scientific-agent-skills
Research and engineering workflows require domain-specific precision that generic AI skills miss — this collection provides ready-to-use agent skills coverin…
A collection of 148 ready-to-use scientific and research skills from K-Dense: unified lookup across 100+ scientific and financial databases (PubChem, ChEMBL, UniProt, ClinicalTrials.gov, FRED, USPTO and more), 70+ optimized Python package skills (RDKit, Scanpy, scikit-learn, BioPython, Qiskit), lab-platform integrations (Benchling, DNAnexus, Opentrons), and literature-review, scientific-writing, and grant-writing tools. Works with any agent supporting the open Agent Skills standard — Claude Code, Cursor, Codex, Google Antigravity.
- Apply structured research methodologies to literature reviews
- Run domain-specific data analysis with validated frameworks
- Generate technical reports following academic or engineering standards
Research and engineering workflows require domain-specific precision that generic AI skills miss — this collection provides ready-to-use agent skills covering research methodology, data analysis, financial modeling, and technical writing.
Researchers, engineers, and analysts who need Claude to follow domain-specific methodologies for scientific analysis, financial modeling, and technical documentation.
https://github.com/K-Dense-AI/scientific-agent-skills
By K-Dense-AI
How to Get It
npx skills add K-Dense-AI/scientific-agent-skills
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me apply structured research methodologies to literature reviews
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 18,260 GitHub stars; 32 contributors; last commit 37d ago; license MIT.
Things to check
- Formerly named Claude Scientific Skills — now standard Agent Skills, no longer Claude-only. Skill quality varies by domain; the repo runs its own security scans but the maintainer notes the agent can call any Python package or API beyond the curated skills, so review what a skill executes before use in regulated research settings.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 18,260 GitHub stars; 32 contributors; last commit 37d ago; license MIT.