Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 600 files from 1 763 authors, of which 61 947 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Pipeline for Neuropixels extracellular electrophysiology: probe geometry (ProbeInterface), Kilosort sorting via SpikeInterface, quality metrics, unit curation (ISI, firing rate, SNR), post-sort analysis (PSTH, tuning curves, population decoding). Supports Neuropixels 1.0/2.0/Ultra in rodent/primate experiments.
Python toolkit for neurophysiological signal processing: ECG (HR, HRV, R-peaks), EEG (complexity, PSD), EMG (activation onset), EDA/GSR (SCR decomposition), PPG, and RSP. Includes synthetic signal simulation. Alternatives: BioSPPy (less maintained), MNE (EEG/MEG specialist), heartpy (ECG only), scipy.signal (raw DSP).
Python library for healthcare ML on EHR data: process MIMIC-III/IV, eICU, OMOP-CDM; encode medical codes (ICD, ATC, NDC); build patient-level datasets; train Transformer, RETAIN, GRASP, MedBERT for mortality, drug recommendation, readmission, diagnosis prediction. Alternatives: FIDDLE (preprocessing), clinical-longformer (clinical NLP), ehr-ml (embeddings).
>- Fast in-memory DataFrame with lazy evaluation, parallel execution, Arrow backend. select, filter, group_by, joins, pivots, window. Lazy mode enables predicate/projection
Python Materials Genomics library for structure analysis, thermodynamics, and electronic properties. Parse/create crystal structures (CIF, POSCAR), query Materials Project for DFT-computed properties, analyze phase and Pourbaix diagrams, compute XRD patterns, generate DFT inputs for VASP, Quantum ESPRESSO, CP2K. Alternatives: ASE (MD/geometry), AFLOW (high-throughput), OVITO (visualization).
Python-based workflow manager for reproducible, scalable pipelines. Define rules with file-based dependencies; Snakemake resolves execution order and parallelism. Runs local, SLURM, LSF, AWS, GCP via profiles; per-rule conda/Singularity envs. For NGS pipelines, ML training, and multi-step file processing. Use Nextflow for Groovy dataflow or nf-core integration.
>- UMAP dimensionality reduction for visualization, clustering prep, and feature engineering. Fast nonlinear manifold learning preserving local and global structure. Standard UMAP (fit/transform, sklearn-compatible), supervised/semi-supervised, Parametric UMAP (NN encoder/decoder, TensorFlow), DensMAP (density), AlignedUMAP (temporal/batch). 15+ distance metrics, custom Numba metrics, precomputed distances. For linear reduction use PCA; for neighborhood graphs use sklearn NearestNeighbors.
>- Out-of-core DataFrame for billion-row data via lazy evaluation and memory-mapped files. Use when data exceeds RAM (10 GB–TB) for fast aggregation, filtering, virtual columns, and visualization without loading. Supports HDF5, Arrow, Parquet, CSV with cloud (S3,
Chunked N-D arrays with compression and cloud storage. NumPy-style indexing. Backends: local, S3, GCS, ZIP, memory. Dask/Xarray integration for parallel and labeled computation. For lineage use lamindb; for labeled arrays use xarray.
Selecting a reference manager and applying citation styles. Compares Zotero, Mendeley, EndNote, Paperpile; covers APA/Vancouver/ACS/Nature styles, DOI management, citation tracking, and Word/Google Docs/LaTeX integration. Use when setting up a reference workflow or fixing citation formatting.
eLife figure preparation: file formats (TIFF/EPS/PDF), striking image requirements (1800x900 px), figure supplement naming, and image screening policy treating selective enhancement as misconduct.
Structured hypothesis formulation: turn observations into testable hypotheses with predictions, propose mechanisms, design experiments. Follows the scientific method. Use scientific-brainstorming for open ideation; hypogenic for automated LLM hypothesis testing on datasets.
The Lancet figure preparation: resolution (300+ DPI at 120%), preferred editable formats (PowerPoint/Word/SVG), column widths (75/154 mm), Times New Roman, in-house redraw policy.
Research posters in LaTeX using beamerposter, tikzposter, or baposter. Layout, typography, color schemes, figure integration, accessibility, and QA for conferences. Includes templates. For figure generation use matplotlib-scientific-plotting or plotly-interactive-plots.
Conducting systematic, scoping, and narrative literature reviews. Covers PRISMA/PRISMA-ScR protocols, search strategy (Boolean, MeSH), database selection (PubMed, Scopus, Web of Science, Embase), screening, data extraction, evidence synthesis (narrative, meta-analysis, thematic), and reporting. Use when planning or executing a formal literature review.
Nature figure preparation: resolution (300+ DPI), formats (AI/EPS/TIFF), RGB color, Helvetica/Arial fonts, lowercase panel labels, image integrity requirements.
NEJM figure preparation: resolution (300-1200 DPI), editable vector formats (AI/EPS/SVG), in-house medical illustration policy, and strict image integrity requirements.
PNAS figure preparation: resolution (300-1000 PPI), formats (TIFF/EPS/PDF), strict RGB-only color, Arial/Helvetica fonts, italicized uppercase panel labels, automated image screening.
Science (AAAS) figure preparation: resolution (150-300+ DPI), formats (PDF/EPS/TIFF), RGB color, Myriad/Helvetica fonts, strict image manipulation policies including gamma adjustment disclosure.
Structured ideation methods: SCAMPER, Six Thinking Hats, Morphological Analysis, TRIZ, Biomimicry, plus more. Decision framework for picking methods by challenge type (stuck, improving, systematic exploration, contradiction). Use when generating research ideas or exploring interdisciplinary connections.
Scientific manuscript writing: IMRAD, citation styles (APA/AMA/Vancouver/IEEE), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA/ARRIVE), writing principles (clarity/conciseness/accuracy), venue-specific style. For LaTeX see companion assets.
Designing scientific schematics, diagrams, and graphical abstracts. Covers tool selection (BioRender, Inkscape, Affinity, PowerPoint), design principles for pathway diagrams, mechanism schematics, experimental workflows, and journal graphical abstracts. Includes composition, icon sourcing, color for biological entities, and accessibility. Use when creating illustrative (not data-driven) scientific figures.
Scientific presentations for conferences, seminars, thesis defenses, and grant pitches. Slide design, talk structure, timing, data viz for slides, QA. PowerPoint and LaTeX Beamer. For posters use latex-research-posters.
Deep learning for drug discovery. 60+ models (GCN, GAT, AttentiveFP, MPNN, ChemBERTa, GROVER), 50+ featurizers, MoleculeNet benchmarks, HPO, transfer learning. Unified load-featurize-split-train-evaluate API. For fingerprints use rdkit-cheminformatics; for featurization-only use molfeat.
Diffusion-based docking that predicts protein-ligand poses without a predefined site. Use for blind docking, when traditional docking fails, or exploring multiple binding modes. Pipeline: prep protein (PDB) and ligand (SMILES/SDF), run inference, analyze confidence-ranked poses.
mdtraj molecular dynamics trajectory analysis (Python). Reads DCD/XTC/TRR/NetCDF/H5/PDB topologies and trajectories; computes RMSD vs time, radius of gyration, per-residue RMSF, residue-residue contact frequency maps, phi/psi torsions for Ramachandran plots (general + Gly/Pro), and 8-state DSSP secondary structure. Modules: trajectory I/O, geometry (distances/angles/dihedrals), structural analysis (RMSD/Rg/RMSF/SASA), contacts, hydrogen bonds, secondary structure (DSSP), NMR observables. For broader atom-selection grammar use mdanalysis-trajectory; for running MD simulations use OpenMM/GROMACS.
>- Medicinal chemistry filters for compound triage. Drug-likeness rules (Lipinski Ro5, Veber, Oprea, CNS, leadlike, REOS, Golden Triangle, Ro3), structural alerts (PAINS, NIBR, Lilly Demerits), chemical group detectors, complexity metrics, and filter composition query language. Built on RDKit/datamol. For hit-to-lead filtering, library design, ADMET pre-screening. For molecular I/O use rdkit-cheminformatics or datamol.
Query PubChem (110M+ compounds) directly via the PUG-REST/JSON API with plain `requests` — no SDK install required. Search by name/CID/SMILES/InChIKey/formula, retrieve properties (MW, XLogP, TPSA, H-bond counts), do similarity/substructure searches with async ListKey polling, fetch synonyms, descriptions, assay summaries, and download SDF/PNG. For local cheminformatics use rdkit; for bioactivity-centric workflows use chembl-database-bioactivity.
Molecular featurization hub (100+ featurizers) for ML. SMILES to fingerprints (ECFP, MACCS, MAP4), descriptors (RDKit 2D, Mordred), pretrained embeddings (ChemBERTa, GIN, Graphormer), pharmacophores. Scikit-learn compatible with parallelization/caching. For QSAR, virtual screening, similarity, and molecular DL.
Read, write, and edit ChemDraw CDX/CDXML files with RDKit's rdkit.Chem.rdChemDraw plus direct XML editing, always paired with a rendered PNG. Parse molecules and reactions from .cdxml/.cdx, write structures with good 2D depiction, and hand-build or modify the parts RDKit cannot write: reaction arrows, plus signs, schemes/steps, and text/labels. Use for reaction schemes, synthesis routes, mechanisms, retrosynthesis, or SI figures. Critical: RDKit writes structures only — round-tripping a reaction through a Mol silently drops arrows and text; this skill shows the XML layer that preserves them. For pure molecular analysis (descriptors, fingerprints, SMARTS) use rdkit-cheminformatics; for multi-format 3D conversion use openbabel.
Cloud quantum chemistry platform with Python SDK. Run geometry optimization, conformer generation, torsional scans, and energy minimization (DFT/semiempirical), and retrieve properties (dipole, partial charges, frontier orbitals) — no local QC software or HPC needed.
smina molecular docking CLI. AutoDock Vina fork with customizable scoring functions, native SDF/MOL2/PDB ligand input, autoboxing, local energy minimization, and per-atom score breakdowns. Pipeline: receptor PDBQT prep -> ligand prep (RDKit/OpenBabel) -> dock via autobox or explicit grid -> rescore/minimize with custom scoring -> rank poses by affinity. Choose smina over Vina when you need custom scoring terms (--custom_scoring), local optimization of an existing pose (--local_only), per-atom contributions (--atom_term_data), or SDF/MOL2 ligands without manual PDBQT conversion. For unknown binding sites use diffdock; for the Python-bindings/Vinardo workflow use autodock-vina-docking.
PyTorch-based ML platform for drug discovery: graph molecular representation learning, property prediction (ADMET, activity), retrosynthesis, drug-target interaction (DTI), and pretraining on large molecular datasets. Provides GNN layers (GraphConv, GAT, MPNN), pretrained models, and benchmark datasets.
Open-source FAIR biology data framework. Version artifacts (AnnData, DataFrame, Zarr), track lineage, validate via ontologies (Bionty), query datasets. Integrates with Nextflow, Snakemake, W&B, scVI. For scRNA-seq use scanpy; for ontology lookups use bionty.
Build and configure Cecil static sites, with focused guidance for content, templates, and site generation.
Expert guidance for PHP 8+ development, prioritizing code quality (SOLID, PSR standards), security practices, and testing requirements
Standard workflow to address pull request review comments in Cecil. Use when responding to review feedback, fixing requested changes, or preparing a clear reviewer reply with reproduction, fix, tests, and response.
Use this for a quick summary of a research paper's core ideas and key points. Use when you want to quickly understand a paper without deep study materials. Triggers on PDF paths, arXiv URLs, or paper URLs.
Start the Claude Paper web viewer to browse and study papers
Use this skill when the user wants to read, study, analyze, or deeply understand a research paper (PDF).
Use this for a quick summary of a research paper's core ideas and key points. Use when you want to quickly understand a paper without deep study materials. Triggers on PDF paths, arXiv URLs, or paper URLs.
Use this skill when the user wants to read, study, analyze, or deeply understand a research paper (PDF).
Start the Claude Paper web viewer to browse and study papers
Use this skill when the user wants to read, study, analyze, or deeply understand a research paper (PDF).
Start the Claude Paper web viewer to browse and study papers
Use this for a quick summary of a research paper's core ideas and key points. Use when you want to quickly understand a paper without deep study materials. Triggers on PDF paths, arXiv URLs, or paper URLs.
> 超圧縮コミュニケーションモード。原始人のように話してトークン使用量を約75%削減。 「原始人モード」「短く」「簡潔に」「トークン節約」と言うか、/genshijin で起動。
> 日本語対応。「PRレビューして」「コードレビュー」「/review」「/genshijin-review」で起動。 プルリクエストレビュー時に自動起動候補。
> 超圧縮コミットメッセージ生成。Conventional Commits形式で件名≤50文字、 「何を」より「なぜ」を重視。日本語・英語両対応。 「コミットメッセージ作って」「/commit」「/genshijin-commit」で起動。 ステージング変更時に自動起動候補。
> 現セッションのリアルトークン使用量と推定削減量を表示。Claude Code セッションログから直接読込 — AI 推定なし。 `/genshijin-stats` で起動。出力は mode-tracker フックが注入し、モデル自身は数値計算しない。
> 全 genshijin モード・スキル・コマンドのクイックリファレンスカード。 1回限り表示・モード変更なし・状態永続化なし。 「/genshijin-help」「原始人ヘルプ」「原始人の使い方」で起動。
> 自然言語メモリファイル（CLAUDE.md, todos, 設定）を原始人形式に圧縮し入力トークン削減。 技術内容・コード・URL・構造は完全保持。圧縮版が原ファイルを上書き、人間可読版は FILE.original.md として保存。「/genshijin-compress <filepath>」「メモリファイル圧縮」で起動。
> 原始人スタイル subagent への委譲判断ガイド。`genshijin-investigator` (コード位置特定)、 `genshijin-builder` (1-2ファイル編集)、`genshijin-reviewer` (diff レビュー) を inline作業 or vanilla `Explore` の代わりにスポーンするタイミングを示す。subagent 出力は原始人圧縮 → 主コンテキストに戻る tool-result が約60%縮小 → 長セッション持続。
Reviews code changes for Rubydex
> Benchmark Rubydex indexing performance on RBS core/stdlib, comparing the current branch against main. Measures maximum RSS and execution time.
> Profile Rubydex indexer performance — CPU flamegraphs, memory usage, phase-level timing. Use this skill whenever the user mentions profiling, performance, flamegraphs, benchmarking, "why is X slow", bottlenecks, hot paths, memory usage, or wants to understand where time is spent during indexing/resolution. Also trigger when comparing performance before/after a change.
Use when benchmarking rubydex MCP against plain Grep/Glob for Ruby code tasks. Guides A/B comparison setup, candidate selection, and metrics collection.
Generate cinematic film-style video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants cinematic, film-like, movie-quality, Hollywood-style, dramatic, or professional film-quality AI video. Triggers on: cinematic, film look, movie scene, dramatic lighting, depth of field, lens flare, anamorphic, letterbox, noir, epic, Steadicam, dolly, crane shot, or any cinematic video generation request. Always use this skill even if the user doesn't explicitly say "cinematic" but describes a film-like aesthetic.
Generate e-commerce product advertisement video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants product ads, e-commerce videos, product showcases, unboxing, product demos, shopping ads, fashion ads, beauty ads, food ads, or any commercial product video for online selling. Triggers on: product ad, e-commerce, product showcase, Amazon video, Shopify ad, Instagram shop, TikTok shop, product commercial, fashion video, beauty ad, food ad, product demo, dropshipping video, or any product promotional video request. Use even for "make a video for my product" or "product promo.
Generate 3D CGI and rendered video prompts for Seedance 2.0 on Higgsfield. Use whenever the user wants 3D rendered, CGI, Pixar-style, Unreal Engine, photorealistic 3D, computer-generated, or digitally rendered video content. Triggers on: 3D animation, CGI, rendered, Blender, Unreal Engine, octane render, ray tracing, volumetric, subsurface scattering, physically based rendering, or any 3D/CG video request. Always use even if the user just says "make it look 3D" or describes a rendered aesthetic.
Claude Skills — questions
Answers built from the skills we actually parsed.