xby-awslabs-aws-diagram
Run the following command in DeepSeek Harness:
dsh plugin install xby-skill/xby-awslabs-aws-diagram
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install xby-skill/xby-awslabs-aws-diagram in your terminal to install; the source repository is at https://github.com/xby-skill/xby-awslabs-aws-diagram
About this plugin
The slowest part of drawing an architecture diagram is rarely the thinking itself — it is dragging, aligning, hunting for icons, and tuning connection styles inside a drawing tool. xby-awslabs-aws-diagram moves that work directly into the DeepSeek Harness chat: describe your system in natural language, and the plugin renders a PNG via the diagrams Python DSL, eliminating back-and-forth with IDEs or online editors.
The plugin ships a full auxiliary toolchain. list_icons lets you filter icons layer by layer by provider and service so you never load the entire catalog at once; get_diagram_examples provides templates across seven categories — AWS, Kubernetes, sequence, flow, class, on-premises, and custom — so you can study syntax before writing your own; generate_diagram executes the code and returns the PNG file path, supporting Cluster grouping and Edge styling (colors, dashed lines) so complex topologies stay readable.
If you regularly demo AWS service orchestration or Kubernetes deployment topology in a Codespace, or need quick turnaround figures for technical docs and design reviews, this plugin shortens the path from idea to finished image dramatically — the chat becomes the canvas, and a few turns yield an architecture diagram ready to drop into your document.
Use Cases
- Drop an AWS service architecture diagram into a design doc or review deck
- Visualize microservice deployment and cluster topology with a K8s diagram
- Generate a sequence or flow diagram for a design walkthrough in a few chat turns
Best For
- Technical writers and architects who produce architecture diagrams regularly
- DevOps and SRE engineers collaborating in GitHub Codespace
- Product teams preparing customer demos or internal design reviews
Related Plugins
A unified suite combining hot runtime injection, task-aware thinking-mode routing, and a graded session protocol with red-team gates to sustain model diligence across long-horizon inference.
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.