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...
control
by SynchronetBBSUse when controlling a running Synchronet instance — recycling/reloading, shutdown, pause, clearing the failed-login list, or forcing a timed event. Covers cross-platform **semaphore files** in `ctrl/`/`data/` (`recycle`/`shutdown`/`pause`/`clear` with per-server `.<service>` and per-host `.<hostname>` suffix variants for shared-`ctrl/` setups), POSIX signals to `sbbscon` (SIGTERM/etc. = quit, SIGHUP = recycle-all), OS service managers (systemctl, service, launchctl, sc.exe), Windows front-ends (sbbsctrl, sbbsNTsvcs), the `node rerun` utility, the "won't recycle while in use" gotcha, and the `NO_RECYCLE` flag. For control via MQTT — often preferred even on the same host — see the `mqtt` skill. Trigger on "recycle the web server", "restart sbbs", "pause connections", "clear failed-login list", "send a signal to sbbs", "force a timed event", or "remove an IP ban".
mqtt
by SynchronetBBSUse when working with Synchronet's MQTT integration — discovering whether MQTT is enabled (the `[MQTT]` section of `ctrl/main.ini`, **not** `sbbs.ini`), reading broker address/port/credentials/TLS settings, connecting with `mosquitto_sub`/`mosquitto_pub` (anonymous, user+pass, or one of four TLS modes: CA, mTLS, PSK, SBBS-internal-CA), or interacting with the topic tree for **monitoring** (server/node status, node-output spying, `action/#`, retained `login_attempts/<IP>` and `max_concurrent/<IP>`, log streams `…/log[/<N>]`) or **controlling** the BBS (production-impacting topics that recycle/pause/resume servers, clear failed-login lists, set node flags, inject input or messages into a node — plus the local-filesystem equivalents in `ctrl/`). Trigger on "is MQTT enabled", "what's the broker address", "subscribe to all sbbs logs", "pause/recycle via MQTT", "inject a message into node N", "clear failed-login for an IP", or "spy on a node remotely".
smbutils
by SynchronetBBSUse when inspecting, validating, repairing, importing into, or maintaining a Synchronet Message Base (SMB) file — mail (mail.shd), message sub-boards (data/subs/<code>.shd), or file bases (data/file/<code>.shd) — via the smbutil, chksmb, or fixsmb command-line tools. Trigger whenever the user mentions smbutil, chksmb, fixsmb, SMB files, .shd / .sdt / .sid / .sha files, "the mail base", "rebuild/renumber the message base", "pack the sub", "check the message base for corruption", "repair an SMB", "dump a hash file", "view headers", "import a message", or any low-level inspection, validation, or repair of a Synchronet messaging file that isn't doable from inside the BBS or MsgBase JS API. Prefer this skill over guessing flags or shelling out blind.
text
by SynchronetBBSUse when a sysop wants to customize the text strings/prompts Synchronet sends to remote users — the runtime `text[]` string database. Covers `ctrl/text.dat` syntax (Ctrl-A codes, @-codes, %-specifiers, mnemonics, the decimal-`\NNN`-vs-hex-`\xNN` trap, multi-line continuation, %-vs-@-code mutual exclusion, missing-line fallback to compiled default), `ctrl/text.ini` override file (three sections: by-ID overrides, `[substr]` global substitution, `[JS]` for `gettext()` strings), `ctrl/text.<lang>.ini` per-language overlays, and the recycle-required consequence. For display files see `menus`; for `gettext()`/`js.load_text()` see `javascript`; for recycling see `control`. Trigger on "change a BBS prompt", "translate strings", "override text.dat without editing it", "what's text.ini", "retheme the BBS colors", "replace \1g with \1m everywhere" (or any global Ctrl-A code substitution), or "why didn't my text.dat change take effect".
menus
by SynchronetBBSUse when authoring or modifying Synchronet Terminal Server display/menu files — anything in `text/`, `text/menu/`, `mods/text/`, `mods/text/menu/`, `data/subs/<code>.*`, `data/dirs/<code>.*`. Covers Ctrl-A (^A) attribute codes, @-code message variables, the file-extension priority by terminal type (rip/ans/mon/asc/msg/seq/utf8), .Xcol/.cX width variants, language overlays, security gating, mouse hotspots, and the C++/JS/Baja entry points that render these files. For the runtime string database (`ctrl/text.dat`, `ctrl/text.ini`, `ctrl/text.<lang>.ini`) see the `text` skill. Trigger on tasks like "add help menu file", "fix CGA brown color", "show this only to sysops", "make this prompt work on PETSCII", "what @-codes are available in this context", "why isn't my .ans file being picked up", "wire @SHOW:LEVEL40@", or any work that touches the look/content of what a remote BBS user sees.
jsexec
by SynchronetBBSUse whenever you need to RUN Synchronet JavaScript — executing inline JS expressions, running scripts from the install's exec/ directory, testing JS modules, or validating changes to .js/.ssjs/.xjs files against a live install. This skill covers the jsexec runner itself: invocation modes, flags, output capture, crash tracing, and (on Windows) running a freshly-built debug binary. Trigger on "run a Synchronet script", "test this JS against Synchronet", "check what jsexec does", or any one-off JavaScript probe of a live install. For the JavaScript LANGUAGE and host API (how MsgBase/User/FileBase behave, SpiderMonkey dialect, the object model, writing tests, stock exec/*.js) see the javascript skill.
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.