Инструменты

Browser Use's video editing skill: put raw footage in a folder and chat with Claude Code or Codex to get a finished cut, with filler words and pauses removed, color grading, burned-in subtitles, animations and per-cut self-checks. Needs ffmpeg, Python (uv) and an ElevenLabs API key.

Have an agent produce high-fidelity clickable prototypes, editable slides, timeline animations (exportable to MP4/GIF) and infographics in HTML from one sentence. Proposes three design directions first and includes a five-dimension design review. By Huashu, MIT licensed.

Content creation plugin by Baoyu (JimLiu): infographics, article illustrations, covers, slide decks and translation, plus Xiaohongshu image cards and publishing to WeChat Official Accounts, Weibo and X. Needs Node.js; image generation needs an OpenAI, Google or Tongyi Wanxiang API key.

Baoyu's (JimLiu) content creation skills: infographics, covers, article illustrations, slide decks, comics and translation, plus Xiaohongshu cards and publishing to WeChat, Weibo and X. Needs Node.js, bun and an image model API key; some skills rely on Chrome automation or unofficial APIs.

CLI and library for evaluating and red-teaming LLM apps: compare prompts and model outputs in bulk, scan for security vulnerabilities and plug into CI/CD, with evals running locally. Now part of OpenAI and still open source under MIT.

Removes image backgrounds with one command: single images, whole folders or watched directories, mask-only output and switchable models like U2Net and SAM. Can also run as an HTTP server or process video frames with FFmpeg. Default models run locally.

Fast speech transcription built on faster-whisper, with word-level timestamps and speaker diarization, suited to meeting notes and subtitles. Diarization needs a Hugging Face token; GPU acceleration needs CUDA.

Veteran open-source video transcoder. HandBrakeCLI uses built-in presets to batch-compress screen recordings, course videos and footage or convert them to MP4, MKV or WebM for phones and the web. Free, runs locally, installable on macOS via Homebrew.

ML-based video upscaling and frame interpolation using Real-ESRGAN, Real-CUGAN, RIFE and other models to upscale old low-res video or raise frame rates; video2x handles one video per run and is scriptable. Needs a Vulkan GPU; Windows, Linux and Docker builds, no native macOS.

Offline speech transcription and translation based on Whisper; audio never leaves your machine. buzz add exports lectures, interviews and meeting recordings to TXT, SRT or VTT. pip install needs Python 3.12 and FFmpeg; a desktop app is also available. Check transcripts manually.

Manages BigQuery datasets, tables and jobs with the bq and gcloud CLIs, runs SQL queries and loads data, with references for client libraries, MCP and Terraform. Google's official skill; requires a Google Cloud project.

Google's official skill that queries account data through the Google Ads MCP server to diagnose conversion drops, falling leads and impression share lost to bids, budgets or ad rank. Needs a Google Ads account, API credentials (developer token and OAuth) and Python 3.12.

Google's official skill library, focused on Google Cloud: 100+ skills for gcloud, Cloud Run, GKE, BigQuery, IAM, monitoring and logging, and the Well-Architected Framework, plus Ads and Analytics.

Google's official skill library and plugin marketplace: nearly 150 skills focused on Google Cloud (GKE, BigQuery, Cloud Run, IAM and more), plus 17 product plugins pairing skills with MCP for Cloud SQL, Spanner, AlloyDB, BigQuery, GCS and others.

Industrial-grade open-source speech recognition toolkit from Alibaba's ModelScope, with an agent-friendly funasr command that turns audio into text, JSON or SRT subtitles in one step, with speaker diarization and timestamps. Strong on Chinese. Requires PyTorch.

Official MCP from the FunASR project: transcribes audio files locally with the SenseVoice model, supporting Mandarin, Cantonese, English, Japanese and Korean, with optional segment timestamps. Local inference needs no API key and audio stays on your machine. Docker image available.

Command-line tool for bulk-downloading galleries and posts from many image hosts and social platforms, with flexible file naming and config, and yt-dlp integration for video. Main development has moved to Codeberg; the GitHub repo stays in sync.

AI2's tool for converting PDFs and scans to Markdown with a vision LLM, handling equations, tables, handwriting and multi-column layouts, suited to bulk digitizing papers and archives. Local runs need an NVIDIA GPU with 12GB+ VRAM; otherwise use a paid OpenAI-compatible remote endpoint.

Turns a project directory or website URL into a roughly 20-second launch video: gathers copy, colors and real UI from the code or live site, storyboards it, and builds visuals, music and the render with tools already on the machine, delivering an MP4, poster frame and share copy.

Turns the current project into a 15-25 second shareable launch video: reads the code, plans a concept and storyboard, hands a composition brief to Hyperframes to render with music and sound effects, and writes share copy. Supports tone, format and duration options plus optional Kokoro voiceover.

All-in-one video translation and dubbing: chains speech recognition, subtitle translation, multi-speaker AI voiceover and audio-video muxing, with local or online models like Faster-Whisper, DeepSeek and Edge-TTS. cli.py supports headless batch runs. Needs FFmpeg.

Browser control from the browser-use team: an editable CDP connection lets agents drive the Chrome you are already using, writing missing helper functions as they go and keeping them for reuse. Also offers an MCP server. Allow remote debugging in Chrome on first use.

Lets Claude Code push ML research forward unattended: literature review, topic selection, experiment deployment, cross-model review loops and paper writing through rebuttal, in 80+ skills. Codex acts as the independent reviewer by default; other model pairings work too.

Context and harness engineering skills: context fundamentals, degradation diagnosis and compression, multi-agent architectures, memory systems, tool design, LLM-as-judge evaluation and self-improvement loops. Focused on principles and design patterns, not tied to any agent platform.