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...
use-teamcity
by KotlinInteract with the kotlinx-rpc TeamCity CI/CD project using the `teamcity` CLI. Use this skill whenever the user wants to trigger builds, check build status, view build logs, monitor failures, manage the build queue, inspect agents, or do anything related to TeamCity CI. Also use it when the user mentions "TC", "TeamCity", "CI build", "run build", "build status", "build log", "trigger build", "check CI", or references a build configuration name or ID. Trigger even if the user doesn't say "TeamCity" explicitly -- if they ask about CI status, build failures, or want to run something on CI rather than locally, this is the right skill. Do NOT use this skill for local Gradle builds -- use `running_gradle_builds` or `running_gradle_tests` instead.
run-local-verifications
by KotlinDetermine which LOCAL verification checks to run for kotlinx-rpc changes and execute them on the developer's machine. TeamCity builds and GitHub Actions workflows are out of scope -- this skill covers only what can and should be run locally before pushing. Use this skill whenever changes are made to the codebase and you need to verify correctness before committing or opening a PR. Also use it when the user asks to "run checks", "verify changes", "run verifications", "what checks do I need", "validate my changes", "pre-PR checks", or "local checks". Trigger proactively after completing any code modification task -- even if the user doesn't explicitly ask, suggest which verifications are relevant based on what changed.
use-develocity
by KotlinQuery and analyze kotlinx-rpc build scans, test results, and failure patterns from the Develocity server (ge.jetbrains.com) using MCP tools. Use this skill whenever the user wants to look at build scans, investigate CI failures across builds, check build cache hit rates, analyze flaky tests, find recurring failure patterns, or query build performance history. Also trigger when the user mentions "Develocity", "build scan", "GE", "ge.jetbrains.com", "build cache stats", "flaky tests", "failure groups", or asks about build trends, test stability, or CI health. Trigger even if the user doesn't say "Develocity" explicitly -- if they want to look at historical build data, cross-build test analysis, or failure aggregation, this is the right skill. Do NOT use this skill for running local Gradle builds -- use `running_gradle_builds` or `running_gradle_tests` instead. Do NOT use this skill for TeamCity build triggering or queue management -- use `use-teamcity`.
update-doc
by KotlinUpdate kotlinx-rpc documentation — version bumps, content edits, Writerside topics, KDoc, README, skills, and internal workflows. Use this skill whenever the user wants to bump the Kotlin version in docs, bump the library version, update the changelog, edit documentation topics, add a migration guide, update the version switcher, fix version references, write or update KDoc on public APIs, update the README, update Claude skills, or modify CLAUDE.md. Also trigger when the user mentions "update docs", "doc version", "release docs", "Writerside", "v.list", "changelog", "KDoc", "Dokka", "README", "skill", "CLAUDE.md", or wants to sync documentation with a new release.
update-shim
by KotlinModify, build, publish, and verify the Kotlin/Native shim artifacts (gRPC shim and protobuf shim) in native-deps/shims/. Use this skill whenever the user wants to change shim C/C++ source code, update shim headers or .def files, bump a shim upstream version, add or remove archives from the overlap excludes list, patch KLIB metadata, update the annotation module, run shim fixture tests, publish shim artifacts locally, or debug any native shim build failure. Also trigger when the user mentions "shim", "cinterop", "native interop", "grpc shim", "protobuf shim", "KLIB patcher", "overlap archives", "native-deps", "Bazel shim build", or "shim verification".
use-youtrack
by KotlinGeneral-purpose YouTrack operations for the kotlinx-rpc project (KRPC). Use this skill whenever the user wants to search, read, update, comment on, link, tag, or otherwise interact with existing YouTrack issues — anything that isn't creating a brand new issue. Also use it when the user asks about issue status, sprint progress, who's working on what, backlog queries, or wants to browse/filter issues. Trigger this even if the user doesn't say "YouTrack" explicitly — if they mention a KRPC-### issue ID, ask about tickets, want to check on an issue, update a status, or log work, this is the right skill. Do NOT use this skill for creating new issues — use file-youtrack-issue instead.
verify-compiler-plugin-compatibility
by KotlinVerify that the kotlinx-rpc compiler plugin compiles successfully against multiple Kotlin compiler versions, and fix any incompatibilities found. Use this skill whenever the user wants to check compiler plugin compatibility across Kotlin versions, test a new Kotlin version, fix compiler plugin build failures after a Kotlin upgrade, ensure the CSM templates produce valid code for all supported versions, or test against Kotlin Master. Trigger on phrases like "verify compiler plugin", "check compatibility", "test Kotlin versions", "compiler plugin broken", "fix for Kotlin X.Y", "support new Kotlin version", or "Kotlin master".
running-gradle-builds
by KotlinExecutes and orchestrates Gradle builds with background management, surgical task output capturing, and structured failure diagnostics; ALWAYS use instead of `./gradlew` for core lifecycle tasks (build, assemble), dev servers, and troubleshooting. Do NOT use for running tests (use `running_gradle_tests`) or dependency graph auditing.
running-gradle-tests
by KotlinExecutes and diagnoses Gradle tests with high-precision `--tests` filtering, surgical per-test failure isolation, and full stack traces; ALWAYS use instead of `./gradlew test` for test execution, failure investigation, and post-mortem analysis. Do NOT use for general build lifecycle tasks (use `running_gradle_builds`) or dependency auditing.
searching-dependency-sources
by KotlinExplores and searches source code of all external library dependencies, plugins, and Gradle internals via indexed symbol, full-text, and glob search; STRONGLY PREFERRED for understanding APIs, finding class/method definitions, and reading implementation logic. Do NOT use for project source code (use grep), Gradle documentation (use `researching_gradle_internals`), or Maven Central discovery (use `managing_gradle_dependencies`).
kotlin-tooling-cocoapods-spm-migration
by KotlinMigrate KMP projects from CocoaPods (kotlin("native.cocoapods")) to Swift Package Manager (swiftPMDependencies DSL) — replaces pod() with swiftPackage(), transforms cocoapods.* imports to swiftPMImport.*, and reconfigures the Xcode project.
kotlin-tooling-java-to-kotlin
by KotlinUse when converting Java source files to idiomatic Kotlin, when user mentions "java to kotlin", "j2k", "convert java", "migrate java to kotlin", or when working with .java files that need to become .kt files. Handles framework-aware conversion for Spring, Lombok, Hibernate, Jackson, Micronaut, Quarkus, Dagger/Hilt, RxJava, JUnit, Guice, Retrofit, and Mockito.
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.