A collection of skills for AI coding agents tailored to ReproNim tools and neuroimaging workflows. Skills are packaged instructions that extend AI agent capabilities when working with ReproNim's ecosystem of tools.
Skills follow the Agent Skills format and are compatible with Claude Code, GitHub Copilot, Cursor, and other AI coding agents.
Skills are located in the skills/ directory. Each skill is a single Markdown file (e.g., skills/my-skill.md) containing structured instructions for the agent.
No skills have been added yet. See Contributing to add one.
npx skills add ReproNim/skillsnpx skills add ReproNim/skills --skill <skill-name>npx skills add ReproNim/skills -a claude-code
npx skills add ReproNim/skills -a cursorThis repository provides reusable, shareable AI agent skills for the ReproNim community. Skills encode domain knowledge about:
- ReproNim tools and best practices (e.g., DataLad, Neurodocker, ReproSchema)
- Neuroimaging data management and FAIR data principles
- Reproducible research workflows
- BIDS (Brain Imaging Data Structure) conventions
By packaging this knowledge as agent skills, researchers and developers get consistent, expert guidance directly inside their AI coding assistant.
Each skill is a single Markdown file placed directly in the skills/ directory:
skills/
└── my-skill.md # SKILL.md-format file describing the skill
---
name: repronim-my-skill
description: >
Brief description of when and how to use this skill.
license: MIT
metadata:
author: ReproNim
version: 1.0.0
---
# My Skill
## When to Apply
...
## Guidelines
...- Create a new Markdown file in the
skills/directory (e.g.,skills/datalad-best-practices.md). - Follow the skill file format above.
- Update this README to list the new skill under Available Skills.
- Open a pull request.
MIT