skills.rest
DaryLu0v0
DaryLu0v0COMMUNITY
Explore all skills by this author →
GitHub

ML-Assisted Inverse Design

Generate and validate ML-assisted surrogates for CST-based inverse design.

Updated Aug 27, 2026
Search Tags:#design-agent#cst#surrogate-model#inverse-design#neural-adjoint#aide
One-click install
npx skills add https://github.com/DaryLu0v0/MetaClaw --skill ml-assisted-inverse-design
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ML-Assisted Inverse Design
Source: https://github.com/DaryLu0v0/MetaClaw/tree/main/skills/ml-design
Command: npx skills add https://github.com/DaryLu0v0/MetaClaw --skill ml-assisted-inverse-design

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

When CST Tuning stalls, this skill accelerates discovery by auto-generating surrogate models and guiding inverse design with ML, reducing manual iteration.

Core Features & Use Cases

  • ML-assisted surrogate training: uses AIDE-enabled design pipelines to auto-create and refine surrogate models.
  • Neural Adjoint inverse design: runs neural adjoint optimization to match target spectra with CST simulations for final validation.
  • End-to-end workflow: from seed data augmentation to validated designs and reports.

Quick Start

Run the ML-assisted inverse design from a CST project to augment seed data, auto-train a surrogate, and validate top designs with CST simulations.

Frequently Asked Questions about ML-Assisted Inverse Design

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

FAQPage Schema
How do I automate CST inverse design when parameter tuning plateaus?▼

Automate CST inverse design by using ML-assisted surrogates to guide neural adjoint optimization, matching target spectra and validating designs with CST simulations to overcome manual tuning plateaus.

What is neural adjoint optimization for matching target spectra?▼

Neural adjoint optimization is an ML technique that uses trained surrogate models to guide inverse design by matching target spectra, which are then validated with CST simulations.

Do I need a specific conda environment to run ML-assisted surrogate training?▼

Yes, ML-assisted surrogate training requires a configured conda environment with aideml and the CST Python API installed to execute the design pipelines and validate simulations.

How to start an end-to-end ML inverse design workflow from a CST project?▼

Start the end-to-end workflow by providing target spectra, seed data, and CST templates to augment data, auto-train a surrogate, and validate top designs with CST simulations.

Can I use AIDE to auto-create surrogate models for CST simulations?▼

Yes, you can use AIDE-enabled design pipelines to auto-create and refine ML surrogate models for CST simulations, accelerating discovery when manual tuning stalls.

What are the limitations of using ML surrogates for inverse design?▼

ML surrogates for inverse design require seed data, CST templates, and target spectra, relying on final CST simulations for validation to ensure the ML-guided designs match actual performance.

Related Skills

Explore More Data & Analytics Skills→
paleopaleo
84

documentation-authoring

Create SKILL.md entries with frontmatter and update AGENTS.md documentation.

Community
Basic
Rafael-RuedaRafael-Rueda

Generate project artifact

Generate project artifacts following established patterns via the /generate command.

Community
Basic
LiorZLiorZ
2

invrotzyme

Enumerate clash-free catalytic rotamer assemblies from Rosetta CST files into PDB outputs.

Community
Advanced
qinyan-aiqinyan-ai
48

pennylane

Build and train hybrid quantum-classical models with automatic differentiation across devices.

Community
Advanced