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...
dicos-blender-bag-gen
by jpfieldingGenerate 3D CT scan visualizations of bags and personal items in airport screening trays using Blender MCP. Supports varied container types (carry-on suitcases, backpacks, purses, laptop bags, duffel bags) and loose tray items (watches, phones, laptops, belts, shoes). Creates realistic randomized packing with CT density-based materials, and optionally voxelizes to raw volume data for DICOS export. Use when the user asks to: create a bag scan, generate a CT bag, build a screening scene, make a bag in Blender, simulate an airport X-ray/CT scan, add items to a bag, voxelize a Blender scene, or generate screening training data. Requires Blender MCP connection.
harbor-navigator
by jpfieldingNavigate and query self-hosted Harbor container registry instances via REST API. Use when the user asks about Harbor projects, container images, repositories, artifacts, tags, vulnerability scans, replication policies, robot accounts, storage quotas, or audit logs. Triggers on mentions of Harbor, container registry, image repositories, docker images, artifact scanning, CVEs in images, replication, or requests to check what images exist or have been recently pushed. Supports multiple Harbor instances.
artificial-lift
by jpfieldingDesign and analyze artificial lift systems for oil and gas wells including rod pumping, electric submersible pumps, gas lift, and plunger lift. Covers liquid loading prediction using Turner and Coleman critical velocity criteria, rod pump design per API RP 11L including polished rod load, gearbox torque, pump displacement and fillage, ESP selection and sizing including stage count, total dynamic head, motor horsepower and cable losses, gas lift design including single-point injection pressure, valve spacing by pressure traverse, kickoff requirements, and GLR effect on flowing gradient, and plunger lift cycle timing. Use when determining if a well is liquid loading, selecting an artificial lift method, sizing an ESP or rod pump, designing a gas lift system, or calculating lift performance for PNGE production courses. Trigger phrases include liquid loading, Turner criteria, rod pump design, ESP sizing, polished rod load, gas lift valve spacing, plunger lift timing, pump-off control, artificial lift selection, c
completion-diagnostics
by jpfieldingInterpret hydraulic fracturing diagnostics and stage execution data including DFIT and minifrac closure analysis, step-rate test interpretation, ISIP estimation, net pressure decomposition, cluster efficiency screening, and treatment-pressure troubleshooting. Use when the user asks about closure pressure, fracture gradient, G-function or square-root-time plots, step-rate breakdown pressure, screenout diagnosis, treating pressure analysis, cluster imbalance, frac calibration tests, or stage-by-stage completion performance. Trigger phrases include DFIT, minifrac, ISIP, closure pressure, step-rate, net pressure, treatment pressure matching, cluster efficiency, screenout, pressure signature, tortuosity, or diagnostic fracture injection test.
flow-assurance
by jpfieldingPredict and mitigate flow assurance problems in oil and gas wellbores and pipelines including hydrate formation, CO2 and H2S corrosion, wax deposition, and carbonate and sulfate scale. Covers hydrate prediction using the Katz chart gravity method and Hammerschmidt inhibitor dosage equation for methanol and glycol injection, CO2 partial pressure calculation and corrosion rate using the de Waard-Milliams equation, H2S partial pressure and NACE MR0175 ISO 15156 sour service threshold determination, wax appearance temperature estimation and inhibition strategies, downhole carbonate scale LSI calculation and BaSO4 sulfate scale ion product, and chemical inhibitor selection and injection rate sizing. Use when evaluating hydrate risk in gas wells or pipelines, sizing methanol or glycol injection systems, assessing CO2 corrosion and material selection, checking H2S sour service requirements, predicting wax or scale problems, or selecting production chemicals. Trigger phrases include hydrate prediction, methanol injec
frac-design
by jpfieldingPerform hydraulic fracture design and analysis calculations for PNGE 341 completions engineering. Covers fracture geometry estimation using PKN and KGD analytical models, net treating pressure, fluid efficiency, proppant transport and settling, Nolte-Smith pressure diagnostics, fracture closure pressure from ISIP analysis, step-rate test interpretation, and post-frac production analysis. Use this skill when the user needs to estimate fracture length or width, analyze treating pressure trends, calculate fluid loss coefficient, determine closure pressure, design proppant schedules, evaluate net pressure and fracture containment, or work through hydraulic fracturing calculations for coursework or research. Trigger for phrases like "fracture half-length estimate", "PKN model fracture width", "net treating pressure", "fluid efficiency calculation", "closure pressure from ISIP", "Nolte-Smith plot", "proppant settling velocity", "G-function analysis", "step-rate test", or "hydraulic fracture geometry". Produces desi
phreeqc-geochem
by jpfieldingRun PHREEQC (USGS geochemical modeling code) to compute aqueous speciation, mineral saturation indices, and scaling/precipitation predictions for produced waters and oilfield brines. Use this skill whenever the user asks about brine chemistry modeling, scaling prediction (barite, calcite, gypsum, celestite, halite, anhydrite), saturation index (SI), aqueous speciation, activity coefficients, ion interference in direct lithium extraction (DLE), produced water treatability, or any question needing thermodynamic equilibrium calculations. Trigger phrases: PHREEQC, speciation, saturation index, SI, scaling prediction, scaling tendency, barite scaling, calcite scaling, gypsum scaling, brine chemistry, aqueous geochemistry, Pitzer model, activity coefficient, high-TDS brine, will this brine scale, DLE interference, equilibrium speciation, mineral solubility, sulfate scaling, carbonate scaling. Selects the right thermodynamic database for the ionic strength, builds the input deck, runs PHREEQC, and interprets the SI
iea-open
by jpfieldingQuery free open data from the International Energy Agency (IEA) API covering electric vehicles, energy prices, CO2 and greenhouse gas emissions, Net Zero Emissions scenario projections, CCUS policies, and SDG energy access. Use this skill whenever the user asks about global EV sales or stock, energy price comparisons across countries, carbon emissions by country or sector, Net Zero 2050 pathways, CCUS regulations, or SDG 7 energy access metrics. Trigger for phrases like "EV sales in China", "gasoline price in Europe", "CO2 emissions by country", "net zero scenario", "IEA data", "global EV stock share", "electricity price comparison", "carbon intensity trend", "CCUS policy", "energy access", or any request for international energy statistics beyond U.S.-only EIA data. Produces trend summaries and raw data tables.
macrostrat
by jpfieldingQuery the Macrostrat geological database for stratigraphic columns, formation ages, lithology, thickness ranges, and depositional environment context. Use this skill when the user asks about the geological age of a formation, stratigraphic position, rock types, formation thickness, depositional setting, or needs to place a formation in its stratigraphic context. Trigger for phrases like "what age is the Marcellus Shale", "stratigraphy of the Appalachian basin", "what formations are above the Utica", "depositional environment of the Smackover", "formation thickness in West Virginia", "stratigraphic column for Ohio", or any request for geological formation context, rock unit properties, or basin stratigraphy. Covers all named geological units in North America and globally. Produces formatted stratigraphic tables with age, lithology, thickness, and environment data.
kggs-well-logs
by jpfieldingSearch and retrieve digitized well log data from state geological survey repositories, primarily the Kansas Geological Survey (KGS) public database and the Digital Well Log Repository (DWLR). Use this skill when the user asks about well logs, wireline log data, gamma ray curves, resistivity logs, neutron-density crossplots, formation evaluation from logs, log-derived porosity or permeability, or needs to access subsurface petrophysical data from public repositories. Trigger for phrases like "well logs for Kansas", "gamma ray log data", "digital wireline logs", "formation tops from well logs", "log-derived porosity", "KGS well data", "petrophysical data from public wells", "LAS file download", "resistivity log for formation", or any request for digitized borehole log data from public geological survey databases. Covers LAS-format digital logs with GR, ILD, NPHI, RHOB, and other curves. Produces log curve summaries and download links.
calgem
by jpfieldingQuery California Geologic Energy Management Division (CalGEM, formerly DOGGR) oil, gas, and geothermal well data — wellbore details, operators, fields, injection and disposal wells, aquifer exemptions, and geothermal wells in the Salton Sea Known Geothermal Resource Area (KGRA). Use this skill when the user asks about California wells, CalGEM data, DOGGR records, Salton Sea lithium, Hell's Kitchen project, Controlled Thermal Resources, EnergySource, BHE Renewables, geothermal lithium, Imperial County geothermal brines, Kern County oilfield produced water, San Joaquin Basin wells, Monterey Formation, Los Angeles Basin wells, California produced water, California Class II injection wells, SB 1281 water reporting, or any California upstream regulatory data. Tie-in: USGS Produced Waters database, USGS Mineral Commodity Summaries, EPA Envirofacts UIC. Produces data tables with narrative summaries.
wri-aqueduct
by jpfieldingQuery World Resources Institute Aqueduct water risk data for U.S. counties, states, and global watershed basins. Provides baseline water stress, interannual variability, seasonal variability, drought risk, riverine flood risk, and groundwater table decline for any location. Use this skill when the user asks about water stress levels in an oil and gas producing region, drought risk for produced water management, water availability for hydraulic fracturing operations, water risk for a county or basin, WRI Aqueduct scores, or environmental water risk context for energy operations. Trigger for phrases like "water stress in Monongalia County", "water risk for Permian Basin", "drought risk West Virginia", "WRI Aqueduct score", "water availability for fracking in Texas", "water stress index", "baseline water stress", "water scarcity risk", or "water risk for oil and gas operations". Produces risk score tables by location with narrative interpretation.
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.