Domain Check

Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong (unit/dimension mismatch, Euclidean distance on lat/lon without a CRS, 0-based/1-based coordinate and strand errors, impossible SMILES valence, uncorrected multiple comparisons, averaging

2,105 stars 231 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ai4s-research/open-science --skill domain-check
Manual install
git clone --depth 1 https://github.com/ai4s-research/open-science.git /tmp/open-science
mkdir -p ~/.claude/skills
cp -r /tmp/open-science/runtime/skills/core/domain-check ~/.claude/skills/domain-check

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Domain-correctness gate

Across every field the top complaint is code that **executes cleanly but is
scientifically wrong**. This gate intercepts that field's classic error classes
**deterministically** — by analysing the code you actually wrote, not by
recalling rules. It verifies specific error classes; it never proves correctness.

It is fast, offline and stdlib-only — but it is an on-request gate, not a
background one.

## When to run

- **When the user asks** to check, validate, review or audit an analysis for
  correctness.
- **When you are the reviewer agent**, running the checks that agent's prompt
  lists (the app's auto-review turn, which the user switches on in Settings).

Do NOT run it on your own initiative while writing or executing analysis code.
A clean run still emits a review block, so an unprompted pass puts a card with
no findings in the user's conversation — noise they did not ask for.

## How to run

The gate ships beside this SKILL.md. Run it on the code files in play (or with
no arguments to scan the workspace):

```bash
python "$XDG_CONFIG_HOME/opencode/skills/domain-check/domain_check.py" <file.py|notebook.ipynb|analysis.R ...>
```
Read the full skill on GitHub

Details

Skill name
domain-check
Path
runtime/skills/core/domain-check/SKILL.md
Repo updated
17 November 2026

FAQ

What does the Domain Check skill do?

Use ONLY when the user asks to check, validate, review or audit analysis code for scientific correctness, or when you are the reviewer agent running its checks. Never run it unprompted as part of ordinary analysis work. Covers physics, earth/geo, biology, chemistry, social science and bioprocess/fermentation. Runs a deterministic domain-correctness gate that catches code which runs but is scientifically wrong (unit/dimension mismatch, Euclidean distance on lat/lon without a CRS, 0-based/1-based coordinate and strand errors, impossible SMILES valence, uncorrected multiple comparisons, averaging

How do I install the Domain Check skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ai4s-research/open-science --skill domain-check. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Domain Check popular?

It lives in ai4s-research/open-science, which has 2,105 GitHub stars and 231 forks.

Related skills

Computer Use

2.1k

ai4s-research/open-science

Use when a task needs an app on the user's own screen — a native desktop application (instrument control software, Origin, GraphPad, ImageJ, a reference manager, a spreadsheet), or a desktop browser window that needs window-level control. Read before the first `computer` call. Covers the observe-act-observe loop, why element indexes go stale, which action to prefer for which control, what "unverified" means and why it must never be reported as success, and the recovery for each error code. Not for page-level web automation (use the browser connector) and not for anything that can be done from

Software Development231

Large File

2.1k

ai4s-research/open-science

Use BEFORE reading any data file that could be large (CSV/TSV, Parquet, HDF5, FITS, NetCDF, NDJSON, genomics FASTQ/FASTA/VCF/BAM, GRIB, ROOT, or big text/simulation logs like VASP OUTCAR). Returns a compact memory pointer — header/schema/shape/sample/key numbers — by introspection and sampling in bounded memory, so you never load a file bigger than the context window into the model. Reference data via the pointer; read specific ranges deterministically.

Productivity & Notes231

Modal Run

2.1k

ai4s-research/open-science

Use when the user asks to run heavy or GPU work on Modal (the cloud compute platform) — writing a Modal function in the workspace, running it with the user's own `modal` CLI + token, and bringing results back. Data-to-compute for jobs too big for the laptop, without a Slurm cluster.

Writing & Content231

Publication Figures

2.1k

ai4s-research/open-science

Use whenever you generate or review a chart, plot, table, or paper figure in this workspace, including work delegated by paper-writing, literature-survey, and experiment skills. Applies the Open Science publication style, enforces readable final-size layout for figures and tables, and rejects generic diagram-tool output as a publication figure. Interactive Plotly/HTML may be used for exploration, but paper delivery requires a static publication-ready export.

Research & Science231

Deep Research

4.3k

davidondrej/skills

Run deep research through DeepAPI and save a report with sources. Use when asked for deep research, DeepAPI research, or Perplexity deep research.

Research & Science628

Traceability Review

2.1k

ai4s-research/open-science

Use when the user asks to review, verify, or audit a report, manuscript, or analysis in the workspace for traceability — resolving citations, flagging numbers with no source, and checking figures against the code that generated them. Emits a structured review block the app renders as reviewer findings. Verifies traceability, never "correctness".

Research & Science231

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.