Plugins
Durchsuche, filtere und installiere DeepSeek-Harness-Plugins.
7 Plugins gefunden
dsh-video-understand
ilps2/dsh-video-understand
Kostengünstiges Video-Verständnis-Tool: Ein video_understand-Tool wandelt einen Bilibili-Link / BV / ein lokales Video in eine AVIS-Informationsschicht (ASR + Szenenstruktur + Objekt-Tracking + YOLO-Labels) um und liefert Zusammenfassung + Q&A. Fragegesteuertes dynamisches Routing über Ebenen hinweg (L0 ASR / L1 Objekt-Tracking / L2 Keyframe-VLM), Wiederverwendung der semantischen Schicht für Wiederholungsfragen, Budgetobergrenze pro Frage. Python-Engine: Die Kernschicht benötigt faster-whisper / opencv / yt-dlp (~200-300MB); die optionale semantische Schicht fügt ~2GB torch / transformers / ultralytics hinzu. Ein mitgeliefertes doctor --fix richtet das venv ein und installiert beide.
dsh-watch-video
zeshuochen/dsh-watch-video
Auf Untertitel ausgerichtete Transkription von Videos mit SRT-Export, abbrechbaren Steuerelementen für den Auftrag und einem Rückgriff auf faster-whisper large-v3, wenn keine Untertitel verfügbar sind.
dsh-bili-video-summary
zz12hui/dsh-bili-video-summary
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.
dsh-bilibili-video-summary
aurum807/dsh-bilibili-video-summary
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.
dsh-bilibili-subtitles
chenfan2/dsh-bilibili-subtitles
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.
dsh-video-eyes
bw741/dsh-video-eyes
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).
dsh-video-understand
zeshuochen/dsh-video-understand
Subtitle-first video transcription and deterministic extractive Markdown summaries, with a faster-whisper large-v3 fallback when subtitles are unavailable.