Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By uw-ssec
Automate end-to-end best practices for scientific Python projects: initialize reproducible pixi environments with conda/PyPI deps, enforce code quality via ruff/mypy/pre-commit, build pytest numerical tests, create distributable Hatchling packages, and generate Sphinx/MkDocs docs with NumPy-style docstrings and Diataxis structure.
npx claudepluginhub uw-ssec/rse-plugins --plugin scientific-python-developmentSet up or fix ruff, mypy, and pre-commit for scientific Python code quality
Set up or manage pixi environments for reproducible scientific Python workflows
Set up or improve Python package structure with pyproject.toml, src layout, and Hatchling following Scientific Python standards
Write or improve pytest tests for scientific Python code with fixtures, parametrization, and numerical testing patterns
Set up or improve documentation for a scientific Python package using Sphinx, MkDocs, and Diataxis framework
Expert scientific Python documentation architect specializing in research software documentation following the Diataxis framework. Creates comprehensive documentation including API references, tutorials, how-to guides, and explanations for scientific codebases.
Expert scientific Python developer for research computing, data analysis, and scientific software. Specializes in NumPy, Pandas, Matplotlib, SciPy, and modern reproducible workflows with pixi. Follows Scientific Python community best practices.
Configure and use automated code quality tools (ruff, mypy, pre-commit) for scientific Python projects. Covers linting rules, type checking configuration, formatting, and CI integration.
Manage scientific Python dependencies and environments using pixi package manager with unified conda-forge and PyPI support, task automation, and reproducible lockfiles.
Create and publish distributable scientific Python packages following Scientific Python community best practices. Covers pyproject.toml, src layout, Hatchling, metadata, CLI entry points, and PyPI publishing.
Write and organize tests for scientific Python packages using pytest. Covers fixtures, parametrization, numerical testing with NumPy utilities, property-based testing with Hypothesis, and CI integration.
Set up and maintain documentation for scientific Python packages. Covers Sphinx, MkDocs, NumPy-style docstrings, Diataxis framework, accessibility standards, and documentation hosting with Read the Docs.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Structured AI-enabled research workflows for software development: Research, Plan, Experiment, Implement
Development automation skills for Python projects
Claude skills for Sciris features covering arrays, containers, file I/O, plotting, parallelization, dates, printing, utilities, and advanced features
Opinionated Python 3.11+ engineering system. Establishes strong defaults (SOLID, typing policy, testing standards, code smell detection) and routes to specialist skills for TDD, CLI, web, data/science, and constrained environments.
OSS Claude Code config: agents, skills, and hooks for professional AI-assisted development workflows
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Structured AI-enabled research workflows for software development: Research, Plan, Experiment, Implement
Comprehensive agents and skills for working with the Zarr array storage format
Benchmark and optimize Zarr chunking strategies for multi-dimensional scientific datasets on cloud object stores (S3, GCS)
Agents and skills for Research-Through-Design approach to research software design
Project lifecycle management — onboarding, documentation quality, handoff readiness, and community health for research software projects
Custom AI agents and skills for Research Software Engineering (RSE) and Scientific Computing tasks, designed for use with Claude Code and compatible AI coding assistants.
This repository provides specialized agents and skills that understand the unique challenges of scientific software development, including:
To use these agents and skills in Claude Code, add this repository to your plugin marketplace:
/plugin marketplace add uw-ssec/rse-plugins
Once installed, the agents and skills will be available in your Claude Code environment and can be invoked when working on scientific software projects.
The repository provides Claude Code plugins organized by domain. Each plugin contains agents (specialized AI personas) and skills (reusable knowledge modules).
Expert agents and comprehensive skills for modern Scientific Python development.
Agents:
Skills:
When to use: Scientific computing projects, data analysis pipelines, research software development, package creation, reproducible research workflows
Domain-specific scientific computing agents and skills for astronomy, geospatial analysis, climate science, and interactive visualization.
Agents:
Skills:
When to use: Astronomy research, telescope data processing, climate data analysis, Earth science workflows, geospatial analysis
Structured AI-enabled workflow for complex software development tasks with explicit phases for research, planning, experimentation, implementation, and validation.
Agent:
Commands:
/research - Document and understand existing code, patterns, and architecture/plan - Create detailed, testable implementation plans through interactive research/iterate-plan - Refine existing plans based on feedback or changed requirements/experiment - Try multiple approaches before committing to implementation (optional)/implement - Execute the plan phase by phase with verification checkpoints/validate - Systematically verify implementation against plan criteriaSkill:
.agents/ directoryWhen to use: Complex feature development, architectural changes, exploratory implementation, technical research tasks, systematic code refactoring, documented decision-making