiary handling, metadata extraction, reverse image search for provenance, visual geolocation, chronolocation from shadows, and manipulation… Use when asked to verify where an image was taken, confirm or refute a claimed location or date, or authenticate media before relying on it
The English summary is being prepared. Showing the original description.
Публикует готовый контент на личный YouTube-канал Антона [аккаунт]: вычерпывает новое из NotebookLM и очереди, рендерит аудио в видео, пишет описание с фрагментом расшифровки для SEO и авторским блоком Антона, грузит и читает статус обратно. Триггеры: /youtube-publish, /yt, выложи на ютуб, залей на youtube, что ждёт выгрузки. НЕ /teach-podcast и не /notebooklm — те ПРОИЗВОДЯТ, этот ПУБЛИКУЕТ.
The English summary is being prepared. Showing the original description.
Учебные аудиоподкасты для Антона в NotebookLM: выбирает, чему учить (труба собеседований, дыры сверки), пишет пакет и промпт ведущим, генерирует аудио RU+EN через CLI notebooklm, кладёт в волт, ведёт учебный план и YouTube-очередь. Триггеры: /teach-podcast, /teach, сделай подкаст, обучи меня, подкаст в машину, что мне послушать. НЕ /notebooklm (общий слой артефактов).
The English summary is being prepared. Showing the original description.
Drive NotebookLM over a programmatic CLI with no browser: turn a vault slice into an audio overview, study guide or mind map, and fold the artifacts back into the vault. Browser automation is the fallback if CLI auth breaks. Triggers: "/notebooklm", "make an audio digest of <topic>", "podcast from the vault".
The English summary is being prepared. Showing the original description.
- Start-here router and tradecraft baseline for any investigation into a person, company, domain, image or selector.
The English summary is being prepared. Showing the original description.
- Reverse image search across Yandex, Google Lens, Bing Visual Search, TinEye and Baidu to find where a picture came from and who published… Use when reverse image searching, identifying a photo, face, logo, product, uniform or building, tracing a profile picture or avatar, finding the oldest copy of an image, checking whether a photo is stock or a repost, or reverse-searching a video by keyframes
The English summary is being prepared. Showing the original description.
- Geolocate and chronolocate a photo or video from visual evidence alone — plate and phone number formats, road markings, utility poles, bollards, signage typefaces, architecture and vegetation for… Use when asked where or when a picture was taken, to verify a claimed location without GPS or EXIF, or to match a scene against Google Earth, Street View, Yandex Panoramas, Mapillary or KartaView
The English summary is being prepared. Showing the original description.
TypeScript-only skill for generating and debugging high-resolution AI images through sub2api OpenAI-compatible APIs. Use this whenever the user wants a TS/Node sub2api image generator, 4K image generation, stream=true /v1/images/generations or /v1/responses image generation, Cloudflare 524 timeout avoidance, partial image capture, or SUB2API_BASE_URL/SUB2API_API_KEY based image generation.
The English summary is being prepared. Showing the original description.
Run one iteration of VL-Harness evolution — evolve video-memory-harness code for long-video MCQ. Called by meta_harness.py or interactively via /vl-harness.
The English summary is being prepared. Showing the original description.
Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models. Supports batch analysis of audio files, generates confidence scores, and produces forensic reports. Activates for requests involving deepfake voice detection, vishing investigation, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.
The English summary is being prepared. Showing the original description.
Perform comprehensive forensic analysis of disk images using Autopsy to recover files, examine artifacts, and build investigation timelines.
The English summary is being prepared. Showing the original description.
Create forensically sound bit-for-bit disk images using dd and dcfldd while preserving evidence integrity through hash verification.
The English summary is being prepared. Showing the original description.