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...
s131-marine-harbour
by philliphoffExpert knowledge of IHO S-131 Marine Harbour Infrastructure Product Specification (FC Edition 1.0.0, PC Edition 2.0.0). Covers GML encoding (S-100 Part 10b) in the application namespace `http://www.iho.int/S131/1.0` over the S-100 GML 5.0 base, the S-131 feature catalogue (berths, bollards, mooring buoys, dolphins, locks, dry docks, terminals, anchorage areas, harbour basins, authorities, etc.), and **Lua-based portrayal** (S-100 Part 9A) — making S-131 the first GML+Lua hybrid in this codebase. USE FOR: S-131 datasets, marine harbour infrastructure features, berths, bollards, mooring buoys, GML parsing for S-131, Lua portrayal of S-131, GML-to-Lua data provider bridge, vector pipeline changes affecting S-131, S-131 reader/source code, S-131 tests, edits to bundled `content/S131/**` assets. DO NOT USE FOR: S-101 ENC ISO 8211 features (use s101-enc), S-127 marine services (use s127-marine-services), S-124 nav warnings (use s124-nav-warnings), generic GML / framework concerns (use s100-framework).
s201-aton-information
by philliphoffExpert knowledge of IALA S-201 Aids to Navigation Information Product Specification (Edition 2.0.0, May 2025; aligned with S-100 Ed 5.2.0). Covers GML encoding (S-100 Part 10b) on the S-100 GML 5.0 profile, the S-201 application schema (62 feature types — buoys, beacons, lights, AIS aids, structures, equipment, aggregations), the 4 information types (AtoNFixingMethod, AtonStatusInformation, PositioningInformation, SpatialQuality), xlink-based information bindings, the equipment-on-structure `parent`/`child` xlink relationship, and the XSLT-based portrayal pipeline (`main_PaperChart.xsl`). USE FOR: S-201 datasets, AtoN-authority data exchange, GML parsing for S-201, XSLT portrayal of S-201, vector pipeline changes affecting S-201, S-201 reader/source code, S-201 tests. DO NOT USE FOR: ECDIS-facing AtoN portrayal (use s125-aton — the ECDIS-facing AtoN spec is **S-125, not S-201**), S-101 ENC AtoN feature classes (use s101-enc), S-124 navigational warnings (use s124-nav-warnings), generic GML (use s100-framework
s100-framework
by philliphoffExpert knowledge of the IHO S-100 Universal Hydrographic Data Model (Edition 5.2.1). Covers Parts 1–10: data model, feature catalogues (ISO 19110), portrayal catalogues, exchange sets (CATALOG.XML), HDF5 encoding (Part 10c), GML encoding (Part 10b), ISO 8211 encoding (Part 10a), and the Lua-based portrayal engine (Part 9A). USE FOR: S-100 framework questions, exchange set layout, CATALOG.XML schema, feature/portrayal catalogue structure, cross-product concerns, changes to EncDotNet.S100.Core, EncDotNet.S100.ExchangeSets, EncDotNet.S100.Features, EncDotNet.S100.Portrayals, or EncDotNet.S100.Specifications, choosing an encoding for a new product, designing pipeline abstractions. DO NOT USE FOR: a single product spec (use s101-enc, s102-bathymetry, s104-water-level, s111-surface-currents, s124-nav-warnings, s129-ukc, or s421-route-plans).
s101-enc
by philliphoffExpert knowledge of IHO S-101 Electronic Navigational Chart Product Specification. Covers ISO 8211 record encoding (S-100 Part 10a), S-101 feature/spatial/information records, the Lua-based portrayal pipeline (S-100 Part 9A) including drawing instructions, symbol references, line/area styles, and the data provider contract used by rule scripts. USE FOR: S-101 datasets, ENC files, ISO 8211 parsing, S101DocumentReader, S101Dataset, S101VectorSource, S101LuaPortrayal, S101LuaDataProvider, DrawingInstructionParser, S101PortrayalCatalogue, drawing instructions, Lua portrayal rules, vector pipeline changes affecting S-101, adding S-101 features. DO NOT USE FOR: S-124 GML-encoded features (use s124-nav-warnings), HDF5 coverage products S-102/S-104/S-111 (use their respective skills), generic S-100 framework questions (use s100-framework).
s102-bathymetry
by philliphoffExpert knowledge of IHO S-102 Bathymetric Surface Product Specification (HDF5-encoded depth/uncertainty grids). Covers BathymetryCoverage groups, Group_F feature codes, depth/uncertainty dataset shapes, NODATA fill value handling (1,000,000f), tiling, georeferencing attributes, CRS conventions (often UTM), and the depth-shading portrayal palette. USE FOR: S-102 datasets, bathymetric grids, depth surfaces, uncertainty grids, HDF5 bathymetry, BathymetryCoverage, CoverageCell layout, depth shading, S102DatasetReader, S102CoverageSource, S102PortrayalCatalogue, PC-driven Lua portrayal, adding S-102 features, reviewing for S-102 spec compliance, RenderS102 tool changes. DO NOT USE FOR: S-104 water levels (use s104-water-level), S-111 currents (use s111-surface-currents), generic HDF5 access (use s100-framework).
s104-water-level
by philliphoffExpert knowledge of IHO S-104 Water Level Information for Surface Navigation Product Specification. Covers HDF5-encoded water-level time-step grids, WaterLevel feature, Group_NNN time-series groups, data coding formats (regular grid, ungeorectified grid, time series at fixed stations, etc.), trend/quality flags, and tide-station metadata. USE FOR: S-104 datasets, water level forecasts/observations, tide grids, S104DatasetReader, S104CoverageSource, S104PortrayalCatalogue, WaterLevelCoverage, WaterLevelValue, time-step iteration, adding S-104 features, S-104 tests. DO NOT USE FOR: S-102 bathymetry (use s102-bathymetry), S-111 currents (use s111-surface-currents), generic HDF5 (use s100-framework).
s111-surface-currents
by philliphoffExpert knowledge of IHO S-111 Surface Currents Product Specification. Covers HDF5-encoded current speed/direction time-step grids, SurfaceCurrent feature, Group_NNN time-series groups, data coding formats (regular grid, ungeorectified grid, time series at fixed stations, moving platform, etc.), and current portrayal (arrows, colour bands). USE FOR: S-111 datasets, surface currents, current speed and direction, S111DatasetReader, S111CoverageSource, S111PortrayalCatalogue, time-step iteration of currents, adding S-111 features, S-111 tests. DO NOT USE FOR: S-104 water levels (use s104-water-level), S-102 bathymetry (use s102-bathymetry), generic HDF5 (use s100-framework).
s124-nav-warnings
by philliphoffExpert knowledge of IHO S-124 Navigational Warnings Product Specification. Covers GML encoding (S-100 Part 10b), the S-124 application schema, warning types (NAVAREA, coastal, local, NAVTEX), in-force/cancellation lifecycle, geometric primitives in GML, and XSLT-based portrayal. USE FOR: S-124 datasets, navigational warnings, GML parsing for S-124, XSLT portrayal of warnings, vector pipeline changes affecting S-124, S-124 reader/source code, S-124 tests. DO NOT USE FOR: S-129 UKC (use s129-ukc), S-101 ENC (use s101-enc), generic GML (use s100-framework).
s125-aton
by philliphoffExpert knowledge of IHO S-125 Marine Aids to Navigation Product Specification. Covers GML encoding (S-100 Part 10b) using the S-100 GML 5.0 profile, the S-125 application schema (lights, buoys, beacons, daymarks, AIS aids), AtoN status indication and status information types, xlink-based information bindings, and the XSLT-based portrayal pipeline. USE FOR: S-125 datasets, marine aids to navigation, GML parsing for S-125, XSLT portrayal of AtoN, vector pipeline changes affecting S-125, S-125 reader/source code, S-125 tests. DO NOT USE FOR: S-101 ENC AtoN feature classes (use s101-enc), S-124 navigational warnings (use s124-nav-warnings), generic GML (use s100-framework).
s127-marine-services
by philliphoffExpert knowledge of IHO S-127 Marine Resources and Services Product Specification (Edition 2.0.0). Covers GML encoding (S-100 Part 10b) in the application namespace `http://www.iho.int/S127/2.0` over the S-100 GML 5.0 base, the S-127 feature catalogue (pilot boarding places, routeing measures, restricted areas, vessel traffic services, signal stations, etc.), and XSLT-based portrayal. USE FOR: S-127 datasets, marine traffic management features, pilot services, routeing measures, restricted/military/caution areas, vessel traffic services, GML parsing for S-127, XSLT portrayal of S-127, vector pipeline changes affecting S-127, S-127 reader/source code, S-127 tests, edits to bundled `content/S127/**` assets. DO NOT USE FOR: S-124 nav warnings (use s124-nav-warnings), S-129 UKC (use s129-ukc), S-101 ENC (use s101-enc), generic GML / framework concerns (use s100-framework).
s128-catalogue
by philliphoffExpert knowledge of IHO S-128 Catalogue of Nautical Products Product Specification (Edition 2.0.0). Covers GML encoding (S-100 Part 10b) in the application namespace `http://www.iho.int/S128/2.0` over the S-100 GML 5.0 base, the S-128 feature catalogue (ElectronicProduct, PhysicalProduct, S100Service, plus producer / distributor / contact metadata features), and XSLT-based portrayal. USE FOR: S-128 datasets, catalogues of nautical products, electronic products, physical products, S-100 services, GML parsing for S-128, XSLT portrayal of S-128, vector pipeline changes affecting S-128, S-128 reader/source code, S-128 tests, edits to bundled `content/S128/**` assets. DO NOT USE FOR: S-127 marine resources and services (use s127-marine-services), S-122 marine protected areas (use s122-marine-protected-areas), S-124 nav warnings (use s124-nav-warnings), S-101 ENC (use s101-enc), generic GML / framework concerns (use s100-framework).
s129-ukc
by philliphoffExpert knowledge of IHO S-129 Under Keel Clearance Management Product Specification. Covers GML encoding (S-100 Part 10b), the S-129 application schema, UKC plan/route geometries, time-step UKC values, and dynamic UKC representations. USE FOR: S-129 datasets, under keel clearance, UKC plans, GML parsing for S-129, S-129 reader/source code, S-129 tests. DO NOT USE FOR: S-124 nav warnings (use s124-nav-warnings), S-104 water levels which UKC depends on (use s104-water-level), generic GML (use s100-framework).
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.