| 8.3 | skills.sh | cellxgene-census cellxgene-census enables programmatic querying of 61m+ standardized single-cell genomics records across tissues and diseases. covers exploratory metadata lookups, small-to-medium anndata retrieval, large out-of-core iteration, pytorch integration, and scanpy workflows with concrete examples for each pattern. |
| 8.3 | skills.sh | dask dask scales pandas, numpy, and unstructured data workflows beyond single-machine memory limits using lazy evaluation and distributed execution. choose dataframes for tabular data, arrays for numeric computation, bags for text/logs, or futures for custom parallel tasks. |
| 8.2 | skills.sh | markdown-mermaid-writing markdown-mermaid-writing establishes a text-first documentation standard using mermaid diagrams embedded in markdown files as the canonical source format. covers 24 diagram types with phase-gated workflows for optional downstream polish via python or ai rendering. |
| 8.2 | skills.sh | modal modal provides serverless python execution on gpus with autoscaling, persistent volumes, web endpoints, and scheduled jobs. deploy ai/ml models, batch jobs, and apis without yaml or dockerfiles. |
| 7.8 | skills.sh | shap shap provides structured guidance for computing shapley values, selecting appropriate explainers, and visualizing feature contributions across tree, deep learning, linear, and black-box models. covers workflows from basic explanation through production deployment with performance optimization. |
| 7.8 | skills.sh | cobrapy cobrapy enables constraint-based metabolic modeling through flux balance analysis, gene knockouts, flux sampling, and minimal media calculations. supports sbml, json, yaml model formats and provides context managers for safe temporary modifications. |
| 7.4 | skills.sh | zarr-python zarr-python provides chunked n-dimensional array storage with compression and cloud backends (s3, gcs). covers array creation, slicing, groups, dask/xarray integration, and performance tuning via chunk alignment and codec selection. |
| 7.3 | skills.sh | generate-image generate-image wraps openrouter api calls to produce or modify images via flux and gemini models, with straightforward cli invocation and model selection based on quality, speed, or cost tradeoffs. |
| 7.3 | skills.sh | umap-learn umap-learn covers nonlinear dimensionality reduction for visualization, clustering preprocessing, and feature engineering. includes supervised/semi-supervised modes, parametric variants with neural networks, and integration with scikit-learn pipelines. |
| 7.2 | skills.sh | geopandas geopandas extends pandas with spatial operations on vector geometries, supporting shapefile, geojson, and geopackage formats. covers coordinate reference systems, geometric operations, spatial joins, and visualization through matplotlib and folium. |
| 7.2 | skills.sh | simpy simpy is a process-based discrete-event simulation framework for modeling systems where entities compete for shared resources. covers queuing, resource contention, capacity planning, and network simulation with generator-based process definitions. |
| 7.2 | skills.sh | qutip qutip simulates open and closed quantum systems via master equations, lindblad dynamics, and monte carlo trajectories. covers state preparation, time evolution, entanglement analysis, and visualization across cavity qed, decoherence, and quantum optics. |
| 6.8 | skills.sh | transformers transformers covers loading and inference with hugging face pre-trained models across nlp, vision, and audio domains via pipelines, manual model loading, and fine-tuning workflows. |
| 6.3 | skills.sh | pyopenms pyopenms wraps the openms library for mass spectrometry data analysis, covering file i/o, signal processing, feature detection, peptide identification, and metabolomics workflows with python bindings. |
| 6.2 | skills.sh | pptx-posters pptx-posters generates research posters in html/css with export to pdf or powerpoint, emphasizing ai-generated visuals and strict simplification rules for readability from distance. primarily for users explicitly requesting pptx format over latex alternatives. |
| 6.2 | skills.sh | pennylane pennylane provides hardware-agnostic quantum circuit training with automatic differentiation, supporting multiple backends (IBM, Amazon Braket, Google, Rigetti, IonQ) and hybrid classical-quantum workflows for ML and chemistry applications. |
| 6.2 | skills.sh | xlsx xlsx covers creation, editing, and analysis of spreadsheet files with detailed formatting and formula standards for financial models, including color-coding conventions, number formatting rules, and error prevention practices. |
| 6.2 | skills.sh | geniml geniml trains embeddings on genomic interval data for region similarity, single-cell clustering, and cross-modal metadata search. covers region2vec, bedspace, scembed, consensus peak building, and supporting utilities. |
| 6.1 | skills.sh | get-available-resources get-available-resources detects cpu, gpu, and memory availability to inform computational strategy selection. generates recommendations for parallelization, acceleration backend choice, and storage approach. |
| 6.1 | skills.sh | usfiscaldata usfiscaldata wraps the treasury fiscal data api for querying federal debt, spending, revenue, interest rates and exchange data via http rest calls with no auth required. |
| 5.8 | skills.sh | gget gget wraps 20+ genomic databases behind a unified cli and python interface for gene lookups, sequence analysis, and protein structure queries. covers common bioinformatics workflows but lacks explicit procedure detail. |
| 5.8 | skills.sh | flowio flowio parses flow cytometry standard files (versions 2.0-3.1), extracting event data as numpy arrays and metadata with minimal dependencies. supports csv export and dataframe conversion for cytometry data pipelines. |
| 5.8 | skills.sh | scanpy scanpy covers standard single-cell rna-seq workflows from quality control through trajectory analysis, but lacks step-by-step procedure detail and omits edge cases entirely. |
| 5.6 | skills.sh | vaex vaex handles out-of-core dataframe operations on billion-row datasets, enabling lazy evaluation and fast aggregations without requiring data to fit in ram. covers format conversion and interactive visualization. |
| 5.6 | skills.sh | astropy astropy provides coordinate transformations, fits file handling, unit conversions, and tabular data operations for astronomical research. covers cosmological calculations and time scale conversions but lacks procedural depth. |
| 5.5 | skills.sh | bioservices bioservices wraps 40+ bioinformatics databases (uniprot, kegg, chembl, reactome) behind a unified python interface for cross-resource queries and identifier mapping. covers sequence retrieval, pathway analysis, and compound search. |
| 5.4 | skills.sh | market-research-reports generates 50+ page market research reports modeled on consulting firm deliverables using LaTeX, frameworks like porter's five forces and swot, and research-lookup integration for data. output contract and error handling both underspecified. |
| 5.3 | skills.sh | pyzotero pyzotero wraps the zotero api v3 for programmatic library management. covers reading, creating, updating items, collections, tags, and citation export but lacks procedural depth and error handling specifics. |
| 5.2 | skills.sh | scientific-visualization scientific-visualization covers plot creation for manuscript submission, including multi-panel layouts, significance annotations, error bars, and colorblind-accessible palettes. exports in pdf/eps/tiff formats. |
| 5.2 | skills.sh | bgpt-paper-search bgpt-paper-search retrieves structured experimental data from peer-reviewed studies via remote mcp server, extracting 25+ metadata fields including methods, results, sample sizes, and quality assessments for systematic review and meta-analysis workflows. |
| 5.2 | skills.sh | statsmodels statsmodels provides regression, time series, and generalized linear models with built-in diagnostics and inference tools. covers ols, arima, glm, and causal estimation but lacks procedural depth on implementation. |
| 5.2 | skills.sh | torchdrug torchdrug provides pytorch-based gnn tooling for drug discovery across molecules, proteins, and knowledge graphs. covers property prediction, retrosynthesis, and molecular generation with 40+ datasets and 20+ model architectures. |
| 5.2 | skills.sh | pydicom pydicom handles reading, writing, and manipulation of dicom medical imaging files including pixel data extraction, metadata operations, and anonymization. covers multiple imaging modalities and compression formats. |
| 5.2 | skills.sh | gtars gtars provides rust-based genomic interval analysis with python bindings for bed file manipulation, overlap detection, coverage track generation, and reference sequence operations. |
| 5.2 | skills.sh | pymatgen pymatgen provides crystal structure manipulation, electronic structure analysis, and materials project database access. covers format conversion, phase diagrams, band structures, and high-throughput workflow setup across 100+ computational code formats. |
| 5.2 | skills.sh | cirq cirq provides circuit design, simulation, and hardware execution for google quantum ai and partner platforms. covers parameterized sweeps, noise modeling, and variational algorithms with templates for common workflows. |
| 5.2 | skills.sh | pysam pysam wraps htslib for python-based genomic file manipulation (sam/bam/cram/vcf/fastq). covers alignment queries, variant inspection, and coverage analysis but lacks procedural depth and error handling guidance. |
| 5.2 | skills.sh | scikit-bio scikit-bio wraps a python bioinformatics toolkit for sequence analysis, phylogenetics, diversity metrics, and ordination. covers fasta/newick i/o and statistical tests on ecological data but lacks procedural detail. |
| 5.2 | skills.sh | ginkgo-cloud-lab ginkgo-cloud-lab enables protocol submission to autonomous biolab infrastructure via web interface, with preset protocols for protein expression and custom workflow assessment through an ai feasibility agent. |
| 5.2 | skills.sh | adaptyv adaptyv covers protein sequence submission to a cloud lab api for automated binding, thermostability, expression, and fluorescence assays, with results delivered in ~21 days. authentication via bearer token. |
| 5.2 | skills.sh | arboreto arboreto infers gene regulatory networks from transcriptomics data using grnboost2 and genie3 algorithms, scaling from single machines to clusters. incomplete documentation limits practical deployment. |
| 5.1 | skills.sh | literature-review literature-review coordinates searches across academic databases and citation tools to assemble systematic reviews, but lacks concrete procedural steps and explicit handling of common failure modes like database downtime or citation conflicts. |
| 5.1 | skills.sh | paper-lookup paper-lookup searches 10 academic databases via rest apis to retrieve research papers, preprints, and scholarly articles. routes queries to appropriate sources and returns raw responses with query lineage. |
| 5.1 | skills.sh | statistical-analysis statistical-analysis guides hypothesis testing, regression, and assumption checking with apa-formatted reporting. covers t-tests, anova, chi-square, bayesian methods, effect sizes, and power analysis for research workflows. |
| 5.1 | skills.sh | deepchem deepchem covers molecular property prediction and featurization for chemistry and biology workflows, with access to pretrained models and benchmark datasets, but lacks procedural depth for end-to-end implementation. |
| 4.8 | skills.sh | scientific-writing scientific-writing provides scaffolding for research-backed manuscript production using imrad structure, citations, and reporting guidelines. lacks concrete procedure steps, trigger conditions, and failure mode handling. |
| 4.8 | skills.sh | matplotlib matplotlib covers low-level plotting with full element customization. useful for scientific visualizations, multi-panel figures, and format exports. typical choice when fine-grained control over plot appearance matters. |
| 4.8 | skills.sh | scholar-evaluation scholar-evaluation applies the ScholarEval framework to assess research quality across multiple dimensions, but lacks concrete procedural steps, specific trigger patterns, and explicit failure handling needed for reliable operation. |
| 4.8 | skills.sh | etetoolkit etetoolkit provides phylogenetic tree manipulation, evolutionary event detection, and visualization across multiple formats (newick, nhx, phyloxml, nexml) with ncbi taxonomy integration for bioinformatics workflows. |
| 4.8 | skills.sh | imaging-data-commons imaging-data-commons provides access to nci cancer imaging datasets via idc-index python bindings, supporting bulk query and download of ct, mr, and pet radiology data without authentication. |
| 4.8 | skills.sh | anndata anndata covers creation, manipulation and i/o of annotated data matrices for single-cell genomics. stores experimental measurements alongside metadata in h5ad or zarr formats, integrates with the scverse ecosystem. |
| 4.6 | skills.sh | what-if-oracle what-if-oracle provides a theoretical framework for multi-branch scenario modeling using the 0-if-1 paradigm, but lacks concrete procedural steps and actionable input/output contracts. |
| 4.6 | skills.sh | phylogenetics phylogenetics covers sequence alignment (mafft), maximum likelihood tree inference (iq-tree 2, fasttree), and tree visualization via ete3. the skill frames the computational pipeline but lacks complete automation guidance. |
| 4.5 | skills.sh | omero-integration omero-integration covers microscopy data management via the omero-py api, including image retrieval, pixel analysis, roi and annotation management, and batch processing for high-content screening workflows. |
| 4.5 | skills.sh | matlab matlab covers matrix operations and numerical computing via MATLAB or GNU Octave. provides basic invocation syntax for running scripts but lacks procedural depth for realistic use cases. |
| 4.4 | skills.sh | deeptools deeptools covers ngs data processing and visualization for chip-seq, rna-seq, and atac-seq including bam conversion, qc metrics, and heatmap generation, but lacks concrete workflow guidance. |
| 4.3 | skills.sh | scientific-critical-thinking scientific-critical-thinking frames evaluation of research rigor using methodology assessment and bias detection, but lacks actionable procedural steps and omits failure modes entirely. |
| 4.3 | skills.sh | latex-posters latex-posters provides high-level context for creating conference and academic research posters using beamerposter, tikzposter, or baposter, but lacks procedural depth and concrete workflow steps for execution. |
| 4.3 | skills.sh | infographics infographics wraps nano banana pro ai for automated visual generation with gemini 3 pro quality gates and optional perplexity sonar research integration, targeting users without design skills. |
| 4.3 | skills.sh | biopython biopython is a python toolkit for molecular biology tasks including sequence manipulation, file parsing, and database access. the provided skill documentation is incomplete and does not specify concrete trigger patterns, procedures, decision logic, or error handling. |
| 4.3 | skills.sh | scvelo scvelo estimates cell state transitions and infers developmental trajectories from unspliced/spliced mrna dynamics in single-cell rna-seq data without time-course labeling. |
| 4.3 | skills.sh | dhdna-profiler dhdna-profiler claims to extract cognitive patterns and thinking fingerprints from text using a 12-dimensional framework, but the skill.md ends abruptly before detailing the actual procedure, decision logic, or output structure. |
| 4.3 | skills.sh | torch-geometric torch-geometric covers graph neural network construction and training with pyg's standard layer library, data structures, and mini-batch support, but lacks complete procedural depth and failure guidance. |
| 4.2 | skills.sh | pymoo pymoo is a multi-objective optimization framework for evolutionary algorithms and pareto front discovery. it supports nsga-ii/iii, moea/d, and constraint handling across mixed variable types, but lacks procedural guidance for implementation. |
| 4.2 | skills.sh | treatment-plans treatment-plans generates LaTeX-formatted clinical care documentation (3-4 page standard) across medical specialties with stated regulatory compliance, but lacks procedural specificity and edge case handling for real-world deployment. |
| 4.2 | skills.sh | polars-bio polars-bio wraps interval operations and file i/o for genomic data atop polars, claiming 6-38x speedup over bioframe. no runnable procedures provided. |
| 4.2 | skills.sh | iso-13485-certification iso-13485-certification provides templated guidance for medical device qms documentation gaps, checklists, and requirement reference without actionable procedures for actual artifact generation or compliance validation. |
| 4.1 | skills.sh | markitdown markitdown converts multiple document formats (pdf, docx, pptx, xlsx, images, audio, html, csv, json, xml, zip) to markdown with optional ocr and transcription, targeting llm-friendly token efficiency. |
| 4.1 | skills.sh | diffdock diffdock predicts 3d protein-ligand binding poses using diffusion models, suitable for structure-based drug discovery. supports pdb structures, multiple ligand formats, and confidence scoring but requires external scoring for binding affinity estimation. |
| 3.9 | skills.sh | geomaster geomaster catalogs geospatial libraries and installation steps across 8 languages but lacks actionable procedures, decision logic, or executable workflows. reads as a package index, not a skill. |
| 3.8 | skills.sh | pdf pdf skill provides basic code snippets for reading and writing pdf files using pypdf, but lacks detailed procedures, error handling, and clear input/output contracts needed for production use. |
| 3.8 | skills.sh | scientific-brainstorming scientific-brainstorming guides open-ended research ideation through structured conversation, helping researchers surface novel hypotheses and interdisciplinary connections without prescriptive methodology. |
| 3.8 | skills.sh | scientific-slides scientific-slides offers broad guidance on presentation design philosophy and audience contexts but lacks concrete, step-by-step procedures for actually building slides in tools like powerpoint or google slides. |
| 3.8 | skills.sh | seaborn seaborn is a python statistical visualization library built on matplotlib, designed for rapid exploratory analysis of distributions and relationships within pandas dataframes with sensible aesthetic defaults. |
| 3.8 | skills.sh | open-notebook open-notebook is a self-hosted research tool that organizes documents and enables ai-powered analysis, podcast generation, and conversational queries with full data privacy and multi-provider llm support. |
| 3.8 | skills.sh | clinical-reports clinical-reports covers documentation of medical information across case reports, diagnostic reports, clinical trials, and patient records. lacks procedural depth and fails to specify actionable steps or recovery strategies for common failures. |
| 3.8 | skills.sh | qiskit qiskit provides circuit building and optimization for quantum computing across multiple backends. covers transpilation, gate reduction, and algorithm libraries but lacks actionable execution guidance. |
| 3.8 | skills.sh | scvi-tools scvi-tools packages pytorch-based probabilistic models for single-cell genomics including batch correction, integration, and transfer learning, but lacks runnable procedures and failure handling. |
| 3.6 | skills.sh | esm esm exposes protein language models (esm3 for generative design, esm-c for embeddings) with incomplete operational guidance. minimal worked examples and no error handling documented. |
| 3.5 | skills.sh | depmap depmap provides reference documentation for the cancer dependency map project and its data sources, but lacks actionable procedure for querying, parsing, or interpreting results. |
| 3.2 | skills.sh | pytdc pytdc wraps therapeutics data commons, a drug discovery dataset platform with standardized benchmarks for molecular property prediction and molecule generation tasks. coverage is broad but incomplete. |
| 0.0 | skills.sh | protocolsio-integration Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or… |
| — | skills.sh | scikit-learn Machine learning in Python with scikit-learn. Use when working with supervised learning (classification, regression), unsupervised learning (clustering,… |
| — | skills.sh | matchms Spectral similarity and compound identification for metabolomics. Use for comparing mass spectra, computing similarity scores (cosine, modified cosine), and… |
| — | skills.sh | neurokit2 Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when… |
| — | skills.sh | scientific-schematics Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only… |
| — | skills.sh | polars Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution,… |
| — | skills.sh | molecular-dynamics Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization… |
| — | skills.sh | aeon This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection,… |
| — | skills.sh | histolab Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best… |
| — | skills.sh | rdkit Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D… |
| — | skills.sh | pptx Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations;… |
| — | skills.sh | citation-management Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and… |
| — | skills.sh | scikit-survival Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival… |
| — | skills.sh | optimize-for-gpu GPU-accelerate Python code using CuPy, Numba CUDA, Warp, cuDF, cuML, cuGraph, KvikIO, cuCIM, cuxfilter, cuVS, cuSpatial, and RAFT. Use whenever the user… |
| — | skills.sh | exploratory-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… |
| — | skills.sh | stable-baselines3 Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick… |
| — | skills.sh | dnanexus-integration DNAnexus cloud genomics platform. Build apps/applets, manage data (upload/download), dxpy Python SDK, run workflows, FASTQ/BAM/VCF, for genomics pipeline… |
| — | skills.sh | rowan Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and… |
| — | skills.sh | molfeat Molecular featurization for ML (100+ featurizers). ECFP, MACCS, descriptors, pretrained models (ChemBERTa), convert SMILES to features, for QSAR and molecular… |
| — | skills.sh | datamol Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization,… |
| — | skills.sh | 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.… |
| — | skills.sh | latchbio-integration Latch platform for bioinformatics workflows. Build pipelines with Latch SDK, @workflow/@task decorators, deploy serverless workflows, LatchFile/LatchDir,… |
| — | skills.sh | tiledbvcf Efficient storage and retrieval of genomic variant data using TileDB. Scalable VCF/BCF ingestion, incremental sample addition, compressed storage, parallel… |
| — | skills.sh | labarchive-integration Electronic lab notebook API integration. Access notebooks, manage entries/attachments, backup notebooks, integrate with Protocols.io/Jupyter/REDCap, for… |
| — | skills.sh | medchem Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and… |
| — | skills.sh | benchling-integration Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for… |
| — | skills.sh | consciousness-council Run a multi-perspective Mind Council deliberation on any question, decision, or creative challenge. Use this skill whenever the user wants diverse viewpoints,… |
| — | skills.sh | glycoengineering Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated… |
| — | skills.sh | fluidsim Framework for computational fluid dynamics simulations using Python. Use when running fluid dynamics simulations including Navier-Stokes equations (2D/3D),… |
| — | skills.sh | neuropixels-analysis Neuropixels neural recording analysis. Load SpikeGLX/OpenEphys data, preprocess, motion correction, Kilosort4 spike sorting, quality metrics, Allen/IBL… |
| — | skills.sh | pylabrobot Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified… |
| — | skills.sh | pydeseq2 Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq… |
| — | skills.sh | opentrons-integration Official Opentrons Protocol API for OT-2 and Flex robots. Use when writing protocols specifically for Opentrons hardware with full access to Protocol API v2… |
| — | skills.sh | primekg Query the Precision Medicine Knowledge Graph (PrimeKG) for multiscale biological data including genes, drugs, diseases, phenotypes, and more. |
| — | skills.sh | timesfm-forecasting Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without… |
| — | skills.sh | pufferlib High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent… |
| — | skills.sh | pathml Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation,… |
| — | skills.sh | clinical-decision-support Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses… |
| — | skills.sh | sympy Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations… |
| — | skills.sh | pyhealth Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14,… |
| — | skills.sh | hypogenic Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical… |
| — | skills.sh | pytorch-lightning Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines,… |
| — | skills.sh | venue-templates Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE,… |
| — | skills.sh | research-grants Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan NSTC. Agency-specific formatting, review criteria, budget preparation, broader… |
| — | skills.sh | pymc Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic… |
| — | skills.sh | networkx networkx — an installable skill for AI agents, published by k-dense-ai/scientific-agent-skills. |
| — | skills.sh | paperzilla Chat with your agent about projects, recommendations, and canonical papers in Paperzilla. Use when users ask for recent project recommendations, canonical… |
| — | skills.sh | database-lookup database-lookup — an installable skill for AI agents, published by k-dense-ai/scientific-agent-skills. |
| — | skills.sh | parallel-web All-in-one web toolkit powered by parallel-cli, with a strong emphasis on academic and scientific sources. Use this skill whenever the user needs to search the… |
| — | skills.sh | docx docx — an installable skill for AI agents, published by k-dense-ai/scientific-agent-skills. |
| — | skills.sh | hypothesis-generation Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with… |
| — | skills.sh | peer-review Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment,… |
