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...
run-maintenance-task
by duckduckgoUse this skill to execute a task from the Android Agentic Maintenance Backlog. Invoke when the user provides an Asana task URL from that backlog and asks to run, start, execute, or work on it. Also invoke when the user says things like "run the next maintenance task", "work on this backlog item", or "pick up a maintenance task". Requires the Asana MCP to be configured.
review-public-api
by duckduckgoUse this skill when the user asks to review a DuckDuckGo Android public API proposal. If given an Asana task URL, first fetch the task and confirm it is an API proposal before invoking — do not invoke just because a URL was paired with "review". Confirmed signals: the task title contains "API Proposal"; the task belongs to project 1212149061863360 (API Proposals); or the description proposes changes to a -api module. Also invoke for any request to review, evaluate, or give feedback on a proposal pasted inline or provided as a file. Covers phrases like "review my API proposal", "is this API design good?", "check my public interface", "I'm about to submit an API proposal". When the user shares Kotlin code, only invoke if the code is explicitly from or intended for a -api module — do not invoke for impl-only changes or general Kotlin questions. IMPORTANT: Always apply these instructions directly — never delegate or summarise.
check-translations-pr
by duckduckgoCheck whether a translations PR provides full language coverage for all translatable strings it contains, and identify which languages are still missing. Use this whenever the user asks about translation status, whether translations are complete or ready, which languages are missing, or wants to verify a translations PR before merging. Also trigger when the user pastes a PR number or URL alongside any mention of translations, or asks something like "are we good to ship?" in a context that involves string changes.
scope-maintenance-task
by duckduckgoUse this skill to interactively scope a maintenance idea into a properly formatted task for the Android Agentic Maintenance Backlog. Invoke when the user wants to add a task to the maintenance backlog, scope a new maintenance idea, or says things like "I want to add something to the backlog", "help me scope a maintenance task", or "can we add this as a maintenance item".
update-entities
by duckduckgoHow to add or remove domains from an entity (company/organization) in Tracker Radar. Use when modifying domain-to-entity mappings.
ddg-diagnose-ci-failure
by duckduckgoInvoke ONLY when the user explicitly runs /ddg-diagnose-ci-failure or names this skill by name (e.g. "use ddg-diagnose-ci-failure on PR 4780"). Do NOT auto-invoke from symptom/intent matching - the skill may query the Apple CI Failing Tests Asana project (Step 3e), which locks other MCPs for the rest of the session under the lethal-trifecta policy, so it must be user-initiated. If the user asks about CI failures, GitHub Actions runs, or flaky tests without naming this skill, answer directly instead. Accepts one optional argument: a GitHub Actions run URL, a PR URL or bare PR number, or an Apple CI Failing Tests Asana task URL - or no argument to use the current branch's open PR.
ddg-apple-feedback-review
by duckduckgoInvoke ONLY when the user explicitly runs /ddg-apple-feedback-review or names this skill by name. Do NOT auto-invoke from symptom/intent matching. If the user asks about Apple feedback, iOS or macOS issues, user reports, or feedback triage without naming this skill, answer directly instead.
ddg-drk-add-icon
by duckduckgoInvoke ONLY when the user explicitly runs /ddg-drk-add-icon or names this skill by name (e.g. "use ddg-drk-add-icon to add these SVGs"). Do NOT auto-invoke from symptom/intent matching — the skill mutates the apple-browsers asset catalog and Swift files and creates a git commit, so it must be user-initiated. If the user asks about adding icons or Swift package assets without naming this skill, answer directly instead. Inputs are a list of local paths and/or HTTP URLs (one entry per icon); category (Glyph/Color/Recolorable) and size are derived from each filename. Handles imageset/symbolset creation, Contents.json variants, and the camelCase accessor in the matching DesignSystemImages+*.swift file, in a single batch commit.
ddg-sentry-report
by duckduckgoInvoke ONLY when the user explicitly runs `/ddg-sentry-report` or names this skill by name (e.g. "use ddg-sentry-report for macOS 1.186"). Do NOT auto-invoke from symptom/intent matching — the skill writes to a shared Asana task and must be user-initiated. If the user asks about Sentry issues or crash triage without naming this skill, answer directly. Inputs: project (iOS/macOS) and optional version, release-type, Asana parent URL, and time range — body documents resolution rules.
publicwww-search
by duckduckgoSearch PublicWWW to find websites using specific HTML/JS/CSS snippets. Use this skill to check if a cookie popup is from a widespread third-party CMP, to find additional test URLs for a CMP rule, or to discover how many sites use a particular consent banner pattern.
verify-pr
by duckduckgoVerifies an autoconsent pull request by running local CI checks, reviewing rule quality, and inspecting Jenkins E2E results. Use when reviewing, verifying, or approving a PR, when checking if a PR is ready to merge, or when the user asks to validate PR changes.
publicwww-search
by duckduckgoSearch PublicWWW to find websites using specific HTML/JS/CSS snippets. Use this skill to check if a cookie popup is from a widespread third-party CMP, to find additional test URLs for a CMP rule, or to discover how many sites use a particular consent banner pattern.
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.