Best Claude skills for science
Science skills give agents domain tools for biology, chemistry, genomics and physics: database lookups, analysis pipelines and lab workflows. K-Dense's scientific-agent-skills and Google DeepMind's science-skills are the largest collections.
216 science skills · ranked live · November 2026
The top 10. Ranked by the Alyn Score.
- 1#1
GitHub
Awesome Copilot
GitHub
Arize Evaluator
Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column…
Pack41k2.4MScore 85 - 2#2
GitHub
Awesome Copilot
Arize Experiment
Creates, runs, and analyzes Arize experiments for evaluating and comparing model performance. Covers experiment CRUD, exporting runs, comparing results, and evaluation workflows using the…
Pack41k2.4MScore 85 - 3#3
JuliusBrussee
Caveman Manage
Inspect Caveman Cloud's experiment lifecycle and block unsafe execution. Use when asked to start, approve, cancel, promote or roll back a Caveman experiment.
Pack119k4.8MScore 85 - 4#4
K-Dense
Scientific Agent Skills
K-Dense
Alphagenome
Looks up precomputed AlphaGenome Atlas effects for any GRCh38 single-nucleotide variant (AVI score with Phred and 18 SHAP feature attributions, plus raw and quantile scores for RNA-seq…
Pack57k328kScore 84 - 5#5
K-Dense
Scientific Agent Skills
Analytical Method Validation
Plans, executes, and documents validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP //, ICH M10 bioanalytical, CLSI EP, or…
Pack57k328kScore 84 - 6#6
K-Dense
Scientific Agent Skills
Arbor
Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses…
Pack57k328kScore 84 - 7#7
Yuan1z0825
Nature Paper Card
Build a structured deep-reading Paper Card for one scientific paper, analysing methods, experiment-to-claim evidence, limitations, and research ideas. Use for 论文精读卡、方法拆解、证据链分析; not…
Pack53k301kScore 84 - 8#8
sickn33
Agentic Awesome Skills
sickn33
Ab Testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
Pack49k584kScore 83 - 9#9
Nature Social Science
社会科学及相邻学科学术写作与选题论证工作台，覆盖选题构思、文献梳理、论证组织、学术表达四大要素。Use for 找论文题目/研究问题、把兴趣或宽泛主题变成可讨论的研究方向、文献综述与领域版图、区分"研究少"与真正未决的知识问题、设计证据路线与主张边界、新颖性审计与"审稿人2"式攻击、博士/论文可行性评估、导师沟通话术、或检查论文中的过度断…
Pack53k301kScore 82 - 10#10
Nature Writing
Draft or restructure scientific manuscript arguments, sections, and initial-submission materials from author-provided evidence. Use for 论文写作、章节起草、论证重构、正文压缩、首次投稿材料. Use nature-polishing for…
Pack53k301kScore 82
What makes a great science skill.
Pinned, real libraries and databases with usage examples.
Validation steps that catch silent errors in pipelines.
Clear licensing for data sources.
All 216 science skills.
GarethManning
Education Agent Skills
GarethManningai-facilitated-collaborative-learning-designer
Design AI-supported collaborative tasks that structure group interaction and address participation problems. Use when students struggle to collaborate effectively on group tasks.
GarethManning
Education Agent Skills
GarethManningai-feedback-design-principles
Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.
product-on-purpose
Pm Skills
product-on-purposedefine-hypothesis
Defines a testable hypothesis with clear success metrics and a validation approach. Use when forming assumptions to test or aligning a team on what success looks like, before any experiment…
posit-dev
Skills
posit-devr-lifecycle
Guidance for managing R package lifecycle according to tidyverse principles using the lifecycle package. Use when: (1) Setting up lifecycle infrastructure in a package, (2) Deprecating…
databricks
Databricks Agent Skills
databricksspark-python-data-source
Build custom Python data sources for Apache Spark using the PySpark DataSource API — batch and streaming readers/writers for external systems. Use this skill whenever someone wants to…
LeoYeAI
Agent Master Skills
LeoYeAIab-testing
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test,"…
jaechang-hitsmolecular-visualization-3dmol
3Dmol.js WebGL molecular visualization emitted as self-contained HTML. Render structures (PDB/SDF/XYZ/MOL2/cube) with stick, sphere, cartoon, line, and surface styles; animate trajectories…
benchflow-ai
Skillsbench
benchflow-aipubchem-database
Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.
jaechang-hitspymc-bayesian-modeling
Bayesian modeling with PyMC 5: priors, likelihood, NUTS/ADVI sampling, diagnostics (R-hat, ESS), LOO/WAIC comparison, prediction. Hierarchical, logistic, GP variants; predictive checks.
benchflow-ai
Skillsbench
benchflow-airdkit
Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For…
jaechang-hitssciagent-skill-creator
Scaffold a new SciAgent-Skills entry. Picks pipeline/toolkit/database/guide template, creates skills/{category}/{name}/SKILL.md with valid frontmatter, appends the registry.yaml entry, runs…
quodsoler
Unreal Engine Skills
quodsolerue-physics-collision
Use when setting up collision channels and profiles, running line/sweep/overlap queries, wiring hit and overlap events, or simulating rigid bodies in Unreal Engine C++. Also use when the…
zLanqing
Codex Claude Academic Skills
zLanqingcitation-management
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX…
zLanqing
Codex Claude Academic Skills
zLanqingexploratory-data-analysis
Perform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its…
zLanqing
Codex Claude Academic Skills
zLanqingliterature-review
Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic…
LeoYeAI
Agent Master Skills
LeoYeAImarketing-psychology
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,'…
benchflow-ai
Skillsbench
benchflow-aiPDF manipulation toolkit. Extract text/tables, create PDFs, merge/split, fill forms, for programmatic document processing and analysis.
freshtechbro
Claudedesignskills
freshtechbroreact-spring-physics
Physics-based animation library combining React Spring (spring dynamics, gesture integration, 60fps animations) and Popmotion (low-level composable animation utilities, reactive streams)…
aipoch
Medical Research Skills
aipochslide-deck-for-lab-meeting
Structures research progress into focused and actionable slides for lab meetings or project reviews without inventing missing content.
GPTomicsbio-alignment-indexing
Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam. Use when enabling random access to alignment files or fetching specific genomic regions.
GPTomicsbio-alignment-pairwise
Perform pairwise sequence alignment using Biopython Bio.Align.PairwiseAligner. Use when comparing two sequences, finding optimal alignments, scoring similarity, and identifying local or…
GPTomicsbio-alignment-structural
Align protein structures using Foldseek 3Di, TM-align, US-align, DALI, or Foldmason for structural MSA. Predict, score, and superpose backbone coordinates when sequence identity is below…
growthenginenowoslawski
Coldoutboundskills
growthenginenowoslawskiexperiment-design
Framework for running single-variable cold email experiments. Defines experiment types (list-only, copy-only, combined), confidence weighting, minimum sample sizes, and success criteria…
tjboudreauxthinking-scientific-method
When a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.
tjboudreauxthinking-thought-experiment
When a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.
brycewang-stanfordaaai-experiments
Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation…
Jakeschincariol
Console Skill
Jakeschincariolconsole-physics
Physics Tuner. Finds the numbers that decide how the game moves (speed, gravity, grip, jump height, frame rate) and tunes them. Scans the user's own game ELF for a float32 value stored in…
kwakseongjaeomd-experiment-gallery
N개 brand experiment를 한 화면에서 비교하는 gallery index.html을 생성. 각 카드는 brand name, wow rating, multi-turn refinement deltas, iframe scaled preview, standalone link 포함. '결과물 한 번에 보여줘', '갤러리 만들어'…
kwakseongjaeomd-lab-02-design-harness
OmD Lab #02 — 디자인 하네스 정교화 실험. 동일 task를 v1, v2, v3... 버전별 하네스 설정으로 돌려서 산출물 품질·토큰 비용·iteration 수·persona ABANDON 율을 비교. 트리거 — '/omd-lab-02', '하네스 lab 시작', '디자인 하네스 v2 돌려서 비교', 'lab #02 자동 비교'.
brycewang-stanfordaamas-experiments
Use when designing or auditing AAMAS experiments - self-play and population-based training, opponent selection, equilibrium and regret metrics, game-theoretic simulations, ablations, seeds…
Microckalphafold-database
Access AlphaFold's 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and…
ArtemXTech
Personal Os Skills
ArtemXTechnotebooklm
Turn expert podcasts into personalized protocols with cited experiments. Load 300 episodes from terminal, run an expert-informed interview, build experiments in your Obsidian morning…
staruhub
ClaudeSkills
staruhuba-share-analyst
A股分析研究助手，提供行情数据获取与技术面/基本面分析框架（仅供研究参考，不构成投资建议）。适用于：(1) 获取A股行情和历史数据，(2) 技术面分析（K线形态、MACD、KDJ、RSI、布林带等），(3) 基本面分析（财务指标、估值分析），(4) 板块热点追踪，(5) 选股策略筛选与量化因子分析，(6) 生成股市分析报告。当用户询问"帮…
brycewang-stanfordaamas-supplementary
Use when preparing AAMAS supplementary material - proofs, extended game and mechanism definitions, extra multiagent experiments, opponent-set details, and the anonymized artifact zip -…
AirsupHQmachine
Turn one line ("a turbofan jet engine", "a mechanical watch", "an LVAD heart pump") into a photoreal, physics based, interactive 3D simulation of that machine in a single HTML file, plus a…
lingzhi227
Agent Research Skills
lingzhi227experiment-design
Design experiment plans with progressive stages — initial implementation, baseline tuning, creative research, and ablation studies. Plan baselines, datasets, hyperparameter sweeps, and…
Science skills, explained.
Also searched as: scientific agent skills, bioinformatics skill, ai scientist skills, deepmind science skills.
What are the best Claude skills for science?
Right now the top-ranked science skills on Alyn are Arize Evaluator (GitHub), Arize Experiment (GitHub), Caveman Manage (JuliusBrussee). Rankings combine GitHub stars, installs, freshness and depth, and update live.
Are there official DeepMind skills?
Yes. google-deepmind/science-skills is published by Google DeepMind for agentic scientific workflows.
Do science skills replace domain review?
No. They speed up analysis; results still need expert review.
How do I install a science skill?
Run npx skills add owner/repo in your project, or copy the folder with SKILL.md into ~/.claude/skills. Every skill on this page has a ready-to-copy command.
More in Science & data
Science skills for your agent