skills

Turn the current conversation content into a visually scannable HTML page, publish it to a personal S3 bucket, and return a short shareable URL. Use when (1) the user asks to "make this an HTML / link / browser-viewable page" (in any language, e.g. "HTML化して", "リンクで渡して", "ブラウザで見れる形に"), (2) "upload to s3" / "s3に上げて" is requested, (3) the content has tables, code, comparisons, charts, timelines, or diagrams that Markdown chat can't convey well, (4) the output is something the user wants to come back to later.

Sentry error monitoring and user behavior tracking via CLI. Use when: (1) debugging user-reported issues, (2) checking recent errors/crashes, (3) tracing user actions before an error occurred, (4) searching issues by user email, (5) user asks "Sentryのログを確認して" or similar.

A skill that extracts keyframes from video files and analyzes their content. Automatically removes duplicate frames and optimizes image quality to reduce token consumption. Use when: - User provides a video file (.mp4, .mov, .avi, etc.) - User requests "watch this video", "analyze this video", "what's in this video" - Checking screen recordings or screencasts - Keyframe extraction is needed from video

Generate and edit images using Google Gemini or OpenAI GPT Image models. Automatically used for requests like "generate an image", "create an illustration", "edit this image". Also supports sticker sheet generation and splitting for requests like "create some stickers" or "generate multiple icons and split them". Choose between Gemini (Nano Banana) and OpenAI (gpt-image-1.5) providers.