플러그인

저비용 영상 이해 도구. video_understand 도구가 Bilibili 링크 / BV / 로컬 영상을 AVIS 정보 계층(ASR + 장면 구조 + 객체 추적 + YOLO 라벨)으로 변환하고 요약 + Q&A를 반환한다. 질문 주도형 계층 간 동적 라우팅(L0 ASR / L1 객체 추적 / L2 키프레임 VLM), 반복 질문용 의미 계층 재사용, 질문별 예산 상한을 갖춘다. Python 엔진: 코어 계층에는 faster-whisper / opencv / yt-dlp가 필요하며(~200-300MB), 선택적 의미 계층을 추가하면 torch / transformers / ultralytics가 약 2GB 더 든다. 번들된 doctor --fix가 venv를 설정하고 둘 다 설치한다.

자막 우선 비디오 전사로, SRT 내보내기, 취소 가능한 작업 제어, 자막을 사용할 수 없을 때 faster-whisper large-v3 폴백을 제공합니다.

Windows only. Bilibili video summarizer: downloads the audio track, transcribes it locally with faster-whisper (Python + faster-whisper, about 725 MB of models on first run), then writes the analysis markdown and renders a one-page infographic PNG.

Downloads a Bilibili video with yt-dlp, samples key frames, and transcribes it — from the site subtitles, or from a local faster-whisper install when there are none. Registers the skill the agent uses to write the summary; activates when a user message contains only a video link. Requires yt-dlp and ffmpeg on PATH; transcription needs faster-whisper.

Extract Bilibili platform/AI subtitles or external/embedded/ASR/OCR fallback and render Markdown, Word, PDF, TXT, SRT or JSON with timestamps, bilingual alignment and a quality report. Requires Python 3.10+; platform/AI subtitles need a Bilibili SESSDATA cookie; OCR/ASR/PDF need ffmpeg, faster-whisper and LibreOffice or reportlab.

Lets the model actually see a video: local ffmpeg samples timestamped stills and faster-whisper transcribes the audio track, so the agent reads real pixels frame by frame instead of trusting a text summary. Fully local, nothing uploaded; reports honestly when the audio has no speech. Windows only; needs Python 3.10+ and ffmpeg installed, and the first video_eyes_setup run downloads about 700 MB (faster-whisper and its model).

Subtitle-first video transcription and deterministic extractive Markdown summaries, with a faster-whisper large-v3 fallback when subtitles are unavailable.