#ffmpeg

Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.

Don't write a bug report — record it. Local MCP: screen recording → transcript, frames, OCR, wall-clock evidence for coding agents.

An open-source tool to extract subtitles (.srt/.vtt) from Douyin video links via OpenAI-compatible ASR APIs. Supports batch processing and 1-click Docker deployment.

Routed Media OS 2026: 96 AI Skills, 13 Modes & 7 Agents for FFmpeg, OBS, DeckLink & Dolby Vision

Turn any video into a self-contained, replayable slide deck or notes — a portable agent skill. Every frame & quote deep-links back to the most relevant moment in the source.

Drop any video file. Get a short-form cut with no timeline scrubbing. Claude transcribes, scores and renders — you tick the candidates.

Generates timestamped descriptions of GoPro / Insta360 footage using Claude AI. Built for editors who need a map of the material before they start cutting.

AI-first vertical (9:16) video editor engine — the LLM plans a declarative Timeline IR; a deterministic FFmpeg renderer executes. Drivable from Claude Code via MCP.

让TA看到这个世界

DeepSeek Harness 视频处理插件：ffmpeg_probe/cut/concat/encode/subtitle/extract/gif 七工具，走官方 subprocess 服务、argv 数组无 shell 注入、零运行时依赖；纯 Node 全平台。· Video processing tools for DeepSeek Harness agents.

Agent skills for pi / Claude Code / Codex — including eu-ai-label, which burns the official EU AI-content labels (AI Act Art. 50) into images and videos

Record narrated, sync-verified teaching videos of a real Claude Code TUI session — deterministic terminal + explainshell panel + voice that leads the typing, with on-screen AskUserQuestion handling. MIT.

Record once. Claude decides the cut. FFmpeg executes it. An AI co-producer for video, as a Claude Code plugin.

🎬 A powerful multimodal AI video summarizer. Supports YouTube/Bilibili/Local videos, smart frame extraction, Whisper transcription, and generates structured summaries via OpenAI/Qwen/Claude. (AI 视频摘要提取神器)

🚀 AI-Powered Multi-Platform Social Media Automation Engine — Schedule, generate & auto-publish to Facebook, YouTube & TikTok from one dashboard. Built with NestJS + Next.js + Prisma + BullMQ + 3 AI Providers (Gemini/OpenAI/Claude)

Diagnose AI-generated art by measuring the output instead of rewriting the prompt — then get it onto a real app surface.

GPU-accelerated Manim workspace + 14 Agent Skills + a 5,523-symbol offline API index, so coding agents can drive Manim as an API instead of guessing. NVENC encoding via a PyAV patch, ManimCE 0.21 and ManimGL/wgpu side by side, reproducible benchmarks, and verified corrections to widely-repeated docs.

Video background removal skill for Codex, Claude Code, and agents. Pick the export format, get ffmpeg recipes, and route AI matting to RemoveVideoBG (removevideobg.com).

开源 Agent Skill：从本地、B站或抖音视频指定片段生成完整画面与去重字幕拼图。

Claude Code skill: turn a walkthrough video into a priced inventory. Frame extraction, rotated zoom crops to read spines and labels, resale-price research, Markdown + PDF report.

Turn any script into a cinematic AI video. Open-source desktop app — AI scene generation, image creation, voiceovers, background music, and FFmpeg rendering. Runs locally. No subscriptions.

Fully automated YouTube publishing on AWS: analyze videos with Claude on Bedrock, extract meaningful Shorts, generate English metadata, publish on schedule.

Telegram bot & CLI that transcribes a video/audio file and returns translated subtitles — .srt or burned-in video. Whisper (local or API) for transcription; OpenAI, DeepSeek, or Gemini for translation. Right-to-left aware; deploys with Docker/Kamal.