# scientific-computing

scientific-computing points the agent at the right Python library for astronomy, bioinformatics, symbolic math or statistics, and shows the API for each.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 197 installs · ★ 7 repo stars
- Author: eyadsibai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eyadsibai/ltk/tree/HEAD/plugins/ltk-data/skills/scientific-computing/SKILL.md
- Updated: 2026-01-15
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/scientific-computing

## What it does

The skill puts a reference for four scientific Python libraries into the agent's context. AstroPy covers astronomy. Quantities carry their units and convert on their own, sky coordinates come in frames such as ICRS or galactic, time can be expressed in UTC, TAI or Julian dates, and FITS files are read and written. BioPython works on DNA, RNA and protein sequences, parses FASTA, GenBank and PDB, and runs BLAST either locally or remotely, with NCBI Entrez for database lookups.

SymPy handles symbolic math: solving equations, simplification, expansion, factoring, derivatives, integrals, limits, series. Matrices and eigenvalues are included, and results can be printed as LaTeX. Statsmodels is the statistics side, from OLS and logistic regression to generalized linear models, ARIMA and VAR, t-tests and ANOVA. Formulas follow R syntax, for instance `y ~ x1 + x2`, and `model.summary()` returns the kind of output R users expect. A decision table maps each problem domain to a library and points numerical work at NumPy and SciPy.

One idea runs through the whole guide: keep units attached to values, so a mismatch shows up where it happened rather than at the end of a calculation. The skill itself is text for the agent; the libraries live in your project environment.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill scientific-computing -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/scientific-computing/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/scientific-computing/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill scientific-computing -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/scientific-computing/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill scientific-computing -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/scientific-computing/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eyadsibai/ltk plugins/ltk-data/skills/scientific-computing
```

2. **Manually: put the files in place**
- File: `.github/skills/scientific-computing/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill scientific-computing -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eyadsibai/ltk --path plugins/ltk-data/skills/scientific-computing
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/scientific-computing/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill scientific-computing -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/eyadsibai/ltk/tree/HEAD/plugins/ltk-data/skills/scientific-computing/SKILL.md

## When to use it
- convert an object's coordinates to the galactic frame
- open a FITS file and pull the data out
- parse a FASTA record and build the reverse complement
- evaluate an integral symbolically
- fit an OLS regression from an R-style formula

## Example prompts
- Get the galactic coordinates for this source with AstroPy
- Parse `sample.fasta` with `SeqIO` and report the GC content
- Simplify this expression in SymPy and print it as LaTeX

## Similar
- [scientific-brainstorming](https://affpapa.org/en/nevibecode/skills/k-dense-ai-scientific-brainstorming.md) — skill · 2500 installs
- [scientific-schematics](https://affpapa.org/en/nevibecode/skills/scientific-schematics.md) — skill · 2400 installs
- [scientific-literature-researcher](https://affpapa.org/en/nevibecode/agents/voltagent-scientific-literature-researcher.md) — subagent · ★ 6505 repo stars
- [scientific-email-polishing](https://affpapa.org/en/nevibecode/skills/scientific-email-polishing.md) — skill · 105 installs
- [scientific-problem-selection](https://affpapa.org/en/nevibecode/plugins/scientific-problem-selection.md) — plugin · ★ 654 repo stars
- [math](https://affpapa.org/en/nevibecode/skills/math.md) — skill · 887 installs

From the same set: [eyadsibai/ltk](https://affpapa.org/en/nevibecode/by/eyadsibai/ltk.md) — 11 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
