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...
drupal-migration
by trebormcHandles Drupal content migrations: D7 to D10/D11 upgrades, custom migrations from external sources (CSV, JSON, API, SQL), Migrate API configuration, source/process/destination plugins, and incremental migration strategies. Examples: - user: "migrate content from D7 to D10" -> plan and implement migration - user: "create a migration from CSV" -> custom source plugin + YAML config - user: "upgrade from Drupal 7" -> plan and implement migration - user: "import data from external API" -> custom source plugin + YAML config Never run migrations on production without --limit testing first.
xdebug-profiling
by trebormcEnables Xdebug tracing and profiling in DDEV to debug errors and analyze performance. Covers trace mode (function call tree, arguments, return values), profile mode (cachegrind analysis), triggering for specific requests, and programmatic output analysis. Use when debugging page errors, analyzing slow pages, finding performance bottlenecks, or tracing code execution paths. Examples: - user: "debug this page error" -> enable Xdebug trace, trigger request, analyze trace - user: "why is this page slow" -> enable Xdebug profiler, trigger request, analyze cachegrind - user: "trace the execution of /admin/content" -> trace mode workflow - user: "find where this error comes from" -> enable Xdebug trace and analyze - user: "this page loads slowly" -> enable profiler and analyze bottlenecks - user: "analyze performance of this request" -> profile mode workflow Never use for step debugging with IDE breakpoints (that requires IDE integration).
beads-task-tracking
by trebormcManages tasks using Beads (bd), a git-backed task tracker running in a dedicated DDEV container. Use for creating, updating, closing, and querying tasks throughout development sessions. A wrapper at /usr/local/bin/bd delegates commands to the Beads container transparently. Examples: - user: "create a task for this feature" -> bd create "Title" -p 1 --json - user: "what tasks are pending" -> bd ready --json - user: "mark this done" -> bd close <id> --reason "Done" --json - user: "create a task" -> bd create "Title" -p 1 --json - user: "what tasks are left" -> bd ready --json - user: "start tracking work" -> bd init, bd create tasks Never use `bd edit` (opens interactive editor). Never run git commit or push.
commit-message
by trebormcGenerates high-quality commit messages by analyzing git diff and status. Saves the message to a text file in the project root for the user to review and commit manually. Uses Conventional Commits format with type(scope) prefix. Writes the message in the same language the user is using unless a specific language is requested. Examples: - user: "generate a commit message" -> analyze diff, write commit-msg.txt - user: "genera un mensaje de commit" -> analyze diff, write commit-msg.txt - user: "prepare commit message for my changes" -> analyze diff, write commit-msg.txt - user: "hazme el mensaje de commit" -> analyze diff, write commit-msg.txt Never use this to execute git commit. Never push to remote.
drupal-config-management
by trebormcManages Drupal configuration: export, import, config_split setup, schema validation, and environment-specific overrides via settings.php. Use when dealing with config sync, config_split, settings.php overrides, or config schema creation. Examples: - user: "set up config split for dev/stage/prod" -> configure config_split - user: "my config import fails" -> diagnose and fix config sync issues - user: "add config schema for my module" -> generate proper schema.yml - user: "configure config split" -> configure config_split - user: "export configuration" -> guide through drush cex workflow - user: "config import fails" -> diagnose config sync issues Never directly modify files in config/sync/ — always use drush cex.
drupal-audit-setup
by trebormcInstalls and configures the Drupal Audit module (drupal/audit) and its submodules. Provides site health scores, module inventory, and code quality analysis via drush commands. Use when the Audit module is not yet installed, or when setting up a new project. Recommended: enable audit_all for production submodules, plus audit_phpcs, audit_phpstan, and audit_complexity for development environments. Examples: - user: "install the audit module" -> composer require + drush en audit_all - user: "set up code quality tools" -> install audit with dev analyzers - user: "audit module is missing" -> install and enable audit submodules
drupal-behat-test
by trebormcGenerates Behat tests for Drupal 10/11 using the Drupal Extension for Behat. Use this skill when the project already has Behat configured (look for behat.yml), when acceptance tests written in natural language (Gherkin) are needed, E2E flows, or when the client needs to read and validate test scenarios. Trigger: "behat test", "acceptance test", "feature file", "gherkin", "behat scenario", "bdd test", "behavior test", or when behat.yml exists in the project. Never use for service/entity logic (use drupal-kernel-test). Never use for simple form testing (use drupal-functional-test). Never use for visual regression (use drupal-playwright-test).
drupal-code-patterns
by trebormcReference patterns and templates for common Drupal 10/11 development tasks: forms, block plugins, routing, controllers, hooks, caching, Batch API, Queue API, and AJAX forms. Use when implementing these patterns in custom modules. For module scaffolding (info.yml, services.yml), use drupal-module-scaffold. Examples: - user: "create a form" -> use Form template pattern - user: "add a block plugin" -> use Block Plugin template - user: "implement hook_form_alter" -> use Hooks patterns - user: "add AJAX to my form" -> use AJAX Form pattern - user: "batch process for importing data" -> use Batch API pattern Never use for module scaffolding (use drupal-module-scaffold) or theming (use drupal-theme agent).
drupal-debugging
by trebormcProvides Drupal debugging commands for inspecting services, entities, cache, configuration, watchdog logs, database queries, and PHP evaluation via drush. Use when diagnosing issues, inspecting Drupal state, or troubleshooting errors. Examples: - user: "check watchdog logs" -> show recent log entries - user: "debug this service" -> inspect service container and definitions - user: "what errors are in the log" -> show watchdog errors - user: "inspect the cache" -> cache debugging commands Never use for destructive operations (use drush-commands skill instead).
drupal-functional-test
by trebormcGenerates Functional tests for Drupal 10/11 using BrowserTestBase. Use this skill when you need to verify rendered forms, form submission via UI, permissions and access via HTTP, HTML output of pages, admin forms, node creation/editing via the interface, redirects, or anything requiring a full HTTP response but NOT JavaScript. Trigger: "functional test", "form test", "permissions test", "page test", "admin form test", "node creation test", "browser test". Never use for logic testable with Kernel test (use drupal-kernel-test). Never use for JavaScript interactions (use drupal-functionaljs-test). Never use for pure PHP logic (use Unit test from drupal-testing rule).
drupal-functionaljs-test
by trebormcGenerates FunctionalJavascript tests for Drupal 10/11 using WebDriverTestBase. Use this skill when the code under test depends on JavaScript: AJAX forms, entity reference autocompletes, modals, drag-and-drop, visibility toggles, CKEditor, complex #states. These are the slowest PHPUnit tests in Drupal, use them only when there is no alternative without JavaScript. Trigger: "javascript test", "ajax test", "autocomplete test", "modal test", "webdriver test", "functional javascript". Never use for non-JS forms (use drupal-functional-test). Never use for service/entity logic (use drupal-kernel-test). Never use for E2E flows (use drupal-behat-test or drupal-playwright-test).
drupal-kernel-test
by trebormcGenerates Kernel tests for Drupal 10/11 using KernelTestBase. Use this skill when the code interacts with container services, entities, database, configuration, plugins, hooks, migrations, event subscribers, or any Drupal API that does not require rendering HTML in a browser. This is the most used and recommended test type by the Drupal community for custom modules. Trigger: "kernel test", "service test", "entity test", "migration test", "plugin test", "CRUD test", "access test", or when the code uses the service container but does not need UI. Never use for HTML rendering verification (use drupal-functional-test). Never use for JavaScript interactions (use drupal-functionaljs-test). Never use for pure PHP logic without Drupal dependencies (use Unit test from drupal-testing rule).
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.