What is neqsim-unisim-reader?

A converter for Honeywell UniSim Design and Aspen HYSYS simulation files in .usc format. It reads the model through Windows automation and recreates it as a NeqSim process model or code.

Use it when transferring fluid packages, components, streams, and flowsheet data from UniSim or HYSYS into NeqSim, or when checking results between the two models.

It reduces the effort of rebuilding an existing process simulation by hand and supports comparison between the original model and the recreated one.

How equinor/neqsim configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to equinor/neqsim. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/equinor/neqsim/master/.github/skills/neqsim-unisim-reader/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/equinor/neqsim

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-unisim-reader/github.svg)](https://agentmods.dev/skills/equinor/neqsim/neqsim-unisim-reader)

Your own site

<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-unisim-reader"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-unisim-reader/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-unisim-reader"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-unisim-reader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 23,932 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium analysis-evasion · line 1
Suspicious Unicode normalization or mixed-script content

Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00111	$0.23932
Opus 5	$0.00056	$0.11966
Sonnet 5	$0.00022	$0.04786
Haiku 4.5	$0.00011	$0.02393

Measured yesterday against content hash a25e9dec3bdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

neqsim-unisim-reader scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/neqsim-unisim-reader/SKILL.md · 1,938 lines

How it starts

The opening of the file, as written. The whole thing — 1,938 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UniSim Design / HYSYS → NeqSim Conversion Skill

Convert Honeywell UniSim Design (.usc) files into NeqSim ProcessSystem or ProcessModule structures using Windows COM automation.

Prerequisites

Windows only — UniSim Design must be installed (COM server)
Python packages: pywin32 (pip install pywin32)
UniSim Design R510+ (R460+ should also work)
COM ProgID: UnisimDesign.Application

Core Module

The devtools/unisim_reader.py module provides three main classes:

Class	Purpose
`UniSimReader`	Opens .usc files via COM, extracts all data
`UniSimToNeqSim`	Converts extracted model to NeqSim JSON builder format or standalone Python code
`UniSimComparator`	Compares UniSim vs NeqSim results for verification

Supporting tools:

Tool	Purpose
`devtools/unisim_batch_check.py`	Convert a whole corpus, one subprocess per case; timings, unmapped types, warnings, compile + undefined-name checks
`devtools/unisim_run_generated.py`	Execute every generated model in its own subprocess and report how far it gets
`devtools/unisim_probe_ops.py`	Dump the readable COM properties of an operation type
`devtools/unisim_probe_column.py`	Dump a column's attached streams and `ColumnFlowsheet` internals
`devtools/test_unisim_outputs.py`	Pure-Python regression tests (no COM needed)

1. UniSim COM Object Model

UniSim's COM automation exposes the following hierarchy:

Application
├── SimulationCases
│   └── Case
│       ├── Solver (CanSolve, Converge)
│       ├── BasisManager
│       │   └── FluidPackages[]
│       │       ├── name, PropertyPackageName
│       │       └── Components[]
│       │           └── name
│       └── Flowsheet (main)
│           ├── MaterialStreams[]
│           │   ├── name
│           │   ├── Temperature.GetValue("C")
│           │   ├── Pressure.GetValue("bar")
│           │   ├── MassFlow.GetValue("kg/h")
│           │   ├── MolarFlow.GetValue("kgmole/h")
│           │   ├── MassDensity.GetValue("kg/m3")
│           │   ├── MolecularWeight.GetValue()
│           │   ├── VapourFraction.GetValue()
│           │   ├── MassEnthalpy.GetValue("kJ/kg")
│           │   ├── ComponentMolarFraction.GetValues()
│           │   └── ComponentMolarFraction.SetValues([...])
│           ├── EnergyStreams[]
│           │   ├── name
│           │   └── HeatFlow.GetValue("kW")
│           ├── Operations[]
│           │   ├── name, TypeName
│           │   ├── Feeds[] (multi-feed ops: mixers, separators)
│           │   ├── Products[] (multi-product ops: tee/splitter)
│           │   ├── FeedStream / ProductStream (single-stream ops)
│           │   ├── Product (singular, for mixers)
│           │   ├── VapourProduct, LiquidProduct, WaterProduct (separators)
│           │   ├── EnergyFeeds[], EnergyProducts[]
│           │   └── Type-specific: DutyValue, AdiabaticEfficiency,
│           │       PolytropicEfficiency, PressureDrop, Length, Diameter
│           └── Flowsheets[] (sub-flowsheets, recursive)

Read the full file on GitHub · 1,938 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday Changed · +228 lines · +17 tokens per session a25e9dec3bdb
4d ago Changed · +79 lines 1a68d43040ce
6d ago First seen · 1,631 lines · 94 tokens per session scan A 546d05828c3f

Subscribe to this mod's changes

neqsim-unisim-reader is a skill published in the GitHub repository equinor/neqsim (151 stars, last pushed today), licensed Apache-2.0. It adds 111 tokens to every session and 23,932 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Data and AI Scientific oil-and-gas phase-equilibrium physical-properties processing pvt thermodynamics

pick-a-pii-model

Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.

maziyarpanahi/openmed · 64 tokens

esm

Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…

synthetic-sciences/openscience · 86 tokens

borzoi

Use Borzoi-style regulatory genomics models for sequence-to-expression or variant-effect analysis. Use when the task asks for noncoding variant impact, regulatory sequence design, or expression prediction.

companion-inc/feynman · 41 tokens

bioprobench

Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.

PKU-YuanGroup/OpenAI4S · 46 tokens

reactome-database

Query the Reactome database (Analysis and Content Services). Use when the user asks about pathway analysis, gene list enrichment, retrieving results by token, finding unmapped or not-found identifiers, mapping identifiers, reaction participants (inputs, outputs), pathway hierarchy (including top-level pathways)…

google-deepmind/science-skills · 73 tokens

version-dataset

Dataset version control for research reproducibility. Builds a deterministic content-hash manifest of a dataset (file SHA-256 + tabular schema + per-column value hashes), verifies a later copy against it to detect drift (schema change, row-count change, value changes), and diffs two manifests. Use to prove an analysis…

Aperivue/medsci-skills · 86 tokens

neqsim: Skill for Claude Code