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...
transportation
by f5xc-salesdemosVehicle records, flight tracking, ship tracking, and transportation intelligence. Use when the user mentions: vehicle, flight tracking, ship tracking, license plate, VIN, maritime, aviation, ADS-B, vessel, aircraft, rail, satellite, package tracking.
f5xc-api
by f5xc-salesdemosF5 Distributed Cloud REST API operations — authenticate, list, create, read, update, delete F5 XC resources (load balancers, origin pools, WAF, DNS, sites, namespaces, app firewall, bot defense, service policies). Activate when user mentions F5 XC, Distributed Cloud, volterra, XC console, API token, load balancer CRUD, origin pool, WAF policy, or platform configuration management.
guardian
by f5xc-salesdemosF5 corporate brand identity enforcement for all content creation. Ensures correct use of F5 colors (45-color palette led by F5 Red #e4002b), typography (Neusa Next Pro Wide headlines, Proxima Nova body), logos (SVG only, light/dark variants), icons (f5-brand and f5xc packs), tone of voice, and WCAG AA accessibility. Use when creating or editing documentation, diagrams, presentations, video thumbnails, social media posts, Mermaid charts, Excalidraw drawings, or any content carrying F5 visual identity. Also use when the user asks about F5 colors, fonts, brand guidelines, or visual standards.
visual-content
by f5xc-salesdemosF5-branded visual content creation for specific media formats. Provides format-specific rules for Mermaid diagrams, Excalidraw drawings, screenshots, PowerPoint presentations, YouTube thumbnails, video scripts, and social media graphics. Builds on the brand-guardian color/typography foundation with output-format guidance including icon pack selection, slide layouts, font fallbacks for non-web environments, and platform-specific dimensions. Use when creating diagrams, making slides, designing thumbnails, preparing screenshots, or producing any visual asset in a specific format. Also use when the user mentions PowerPoint, Mermaid, Excalidraw, YouTube, or social media content creation.
images-videos
by f5xc-salesdemosReverse image search, face recognition, video analysis, document metadata extraction, and EXIF data. Use when the user mentions: reverse image, face recognition, EXIF, metadata, image search, video analysis, document analysis, OCR, font identification, webcam, image forensics.
github-ops
by f5xc-salesdemosGitHub operations toolkit — PR descriptions, code review, issue triage, commit messages, and gh CLI command generation
azure-index
by f5xc-salesdemosTop-level intent router for Azure operations. Routes auth requests to azure-auth, resource queries to the cli-operator agent, and help/discovery to the az_help tool. Use when the user mentions Azure, az CLI, subscriptions, resource groups, VMs, or any Azure topic but the request does not clearly match a specific skill trigger.
reviewer
by f5xc-salesdemosReview existing content for F5 brand compliance. Audits colors, typography, logo format, icon selection, alt text, contrast ratios, and product terminology against F5 brand guidelines. Produces a structured report with VIOLATIONS, WARNINGS, and SUGGESTIONS. Use when the user says "review brand", "check branding", "brand audit", "brand compliance", or invokes /review-brand. Also use before committing visual content or creating PRs that include brand assets, diagrams, or styled documentation.
monitor
by f5xc-salesdemosCloud service status monitoring and operational intelligence via Atlassian Statuspage.io API. Activates when the user asks about cloud status, service health, F5 status, active incidents, outages, degraded services, maintenance windows, component status, operational status, or requests a status briefing. Also activates for: "is [service] up", "any outages", "what's down", "status report for stakeholders", "executive status summary". Delegates all API calls to the status-operator agent — never runs cURL in the main session.
self-awareness
by f5xc-salesdemosContainer identity and self-diagnosis. Activates when asked who you are, what version, where you come from, your build info, self-diagnosis, health check, container history, recent changes, contributors, or any existential question about identity, origin, or container state.
tool-catalog
by f5xc-salesdemosContainer tool knowledge base — knows every CLI tool installed in this devcontainer, organized by category. Activates when the user asks which tool to use, how to use a tool, whether something is installed, or needs help with tasks like sending email, scanning networks, converting files, managing cloud resources, automating browsers, or any operation that requires choosing the right installed CLI. Also activates when you need to determine which command-line tool is appropriate for a task.
content-author
by f5xc-salesdemosContent authoring guide for f5xc-salesdemos docs repos — file structure, MDX syntax rules, frontmatter requirements, image references, and local Docker preview. Use when creating or editing docs/ content, working with MDX files, setting up local preview, or when the user asks about content structure, MDX syntax, or how to preview docs locally.
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.