skills.rest
caidish
caidishCOMMUNITY
Explore all skills by this author →
GitHub

nanodevice_e2e_design

Coordinate seven-step nanodevice design workflows in KLayout using MCP tools.

32|6|Updated Mar 8, 2026
Search Tags:#routing#mcp#orchestration#design-evaluation#device-agnostic#klayout#nanodevice
One-click install
npx skills add https://github.com/caidish/KlayoutClaw --skill nanodevice-e2e-design
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nanodevice_e2e_design
Source: https://github.com/caidish/KlayoutClaw/tree/main/skills/nanodevice_e2e_design
Command: npx skills add https://github.com/caidish/KlayoutClaw --skill nanodevice-e2e-design

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Orchestrate end-to-end nanodevice design from user query through optional flake detection, material analysis, device geometry creation, routing, evaluation, and save. Device-agnostic methodology -- the agent derives physics rules from device type and available materials.

Core Features & Use Cases

  • The agent coordinates a seven-step pipeline (QUERY, PREPARE, ANALYZE, DESIGN, ROUTE, EVALUATE, SAVE) with gate checks and up to two retries per step.
  • Pure-text orchestrator that uses MCP tools and sub-skills at each step, without hard-coding device specifics.
  • Automatically derives device physics rules from context and materials, enabling device-agnostic workflows in KLayout.

Quick Start

Prompt the agent to start the end-to-end nanodevice design workflow for a graphene region and a Hall-bar device.

Frequently Asked Questions about nanodevice_e2e_design

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate end-to-end nanodevice design in KLayout?▼

Nanodevice design in KLayout is automated by orchestrating a seven-step pipeline (QUERY, PREPARE, ANALYZE, DESIGN, ROUTE, EVALUATE, SAVE) that coordinates sub-skills and MCP tools to generate a final GDS layout.

Can I create a device-agnostic workflow for nanodevice geometry and routing?▼

Yes, a device-agnostic workflow is possible because the orchestrator automatically derives physics rules from the device type and available materials, rather than hard-coding device specifics into the routing and geometry steps.

What's the best way to run flake detection and material analysis before layout routing?▼

Flake detection and material analysis are executed as optional preparatory steps within the orchestration pipeline, using MCP tools to extract context before proceeding to device geometry creation and auto routing.

How does design evaluation work in an automated nanodevice pipeline?▼

Design evaluation uses the evaluate_design MCP tool during the EVALUATE step, applying gate conditions with up to two retries per step to validate the nanodevice layout before saving the GDS file.

Do I need to manually validate pixel size and layout info when saving a GDS file?▼

No, manual validation is unnecessary because the orchestrator leverages validate_pixel_size and get_layout_info MCP tools during the pipeline, automatically ensuring the layout is correct before saving the final GDS and summary.

Related Skills

Explore More Design & Creative Skills→
caidishcaidish
32

nanodevice_flakedetect_commit

Insert detected flake polygons from traces.json into KLayout as GDS geometry.

Community
Intermediate
ShenShan123ShenShan123
41

signoff-loop

Automate EDA signoff from RTL to GDS with DRC, LVS, and RCX verification.

Community
Advanced
caidishcaidish
32

klayoutclaw:geometry

Draw and place rectangles, polygons, paths, cells, and cell instances in KLayout via MCP scripts.

Community
Intermediate
mcauduro0mcauduro0
1

ln-520-test-planner

Orchestrate multi-phase test planning by delegating research, manual testing, and automated test planning to sub-agents.

Community
Advanced