MemDreamer 是做什麼的？
透過分層圖記憶和智能檢索機制，將感知與推理分離，從而理解長影片。
- 來源：https://github.com/Free-Soul/MemDreamer
- GitHub 星數：0
- 最後推送：2026-06-16T08:27:45Z
- 由 Awesome Skills 每日技能獵人於 2026-06-16 新增。
通過分層圖記憶和智能檢索機制，將感知與推理分離，從而理解長影片。
MemDreamer 是一個專門設計用來理解長影片的先進 AI 技能。它通過將感知（perception）與推理（reasoning）分離，並採用分層圖記憶（hierarchical graph memory）和智能檢索（agentic retrieval）機制，有效解決傳統模型在處理長時間影片時常面臨的上下文遺忘與計算效率問題。該技能支援在如 Claude Code、Cursor 等 AI agent 平台上使用，開發者可以藉由它對長影片內容進行結構化分析、摘要生成或問答，顯著提升影片理解的精準度與可擴展性。其工作流程包括將影片分割為多個時空片段，建立分層記憶圖，並透過智能檢索動態擷取相關資訊來支援推理，適合應用於監控分析、教學影片總結、多模態內容管理等場景。
npx skills add Free-Soul/MemDreamer透過分層圖記憶和智能檢索機制，將感知與推理分離，從而理解長影片。
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.