qingyu321

qingyu321/Little-Claude

Skill Claude CodeCodex

Read, describe, or extract text (OCR) from an image — screenshots, photos, charts, diagrams, UI mockups, scanned documents — by delegating to an external vision-capable model through an OpenAI-compatible endpoint. Use this skill whenever the user asks to look at, view, describe, recognize, OCR, or answer questions…

qingyu321/Little-Claude

Skill Claude CodeCodex needs its repo

Analyze authorized video content from a local video file, a public direct HTTP(S) video URL, or—with --allow-platform—a single public video on a platform page (e.g. Bilibili/YouTube watch links, fetched via yt-dlp without login or cookies). Use this skill whenever the user asks to read, understand, summarize…