OpenScience includes 372 skill files in this version. This directory is generated from the bundled library. Each entry describes the procedure and links to its full usage instructions and supporting files on GitHub.
Use Customize → Skills or openscience skill list --all for the library available in your installed version. A listed skill is a procedure, not a claim that all of its software, data, or services are installed.
How to use any entry
Find the skill by name in Customize → Skills, enable it, then select it through the conversation's / picker or ask OpenScience to use it. Give the actual input path, expected output, and checks. Open the linked instructions for prerequisites and detailed usage.
For example: "Use peer-review on drafts/paper.md. Save prioritized findings with source sections and proposed checks in results/review.md."
See Skills for installation and authoring, and Skill recipes for complete example requests. The summaries below describe skill instructions, not a guarantee of installed software, account access, or current third-party product terms.
Where the skills come from
Most of these skills were written by other people and adapted for OpenScience's tools: Scientific Agent Skills and Claude Scientific Writer by K-Dense Inc. (MIT), AI Research Skills by Orchestra Research (MIT), Hugging Face skills (Apache-2.0), Anthropic's document skills, and the NVIDIA BioNeMo Agent Toolkit. Each skill's frontmatter names its original author, and ATTRIBUTION.md lists every derived skill with its upstream path and license. If a K-Dense skill contributes to published work, cite Kassis et al. (2026).
Biology
| Skill and usage instructions | What the procedure covers |
|---|---|
| anndata | Data structure for annotated matrices in single-cell analysis. |
| benchling-integration | Benchling R&D platform integration. |
| bids | Use this skill when working with Brain Imaging Data Structure (BIDS) datasets: organizing neuroscience and biomedical data (MRI, EEG, MEG, iEEG, PET, microscopy, NIRS, motion capture, EMG, MR spectroscopy, behavioral), querying BIDS layouts, validating… |
| bioimage-analysis | Microscopy image analysis for cell biology. |
| bionemo-nims | Run NVIDIA BioNeMo NIMs through the hosted scientific_capability tool with your own NVIDIA API key. |
| biopython | Comprehensive molecular biology toolkit. |
| bioservices | Unified Python interface to 40+ bioinformatics services. |
| bulk-rnaseq | End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression… |
| cancer-genomics-analysis | Computational cancer genomics workflows. |
| clinical-decision-support | Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with… |
| clinical-imaging | Clinical and physiological imaging analysis. |
| clinical-reports | Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). |
| cobrapy | Constraint-based metabolic modeling (COBRA). |
| curated-bio-datasets | Guide to accessing curated biological datasets for computational biology. |
| deepspot-m | Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. |
| deeptools | NGS analysis toolkit. |
| dnanexus-integration | DNAnexus cloud genomics platform. |
| esm | Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). |
| etetoolkit | Phylogenetic tree toolkit (ETE). |
| flow-cytometry-analysis | Complete flow cytometry analysis pipeline. |
| flowio | Parse FCS (Flow Cytometry Standard) files v2.0-3.1. |
| folklore-variant-evidence | Retrieve ClinGen gene-disease validity assertions for a public gene or disease, and review source-linked public evidence and literature for one supported GRCh38 germline nuclear SNV or simple indel through Folklore Clinical Variant Interpretation MCP. |
| genomic-coordinates | Convert genomic intervals between coordinate conventions, normalise and compare variant representations, and detect assembly or contig-naming mismatches before they corrupt an analysis. |
| genomic-intelligence | Predict regulatory features, gene structure, and expression directly from DNA sequence using Genomic Intelligence's hosted transformer DNA language models — no local GPU or model weights. |
| gget | Fast CLI/Python queries to 20+ bioinformatics databases. |
| ginkgo-cloud-lab | Submit and manage protocols on Ginkgo Bioworks Cloud Lab (cloud.ginkgo.bio), a web-based interface for autonomous lab execution on Reconfigurable Automation Carts (RACs). |
| glycobiology | Glycosylation site prediction and glycobiology analysis. |
| glycoengineering | Analyze and engineer protein glycosylation. |
| histolab | Lightweight WSI tile extraction and preprocessing. |
| immunology-assays | Computational analysis of immunology experimental data. |
| lamindb | This skill should be used when working with LaminDB, an open-source data framework for biology that makes data queryable, traceable, reproducible, and FAIR. |
| latchbio-integration | Latch platform for bioinformatics workflows. |
| marker-panel-annotation | Assigns cell-type labels to clusters from a protein marker panel (multiplexed imaging such as MIBI, CODEX, IMC and CyCIF; mass and flow cytometry; CITE-seq protein), where the labels are judged against an expert reference. |
| microbial-dynamics | Microbial population dynamics modeling and analysis. |
| molecular-cloning | Molecular cloning simulation and design. |
| neurokit2 | Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. |
| neuropixels-analysis | Neuropixels neural recording analysis. |
| nextflow | Build, run, and debug Nextflow data pipelines and nf-core workflows end to end. |
| omero-integration | Microscopy data management platform. |
| opentrons-integration | Official Opentrons Protocol API for OT-2 and Flex robots. |
| pacsomatic | Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. |
| pathml | Full-featured computational pathology toolkit. |
| pathogen-variant-surveillance | Query live pathogen genomic surveillance data through the GenSpectrum LAPIS API to find which viral lineages are circulating now, how fast they are growing, and what mutations they carry. |
| pathway-enrichment | Run pathway and gene-set enrichment analysis on gene lists or ranked gene data, then interpret the results. |
| pharmacology-wetlab | Computational analysis of pharmacology wet-lab experiments. |
| phylogenetics | Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). |
| polars-bio | High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. |
| protein-binder-design | Design and validate de novo protein binders with the current NVIDIA BioNeMo Agent Toolkit workflow, while adapting honestly when NVIDIA-hosted credentials are unavailable. |
| protocolsio-integration | Integration with protocols.io API for managing scientific protocols. |
| pydeseq2 | Differential gene expression analysis (Python DESeq2). |
| pydicom | Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. |
| pyhealth | Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. |
| pylabrobot | Vendor-agnostic lab automation framework. |
| pysam | Genomic file toolkit. |
| relsa-severity-assessment | Multivariate severity assessment and humane endpoint prediction for laboratory animal studies using the RELSA (RELative Severity Assessment) score and ARIMA-based foRcast forecasting. |
| scanpy | Standard single-cell RNA-seq analysis pipeline. |
| scikit-bio | Biological data toolkit. |
| scikit-survival | Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. |
| scvelo | RNA velocity analysis with scVelo. |
| scvi-tools | Deep generative models for single-cell omics. |
| structure-analysis | Handles protein structure files and geometric criteria so that residue counts, contacts, hydrogen bonds and interfaces are reproducible, covering PDB versus mmCIF, author versus label chains and numbering, HETATM, water and ligand policy, alternate… |
| synthetic-biology | Synthetic biology design and simulation tools. |
| tamarind | Access a collection of open-source molecular design and structural biology tools on the Tamarind Bio platform, via its REST API or MCP server — no local GPUs required. |
| tiledbvcf | Efficient storage and retrieval of genomic variant data using TileDB. |
| treatment-plans | Generate concise (3-4 page), focused medical treatment plans in LaTeX/PDF format for all clinical specialties. |
| waypoint-bio | Use when working with Outpost Bio's open microbiome foundation models - the Waypoint checkpoints (Waypoint-6m, Waypoint-45m, Waypoint-170m), the Atlas pretraining corpus, the Compass eight-task benchmark, or the waypoint CLI from the waypoint-bio package. |
Chemistry
| Skill and usage instructions | What the procedure covers |
|---|---|
| admet-prediction | ADMET property prediction for drug candidates. |
| admet-reasoning | Interpretable ADMET analysis with mechanistic reasoning. |
| analytical-method-validation | Plan, execute, and document validation, verification, and transfer of analytical procedures under the governing framework - ICH Q2(R2) and Q14, USP <1220>/<1225>/<1226>, ICH M10 bioanalytical, CLSI EP, or ISO/IEC 17025. |
| atomistic-workflows | Sets up and reports atomistic calculations so they are reproducible and converged, covering ASE Atoms, calculators, optimizers and MD drivers, pymatgen structures, symmetry analysis and the Materials Project API, LAMMPS and GROMACS input basics for… |
| binding-affinity | Empirical affinity estimates, ligand energy inspection, docking-score consensus, and batch virtual screening. |
| cheminformatics-definitions | Pins down the RDKit definitions that differ between conventions before computing molecular descriptors, including Lipinski donor and acceptor counts (Lipinski.NumHDonors and NumHAcceptors versus rdMolDescriptors.CalcNumLipinskiHBD and HBA), TPSA with or… |
| datamol | Pythonic wrapper around RDKit with simplified interface and sensible defaults. |
| deepchem | Molecular ML with diverse featurizers and pre-built datasets. |
| denovo-design | De novo molecule generation for drug discovery. |
| diffdock | Diffusion-based molecular docking. |
| drug-design | End-to-end drug discovery pipeline orchestration. |
| framework-topology | Turns a crystal structure (CIF) of a hydrogen-bonded, coordination or covalent framework into its underlying net and the quantities a topology question asks for: node definition, the periodic quotient graph, connectivity as distinct neighbours rather than… |
| hypogenic | Automated LLM-driven hypothesis generation and testing on tabular datasets. |
| matchms | Spectral similarity and compound identification for metabolomics. |
| medchem | Medicinal chemistry filters. |
| molecular-docking | End-to-end molecular docking pipeline. |
| molecular-dynamics | Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. |
| molecular-optimization | Iterative lead optimization with analyze-reason-generate-verify-evaluate loop. |
| molecular-rag | Retrieve structurally similar compounds with known properties from ChEMBL/ZINC to ground predictions and inform optimization. |
| molecule-visualization | Publication-quality molecular visualization. |
| molfeat | Molecular featurization for ML (100+ featurizers). |
| nmr-compound-inference | Analyze 1D 1H or 13C NMR data with nmrglue, generate spectrum plots and peak tables, compare against standard NMR libraries such as BMRB, HMDB, SDBS, and nmrshiftdb2, then produce a ranked candidate-compound report with evidence, caveats, and direct links. |
| pkpd-modeling | Pharmacokinetic and pharmacodynamic modelling and simulation - non-compartmental analysis, compartmental and population PK, PK/PD and exposure-response, TMDD, PBPK orientation, bioequivalence, allometric scaling and first-in-human dose, drug interaction… |
| pocket-detection | Multi-method binding pocket detection and druggability assessment. |
| pyopenms | Complete mass spectrometry analysis platform. |
| pytdc | Therapeutics Data Commons. |
| rdkit | Cheminformatics toolkit for fine-grained molecular control. |
| smiles-validation | Strict SMILES validation, structural comparison, and modification verification. |
| structure-prediction | Protein structure prediction from sequence. |
| torchdrug | PyTorch-native graph neural networks for molecules and proteins. |
Coding
| Skill and usage instructions | What the procedure covers |
|---|---|
| arboreto | Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). |
| audiocraft-audio-generation | PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). |
| denario | Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. |
| exploratory-data-analysis | Analyze scientific data files across 200+ formats at the depth the user requests. |
| gtars | High-performance toolkit for genomic interval analysis in Rust with Python bindings. |
| matlab | MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. |
| multi-objective-optimization | Pareto-aware molecular design balancing multiple ADMET properties simultaneously. |
| networkx | Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. |
| optimize-for-gpu | GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. |
| pymc-bayesian-modeling | Bayesian modeling with PyMC. |
| pymoo | Multi-objective optimization framework. |
| rowan | Cloud-based quantum chemistry platform with Python API. |
| scikit-learn | Machine learning in Python with scikit-learn. |
| shap | Model interpretability and explainability using SHAP (SHapley Additive exPlanations). |
| simpy | Process-based discrete-event simulation framework in Python. |
| slime-rl-training | Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. |
| statistical-analysis | Guided statistical analysis with test selection and reporting. |
| statsmodels | Statistical models library for Python. |
| sympy | Use this skill when working with symbolic mathematics in Python. |
| timesfm-forecasting | Zero-shot time series forecasting with Google's TimesFM foundation model. |
| torch-geometric | Graph Neural Networks (PyG). |
| umap-learn | UMAP dimensionality reduction. |
Compute workflows
| Skill and usage instructions | What the procedure covers |
|---|---|
| fireworks-ai-inference | Use your Fireworks account for supported inference and fine-tuning workflows. |
| givemeanode-agent-compute | Use a connected GiveMeANode service for GPU work, jobs, and storage with explicit resource limits. |
| lambda-gpu-cloud | Safely inspect and operate Lambda Cloud GPU instances through the documented Cloud API and SSH, with explicit approval before billable or destructive actions. |
| modal-serverless-gpu | Run approved CPU or GPU work through OpenScience compute_job on the user's configured Modal account. |
| runpod-gpu-cloud | Safely inspect and operate RunPod resources with runpodctl, live product data, and explicit approval before paid or destructive actions. |
| skypilot-multi-cloud-orchestration | Multi-cloud orchestration for ML workloads with automatic cost optimization. |
| tensorpool-gpu-cloud | Safely inspect and operate TensorPool GPU clusters and jobs using the current tp CLI, with explicit approval before any billable or destructive action. |
| tinker-fine-tuning | Provides guidance for fine-tuning LLMs using the Tinker cloud training API from Thinking Machines Lab. |
| tinker-training-cost | Calculates training costs for Tinker fine-tuning jobs. |
| together-ai-inference | Use your Together account for supported inference, embeddings, and fine-tuning workflows. |
| vast-ai-gpu-cloud | Safely inspect and operate Vast.ai marketplace instances with the vastai CLI, live offer data, and explicit approval before paid or destructive actions. |
core
| Skill and usage instructions | What the procedure covers |
|---|---|
| acceptance-checks | Turns the acceptance criteria a task states into executable checks and runs them against the finished outputs before delivering, rather than trusting that a correct-looking analysis satisfies them; rehearses the hidden condition when the grader scores… |
| analysis-report | Writes the trace and report for an analysis whose output a reader will judge, restating the question with its binding clauses, recording data provenance, the method with every parameter that matters, results with raw and adjusted numbers and uncertainty,… |
| autoresearch | Runs a hill-climbing study over many training or analysis runs with the study and experiments tools, one metric and direction, a baseline, ideas ranked by expected value, exactly one run per idea, kill criteria and a budget, verdicts with analysis and… |
| brainstorming | Generates and selects research directions, mapping what is known and what is open, producing many candidate ideas by named moves (gap, transfer, inversion, constraint change, scale, failure analysis), then ranking them by tractability and value and… |
| citations | Resolves, verifies and formats references, every citation confirmed against Crossref, OpenAlex, arXiv or PubMed before it enters the bibliography, BibTeX built from resolved metadata, and existing .bib files audited for fabricated or mismatched entries. |
| compute | Chooses and runs compute for research work, local shell or kernel versus a detached compute_job on this machine, a saved SSH or Slurm host, or Modal GPUs, with the target discovered from what is actually configured, the run sized and priced before… |
| delegation | Delegates independent work to worker agents through the Task tool, choosing between the explore scout and the ml, biology, physics, chemistry and data specialists, writing a self-contained brief for a worker that cannot see the conversation, setting… |
| execution-hygiene | Runs computations so they finish, reproduce and fit the machine that will re-execute them, detaching long jobs through compute_job instead of blocking or sleeping shells, checkpointing so reruns resume, fixing seeds and capping BLAS and OpenMP threads,… |
| figures | Makes publication-quality plots from data with matplotlib, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. |
| generate-image | Generate illustrations, graphical abstracts and image edits with generate_image through Ace or a Gemini or OpenAI key. |
| hypotheses | Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified… |
| literature-review | Finds, ranks and reads the literature on a question, the retrieval loop the lead runs itself over OpenAlex, arXiv, Crossref, PubMed and bioRxiv with a fixed budget, deduplication, ranking by topical fit, reading of the load-bearing papers and claim-level… |
| ml-paper-writing | Writes and revises machine-learning papers for NeurIPS, ICML, ICLR, ACL, COLM and AAAI, from a research repository or a set of tracked runs to a compiling LaTeX draft in the venue's template, with the contribution stated as claims backed by experiments,… |
| paper-writing | Writes and revises scientific manuscripts, journal articles, preprints, theses, reports, in full paragraphs with the argument built from the project's actual results and sources, as a real .tex or .md file in the working folder. |
| peer-review | Reviews a manuscript, proposal, analysis or result the way a careful referee does, reading the whole artifact, checking the methods against the claims, the statistics against the design, the figures against the numbers, and reporting BLOCKING issues… |
| reproduce | Reproduces a paper's result, a claim, an artifact or a previous run with the target and success criterion frozen first, the canonical code path run before any substitute, exact inputs, environment, seeds and commands captured, and a verdict from a fixed… |
| research-lookup | Find current research and technical references with configured search access and citations. |
| schematics | Creates or refines publication-quality technical diagrams with the native generate_image tool (Nano Banana Pro through Ace or a Gemini key, GPT Image 2 through an OpenAI key), method and architecture overviews, pipelines, CONSORT and PRISMA flows,… |
| scientific-visualization | Creates and audits truthful, accessible, publication-ready scientific figures with Matplotlib, Seaborn or Plotly, covering figure design, multi-panel layouts, uncertainty and missing-data displays, colour and contrast review, image metadata validation and… |
| sources | Audits claims against their sources, each statement in a draft, report, answer or summary traced to the passage, table, dataset or run that supports it, and marked supported, partially supported, unsupported or contradicted, with a provenance table as the… |
| statistical-conventions | Chooses and reports statistical tests the way a careful referee expects, deciding paired versus unpaired and parametric versus rank-based from the design, using ordered-trend tests such as Jonckheere-Terpstra and Cochran-Armitage for dose or grade levels,… |
| submitted-code | Writes code that survives being re-executed by someone else on inputs you never saw, targeting the grader's or collaborator's runtime rather than your own, with one self-contained entry point using only the libraries the specification names, no reliance on… |
Data engineering
| Skill and usage instructions | What the procedure covers |
|---|---|
| aeon | This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. |
| dask | Distributed computing for larger-than-RAM pandas/NumPy workflows. |
| datalad | Retrieve, version, and publish scientific datasets with DataLad and git-annex, and capture computational provenance with datalad run, rerun, and containers-run. |
| geomaster | Comprehensive geospatial science skill covering remote sensing, GIS, spatial analysis, machine learning for earth observation, and 30+ scientific domains. |
| geopandas | Python library for working with geospatial vector data including shapefiles, GeoJSON, and GeoPackage files. |
| hdf5-pde-data-loading | Patterns for loading PDE simulation datasets (PDEBench, PhiFlow, JAX-CFD) from HDF5 files. |
| hugging-face-datasets | Create and manage datasets on Hugging Face Hub. |
| markitdown | Convert files and office documents to Markdown. |
| polars | Fast in-memory DataFrame library for datasets that fit in RAM. |
| ray-data | Scalable data processing for ML workloads. |
| vaex | Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. |
| zarr-python | Chunked N-D arrays for cloud storage. |
Databases
| Skill and usage instructions | What the procedure covers |
|---|---|
| alphafold-database | Access AlphaFold 200M+ AI-predicted protein structures. |
| biorxiv-database | Efficient database search tool for bioRxiv preprint server. |
| brenda-database | Access BRENDA enzyme database via SOAP API. |
| cellxgene-census | Query the CELLxGENE Census (61M+ cells) programmatically. |
| chembl-database | Query ChEMBL bioactive molecules and drug discovery data. |
| clinicaltrials-database | Query ClinicalTrials.gov via API v2. |
| clinpgx-database | Access ClinPGx pharmacogenomics data (successor to PharmGKB). |
| clinvar-database | Query NCBI ClinVar for variant clinical significance. |
| cosmic-database | Access COSMIC cancer mutation database. |
| database-lookup | Query documented public database APIs with explicit endpoints, filters, pagination, and provenance. |
| datacommons-client | Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. |
| depmap | Query the Cancer Dependency Map (DepMap) for cancer cell line gene dependency scores (CRISPR Chronos), drug sensitivity data, and gene effect profiles. |
| drugbank-database | Access and analyze comprehensive drug information from the DrugBank database including drug properties, interactions, targets, pathways, chemical structures, and pharmacology data. |
| ena-database | Access European Nucleotide Archive via API/FTP. |
| ensembl-database | Query Ensembl genome database REST API for 250+ species. |
| fda-database | Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research. |
| fred-economic-data | Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources. |
| gene-database | Query NCBI Gene via E-utilities/Datasets API. |
| geo-database | Access NCBI GEO for gene expression/genomics data. |
| gwas-database | Query NHGRI-EBI GWAS Catalog for SNP-trait associations. |
| hmdb-database | Access Human Metabolome Database (220K+ metabolites). |
| imaging-data-commons | Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. |
| kegg-database | Direct REST API access to KEGG (academic use only). |
| metabolomics-workbench-database | Access NIH Metabolomics Workbench via REST API (4,200+ studies). |
| ncats-arax | Queries the NCATS Translator ARAX production API for bounded, typed, provenance-rich one-hop and endpoint-pinned two-hop biomedical knowledge-graph relationships. |
| onekgpd | Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants. |
| ontology-term-resolution | Resolve free-text scientific labels to ontology term IDs and validate existing CURIEs against the EBI Ontology Lookup Service (OLS4). |
| openalex-database | Query and analyze scholarly literature using the OpenAlex database. |
| opentargets-database | Query Open Targets Platform for target-disease associations, drug target discovery, tractability/safety data, genetics/omics evidence, known drugs, for therapeutic target identification. |
| pdb-database | Access RCSB PDB for 3D protein/nucleic acid structures. |
| primekg | Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more. |
| pubchem-database | Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). |
| pubmed-database | Direct REST API access to PubMed. |
| reactome-database | Query Reactome REST API for pathway analysis, enrichment, gene-pathway mapping, disease pathways, molecular interactions, expression analysis, for systems biology studies. |
| string-database | Query STRING API for protein-protein interactions (59M proteins, 20B interactions). |
| uniprot-database | Direct REST API access to UniProt. |
| usfiscaldata | Query the U.S. |
| uspto-database | Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches. |
| zinc-database | Access ZINC (230M+ purchasable compounds). |
document-parsing
| Skill and usage instructions | What the procedure covers |
|---|---|
| docx | Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). |
| Use this skill whenever the user wants to do anything with PDF files. | |
| pptx | Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. |
| xlsx | Create, edit, analyze, or convert Excel spreadsheets (.xlsx, .xlsm, .xltx) where the workbook file is the primary deliverable. |
General
| Skill and usage instructions | What the procedure covers |
|---|---|
| checkpoint | Save a local recovery packet from durable session state. |
| compact | Compact the current chat context into a concise summary. |
| goal | Set an explicit objective, success criteria, and stopping conditions for the current OpenScience session. |
| handoff | Create a self-contained continuation packet for another agent. |
| init | Create or refresh an AGENTS.md project instruction file. |
| liteparse | Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally without cloud dependencies. |
| plan | Enter read-only plan mode and produce a decision-ready plan. |
| stop | Stop active work in the current conversation and check the state of ongoing jobs. |
Language model tools
| Skill and usage instructions | What the procedure covers |
|---|---|
| autogpt-agents | Autonomous AI agent platform for building and deploying continuous agents. |
| blip-2-vision-language | Vision-language pre-training framework bridging frozen image encoders and LLMs. |
| chroma | Open-source embedding database for AI applications. |
| clip | Work on image-text matching, image classification, and related vision-language tasks. |
| constitutional-ai | Anthropic's method for training harmless AI through self-improvement. |
| crewai-multi-agent | Multi-agent orchestration framework for autonomous AI collaboration. |
| dspy | Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming |
| faiss | Facebook's library for efficient similarity search and clustering of dense vectors. |
| guidance | Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework |
| hugging-face-cli | Execute Hugging Face Hub operations using the hf CLI. |
| hugging-face-tool-builder | Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. |
| huggingface-tokenizers | Fast tokenizers optimized for research and production. |
| instructor | Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library |
| langchain | Build language-model applications with retrieval, tools, and connected services. |
| langsmith-observability | LLM observability platform for tracing, evaluation, and monitoring. |
| llamaguard | Meta's 7-8B specialized moderation model for LLM input/output filtering. |
| llamaindex | Data framework for building LLM applications with RAG. |
| llava | Large Language and Vision Assistant. |
| llm-as-judge-evaluation | Evaluate LLM outputs using frontier models as judges. |
| long-context | Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. |
| nemo-guardrails | NVIDIA's runtime safety framework for LLM applications. |
| outlines | Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library |
| pinecone | Managed vector database for production AI applications. |
| qdrant-vector-search | High-performance vector similarity search engine for RAG and semantic search. |
| segment-anything-model | Foundation model for image segmentation with zero-shot transfer. |
| sentence-transformers | Framework for state-of-the-art sentence, text, and image embeddings. |
| sentencepiece | Language-independent tokenizer treating text as raw Unicode. |
| stable-diffusion-image-generation | State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. |
| transformers | This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. |
| whisper | Transcribe speech, identify language, or translate speech to English with available Whisper models. |
Machine learning inference
| Skill and usage instructions | What the procedure covers |
|---|---|
| gguf-quantization | GGUF format and llama.cpp quantization for efficient CPU/GPU inference. |
| groq-inference | Use your Groq account for supported inference and audio workflows. |
| llama-cpp | Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. |
| miles-rl-training | Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. |
| phoenix-observability | Open-source AI observability platform for LLM tracing, evaluation, and monitoring. |
| serving-llms-vllm | Serve language models with vLLM and investigate memory, throughput, and inference configuration. |
| sglang | Fast structured generation and serving for LLMs with RadixAttention prefix caching. |
| speculative-decoding | Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. |
| tensorrt-llm | Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. |
Machine learning training
| Skill and usage instructions | What the procedure covers |
|---|---|
| adaptyv | Cloud laboratory platform for automated protein testing and validation. |
| awq-quantization | Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. |
| axolotl | Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support |
| colab-finetuning | Fine-tune LLMs on Google Colab GPUs directly from openscience. |
| deepspeed | Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention |
| distributed-llm-pretraining-torchtitan | Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). |
| evaluating-code-models | Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. |
| evaluating-llms-harness | Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). |
| fine-tuning-with-trl | Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. |
| geniml | This skill should be used when working with genomic interval data (BED files) for machine learning tasks. |
| gptq | Post-training 4-bit quantization for LLMs with minimal accuracy loss. |
| grpo-rl-training | Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training |
| hqq-quantization | Half-Quadratic Quantization for LLMs without calibration data. |
| hugging-face-evaluation | Add and manage evaluation results in Hugging Face model cards. |
| hugging-face-model-trainer | This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. |
| huggingface-accelerate | Simplest distributed training API. |
| implementing-llms-litgpt | Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). |
| knowledge-distillation | Compress large language models using knowledge distillation from teacher to student models. |
| llama-factory | Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support |
| mamba-architecture | State-space model with O(n) complexity vs Transformers' O(n²). |
| ml-benchmark-evaluation | Rigorous methodology for evaluating ML models on established benchmarks. |
| mlflow | Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform |
| model-economics | Cost modeling and ROI analysis for specialized LLM development. |
| model-merging | Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. |
| model-pruning | Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. |
| moe-training | Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. |
| nanogpt | Educational GPT implementation in ~300 lines. |
| nemo-curator | GPU-accelerated data curation for LLM training. |
| nemo-evaluator-sdk | Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. |
| nnsight-remote-interpretability | Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. |
| openrlhf-training | High-performance RLHF framework with Ray+vLLM acceleration. |
| optimizing-attention-flash | Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. |
| peft-fine-tuning | Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. |
| prime-intellect | Safely inspect Prime Intellect identity and plan compute or training workflows using the installed prime CLI and current official documentation. |
| pufferlib | High-performance reinforcement learning framework optimized for speed and scale. |
| pytorch-fsdp | Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2 |
| pytorch-lightning | High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. |
| pyvene-interventions | Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. |
| quantizing-models-bitsandbytes | Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. |
| ray-train | Distributed training orchestration across clusters. |
| rwkv-architecture | RNN+Transformer hybrid with O(n) inference. |
| simpo-training | Simple Preference Optimization for LLM alignment. |
| sparse-autoencoder-training | Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. |
| stable-baselines3 | Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. |
| tensorboard | Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit |
| torchforge-rl-training | Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. |
| training-data-pipeline | Build training datasets for LLM specialization from production data, frontier model distillation, and synthetic bootstrapping. |
| training-llms-megatron | Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. |
| transformer-lens-interpretability | Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. |
| unsloth-fine-tuning | Fast LLM fine-tuning with Unsloth - 2-5x faster training, 50-80% less VRAM. |
| verl-rl-training | Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). |
| weights-and-biases | Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform |
Other workflows
| Skill and usage instructions | What the procedure covers |
|---|---|
| coq | Develops and checks proofs in Coq and its renamed successor Rocq, covering the _CoqProject and coq_makefile (or rocq makefile) build, coqc and coqchk (or rocq compile and rocq check), finding lemmas with Search and SearchPattern, choosing… |
| get-available-resources | This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). |
| hugging-face-jobs | This skill should be used when users want to run any workload on Hugging Face Jobs infrastructure. |
| hugging-face-trackio | Track and visualize ML training experiments with Trackio. |
| iso-13485-certification | Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems. |
| iso-standards-readiness | Prepares and structurally reviews readiness evidence for ISO management-system and laboratory-competence standards - ISO 13485 medical device QMS, ISO 14971 device risk management, ISO/IEC 17025 testing and calibration laboratories, and ISO 15189 medical… |
| lab-hardware-cad | Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks,… |
| labarchive-integration | Electronic lab notebook API integration. |
| lean4-mathlib | Formalizes and checks mathematical statements in Lean 4 with Mathlib, covering the lake project layout and pinned toolchain, lake exe cache get before lake build, searching Mathlib through Loogle, exact?, apply? and simp?, tactic hygiene,… |
| skill-installer | Install or remove third-party openscience skills from a public git repository. |
Physics
| Skill and usage instructions | What the procedure covers |
|---|---|
| astronomy-inference | Carries astronomical data from file to posterior with the conventions the field expects, covering astropy units, coordinates, FITS, WCS and Time with barycentric corrections, photometric systems and magnitude arithmetic, period finding with the astropy… |
| astropy | Comprehensive Python library for astronomy and astrophysics. |
| autoregressive-neural-pde-solver | Training patterns for autoregressive neural PDE solvers (FNO, DeepONet, CNO). |
| bayesian-inference | Bayesian parameter estimation with MCMC (emcee) and probabilistic programming (PyMC). |
| conservation-law-discovery | Discover conserved quantities and symmetries from trajectory data. |
| dimensional-analysis | Automated dimensional analysis — Buckingham Pi theorem, non-dimensionalization, unit validation with pint, and characteristic scale estimation. |
| dynamical-systems | Analyze nonlinear dynamical systems — phase portraits, fixed points, stability analysis, bifurcation diagrams, Poincare sections, Lyapunov exponents, and chaos detection. |
| energy-systems | Applies energy-systems modelling conventions so that capacity, energy, cost and emissions numbers are consistent and comparable, covering kW versus kWh and MW versus MWh, capacity versus energy, capacity factors, load duration curves, the LCOE formula with… |
| fluid-dynamics | Computational fluid dynamics — Navier-Stokes solvers, lid-driven cavity, channel flow, vortex methods, turbulence statistics, drag/lift computation. |
| fluidsim | Framework for computational fluid dynamics simulations using Python. |
| geoscience-data | Reads, transforms and summarizes gridded and geospatial data without losing the metadata that gives it meaning, covering NetCDF and HDF5 through xarray and netCDF4 with CF conventions, dimensions versus coordinates, time encodings and calendars and fill… |
| hamiltonian-mechanics | Hamiltonian mechanics — symplectic integrators (leapfrog, Yoshida), Hamilton's equations, Poisson brackets, canonical transformations, action-angle variables, and KAM theory analysis. |
| neural-operator | Train neural operators (FNO, DeepONet) to learn solution maps for parametric PDE families. |
| ode-solver | Solve ordinary differential equations (initial and boundary value problems). |
| openpiv | Particle Image Velocimetry (PIV) analysis with OpenPIV. |
| pde-solver | Solve partial differential equations — finite differences, spectral methods, and physics-informed neural networks (PINNs via DeepXDE). |
| physics-databases | Query physics databases — NIST CODATA constants, NIST Chemistry WebBook, Materials Project, Particle Data Group (PDG), OEIS sequences. |
| physics-fitting | Nonlinear curve fitting for physics data with proper error propagation, chi-squared analysis, residual diagnostics, confidence intervals, and model comparison (AIC/BIC). |
| physics-visualization | Publication-quality physics plots — vector fields, streamlines, contour maps, 3D surfaces, phase space, spectrograms, and animations. |
| pinn-training | Train Physics-Informed Neural Networks (PINNs) using DeepXDE. |
| pymatgen | Materials science toolkit. |
| shock-capturing-neural-operators | Architectures and techniques for neural operators on discontinuous PDE solutions (shocks, contact discontinuities, steep gradients). |
| sindy-identification | Sparse Identification of Nonlinear Dynamics (SINDy) — discover governing equations from time-series data. |
| spectral-analysis | Frequency-domain analysis — FFT, power spectral density (Welch/periodogram), spectrograms, wavelet transforms, and coherence. |
| statistical-mechanics | Monte Carlo simulation for statistical mechanics — Ising model, Metropolis-Hastings, Wolff cluster algorithm, observables (magnetization, susceptibility, specific heat), finite-size scaling, and critical phenomena analysis. |
| symbolic-regression | Discover governing equations from data using PySR (evolutionary symbolic regression). |
| uncertainty-and-units | Track physical units and propagate measurement uncertainty in scientific calculations using pint and uncertainties. |
| wave-propagation | Simulate wave propagation — acoustic, electromagnetic, elastic, and quantum waves. |
Quantum science
| Skill and usage instructions | What the procedure covers |
|---|---|
| cirq | Google quantum computing framework. |
| pennylane | Hardware-agnostic quantum ML framework with automatic differentiation. |
| qiskit | IBM quantum computing framework. |
| qutip | Quantum physics simulation library for open quantum systems. |
Research methods
| Skill and usage instructions | What the procedure covers |
|---|---|
| compare | Compare runs, artifacts, methods, models, or claims on a fair and explicit decision basis. |
| experimental-design | Design experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. |
| export | Package results with provenance, reproduction instructions, declared gaps, and the requested output format. |
| market-research-reports | Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). |
| paper-lookup | Search 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA status, and return results with reproducible provenance. |
| patent-mining | Retrieves and interprets patent data with the conventions that make counts and claims defensible, covering Google Patents, Lens, EPO Open Patent Services, USPTO data through PatentsView and the Open Data Portal, and WIPO PATENTSCOPE, together with kind… |
| research-grants | Write competitive research proposals for NSF, NIH, DOE, and DARPA. |
| research-workflows | Plan, review, verify, reproduce, compare, audit sources, and package scientific work. |
| review | Independently review code, results, claims, or an artifact and return prioritized, evidence-backed findings. |
| scholar-evaluation | Evaluate scholarly work with structured criteria for rigor, methodology, evidence, writing, and publication readiness. |
| statistical-power | Sample-size and statistical power calculations for planning studies. |
Visualization
| Skill and usage instructions | What the procedure covers |
|---|---|
| dna-visualization | Publication-quality DNA/RNA visualizations. |
| infographics | Create and review explanatory infographics; this procedure is experimental. |
| matplotlib | Low-level plotting library for full customization. |
| plotly | Interactive visualization library. |
| protein-diagram | Publication-quality protein analysis diagrams. |
| seaborn | Statistical visualization with pandas integration. |
Writing
| Skill and usage instructions | What the procedure covers |
|---|---|
| hugging-face-paper-publisher | Publish and manage research papers on Hugging Face Hub. |
| latex-posters | Create professional research posters in LaTeX using beamerposter, tikzposter, or baposter. |
| markdown-mermaid-writing | Comprehensive markdown and Mermaid diagram writing skill. |
| paper-2-web | This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference posters (Paper2Poster). |
| pptx-posters | Create research posters using HTML/CSS that can be exported to PDF or PPTX. |
| pyzotero | Interact with Zotero reference management libraries using the pyzotero Python client. |
| scientific-slides | [EXPERIMENTAL] Build slide decks and presentations for research talks using Nano Banana Pro AI. |
| zotero-local | Read or search the user's local Zotero reference library when explicitly requested. |