// Skill profile
K-Dense-AI/scientific-agent-skills is the leading scientific-vertical skill bundle for AI coding agents, with 41K+ GitHub stars and 165 validated skills covering 100+ scientific databases across biology, chemistry, medicine, and drug discovery. Used by 190,000+ scientists worldwide, it ships explicit chained skills: a literature-review skill calls a citation-graph skill, which calls a PDF-extraction skill, which feeds a methodology-comparison skill. The repo's design partners are computational chemistry and structural biology groups — making this one of the first credible scientific-vertical bundles where the authors are inside the named user cohort. Skills include protein-structure prediction prompts, lab-notebook automation, literature scraping with citation graph traversal, and experiment-design rubrics. Cross-harness — works with Claude Code, Cursor, Codex, Pi, Antigravity, and any harness that respects the Agent Skills standard. Part of the vertical-bundle convergence alongside Imbad0202/academic-research-skills — the cycle that marked skill packs moving from generic directory race into domain-specialized verticals.
AI agents that work well with Scientific Agent Skills.
Single 70-line CLAUDE.md derived from Karpathy's LLM coding-pitfall observations — #1 GitHub trending for 28 consecutive days.
A complete software development methodology and composable skills framework for coding agents — brainstorm, plan, execute, review, ship.
Agent skill that makes your coding agent think like the laziest senior dev in the room — skip unnecessary code, reuse existing patterns, and write 54% less code while staying 100% safe.