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...
gcms-processing
by dailycafiProcess GC-MS data for metabolomics and volatile compound analysis including peak detection, deconvolution, and NIST library matching. Use when: user has GC-MS data, needs retention index calculation, wants to identify volatiles, match EI spectra against NIST, or process derivatized metabolites. Triggers: GC-MS, gas chromatography, volatile analysis, NIST library, retention index, Kovats index, EI spectrum, electron ionization, deconvolution, AMDIS, TMS derivatives, volatile profiling, headspace analysis, SPME.
bio-metabolomics-clinical-reporting
by dailycafiInterpret clinical metabolomics results for inborn errors of metabolism (IEM) screening, newborn screening, and diagnostic reporting. Use when: user has clinical metabolite panels, needs IEM differential diagnosis, wants to analyze acylcarnitine profiles or amino acid panels, or calculate z-scores against reference ranges. Triggers: newborn screening, IEM, inborn error of metabolism, acylcarnitine, amino acid panel, organic acid analysis, clinical diagnosis, tandem MS screening, PKU, MCADD, maple syrup urine disease, clinical metabolomics, reference range, z-score.
pyopenms
by dailycafiFull-featured mass spectrometry data processing with pyopenms (OpenMS Python bindings) for LC-MS, LC-MS/MS, and proteomics pipelines. Use when: user needs to read/write mzML files, run feature detection on LC-MS data, process chromatograms, extract ion chromatograms (XIC/EIC), or build complex MS workflows. Triggers: LC-MS data processing, mzML processing, feature detection, peak picking from mzML, chromatogram extraction, OpenMS, pyopenms, MS1/MS2 data, centroiding, mass spectrometry pipeline. For spectral library matching use matchms instead.
bio-multi-omics-microbiome-metabolomics
by dailycafiIntegrate microbiome (16S/shotgun) with metabolomics to analyze host-microbe metabolic interactions. Use when: user has paired microbiome and metabolomics data, asks about gut metabolites, needs SCFA quantification, bile acid profiling, tryptophan metabolism, or microbe-metabolite co-occurrence. Triggers: gut metabolites, SCFA, short-chain fatty acids, bile acids, microbiome, 16S, microbiome-metabolomics, mmvec, microbe-metabolite, tryptophan pathway, indole derivatives, gut-brain axis metabolites, fecal metabolomics.
matchms
by dailycafiCompare mass spectra and identify unknown compounds by spectral library searching with matchms. Use when: user wants to match MS/MS spectra against a library, compute spectral similarity scores, identify an unknown compound from its spectrum, or process MGF/MSP spectral files. Triggers: spectral library search, MS/MS matching, identify unknown compound, cosine similarity score, modified cosine, spectral matching, MGF file, MSP file, GNPS library, MassBank, compound identification from spectra, tandem MS matching.
hmdb-database
by dailycafiLook up any metabolite in the Human Metabolome Database (HMDB) via REST API across 220,000+ entries. Use when: user asks 'what is this metabolite', needs an HMDB ID, wants metabolite pathways or disease associations, queries a metabolite database, or needs cross-references to KEGG/PubChem/ChEBI. Triggers: metabolite lookup, HMDB search, metabolite properties, metabolite spectra, metabolite biomarker, compound information, metabolite concentration, biofluid metabolites, serum metabolites, urine metabolites.
cobrapy
by dailycafiConstraint-based metabolic modeling with COBRApy. Flux balance analysis (FBA), flux variability (FVA), gene knockouts, flux sampling, production envelopes, and gap filling on genome-scale SBML models. Use when: predicting growth rates, optimizing metabolic fluxes, screening gene deletions, or building metabolic models. Triggers: FBA, FVA, COBRA, metabolic model, SBML, flux analysis, gene knockout simulation, metabolic engineering, growth prediction.
bio-metabolomics-metabolite-annotation
by dailycafiAnnotate and identify metabolomics features by matching m/z, retention time, and MS/MS spectra against databases. Use when: user has a feature table and wants compound IDs, needs to annotate m/z values, assign metabolite identities with confidence levels, or match features against HMDB/METLIN/MassBank. Triggers: identify features, m/z annotation, compound identification, metabolite ID, putative annotation, MSI confidence levels, adduct matching, ppm tolerance, neutral mass search, what compound is this m/z.
bio-metabolomics-normalization-qc
by dailycafiNormalize metabolomics data and remove batch effects using QC sample-based correction, LOESS, ComBat, and transformation methods. Use when: user needs to correct batch effects, normalize a metabolomics feature table, apply QC-based drift correction, or prepare data for statistical analysis. Triggers: batch correction, QC samples, normalize metabolomics, batch effect, LOESS correction, ComBat, signal drift, QC-RSC, pooled QC, data transformation, log transformation, PQN normalization, MetaboAnalystR normalization.
bio-metabolomics-targeted-analysis
by dailycafiPerform targeted metabolomics quantification using MRM/SRM transitions, calibration curves, and internal standards. Use when: user needs absolute quantification of metabolites, has MRM/SRM data, wants to build calibration curves, validate a targeted method, or process Skyline output. Triggers: MRM, SRM, calibration curve, absolute quantification, targeted quantification, internal standard, Skyline, targeted metabolomics, LOD, LOQ, method validation, standard curve, concentration calculation, quantitative metabolomics.
ms-format-conversion
by dailycafiConvert mass spectrometry vendor files to open formats using msConvert and pyopenms. Use when: user needs to convert RAW files to mzML, convert WIFF/Agilent .d/Waters .raw to open format, batch convert instrument files, or troubleshoot format issues. Triggers: convert RAW file, mzML conversion, mzXML, vendor format, msConvert, ProteoWizard, Thermo RAW, AB SCIEX WIFF, Agilent .d, Waters .raw, Bruker .d, centroid mode, profile mode, batch conversion, format conversion.
bioservices
by dailycafiQuery 40+ bioinformatics databases (KEGG, UniProt, ChEMBL, Reactome, ChEBI) from Python with a unified API via bioservices. Use when: user needs to map metabolite IDs across databases, query KEGG pathways/reactions programmatically, retrieve enzyme data from UniProt, search ChEMBL for bioactive compounds, or cross-reference identifiers. Triggers: bioservices, KEGG API, Reactome API, ChEBI lookup, UniProt query, cross-database ID mapping, metabolite ID conversion, enzyme lookup, compound-target interaction, pathway query from Python.
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.