Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From ai-infra-auto-driven-skills
Returns public original architecture diagrams for LLM, VLM, MoE, diffusion, and OCR model families. Invoke when a user requests a model structure chart or diagram for specific models like DeepSeek, Qwen, or Hunyuan.
npx claudepluginhub bbuf/ai-infra-auto-driven-skills --plugin ai-infra-auto-driven-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/ai-infra-auto-driven-skills:model-architecture-diagramThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Return only public original diagrams indexed by this skill.
Creates publication-quality scientific diagrams (neural architectures, pathways, flowcharts) using Nano Banana 2 AI with Gemini quality review and smart iterative refinement. Only regenerates if below quality threshold.
Generates interactive HTML architecture diagrams with animated step-by-step flows, mode toggles, and side panel details. For service maps, CI/CD pipelines, data flows, and workshop diagrams.
Generates Excalidraw diagram JSON files that argue visually, not just display information. Use for workflows, architectures, or concepts.
Share bugs, ideas, or general feedback.
Return only public original diagrams indexed by this skill.
python3 skills/model-architecture-diagram/scripts/model_architecture_diagram.py "<model name>"
kind: existing, return the raw image Markdown it prints and preserve the source attribution line.kind: no_match, tell the user that no public original architecture diagram is indexed for that model.Use references/diagram-index.json as the source of truth. It stores raw GitHub image URLs from:
datawhalechina/self-llmCalvinXKY/InfraTechTongyi-MAI/Z-ImageWan-Video/Wan2.1Wan-Video/Wan2.2Tencent-Hunyuan/HunyuanVideoTencent-Hunyuan/Hunyuan3D-2brayevalerien/Flux.1-Architecture-DiagramPrefer detailed implementation, cookbook, or architecture-card diagrams over paper figures. Good sources show module boundaries, dataflow, MoE / attention / cache paths, or model-specific runtime structure rather than only a high-level paper overview. Official repository diagrams and curated implementation diagrams are first choice; paper figures are fallback only when no more detailed public original diagram is indexed.
Do not copy remote image binaries into the skill. Return the raw GitHub URLs so the chat renderer can display the original image.
For a direct match, show the original image. Good direct matches include:
If multiple diagrams match, show all high-confidence matches up to the resolver's default limit. For example, DeepSeek V3 may return the full architecture plus MLA MHA/MQA diagrams.
Do not commit the sgl-cookbook-model-architecture-images/ gallery into the repository. The public-original image set is hosted as a GitHub Release asset and indexed by a GitHub issue.
Current hosted artifact:
sha256:ea432081849a250429d3d1ecf246e267c5cc42f989aaf4b9ca695b581e7fa50fThe artifact contains 44 public original diagram image files from the indexed upstream repositories, plus a lightweight index.html, index.md, manifest.json, HTML contact sheet, and architecture-audit.md.
To inspect the gallery locally:
curl -L -o /tmp/sgl-cookbook-model-architecture-images-2026-05-02.zip \
https://github.com/BBuf/AI-Infra-Auto-Driven-SKILLS/releases/download/sgl-cookbook-architecture-images-2026-05-02/sgl-cookbook-model-architecture-images-2026-05-02.zip
unzip -q /tmp/sgl-cookbook-model-architecture-images-2026-05-02.zip -d /tmp
open /tmp/sgl-cookbook-model-architecture-images/index.html
List known original diagram aliases:
python3 skills/model-architecture-diagram/scripts/model_architecture_diagram.py --list-known
Emit JSON for automation:
python3 skills/model-architecture-diagram/scripts/model_architecture_diagram.py "GLM-5" --format json
references/diagram-index.json: original diagram link index and aliases.references/source-notes.md: audited source repositories and local cache paths.