Plugins

Ferramenta de compreensão de vídeo de baixo custo: uma ferramenta video_understand transforma um link do Bilibili / BV / vídeo local em uma camada de informação AVIS (ASR + estrutura de cena + rastreamento de objetos + rótulos YOLO) e retorna resumo + Q&A. Roteamento dinâmico entre camadas orientado por perguntas (L0 ASR / L1 rastreamento de objetos / L2 VLM de keyframe), reutilização da camada semântica para perguntas repetidas, teto de orçamento por pergunta. Motor Python: a camada principal precisa de faster-whisper / opencv / yt-dlp (~200-300MB); a camada semântica opcional adiciona ~2GB de torch / transformers / ultralytics. Um doctor --fix incluído configura o venv e instala ambos.

Transcrição de vídeo com prioridade a legendas e exportação SRT, controlos de tarefas canceláveis, e recurso a faster-whisper large-v3 quando não existem legendas.

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.