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...
ref-struct-delegates
by corvus-dotnetReplace Func<> and Action<> with custom delegate types when any parameter or return type is a ref struct (Span<T>, ReadOnlySpan<T>, etc.). Ref structs cannot appear as generic type arguments, so Func<ReadOnlySpan<byte>, bool> is a compile error. The fix is a named delegate. USE FOR: writing public APIs that accept callbacks involving spans, storing span-accepting lambdas in fields, wrapping IJsonPathFunction or similar interfaces with delegate-based factories. DO NOT USE FOR: APIs where all parameters are regular (non-ref-struct) types — plain Func<>/Action<> is fine there.
corvus-numeric-types
by corvus-dotnetUnderstand and work with the Corvus.Text.Json numeric type system including parsed components, BigNumber arbitrary-precision decimal, format-based type selection, and precision-preserving validation. USE FOR: working with JSON numbers in Corvus types, understanding format validation for numeric schemas, implementing numeric operations, choosing between BigNumber and standard .NET numeric types. DO NOT USE FOR: general JSON parsing (use corvus-parsed-documents-and-memory).
corvus-v4-migration
by corvus-dotnetMigrate code from Corvus.Json V4 to Corvus.Text.Json V5. Covers namespace and type renames, parsing pattern changes, the mutation model shift from functional With*() to imperative Set*() with workspace/builder, validation API changes, composition type changes, migration analyzer diagnostics (CVJ001-CVJ025), and the Copilot-assisted migration workflow. USE FOR: migrating V4 consumer code to V5, understanding API differences between V4 and V5, using migration analyzers and code fixes. DO NOT USE FOR: general V5 development (use other skills), modifying the V4 engine itself.
corvus-ecma-regex
by corvus-dotnetTranslate ECMAScript 262 /u mode regular expressions to .NET regex patterns. Covers semantic differences between ECMAScript and .NET regex engines, supplementary code point handling via surrogate pairs, Unicode property escapes, backreference conditionals, character class strategies, and strict /u mode validation. USE FOR: understanding regex translation in generated validation code, debugging pattern matching issues in JSON Schema pattern/patternProperties, extending regex support for new Unicode properties or constructs. DO NOT USE FOR: general .NET regex usage, writing custom regex patterns.
corvus-analyzers
by corvus-dotnetUnderstand and work with the Roslyn analyzers shipped with Corvus.Text.Json. Covers 10 production diagnostics (CTJ001-CTJ010) for correct and performant V5 code, the CTJ-NAV refactoring for navigating from types to JSON Schema definitions, and the analyzer packaging convention. USE FOR: understanding what each analyzer checks, writing code that passes analyzer checks, packaging analyzer DLLs. DO NOT USE FOR: the 25 migration analyzers (use corvus-v4-migration for the workflow and CVJ001-CVJ025 reference).
corvus-benchmarks
by corvus-dotnetRun, interpret, and maintain BenchmarkDotNet benchmarks for JSON Schema validation and query languages. Covers the B/ (frozen baseline) vs C/ (current) directory convention, stale Job-* cleanup, --buildTimeout, result file polling, regenerating C/ models after codegen changes, and JSONata/JMESPath/JsonLogic/JSONPath benchmarks. USE FOR: running benchmarks, interpreting results, regenerating benchmark models, troubleshooting BDN issues, adding new benchmark schemas. DO NOT USE FOR: general .NET performance analysis (use the analyzing-dotnet-performance skill).
corvus-bowtie-testing
by corvus-dotnetTest Corvus.JsonSchema against the JSON Schema Test Suite using Bowtie, the cross-implementation meta-validator. Covers local package building, configuring a local Bowtie checkout to use locally-built packages, running the test suite via Docker/Podman containers, interpreting results, the iteration loop, and teardown. Both V4 (dotnet-corvus-jsonschema-v4engine) and V5 (dotnet-corvus-jsonschema-v5engine) implementations are supported. USE FOR: running Bowtie conformance suites against local changes, setting up the local development loop, interpreting Bowtie failure reports, testing schema dialect compliance (Draft 4 through 2020-12). DO NOT USE FOR: running the in-repo MSTest test suite (use corvus-build-and-test), regenerating test classes from the submodule (use corvus-test-suite-regeneration).
corvus-buffer-and-pooling
by corvus-dotnetWrite allocation-efficient buffer code in Corvus.JsonSchema using the codebase's established three-tier pooling pattern: stackalloc → ArrayPool → ThreadStatic caches. Covers threshold constants, the rent/return pattern, UTF-8-first processing, thread-local writer and workspace caches, and PooledByteBufferWriter. USE FOR: writing any code that needs temporary byte/char buffers, adding new pooled caches, working with UTF-8 data, avoiding heap allocation on hot paths. DO NOT USE FOR: choosing which ref-struct collection to use (use corvus-low-alloc-data-structures), document model internals (use corvus-parsed-documents-and-memory).
corvus-build-and-test
by corvus-dotnetBuild, test, and run the Corvus.JsonSchema solution correctly. Covers multi-targeting (net9.0/net10.0/net481/netstandard2.0), mandatory test category filters, solution file selection, running specific test classes or methods, writing new tests, and diagnosing common build/test failures. USE FOR: building the solution, running tests, writing new test files, diagnosing test failures, understanding TFM targeting, finding the right test project for a feature area. DO NOT USE FOR: benchmark execution (use corvus-benchmarks), code generation (use corvus-codegen), test suite regeneration (use corvus-test-suite-regeneration).
corvus-codegen
by corvus-dotnetGenerate strongly-typed C# from JSON Schema using the Roslyn source generator or the corvusjson CLI tool. Covers the JsonSchemaTypeGenerator attribute, CLI options, naming heuristics, AdditionalFiles registration, config file format, MSBuild properties, and troubleshooting generated output. USE FOR: generating types from schemas, configuring the source generator or CLI tool, understanding naming heuristics, inspecting generated output, troubleshooting generation issues. DO NOT USE FOR: modifying the generator internals (use corvus-keywords-and-validation), running benchmarks (use corvus-benchmarks).
corvus-ctj-handler-implementation
by corvus-dotnetImplement OpenAPI server handlers using Corvus.Text.Json generated types. Covers the workspace-owned lifetime model, the Read/ReadMutable store pattern, builder pattern for responses, From<T>() for zero-copy cross-namespace values, TryX out-parameter pattern for lookups, EnumerateArray() iteration, and the two-hop cast requirement for Mutable→Source. USE FOR: implementing handler methods for generated IApi*Handler interfaces, reading/writing blob stores with correct document lifetime, building response bodies, avoiding memory leaks and use-after-free. DO NOT USE FOR: code generation itself (use corvus-codegen), mutable document manipulation details (use corvus-mutable-documents), parsing standalone documents (use corvus-parsed-documents-and-memory).
corvus-docs-website
by corvus-dotnetBuild, serve, and maintain the Corvus.Text.Json documentation website and the six Blazor WASM playgrounds (JSON Schema, JSONata, JMESPath, JsonLogic, JSONPath, YAML). Covers the 12-step build.ps1 pipeline (steps 0-11, with sub-steps), generated vs hand-authored file boundaries, incremental rebuild patterns, XmlDocToMarkdown API doc generation, SCSS/JS asset compilation, and playground startup with Monaco editor. USE FOR: building or previewing the docs site, modifying website content or theme, updating API documentation, running or modifying playgrounds. DO NOT USE FOR: library development (use other skills).
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.