MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
ClipKit — the open video runtime and protocol.
Hosted by authorApache-2.0★ 19No key
InternVideo2-CLIP L14 (TAO video_clip) for video-text retrieval, zero-shot classification, embedding extraction, LoRA fine-tuning, ONNX export, and TensorRT deployment. Use when the user asks to "fine
OfficialSkillApache-2.0★ 3.6k in collectionNo key
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot clas
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Give 3D AI agents a voice and a face from any MCP client — text-to-speech, speech-to-text, audio-to-face lipsync (ARKit blendshapes), and the motion-capture clip library. Read-only over the live three
Node.jsApache-2.0★ 10No key
Compose the edit, not the pixels. A song -> its music video, vertical cuts, covers and release copy: cut from your own footage, processed frame by frame, or drawn as a canvas piece from nothing but th
SkillApache-2.0★ 1Few starsNo key
Your agent cannot listen to audio. harken fixes that — locally. MCP server + CLI, one 13 MB binary, fully offline: no Python, no ffmpeg, no API key.
SkillApache-2.0★ 13No key
Index a video once, query it cheaply with any LLM. Open model-free video context format (.vctx) + MCP server + accuracy-per-dollar benchmark.
PythonApache-2.0★ 1Few starsNo key
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
MCP server for FilmCraft on Windows, macOS and Linux: split, trim, effects, Lumetri looks, titles, speed, transitions, export and editable timelines (fcproj/OTIO/FCPXML/XML/EDL/AAF)
Node.jsApache-2.0Few starsNo key
Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint. Use when a workflow needs embeddings before nearest-neighb
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Remotion renderer for json-render that turns JSON timeline specs into videos. Use when working with @json-render/remotion, building video compositions from JSON, creating video catalogs, or rendering
OfficialSkillApache-2.0★ 19k in collectionNo key
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use when training, evaluating, exporting, or
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Agent skill for Ableton Live 12: the Arrangement and Session views; clips and the Clip View; audio warping and tempo; MIDI and MPE editing; MIDI tools; converting audio to MIDI; comping; stem separati
SkillApache-2.0★ 4Few starsNo key
Claude Opus 视频效果的稳定平替：用 Claude 创作出片一次，蒸馏成视频配方，其他模型按配方复刻出类似效果。
SkillApache-2.0★ 84No key
Transcribing audio to generate captions in Remotion
OfficialInstructionsApache-2.0★ 19k in collectionNo key
Local, zero-network CLI scoring AI short-drama clips for character-consistency drift and physics-plausibility flags
PythonApache-2.0Few starsNo key
SkillApache-2.0Few starsNo key
Agent Desktop gives any agent reliable computer use on the desktop. Built with Rust, it sees any app's real UI structure through OS accessibility trees and operates it — refs stay stable and actions s
SkillApache-2.0★ 1.8kNo key
Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use vss-ask-video), live captioning (use vss-
OfficialSkillApache-2.0★ 3.6k in collectionNo key
28 Claude Skills for AI video production — kkirikkiri + pumasi dual-team architecture
SkillApache-2.0★ 2Few starsNo key
FireRed-OpenStoryline is an AI video editing agent that transforms manual editing into intention-driven directing through natural language interaction, LLM-powered planning, and precise tool orchestra
SkillApache-2.0★ 3.6kNo key
Who stands behind it
