DeepSeek · Diagrams

Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images.

xiincs/claude-code-vision-skill

Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.

BBuf/AI-Infra-Auto-Driven-SKILLS

Analyze one or more code repositories and produce a Normify module-tree structure database (per-module Markdown files with strict YAML frontmatter), then validate, build, and render it into an…

yan-mc/dsh-normify

Draw Sebastian-Raschka-gallery-style TikZ architecture diagrams for any HuggingFace decoder-only LLM, with per-block parameter formulas and concrete numbers.

yzlnew/infra-skills