mcpbeat Sign in

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.

62 217
unique skills
out of 79 870 files found on GitHub
17 653
are copies
same content, someone else's repository
1 743
tokens, median
what a typical skill costs you in context
7 935
name collisions
two skills with one name cannot sit side by side

36 181–36 240 of 62 217

page 604 of 1 037
Scientific Impact Assessment
by BioTender-max

Assess paper and journal impact using OpenAlex citation counts, optional Altmetric data, and curated journal impact-factor references. Use when comparing papers, journals, or literature shortlists by reach and influence.

6k tokens scripts
Tracking Taxonomy Updates
by BioTender-max

Track and reconcile taxonomy updates across NCBI, GTDB, ICTV, and community eukaryote frameworks with versioned provenance.

6k tokens
Bulk Omics Clustering Analysis
by BioTender-max
7k tokens
Bulk RNAseq differential expression (DeSeq2)
by BioTender-max
7k tokens
Cell Cell Communication Analysis (CellChat)
by BioTender-max
3k tokens
ChIP Atlas Diff Analysis
by BioTender-max
4k tokens
ChIP Atlas Peak Enrichment
by BioTender-max
4k tokens
ChIP Atlas Target Genes
by BioTender-max
3k tokens
ClinicalTrials gov Disease Landscape Scanner
by BioTender-max
3k tokens
Weighted Gene Co expression Network Analysis (WGCNA)
by BioTender-max
4k tokens
Disease Progression Trajectory Analysis
by BioTender-max
4k tokens
Experimental Design
by BioTender-max
5k tokens
Functional Enrichment Analysis (GSEA + ORA)
by BioTender-max
5k tokens
Genetic Variant Annotation
by BioTender-max
5k tokens
Gene Regulatory Network Inference (pySCENIC)
by BioTender-max
4k tokens
GWAS to Function via TWAS
by BioTender-max
5k tokens
LASSO Biomarker Panel Discovery & Validation
by BioTender-max
5k tokens
Preclinical Literature Extraction
by BioTender-max
3k tokens
Two Sample Mendelian Randomization
by BioTender-max
3k tokens
Multi Omics Integration (MOFA+)
by BioTender-max
3k tokens
PCR Primer Design
by BioTender-max
4k tokens
Polygenic Risk Score (PGS Catalog)
by BioTender-max
2k tokens
Pooled CRISPR Screen Analysis
by BioTender-max
5k tokens
Proteomics Differential Expression (limma + DEqMS)
by BioTender-max
3k tokens
Single Cell Trajectory Inference
by BioTender-max
3k tokens
Single Cell RNA seq Core Analysis (Scanpy)
by BioTender-max
5k tokens
Single Cell RNA seq Core Analysis (Seurat)
by BioTender-max
7k tokens
Spatial Transcriptomics Visium Analysis
by BioTender-max
3k tokens
Clinical Survival & Outcome Analysis
by BioTender-max
5k tokens
Upstream Regulator Analysis
by BioTender-max
3k tokens
Mage
by BioTender-max
1809k tokens scripts
STAgent
by BioTender-max
20708k tokens scripts
SpatialAgent
by BioTender-max
616 tokens
Aav Vector Design Agent
by BioTender-max
1k tokens
Agentd Drug Discovery
by BioTender-max
3k tokens scripts
AI Analyzer
by BioTender-max

AI驱动的综合健康分析系统,整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。

2k tokens zh
Antibody Design Agent
by BioTender-max
1k tokens
Armored Cart Design Agent
by BioTender-max
2k tokens
Autonomous Oncology Agent
by BioTender-max
762 tokens
Bayesian Optimizer
by BioTender-max
4k tokens scripts
Bio Alignment Files Bam Statistics
by BioTender-max
4k tokens scripts
Bio Data Visualization Genome Browser Tracks
by BioTender-max
4k tokens scripts
Bio Data Visualization Specialized Omics Plots
by BioTender-max
3k tokens
Bio Data Visualization Volcano Customization
by BioTender-max
5k tokens scripts
Bio Research Tools Biomarker Signature Studio
by BioTender-max
6k tokens scripts
Bio Sequence Similarity
by BioTender-max
4k tokens scripts
Bioinformatics Singlecell
by BioTender-max
2k tokens
Biokernel
by BioTender-max
399 tokens
Biologist Analyst
by BioTender-max

| Analyzes living systems and biological phenomena through biological lens using evolution, molecular biology, ecology, and systems biology frameworks. Provides insights on mechanisms, adaptations, interactions, and life processes.

19k tokens
Biomaster Workflows
by BioTender-max
245k tokens scripts
Biomcp Server
by BioTender-max
2440k tokens scripts
Biomedical Data Analysis
by BioTender-max
9k tokens
Biomedical Search
by BioTender-max

Complete biomedical information search combining PubMed, preprints, clinical trials, and FDA drug labels. Powered by Valyu semantic search.

2k tokens scripts
Biomni General Agent
by BioTender-max
725k tokens scripts
Biomni Research Agent
by BioTender-max
715 tokens
Bone Marrow AI Agent
by BioTender-max
1k tokens
Bulk RNA-seq batch correction with ComBat
by BioTender-max

Use omicverse's pyComBat wrapper to remove batch effects from merged bulk RNA-seq or microarray cohorts, export corrected matrices, and benchmark pre/post correction visualisations.

1k tokens
Bulk RNA-seq differential expression with omicverse
by BioTender-max

Guide Claude through omicverse's bulk RNA-seq DEG pipeline, from gene ID mapping and DESeq2 normalization to statistical testing, visualization, and pathway enrichment. Use when a user has bulk count matrices and needs differential expression analysis in omicverse.

2k tokens
Bulk RNA-seq DESeq2 analysis with omicverse
by BioTender-max

Walk Claude through PyDESeq2-based differential expression, including ID mapping, DE testing, fold-change thresholding, and enrichment visualisation.

1k tokens
STRING protein interaction analysis with omicverse
by BioTender-max

Help Claude query STRING for protein interactions, build PPI graphs with pyPPI, and render styled network figures for bulk gene lists.

907 tokens

Claude Skills — questions

Answers built from the skills we actually parsed.

What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 11 541 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 79 870 files found on GitHub, 62 217 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 7 935 skills here share a name with another skill, and two of them cannot sit side by side.