Enhance Difflow with AI: Add Custom Unit Operations

Enhance Difflow with AI: Add Custom Unit Operations

This AI agent skill enables developers to add a new unit operation to the Difflow codebase, supporting either core or dynamic configurations, including plugins such as Difflow Refinery or Difflow CC. Adhering to project conventions, it features a ParamsMixin params dataclass, JAX-only __call__, gradient checks, documentation, and catalog registration.

What this skill does

• Introduces a new unit operation, aligning with Difflow’s existing architecture by following project-specific naming and placement conventions.
• Prompts users to specify the physics (balances, equations) of the unit for accurate implementation.
• Updates necessary imports and exports within Difflow’s core or plugin structures.
• Implements unit tests to ensure operational integrity, including gradient checks for verification.
• Integrates the new operation into the documentation and catalog for seamless developer access.

Who it is for

This skill is intended for developers and teams using AI coding agents like Claude Code, Cursor, or Codex, who are involved in enhancing and contributing to the Difflow project. Specifically, those tasked with developing new unit operations in process simulation applications will find this skill beneficial.

Use cases

• Adding a custom reactor, column, separator, or any unit operation to the Difflow core or plugin.
• Contributing to Difflow with new simulation modules following precise project guidelines.
• Integrating domain-specific equations and balances into Difflow’s simulation environment.

Technical details

• Utilizes ParamsMixin for data structure consistency.
• Employs JAX for numerical operations and __call__ implementations.
• Incorporates unit testing with gradient checks to verify operation functionality.
• Ensures updates align with Difflow’s .py files and CLAUDE.md directives.

Source & Licence

This package is built on open-source work published by jkitchin (jkitchin/differentiable-flowsheets) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.