Jaxsr

Symbolic regression assistant for the JAXSR Python library. Discovers interpretable algebraic equations from data with sparse basis-function selection (ALAMO-style), and guides design of experiments (DOE), response surface methodology (RSM), active learning, uncertainty quantification, constrained and known-model fitting, and model export. Use when the user wants to find an equation or surrogate model from data, mentions jaxsr or symbolic regression, sets up a DOE study, chooses basis functions, selection strategies or UQ methods, or writes notebooks, scripts or reports for symbolic regression

44 stars 3 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jkitchin/jaxsr --skill jaxsr
Manual install
git clone --depth 1 https://github.com/jkitchin/jaxsr.git /tmp/jaxsr
mkdir -p ~/.claude/skills
cp -r /tmp/jaxsr/.claude/skills/jaxsr ~/.claude/skills/jaxsr

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

From the SKILL.md

# JAXSR Skill — Symbolic Regression Assistant

JAXSR is a JAX-based symbolic regression library that discovers interpretable algebraic
expressions from data using sparse optimization. It follows ALAMO-style methodology:
build a rich candidate basis, then select the simplest model that explains the data.

## Skill Activation

Activate this skill when the user wants to:
- Discover algebraic expressions or equations from data
- Set up a Design of Experiments (DOE) study
- Fit, interpret, or export symbolic regression models
- Choose between basis functions, strategies, UQ methods, or design methods
- Generate reports from experimental data
- Use the `jaxsr` CLI tool
- Build notebooks or scripts for symbolic regression workflows

## Assistant Mode

When the user asks for help deciding how to set up, analyze, or report on their problem,
enter **assistant mode**. In this mode, ask diagnostic questions to guide them to the right
configuration. Do not dump all options at once — walk through decisions sequentially.

### Step 1: Characterize the Problem

Ask the user:
1. **What are you modeling?** (physical system, chemical process, ML feature engineering, etc.)
2. **How many input features?** (1-3 is small, 4-8 is medium, 9+ is large)
3. **How many data points?** (< 20 is very small, 20-100 is typical, 100+ is large)
4. **Do you have domain knowledge?** (known physics, monotonicity, bounds, symmetry)
Read the full skill on GitHub

Details

Skill name
jaxsr
Repository
jkitchin/jaxsr
Path
.claude/skills/jaxsr/SKILL.md
License
MIT
Repo updated
27 October 2026

FAQ

What does the Jaxsr skill do?

Symbolic regression assistant for the JAXSR Python library. Discovers interpretable algebraic equations from data with sparse basis-function selection (ALAMO-style), and guides design of experiments (DOE), response surface methodology (RSM), active learning, uncertainty quantification, constrained and known-model fitting, and model export. Use when the user wants to find an equation or surrogate model from data, mentions jaxsr or symbolic regression, sets up a DOE study, chooses basis functions, selection strategies or UQ methods, or writes notebooks, scripts or reports for symbolic regression

How do I install the Jaxsr skill?

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

Is Jaxsr popular?

It lives in jkitchin/jaxsr, which has 44 GitHub stars and 3 forks.

Related skills

Jaxsr Review

44

jkitchin/jaxsr

Red-team, software-engineering and pedagogical review of JAXSR code, docs, guides, templates and notebooks. Checks every jaxsr API call against the real signatures and return types, flags unsafe or fragile engineering, and assesses clarity for first-time users. Use when the user invokes /jaxsr-review or asks to review, audit, or check the correctness of JAXSR-related files.

Software Development

LangSmith Fetch

52

ArogyaReddy/ComposioHQ-awesome-claude-skills

Debug LangChain agents via LangSmith execution traces. Fetch and analyze traces to understand agent behavior and debug issues.

AI, LLMs & Agents11

AI Tech News Video

49

topo-ai/ai-video-skills

用于制作 AI 科技资讯快报视频。包含:新闻检索与筛选、真实素材下载、edge-tts 口播、HyperFrames 画面编排、音频与字幕同步、最终渲染导出。触发词:AI快报、科技资讯视频、AI新闻视频、news flash video、weekly AI digest。

AI, LLMs & Agents

Olore A2a Latest

119

olorehq/olore

Local A2A (Agent-to-Agent) protocol documentation (latest). Use for agent communication, task management, streaming, push notifications, and enterprise-ready agent interoperability.

AI, LLMs & Agents

Agent Framework Builder Dotnet

119

olorehq/olore

Use this skill when building, modifying, reviewing, evaluating, integrating, or hosting .NET (C#) applications with Microsoft Agent Framework. Use it for Agent Framework agents, harness agents, workflows, orchestrations, declarative definitions, tools, sessions, middleware, evaluation, observability, integrations, or hosting, even when the user has not yet chosen the correct framework pattern.

AI, LLMs & Agents

Olore Agentskills Latest

119

olorehq/olore

Local agentskills documentation reference (latest). Agent Skills format documentation — use for creating SKILL.md files, understanding the specification, integrating skills support into AI coding agents, and following best practices for skill creation and evaluation.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.