Loading...
Loading...
Found 5 Skills
Cosmos-Reason2-8B video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video question-answering models, fine-tuning Cosmos-Reason2 with SFT, or working with Cosmos-RL. Trigger phrases include "fine-tune Cosmos-Reason", "Cosmos-RL SFT", "video QA fine-tune", "Cosmos-Reason2-8B training".
Watch, analyze, summarize, or answer questions about a video — a pasted link (YouTube, TikTok, Vimeo, Loom, X, Twitch, most sites) or a local video file (.mp4, .mov, .mkv, .webm, .avi). Use this whenever the user shares a video link or file and asks anything about its contents — what's in it, what happens, what's said, what's on screen, a summary, a transcript, or a specific moment — and whenever they say "watch this", "watch the video", "what's in this video", or similar, even if they never type /watch. Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video. With a question, evidence mode retrieves only the relevant chapters, numeric facts, and on-screen moments instead of sampling the whole timeline.
Render, inspect, test, and export high-performance WebGPU video and frame grids with the gitframes headless engine. Use when verifying compositions, diagnosing blank frames, profiling GPU pipelines, running visual frame grids, or exporting final MP4 video in gitframes.
Make clean, high-taste motion graphics videos (explainers, product promos, tutorials, social reels) with Remotion. Use when the user asks for a motion graphics video, an animated explainer, a promo or launch video, a reel/short with kinetic text, or wants to copy the style of a reference video. Covers research, script, voiceover timing, original music and sound effects, a ready Remotion template with a locked style, automatic overlap QA, and final render.
Cria vídeos de motion design de nível de estúdio por código (Remotion/React), com trilha licenciada, SFX sincronizados, voz opcional (ElevenLabs ou modelo TTS local escolhido pelo hardware) e gates automáticos de lint e QA antes da entrega. Use quando pedirem motion design, motion graphics, vídeo animado, explainer, vídeo de produto ou lançamento, reel ou TikTok animado, tipografia cinética, logo animado, animação de UI, loop, narração ou voiceover para vídeo, ou técnicas como keyframing, zoom in e zoom out, motion smooth, morphing, rigging, frame a frame, cel animation, stop motion, rotoscopia, motion tracking, match moving, compositing, motion 3D, speed ramp, match cut, overshoot, parallax e transições. Also for animated video, kinetic typography, product launch video, explainer with voiceover, text to speech narration.