Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
bio-variant-calling-joint-calling
by GPTomicsJoint genotype calling across multiple samples using GATK CombineGVCFs and GenotypeGVCFs. Essential for cohort studies, population genetics, and leveraging VQSR. Use when performing joint genotyping across multiple samples.
bio-flow-cytometry-cytometry-qc
by GPTomicsQuality control for flow, spectral, and mass cytometry - time-based anomaly cleaning (flowAI, flowCut, PeacoQC, flowClean), margin/boundary event removal, signal-drift detection, dead-cell exclusion, CyTOF Gaussian/DNA/event-length checks, instrument calibration/standardization (MESF, CS&T, peak-2), and batch-level outlier flagging. Use when assessing acquisition quality, choosing a cleaning tool, ordering QC relative to compensation, deciding margin removal before density-based steps, or flagging problematic samples before clustering or differential analysis.
bio-microbiome-qiime2-workflow
by GPTomicsOperates the QIIME2 framework as the glue for an amplicon analysis - the .qza/.qzv artifact model, semantic types (FeatureTable[Frequency], SampleData[PairedEndSequencesWithQuality], Phylogeny[Rooted], FeatureData[Taxonomy]), embedded provenance plus provenance replay, import (Casava/manifest/EMP/BIOM), export, the Metadata object, and the q2cli vs Artifact API interfaces. Covers why a .qza is data-plus-executable-history not a file, why export drops provenance, why a .qzv is terminal, why classifier .qza are version-pinned, and the 2026 distribution/rachis rename. Use when importing reads, choosing a manifest/Casava/EMP/BIOM path, reading or replaying provenance, exporting to BIOM/phyloseq, fixing semantic-type or Phred or sklearn-version errors, or orchestrating the pipeline. Denoising -> amplicon-processing; classifier/DB -> taxonomy-assignment; diversity metric/depth -> diversity-analysis; DA tool -> differential-abundance; PICRUSt2 -> functional-prediction; shotgun moshpit -> metagenomics.
bio-primer-design-primer-validation
by GPTomicsValidates chosen PCR/qPCR oligos for intramolecular thermodynamic liabilities with primer3-py - hairpins, self-dimers, cross-dimers (calc_hairpin/homodimer/heterodimer), and 3'-end stability (calc_end_stability) - returning ThermoResult dG/Tm and ASCII structures. Covers why a "dimer-free" verdict is a PREDICTION at the supplied salt/Mg/dNTP/oligo conditions and temp_c (so the same primer is fine or dimer-prone depending on conditions), why a 3'-END dimer or hairpin is the lethal class (polymerase-extendable into primer-dimer) so structures are ranked by dG at the annealing temperature and 3'-end involvement rather than global Tm, that ThermoResult dG is in cal/mol not kcal/mol, and that .structure_found must gate the numbers. Use when checking primer pairs before ordering, troubleshooting primer-dimers or smears, or screening oligos for secondary structure. Genome off-target/mispriming is primer-specificity; design is primer-basics; probe assays are qpcr-primers.
bio-variant-normalization
by GPTomicsNormalize indel representation, decompose MNPs, and split multiallelic variants using bcftools norm. Use when comparing variants from different callers, preparing VCF for database annotation, or merging VCFs from multiple sources.
bio-causal-genomics-effector-gene-prioritization
by GPTomicsMaps GWAS-implicated loci to candidate effector (causal) genes by integrating variant-to-gene (V2G) features via Open Targets L2G (Mountjoy 2021), MAGMA gene-based association (de Leeuw 2015), FUMA SNP2GENE, cS2G combined SNP-to-gene scores (Gazal 2022), Polygenic Priority Scores (PoPS, Weeks 2023), FLAMES, INQUISIT, DEPICT, and enhancer-gene predictors (ABC, ENCODE-rE2G). Use when narrowing a GWAS lead locus to a candidate causal gene, picking between proximity, eQTL-based, and similarity-based prioritizers, integrating multi-evidence streams (fine-mapping, colocalization, ABC enhancer-gene, distance, chromatin), reconciling discordant L2G vs PoPS calls, prioritizing tissue-specific eQTL evidence, or triangulating across at least three independent lines of evidence for a publication-grade effector-gene nomination.
bio-single-cell-scatac-analysis
by GPTomicsSingle-cell ATAC-seq analysis with Signac (R/Seurat) and ArchR. Process 10X Genomics scATAC data, perform QC, dimensionality reduction, clustering, peak calling, and motif activity scoring with chromVAR. Use when analyzing single-cell ATAC-seq data.
bio-long-read-sequencing-basecalling
by GPTomicsBasecalls raw Oxford Nanopore signal (POD5/FAST5) into reads with Dorado, choosing the chemistry-matched model and accuracy tier (fast/hac/sup), requesting modified bases (5mCG_5hmCG, 6mA, m6A) at basecall time, and handling duplex, demultiplexing, trimming, and HERRO read correction. Covers why the model+version is an irreversible analysis decision, why methylation cannot be recovered later, and why downstream polish/variant models must match the basecaller. Use when converting POD5/FAST5 to reads, picking a Dorado model for R9/R10 or RNA004, enabling methylation calling, basecalling duplex, demultiplexing barcoded runs, or correcting reads for assembly.
bio-clinical-biostatistics-power-sample-size
by GPTomicsComputes sample size and power for clinical trials including continuous, binary, and time-to-event endpoints; superiority, non-inferiority, and equivalence designs; FDA 2016 non-inferiority margin selection with M1/M2 framework; Schoenfeld 1981 and Lakatos 1988 for survival; Schuirmann TOST and 80-125% bioequivalence; minimum clinically important difference (MCID) vs δ distinction. Use when justifying trial size in protocol or SAP per CONSORT 2025 item 7.
bio-data-visualization-color-palettes
by GPTomicsSelect colormaps and qualitative palettes for scientific figures using perceptual-uniformity, color-vision-deficiency safety, and luminance-monotonicity criteria. Covers Crameri scientific colormaps, viridis/cividis/magma, Okabe-Ito categorical, ColorBrewer, and the rainbow/jet critique. Use when choosing palettes for heatmaps, scatter, networks, or any encoding where color carries quantitative or categorical meaning.
bio-pathway-go-enrichment
by GPTomicsRuns Gene Ontology over-representation analysis (ORA) on a gene LIST with clusterProfiler enrichGO, the one-sided hypergeometric/Fisher 2x2 test phyper(k-1, M, N-M, n, lower.tail=FALSE). Covers why the BACKGROUND universe (not the gene list) is the null and decides significance, why omitting universe= is a bug, why enrichGO defaults to ont='MF' not 'BP', why pvalueCutoff filters p.adjust not raw p, why ORA discards effect magnitude and inherits GO-DAG true-path redundancy (simplify, topGO), why RNA-seq gene-length bias inflates long-gene terms (GOseq Wallenius), plus GeneRatio/BgRatio, bitr ID mapping, minGSSize/maxGSSize, groupGO. Use when a pre-selected gene list (DE hits, co-expression module, screen, GWAS-mapped) needs GO annotation. For a ranked no-cutoff analysis see gsea; for other databases see kegg-pathways, reactome-pathways, wikipathways; DE source is differential-expression/de-results; plots in enrichment-visualization.
bio-population-genetics-linkage-disequilibrium
by GPTomicsComputes linkage disequilibrium (r2, D', composite Rogers-Huff r2), prunes correlated variants, clumps GWAS summary statistics to lead SNPs, and defines haplotype blocks with PLINK 1.9/2.0 and scikit-allel. r2 and D' answer different questions - r2 (= chi2/N) is the tagging and GWAS-power currency, D' marks observed recombination and is upward-biased for rare variants. PLINK 2.0 has no bare --r2 (split into --r2-phased and --r2-unphased); pruning (--indep-pairwise, genotype-blind) and clumping (--clump, p-value-aware) are distinct operations that are constantly confused. The clumping or fine-mapping LD reference must be ancestry-matched or it fails silently into false credible sets. Use when calculating LD, pruning variants for PCA or structure, clumping GWAS hits, or selecting tag SNPs. For QC see plink-basics; for PCA see population-structure; fine-mapping is causal-genomics/fine-mapping.
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.