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...
dog-walk
by DbochmanAutomated dog walk detection and Roomba control. Detects departures via Fi GPS collar, starts Roombas, and monitors return via Ring motion + WiFi + Fi GPS. Use when asked about dog walks, Roomba automation during walks, or walk tracking.
fi-collar
by DbochmanCheck Potato's Fi collar GPS location, battery, and connection status. Use when asked where Potato is, collar battery level, or whether Potato is at Crosstown or the Cabin.
resy
by DbochmanSearch restaurants, check availability, and book reservations on Resy. Use when asked about restaurant reservations, dinner plans, booking a table, finding available restaurants, or sniping hard-to-get reservations.
samsung-frame-tv-ws-popup
by DbochmanFix Samsung Frame TV showing a connection notification on the panel every time a samsungtvws WebSocket is opened, even with a saved token. Use when: (1) polling a Samsung Frame TV for status from a dashboard/cron and the panel briefly wakes or shows "[App] is connecting" each poll, (2) using samsungtvws / SamsungTVWS.open() against a Frame TV, (3) art-mode or app_list calls cause a visible popup. Solution: do REST-only polling (rest_device_info, rest_app_status) and reserve WebSocket calls for user-initiated commands.
samsung-tv
by DbochmanControl Samsung The Frame TV. Use when asked about TV, television, art mode, Samsung Frame, turning on/off the TV, or changing TV input/volume/apps.
irobot-mqtt-dock-requires-stop
by DbochmaniRobot Roomba MQTT dock command is silently ignored during active cleaning (run phase). Use when: (1) dock commands return ok but robot keeps cleaning, (2) repeated dock calls have no effect, (3) dorita980 dock not working. Must send stop first, wait 2s, then dock.
roomba
by DbochmanControl iRobot Roomba vacuums at the Cabin (Philly). Use when asked to vacuum, start/stop/dock the Roomba, clean the house, or anything about Floomba or Philly (the two Roombas).
pinchtab-0-11-upgrade-gotchas
by DbochmanSurvive the upgrade from pinchtab v0.7.x/v0.8.x → v0.11.x without silent breakage. Use when: (1) you ran `npm install -g pinchtab@latest` and every CLI invocation errors with "Pinchtab binary not found at: ~/.pinchtab/bin/pinchtab-darwin-arm64 ... To fix this, run: npm rebuild pinchtab" (and `npm rebuild` doesn't actually fix it), (2) `pinchtab eval` or curl POST to `/evaluate` returns "Error 403: evaluate endpoint is disabled; enable security.allowEvaluate in config to use this endpoint", (3) any downstream automation that hits `pinchtab eval` (e.g. grocery-reorder with custom event-dispatch JS for Angular click) silently fails after a pinchtab major-version bump, (4) you're auditing a pinchtab profile dir at `~/.pinchtab/chrome-profile/` and wondering why the new version ignores it. Covers the platform-specific Mach-O binary download, the new `security.allowEvaluate` gate, and the profile path migration.
pinchtab-cdp-token-capture
by DbochmanCapture authentication tokens from reCAPTCHA-protected websites using pinchtab + Chrome DevTools Protocol (CDP). Use when: (1) need to automate token refresh for sites with reCAPTCHA login, (2) need to find Chrome's CDP port when pinchtab uses --remote-debugging-port=0, (3) lsof not working in LaunchAgent context on macOS, (4) need to click inside cross-origin iframes via CDP Input.dispatchMouseEvent, (5) Chrome cookies not persisting between pinchtab restarts, (6) Network.getResponseBody returns empty for fetch() API responses (use Fetch.enable + Fetch.getResponseBody instead), (7) need to capture tokens from login responses by monitoring CDP network traffic passively during browser form submission, (8) API response body structure nests tokens in unexpected locations (e.g., data.user.X not data.X).
pinchtab-react-click-fix
by DbochmanFix Pinchtab/headless browser JavaScript .click() not triggering React event handlers. Use when: (1) pinchtab eval element.click() runs but React app doesn't respond, (2) clicking links/buttons on React SPAs via headless browser automation has no effect, (3) OpenTable or other React sites ignore programmatic clicks but work with real user clicks. Solution: use dispatchEvent with full MouseEvent sequence (mousedown/mouseup/click) with real coordinates from getBoundingClientRect().
red-apple-events
by DbochmanFetch upcoming events from Red Apple Farm and Brew Barn (near the cabin in Phillipston, MA), then sync them to the clawdbotbochman calendar. Use when asked about farm events, Brew Barn events, or cabin-area happenings.
grocery-reorder
by DbochmanReorder groceries from Star Market by replaying the most recent order. Adds items to cart but does NOT checkout. Use when asked to reorder groceries, restock the kitchen, or place a Star Market order.
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.