Agent Skills for Claude Code — video understanding (grid-packed frames + transcript, ~7x cheaper than frame-by-frame) and headless, API-key-free image generation. Install: npx skills add andrewii23/ii23-skills
This repository also configures its own agents. See what ii23-skills tells them →
Skill Codex
Generate an image from a text prompt using one of two local headless backends - GPT (Codex CLI, under your ChatGPT login) or Gemini (Antigravity agy CLI, under your Google login). Both are API-key-free with no per-image billing. Use whenever the user wants to create, generate, draw, make, or render a picture…
Skill Claude CodeCodex
Watch and fully understand any video — local file or URL, a 10-second clip or a full-length film, with or without speech — by indexing every shot (motion, light, sound hits, silences, on-screen text), packing one timestamp-labelled frame per shot into grid images, and pairing them with a timestamped transcript. Use…