neqsim-document-intelligence-extraction SKILL.md skillA

neqsim-document-intelligence-extraction from equinor/neqsim is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add equinor/neqsim/neqsim-document-intelligence-extraction@v0.1.0

Pins v0.1.0 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-document-intelligence-extraction/SKILL.md
Versions recorded
2
Latest version
v0.1.0, committed Oct 18, 2026
First version recorded
Jul 11, 2026
Size
10,723 bytes
Repository stars
167
License
Apache-2.0

Classify mixed engineering documents and images, route native text/table, OCR, and vision extraction, and produce source-traceable evidence packages with confidence and human-review gates. USE WHEN: a NeqSim task receives PDFs, scans, Word/Excel files, drawings, charts, photographs, or multiple conflicting engineering sources.

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

# Document Intelligence Extraction

Use this skill as the intake layer for documents and images supplied to NeqSim tasks. It makes extraction automatic where tools are available without treating OCR or model output as verified engineering data.

## When to Use

- A task receives PDF, DOCX, XLSX, CSV, HTML, XML, presentation, image, scan, drawing, chart, or photograph inputs.
- A PDF may contain both embedded text and visual engineering content.
- Multiple sources must be reconciled without silently choosing one value.
- Extracted values will feed simulation, design, safety, operations, or reporting workflows.

## Inputs

- `source_path`: source file path; retain the original file unchanged.
- `embedded_text_chars`: optional PDF text-layer yield used to trigger OCR.
- `contains_visuals`: optional Office-document visual-content hint.
- Adapter-produced facts with original text, page or locator, extraction method, confidence, and optional normalized value/unit.

## Outputs

- `ExtractionPlan`: source kind plus ordered native-text, table, OCR, rendering, and vision operations.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add equinor/neqsim/neqsim-document-intelligence-extraction@sha256:5d02353defd3adcc

The line at the top of this page pins the label v0.1.0, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_iobfy5zcxowpflqz.svg)](https://markdownregistry.com/a/art_iobfy5zcxowpflqz)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jul 11, 2026 and Oct 18, 2026, about one every 99 days.

versioncommittedcommitsizeaudit
v0.1.0 latest2026-10-18 2bcd926 10,723 BA view · diff
v0.1.02026-07-11 c70b356 8,648 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10723 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

GitHub

equinor/neqsim · 167 stars · license Apache-2.0 · pushed 2026-11-08 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_iobfy5zcxowpflqz
GET https://markdownregistry.com/api/v1/resolve?ref=equinor/neqsim/neqsim-document-intelligence-extraction
GET https://markdownregistry.com/api/v1/blob/5d02353defd3adcc4107c9e2c81693b3fcaf6e9f58856e9e7e719f81c587e986

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.

More from equinor/neqsim

.cursorrules Cursor rule
equinor/neqsim · .cursorrules
git:20260418.119a3f4 · audit A · 167 stars
analyze-convergence SKILL.md skill
equinor/neqsim · .github/skills/analyze-convergence/SKILL.md · Interpret flash algorithm convergence metrics, identify patterns, and produce
git:20260919.77c34a0 · audit A · 167 stars
analyze-gibbs-convergence SKILL.md skill
equinor/neqsim · .github/skills/analyze-gibbs-convergence/SKILL.md · Interpret Gibbs energy minimization convergence metrics, analyze Jacobian
git:20260919.77c34a0 · audit A · 167 stars
book-creation SKILL.md skill
equinor/neqsim · .github/skills/book-creation/SKILL.md · PaperLab skill for book creation workflows in scientific writing and book production.
git:20260919.77c34a0 · audit B · 167 stars
design-flash-benchmark SKILL.md skill
equinor/neqsim · .github/skills/design-flash-benchmark/SKILL.md · Create a structured test matrix for comparing flash algorithm performance
git:20260919.77c34a0 · audit A · 167 stars
design-reactor-benchmark SKILL.md skill
equinor/neqsim · .github/skills/design-reactor-benchmark/SKILL.md · Create a structured test matrix for evaluating Gibbs energy minimization
git:20260919.77c34a0 · audit A · 167 stars
figure-discussion SKILL.md skill
equinor/neqsim · .github/skills/figure-discussion/SKILL.md · PaperLab skill for figure discussion workflows in scientific writing and book production.
git:20260919.77c34a0 · audit A · 167 stars
generate-publication-figures SKILL.md skill
equinor/neqsim · .github/skills/generate-publication-figures/SKILL.md · Create matplotlib figures that meet journal submission standards: correct fonts,
git:20260919.77c34a0 · audit A · 167 stars
journal-formatting SKILL.md skill
equinor/neqsim · .github/skills/journal-formatting/SKILL.md · Apply journal-specific formatting rules to transform a manuscript from Markdown
git:20260919.77c34a0 · audit A · 167 stars
neqsim-acid-gas-treating SKILL.md skill
equinor/neqsim · .github/skills/neqsim-acid-gas-treating/SKILL.md · Guides NeqSim agents through acid-gas and contaminant removal with SimpleAmineAbsorber, SimpleAmineRegenerator…
git:20261004.fc23e28 · audit A · 167 stars
neqsim-advanced-control-mpc-and-virtual-sensing SKILL.md skill
equinor/neqsim · .github/skills/neqsim-advanced-control-mpc-and-virtual-sensing/SKILL.md · Guides agents through ProcessLinkedMPC, ProcessLinearizer, ModelPredictiveController, VirtualFlowMeter, SoftSensor, and…
git:20261004.fc23e28 · audit A · 167 stars
neqsim-agent-handoff SKILL.md skill
equinor/neqsim · .github/skills/neqsim-agent-handoff/SKILL.md · Agent-to-agent communication schema for NeqSim. USE WHEN: composing multi-agent pipelines where one agent's output…
git:20260926.08d0028 · audit A · 167 stars

Every file in equinor/neqsim

Browse by kind, by grade A, or by owner.