neqsim-in-writing SKILL.md skillA
neqsim-in-writing from equinor/neqsim is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add equinor/neqsim/neqsim-in-writing@git:20261026.b2bf93bPins git:20261026.b2bf93b in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- equinor/neqsim
- Path
.github/skills/neqsim-in-writing/SKILL.md- Versions recorded
- 2
- Latest version
- git:20261026.b2bf93b, committed Oct 26, 2026
- First version recorded
- Sep 19, 2026
- Size
- 9,848 bytes
- Repository stars
- 167
- License
- Apache-2.0
Author scientifically rigorous chapters and papers where every quantitative claim is backed by a NeqSim simulation, regression test, or notebook. Covers the dual-boot setup cell, claim → test linkage, equation → Java method cross-references, units enforcement against `nomenclature.yaml`, and notebook-driven figure / results-table injection.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# NeqSim integration for scientific writing
This skill is loaded by `book_author.agent` and `solve.task.agent` whenever a
chapter or paper section must defend a numerical statement with a NeqSim
artifact. It complements `book-creation` (which handles structural authoring)
and `journal-formatting` (which handles paper layout).
The objective is **traceability**: a reader (or reviewer) following any number,
table, or figure in the manuscript must be able to land on a runnable NeqSim
artifact in the repo within one click.
---
## 1. Standard chapter setup cell (Jupyter)
Every chapter notebook **must** start with the dual-boot cell. It tries the
local devtools build first (so an editor sees fresh code) and falls back to
the published `neqsim` PyPI package on Colab / external readers.
```python
import importlib, subprocess, sys
try:
from neqsim_dev_setup import neqsim_init, neqsim_classes
ns = neqsim_init(recompile=False)
ns = neqsim_classes(ns)
NEQSIM_MODE = "devtools"
except Exception:
try:
import neqsim
except ImportError:
subprocess.check_call([sys.executable, "-m", "pip", "install", "-q", "neqsim"])
from neqsim import jneqsim
…Read the whole file at its exact version.
How to install
mdr add equinor/neqsim/neqsim-in-writing@sha256:62b1c3bd89adea1fThe line at the top of this page pins the label git:20261026.b2bf93b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xob6rynaj6jy3fl4)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 19, 2026 and Oct 26, 2026, about one every 38 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261026.b2bf93b latest | 2026-10-26 | b2bf93b | 9,848 B | A | view · diff |
| git:20260919.77c34a0 | 2026-09-19 | 77c34a0 | 9,845 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9848 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
equinor/neqsim · 167 stars · license Apache-2.0 · pushed 2026-11-08 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_xob6rynaj6jy3fl4 GET https://markdownregistry.com/api/v1/resolve?ref=equinor/neqsim/neqsim-in-writing GET https://markdownregistry.com/api/v1/blob/62b1c3bd89adea1f2d231cf7117210f3eb21ee9f0feea36a9e478a1d1395bf59
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.