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...
session-handler-test
by detainCreates a PHPUnit test class in tests/src/ for a SessionHandlerInterface implementation. Use when user says 'add tests', 'write tests for handler', or when a new handler is created without tests. Generates testOpen, testClose, testRead, testWrite, testDestroy, testGc, testCreateSid, testValidateId, testUpdateTimestamp following MySessionHandlerTest.php patterns. Do NOT use for non-handler test classes or general PHPUnit scaffolding.
bin-script
by detainCreates a new CLI script in `bin/` that instantiates `\Detain\Cpanel\Cpanel` with `argv[1]`/`argv[2]` credentials, calls a method, and prints results. Use when user says 'add script', 'create CLI tool', 'new bin file', or needs a command-line wrapper for a Cpanel API method. Do NOT use for library code in `src/` or test code in `tests/`.
run-checks
by detainRuns the full composer test suite (phpcs + phpstan + phpunit) and interprets failures for the session-samurai project. Use when the user says 'run tests', 'check code', 'does it pass', 'verify my changes', or before committing. Knows phpcs uses phpcs.xml (PSR-12 with exclusions), phpstan uses phpstan.neon (level: max, src/ only), and phpunit bootstraps via tests/Bootstrap.php with optional TestConfiguration.php. Do NOT use mid-refactor when tests are intentionally broken.
write-validator-test
by detainCreates PHPUnit test cases for Validator methods in tests/Detain/Tests/ZipZapper/ValidatorTest.php following existing patterns. Use when user says 'add test', 'write test for country', 'test isValid', 'test getFormats', 'test hasCountry', or 'test getZipName'. Covers isValid(), hasCountry(), getFormats(), getZipName(), and ValidationException throwing. Do NOT use for integration tests, parser tests, or bin/parse.php testing.
update-postal-formats
by detainUpdates the $formats array in src/Validator.php from Wikipedia's postal codes list via bin/parse.php. Use when user says 'update formats', 'refresh postal codes', 'sync from Wikipedia', or 'formats are outdated'. Explains the parse.php workflow, MyAdmin dependency requirement, and how to paste output into Validator.php. Do NOT use for adding a single country manually — that is a direct edit to src/Validator.php.
phpunit-mock-test
by detainWrites a PHPUnit 10 unit test under `tests/Unit/{Module}/{Class}Test.php` extending `PHPUnit\Framework\TestCase`, following the exact patterns in `tests/Unit/Auth/JwtHandlerTest.php` and `tests/Unit/Media/Library/ItemRepositoryTest.php` — uses `$this->createMock(Connection::class)` for `Workerman\MySQL\Connection` with `->method('query')->willReturn([['col' => 'val']])` for reads and `->expects($this->once())->method('query')->with($this->stringContains('SQL'), $this->callback(fn))` for writes. Use when the user says 'write a test', 'add unit test', 'TDD this', 'test this class', or adds files under `tests/Unit/`. Covers PSR-4 namespacing (`Phlix\Tests\Unit\{Module}`), constructor-injection mocking, return-value stubs, expectation-based assertions, and running with `vendor/bin/phpunit --testsuite Unit`. Do NOT use for JS tests (project has no JS test runner), integration/E2E tests that need a real DB (no integration testsuite is configured), or non-`tests/Unit/` paths.
fantastico-api-method
by detainAdds a new public method to `src/Fantastico.php` following the SOAP call pattern used by addIp/editIp/deactivateIp. Use when user says 'add method', 'new API call', 'add function', or needs to expose a new Fantastico API operation. Key capabilities: SOAP call wiring, StatisticClient instrumentation, cache management, PHPDoc blocks, and a matching test stub. Do NOT use for modifying the constructor, connect(), or soapIpFunction() internals.
phpunit-test
by detainAdds a test method to `tests/FantasticoTest.php` following the project's PHPUnit pattern. Use when user says 'add test', 'write test', 'implement test', or when filling in `markTestIncomplete` stubs. Key capabilities: setUp with env-var credentials, assertion patterns, incomplete test stubs. Do NOT use for creating new test files or testing non-Fantastico classes.
soap-client-setup
by detainScaffolds SOAP client initialization and credential handling as used in src/Fantastico.php. Use when user says 'new soap client', 'connect to API', or creates a new API wrapper class in src/. Key capabilities: ext-soap wiring with nusoap fallback, connected flag, constructor credential injection, md5 hash auth, response caching skeleton. Do NOT use for REST or non-SOAP integrations.
add-library-checklist
by detainScaffolds a new SugarCraft monorepo port end-to-end across all 14 touchpoints: creates <slug>/composer.json + phpunit.xml + README.md + CALIBER_LEARNINGS.md + src/<Class>.php, then wires it into root composer.json (require + repositories[]), docs/MATCHUPS.md, PROJECT_NAMES.md, root README.md, docs/index.html, docs/lib/<slug>.html, media/icons/<slug>.png, .github/workflows/vhs.yml matrix, and codecov.yml (flag + component). Use when the user says 'add a library', 'port <upstream>', 'scaffold lib <slug>', 'new SugarCraft lib', 'create candy-X / sugar-Y / honey-Z'. Do NOT use to edit an existing lib's metadata (use direct Edit), add a feature to an existing lib (follow that lib's CALIBER_LEARNINGS.md), or rename a lib (separate flow).
scaffold-library
by detainScaffolds a new SugarCraft library end-to-end per the AGENTS.md checklist. Creates <slug>/composer.json (path-repo closure copied from sugar-charts), README.md, CALIBER_LEARNINGS.md, phpunit.xml, src/<Class>.php with declare(strict_types=1) + PSR-4 namespace, tests/ stub, and updates root composer.json + MATCHUPS.md + PROJECT_NAMES.md + README.md table + docs/index.html tile + docs/lib/<slug>.html + .github/workflows/ci.yml + .github/workflows/vhs.yml + codecov.yml. Use when user says 'add new library', 'port <upstream>', 'create candy-X', 'create sugar-Y', or 'create honey-Z'. Do NOT use for adding features to an existing lib (follow that lib's CALIBER_LEARNINGS.md instead) or for renaming libs (separate flow).
php-pro
by detainUse when building PHP applications with modern PHP 8.3+ features, Laravel, or Symfony frameworks. Invokes strict typing, PHPStan level 9, async patterns with Swoole, and PSR standards. Creates controllers, configures middleware, generates migrations, writes PHPUnit/Pest tests, defines typed DTOs and value objects, sets up dependency injection, and scaffolds REST/GraphQL APIs. Use when working with Eloquent, Doctrine, Composer, Psalm, ReactPHP, or any PHP API development.
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.