Give Claude smarter eyes for video. /see watches videos with scene-aware frame extraction and optional OCR; /skillgen scaffolds Claude Code skills from tutorial videos.
Not in a marketplace yet, so it loads for one session with --plugin-dir.
Plugin claude-eyes in jain777/claude-eyes. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
seeWatch a video (URL or local path) and answer questions about it. Use when the user shares a video URL, asks Claude to look at a video file, or asks about content in a video. Smart scene-aware frame extraction + optional OCR keep token cost low.
skillgenWatch a tutorial or demo video and scaffold a runnable Claude Code skill from it. Use when the user wants to turn a how-to video, screencast, or tool demo into an invocable skill or plugin.
"${CLAUDE_PLUGIN_ROOT}"/scripts/setup.py --check --quiet || true
Recommended: all published HyperFrames skills in one versioned bundle. Create and render videos from HTML: the contract, film, captions, overlays, motion and look references, the CLI, the registry, media, Figma, slideshows and Remotion ports.
22 skills
53 marketing skills for technical marketers and founders: CRO, copywriting, cold email, prospecting, SEO, AI SEO, paid ads, SMS, ad creative, video production, image generation, co-marketing, churn prevention, pricing, referrals, revenue operations, sales enablement, customer research, site architecture, comprehensive AARRR-structured marketing plans, public relations and earned media, offer design, event marketing and webinars, and more
53 skills
HyperFrames by HeyGen. Write HTML, render video. Compositions, GSAP and runtime adapter animations, captions, voiceovers, audio-reactive visuals, and website-to-video capture for HyperFrames.
34 skills
Eval-gated LLM fine-tuning lifecycle (LoRA/QLoRA, DPO, GRPO/RLVR, vision SFT, quantized export). Use when fine-tuning an open-weights model end-to-end: building the eval harness first, selecting method and model, preparing data, training with Unsloth or TRL, gating checkpoints, and exporting GGUF/FP8.
10 skills · 2 commands · 3 agents
Plan, build, and debug Zoom integrations across REST APIs, Meeting SDK, Video SDK, webhooks, bots, and MCP workflows. Search meetings, retrieve recordings, access transcripts, and design AI-powered Zoom experiences.
44 skills · 3 MCP servers
Create polished demo videos from screenshots and scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts with story structure, scene design system, and narration guidance.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.