1
Large collection of skills for scientific computing, bioinformatics and research tools
★ 47k · +711 this week · MIT · updated 2026-10-01
7.8/10
What it does Scientific Agent Skills, by K-Dense, is a large collection of skills that turns a general coding agent into a research assistant. The project used to be called Claude Scientific Skills. Each skill gives the agent curated documentation, examples and working patterns for a scientific Python library, database or research method. The agent can still use any package… Read more →
Pros
- Very broad scientific coverage
- Ready-made workflows for research libraries
Cons
- Quality varies between skills
- Large; install only what you need
Pricing: Free · science research
2
Skills for training, evaluating and publishing models with Hugging Face tools
★ 11k · +20 this week · Apache-2.0 · updated 2026-10-01
7.7/10
What it does Hugging Face Skills is Hugging Face's official set of Agent Skills for machine-learning work on the Hub. The entry point is hf-cli, a skill that teaches the agent the hf command line. With it, the agent can search models, manage datasets and buckets, launch Spaces and run jobs. From there, more specialised workflow skills can be added… Read more →
Pros
- Official Hugging Face workflows
- Cross-agent
Pricing: Free · ml hugging face
3
98 skills for ML research with coding agents, from ideation and training to paper writing
★ 13k · +160 this week · MIT · updated 2026-06-16
7.6/10
What it does AI Research Skills, from Orchestra Research, is a large skill library for machine learning research and engineering. It aims to let a coding agent take a research project from literature survey and idea generation through experiments to a written paper. A central "autoresearch" skill runs the process in two loops, one for inner optimisation and one for… Read more →
Pros
- Deep, framework-specific skills for training, serving, evaluation and interpretability
- Autoresearch orchestrator ties the domain skills into one workflow
Cons
- Last updated June 2026, so framework details may lag
- README suggests agents fetch and follow a remote instruction file
Pricing: Open source · machine-learning llm-training fine-tuning research autoresearch
4
Forkable Claude Code setup for academics: LaTeX/Quarto slides, R analysis and review gates
★ 1.6k · +9 this week · MIT · updated 2026-09-27
6.3/10
What it does Claude Code My Workflow is a ready-to-fork repository that packages one economist's Claude Code setup for academic work: lecture slides in LaTeX Beamer and Quarto, papers, R and Stata analysis, and replication packages. You fork it, paste a starter prompt, and Claude adapts the configuration to your project. After that you work in what the author calls… Read more →
Pros
- Specialist reviewers and adversarial critic-fixer loops
- Reproducibility and claim-verification skills
- Extensive companion guide
Cons
- Built for academic research workflows, not general app development
- Fork-based setup with LaTeX and Quarto prerequisites
Pricing: Open source · academic latex r reproducibility quality-gates