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. 79 870 files from 1 769 authors, of which 62 217 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.
分析减肥数据、计算代谢率、追踪能量缺口、管理减肥阶段
Integrate digital health data sources (Apple Health, Fitbit, Oura Ring) and connect to WellAlly.tech knowledge base. Import external health device data, standardize to local format, and recommend relevant WellAlly.tech knowledge base articles based on health data. Support generic CSV/JSON import, provide intelligent article recommendations, and help users better manage personal health data.
Search and fetch structured content from Wikipedia using the MediaWiki API for reliable, encyclopedic information
Use when you have a spec or requirements for a multi-step task, before touching code
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
| image restoration, and spatial data processing.
| Skills for querying and downloading data from genomic, transcriptomic, 3D-genome, and cancer-genomics databases. Covers programmatic access to public repositories, gene annotation, sequence retrieval, processed functional-genomics tracks, Hi-C / Micro-C contact matrices, TCGA-style cohorts, and large-scale single-cell data.
| Aesthetic guidelines for scientific figure production. Each style file specifies palettes, typography, layout, and domain-specific sub-styles for a given target venue (NeurIPS, Nature, IEEE, etc.) and figure class (methodology diagram vs. statistical plot). Used by the Graph Maker Team's `illustrator` and `data_plotter` agents.
| dataset understanding + smart downsampling + train/test splits, algorithmic selection (HVG/DE/RF/scGeneFit/SpaPROS), optimal sub-panel discovery (ARI vs size), biological completion with a stability gate (Completion Rule), consensus scoring and completion (only if there is still room), and benchmarking on test splits (ARI/NMI/Silhouette + UMAP similarity).
| parallel computing, and performance optimization.
| Skills for opening and driving agent-controllable visualization components in the Pantheon UI sidebar — interactive viewers the agent cell omics), Viv (bioimage / microscopy), plus agent-generated apps.
| Skills for using nf-core community pipelines to process omics data, from installation and configuration to running specific analysis pipelines.
| Skills for single-cell and spatial omics data analysis. Best practices, code snippets, and workflows for the scverse ecosystem.
| Skills for Open-ST spatial transcriptomics data processing, from raw BCL files to spatially-resolved single-cell h5ad objects.
| HTML/PDF rendering. Each template file is self-contained (HTML + CSS or LaTeX in a single markdown file).
| Skills for creating presentations, slides, and visual documentation.
| Skills derived from the Single-cell Best Practices book (sc-best-practices.org). Comprehensive workflows and guidelines for single-cell and spatial omics analysis.
| Workflow guidance and model reference for single-cell foundation models (scGPT, Geneformer, UCE, scBERT, etc.). Covers model selection, validation-first workflow, and per-model I/O contracts.
| Cell and nucleus segmentation tools for microscopy images. Covers Cellpose, SAM-based methods, StarDist, InstanSeg, and Mesmer.
| annotation, and trajectory inference. These are high-priority actionable workflows — load them first for common single-cell tasks.
| Skills for spatial transcriptomics analysis including single-cell to spatial mapping (MOSCOT), 3D visualization (PyVista), and related spatial workflows.
| Obtain and predict protein 3D structures — fetch AlphaFold predicted models from the AlphaFold DB, experimental structures from the RCSB PDB, or predict a novel sequence with ColabFold — and visualise them in the Mol* LiveView.
| Skills for upstream data processing in single-cell and spatial omics, covering raw data generation, barcode processing, alignment, spatial registration, and technology-specific preprocessing pipelines.
> pathways, ChEMBL/ChEBI/PubChem, BLAST, cross-database ID mapping, GO annotations, PPI. For deep single-DB queries use dedicated tools (gget for Ensembl, pubchempy for PubChem); bioservices excels at cross-database workflows.
Cancer genomics (TCGA et al.) via cBioPortal REST API. Retrieve somatic mutations, CNAs, expression, clinical data (survival/stage/treatment) across thousands of studies. Use for TMB, oncoprints, survival analysis. For population frequencies use gnomad-database; for drug-gene interactions use dgidb-database.
Bulk RNA-seq DE with R/Bioconductor DESeq2. Negative binomial GLM, empirical Bayes shrinkage, Wald/LRT tests, multi-factor designs, Salmon tximeta import, apeglm LFC shrinkage, MA/volcano/heatmap viz. R gold standard. Use pydeseq2-differential-expression for Python; use edgeR for TMM normalization.
Protein language models (ESM3, ESM C) for sequence generation, structure prediction, inverse folding, and embeddings. Design novel proteins, extract ML features, or fold sequences. Local GPU or EvolutionaryScale Forge API. Use AlphaFold for traditional folding; RDKit for small molecules.
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.
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-visualization.
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.
Graph and network analysis toolkit. Four graph types (directed, undirected, multi-edge), centrality, shortest paths, community detection, generators, I/O (GraphML, GML, edge list), matplotlib viz. For large graphs (100K+ nodes) use igraph or graph-tool; for GNNs use PyG.
protocols.io REST API: search and fetch wet-lab, bioinformatics, and clinical protocols by keyword, DOI, or category, with steps, reagents, materials, equipment, timing. Public access free; auth needed for private or publishing. Pair with opentrons-integration or benchling-integration to execute.
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.
Query UniProt REST API: search by gene/protein name, fetch FASTA, map IDs (Ensembl, PDB, RefSeq), access Swiss-Prot annotations. Use bioservices for multi-DB access; alphafold-database for structures.
Migrate a click-ui component from styled-components to CSS Modules with byte-for-byte visual regression coverage. Use whenever a component still uses styled-components and is on the CSS Modules migration list.
Compact this Claude Code session.
Audit brand AI visibility readiness and prepare OranGEO-style GEO, AEO, LLM SEO, and AI search optimization action plans. Use when asked for a Claude Code skill, Codex skill, GEO skill, generative engine optimization skill, answer engine optimization skill, AI visibility audit, AI search visibility checker, llms.txt checker, robots.txt AI crawler check, brand visibility scan, source-gap review, or buyer prompt generator for ChatGPT, Gemini, DeepSeek, Grok, Perplexity, Claude, and other AI answer engines.
Live-test any Electron desktop app with native-devtools-mcp, Chrome DevTools Protocol, screenshots, OCR, and accessibility tools. Use when the user asks for Electron UI verification, MCP-driven app control, renderer CDP interaction, native desktop automation, screenshots, or OCR-driven checks.
Use this skill when the user wants to turn an application, product, startup idea, SaaS, mobile app, web app, API, AI product, or internal tool into a production-ready Markdown specification package for coding agents. Creates PRD/product spec, UX flows, design system brief, technical architecture, ADRs, AI/safety/privacy specs, API/data model, client/backend implementation specs, QA acceptance tests, release readiness, and executable task checklists. Do not use for simple one-off coding tasks unless the user asks for a complete spec, PRD, ADR, project plan for coding agents, or build package.
Create a new GitHub repository with the gh CLI and bootstrap a local project in ~/projects with git init, README, remote setup, and initial push. Use when the user asks to create a repo (public/private) in their account, set up the local folder, add the upstream remote, and push the first commit.
Decide exactly where bug-fix test coverage belongs. Use before adding, moving, or deleting tests after a bug fix or architectural change. Select one owning layer, reuse existing canonical suites, block redundant or weakly placed tests, and remove weaker duplicates.
Determine runtime owner, first-fix layer, and canonical long-term module or package owner in layered codebases. Use when placing code across UI vs platform shell vs runtime orchestration vs domain or application vs shared core vs adapter or integration layers, debugging ownership issues, removing duplicate policy paths, or answering "where should this live?" architecture questions.
Find duplicate ownership, hidden second sources of truth, and contract drift in layered codebases. Use when reviewing normalization, validation, defaulting, canonicalization, persistence mapping, runtime-vs-durable state, duplicated helpers, query or cache ownership, or any "who owns this rule?" architecture question. Especially useful for SSOT audits across frontend, backend, shared core, and adapter layers, and when the user explicitly asks for duplicate-ownership exploration with subagents.
Capture and analyze thread backtraces with LLDB/GDB to debug hangs, deadlocks, UI freezes, IPC stalls, or high-CPU loops across any language or project. Use when an app becomes unresponsive, switching contexts stalls, or you need thread stacks to locate lock inversion or blocking calls.
Safely inspect, stage, commit, and (only if asked) push changes made by an AI agent. Use for commit/push requests, end-of-task checkpoints, merge conflict resolution, worktree safety checks, or deciding whether to use git commit --amend.
Enforce a hard-cut cleanup policy: keep one canonical implementation and delete compatibility, migration, fallback, adapter, coercion, and dual-shape code. Use for pre-release or internal-draft refactors where the goal is one final shape, especially when changing schemas, contracts, persisted state, routing, configuration, feature flags, enum/value sets, or architecture.
Build, critique, and iterate high-converting marketing or product landing pages using React + Vite + TypeScript + Tailwind and shadcn/ui components, with all icons sourced from Iconify. Use when the user asks for a landing page, sales page, signup page, CRO improvements, above-the-fold vs below-the-fold structure, hero + CTA copy, section order, or wants production-ready shadcn + Vite code.
Claude Skills — questions
Answers built from the skills we actually parsed.