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...
pydoll-antibot-bypasser
by EsonhughStealth browser automation using pydoll library, specialized in bypassing Cloudflare WAF, Turnstile CAPTCHA, and other bot detection systems. **Must invoke this skill when users need to bypass WAF (Cloudflare, DataDome, PerimeterX, etc.) or human verification.** Also suitable for: anti-scraping bypass, stealth browser operations, crawling protected websites, handling Shadow DOM, simulating human behavior, and web automation testing.
close-case
by EsonhughThis skill should be used when the user asks to "close the case", "conclude the investigation", "wrap up", "present findings", or when the convergence check indicates the case has been solved. Produces the final resolution with complete evidence chain.
discuss-case
by EsonhughThis skill should be used when the user asks to "discuss the case", "brainstorm about the investigation", "I'm stuck", "what do you think", or when the investigation loop detects a deadlock, hypothesis ambiguity, or needs user input to break a tie. Facilitates structured case discussion.
investigate
by EsonhughThis skill should be used when the user asks to "investigate", "continue the investigation", "run the detective loop", "next investigation step", or wants to execute the Scan-Evolve-Focus-Act-File cycle on an active case. Runs the core investigation loop with periodic checkpoints.
open-case
by EsonhughThis skill should be used when the user asks to "open a case", "start an investigation", "investigate this problem", "begin detective mode", or wants to apply structured investigation methodology to solve an unknown-target problem. Initializes a CaseBoard and begins the case-opening phase.
review-board
by EsonhughThis skill should be used when the user asks to "review the board", "show the case status", "what's on the board", "show investigation progress", "display the case", or wants to see the current state of their investigation CaseBoard.
brainstorm
by EsonhughThis skill should be used when the user has a vague problem, wants to think through what to investigate before opening a case, says "I'm not sure what's wrong", "help me think about this", "let's figure out what to investigate", or needs collaborative exploration of the problem space before committing to a structured investigation. Produces a case brief that feeds directly into open-case.
terminal-session-debugging
by EsonhughUse when debugging interactive CLI, REPL, TUI, ssh, telnet, nc, watch-mode, dev server, long-running command, terminal prompt flow, or any command that may not exit. Provides a PTY-backed MCP workflow for spawning terminal sessions, sending text and keys, reading output, managing multiple sessions, and exporting full transcripts.
interactive-cli-systemic-debugging
by EsonhughThis skill should be used when a user asks to debug an interactive CLI, REPL, TUI, prompt loop, shell wizard, watch mode, long-running terminal process, or any command that hangs, waits for input, redraws incorrectly, needs multiple inputs, behaves differently in a real terminal, or requires comparing tmux panes. Trigger on phrases like “it hangs after Continue?”, “the prompt never appears,” “my curses UI breaks in a small terminal,” “the watcher only fails after I answer the prompt,” or “inspect pane 2.”
macos-control-bypasses
by EsonhughmacOS offensive security assistant — helps engineers audit applications for security vulnerabilities, identify bypass vectors in macOS security controls, and learn macOS internals through real-world case studies (CVEs). Covers: app vulnerability assessment (entitlement/injection/sandbox/TCC analysis), system internals, binary analysis, shellcode crafting (x64/ARM64), dylib injection, Mach IPC exploitation, function hooking, XPC attacks, sandbox escapes, TCC bypasses, symlink/hardlink attacks, kernel code execution, persistence mechanisms, Gatekeeper/XProtect bypass, AMFI/MACF internals, launch constraints, application-runtime injection (Electron/Chromium/NIB/.NET/Java/Python), IOKit/DriverKit driver attacks, MDM/DEP exploitation, keychain attacks, dangerous entitlements, and full penetration testing workflows. Use this skill whenever the user asks about: checking macOS apps for security issues, auditing entitlements or sandbox profiles, learning macOS security internals, macOS security research, macOS privile
threatbook-intel
by Esonhugh微步在线威胁情报查询工具。支持IP、域名、文件哈希威胁情报查询，漏洞情报查询，资产测绘等功能。支持微信登录自动化和X语言高级搜索。当用户需要查询威胁情报、进行资产测绘或使用微步在线平台时，应使用此技能。
fofa-intel
by EsonhughFOFA 网络空间搜索引擎查询工具。当用户需要进行 FOFA 查询、网络资产测绘、 IP/域名/证书/端口搜索、OSINT 侦察、资产发现时，必须使用此 skill。 支持 search/dump/host/stats/count/domains 等全部 fofa CLI 功能。 如果 chrome-devtools MCP 可用，可额外通过浏览器访问 fofa.info 做可视化查询。
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.