optimatika

OjAlgo Skills — AI skill for Claude Code

AI community

Agent skills for AI coding assistants (Claude, ChatGPT/Codex): write correct ojAlgo code for LP/QP/MIP models, linear algebra and portfolio optimization.

How to install OjAlgo Skills

This entry records only its repository, not the path inside it, so there is no exact command to give. Open optimatika/ojAlgo-skills and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What OjAlgo Skills does

Agent skills for AI coding assistants (Claude, ChatGPT/Codex): write correct ojAlgo code for LP/QP/MIP models, linear algebra and portfolio optimization.

Alternatives in AI

Repomix — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file 22.7k ★
Bot On Anything — A large model-based chatbot builder that can quickly integrate AI models (including ChatGPT, Claude, Gemini) i 4.2k ★
OpenContext — A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC 1.1k ★

README

ojAlgo skills for coding agents

[Agent Skills](https://agentskills.io) that teach AI coding assistants to work with [ojAlgo](https://www.ojalgo.org/), the pure-Java, zero-dependency library for optimisation (LP, QP, MIP) and linear algebra, and with Optimatika's [Optimisation Service](https://www.optimatika.se/optimisation-service/).

Skill	What it teaches
`ojalgo-optimisation`	Writing and debugging optimisation models with ojAlgo
`ojalgo-linear-algebra`	Equation systems, least squares, matrix decompositions (LU, QR, Cholesky, SVD, eigenvalues), sparse systems, and memory-efficient matrix code with ojAlgo
`ojalgo-portfolio`	Portfolio optimisation: Markowitz mean-variance, Black-Litterman, covariance matrices from price histories, Sharpe ratio and value at risk
`optimisation-service-rest`	Level 1: solving models over the service's REST API, from any language
`optimisation-service-client`	Levels 2 and 3: the Java client library, from any JVM language. Submit model files, or build models with its own modeller (no ojAlgo needed, older Java versions supported)
`optimisation-service-ojalgo`	Level 3: solving existing ojAlgo models remotely, with no changes to the model code

With the first one, an assistant that is asked to allocate, assign, schedule, pack, select, blend, locate or build a portfolio in a JVM application will:

decide whether a solver is actually needed, and which problem type it is;
start from a verified recipe in the Optimisation Cookbook rather than write a model from scratch;
follow the rules that decide wh