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...
vault-clarification
by jbaruchRuns interactive clarification sessions with the speaker after talk processing. Resolves ambiguities in rhetoric observations, validates findings, captures speaker intent, conducts humor post-mortems, and probes for blind-spot moments invisible to transcripts. Stores confirmed intents and infrastructure config in the tracking database. Triggers: "run clarification session", "humor post-mortem", "blind spot review", "capture speaker intent", "clarify rhetoric findings".
illustrations
by jbaruchGenerates the visual layer of a talk: deck illustrations (FULL / IMG+TXT slides with a shared style anchor), progressive-reveal build chains, and YouTube thumbnails. Owns style-strategy collaboration (informed by the speaker's visual_style_history in the vault), prompt safety, edit-vs-regenerate asymmetry, build chaining, title-safe-zone composition, and thumbnail composition with a real speaker photo. Invoked by presentation-creator during illustration strategy (Phase 2), illustration generation and application to the deck (Phase 5), and the post-event YouTube thumbnail (Phase 7). Triggers: "illustrate the deck", "generate illustrations", "create slide visuals", "design the visual style", "make a thumbnail", "build a YouTube thumbnail", "add visuals to my talk", "regenerate slide image", "fix the thumbnail", "generate progressive reveals", "build sequence for a slide".
vault-ingress
by jbaruchParses presentation talks to catalog rhetoric patterns: opening hooks, humor style, pacing, transitions, audience interaction, slide design, and verbal signatures. Downloads YouTube transcripts and analyzes slides (from PPTX, Google Drive PDFs, or video extraction), examining HOW the speaker presents. Processes talks in parallel batches and updates the running rhetoric summary. Triggers: "parse my talks", "run the rhetoric analyzer", "analyze my presentation style", "how many talks have been processed", "update the rhetoric knowledge base", "check rhetoric vault status", "process remaining talks for style patterns".
whoami
by jbaruchLists permitted and prohibited actions, blocks disallowed content types, and responds to permission queries in shared or public group settings. Use when joining a new group, when unsure about rules, permissions, or boundaries, when someone asks what you are allowed to do here, or when operating in a public channel or untrusted group chat environment.
promote
by jbaruchPromote agent-created skills and rules from NAS staging to tile GitHub repos via a full PR lifecycle — opens a PR, summons Copilot, iterates fixups until the review is clean, then merges so GHA publishes. Use when there are new items on staging, after check-staging shows pending items, or when asked to deploy skills, push to production, or publish rules to a tile repo.
nuke
by jbaruchKill a running agent container on the NAS by Telegram group JID. The orchestrator respawns a fresh container on the next message. Does NOT delete registration or group folder. Use when a container is stuck, stale, or needs a fresh start.
nullable-cleanup
by jbaruchReplace java.util.Optional usage (Optional.of, Optional.empty, Optional.ofNullable, orElse, ifPresent, etc.) with idiomatic Kotlin nullable types using the question-mark suffix and the safe-call, elvis, and let operators. Strips Java's Optional workaround out of Kotlin code where the language has a better answer. Use when the user asks to "remove Optional," "kotlinify nullables," "strip Optional wrappers," or shows code that wraps nullable values in Optional for no benefit.
govee-h6056-control
by jbaruchControls Govee H6056 Flow Plus light bars (smart LED lights) via cloud REST API with correct segment-to-bar mapping (Yankee=0-5, Golf=6-11), phantom-segment awareness (12-14 return 200 OK but do nothing), correct "off" semantics (rgb=(1,1,1), not (0,0,0)), and rate-limit guidance (~7 req/min sustained → pair with iot-actuator-patterns-kotlin debounce). Use when the user wants to control Govee H6056 light bars, change LED light colors or brightness, set bar segment colors, or automate Govee smart lighting scenes.
render-progress-bar-kotlin
by jbaruchRender a segmented LED progress bar that fills bottom-up with red/yellow/green gradient — thermometer pattern, not falling-bar. Handles top-indexed hardware (where segment[0] is physically at the top) and bottom-indexed hardware. Use when wiring a quantised level (0..N) into an LED bar, especially Govee H6056, Hue Lightstrip, or similar segmented devices where fill direction and gradient matter.
frame-skip-policy
by jbaruchRun expensive per-frame inference (face recognition, emotion classification, ViT embeddings) at a fraction of the capture rate so the camera loop stays responsive. Use when designing a vision pipeline that combines high-rate capture (30fps+) with heavy per-frame work (dlib, ViT, DeepFace) and you don't need every frame to be inferred.
add-jfr-event
by jbaruchAdd a new Java Flight Recorder event to a TamboUI module following project conventions — `dev.tamboui.AREA.THING` naming, `enabled()` guards, static `commit(...)` helper, and `compileOnly(libs.jfr.polyfill)` for Java 8 modules. Use when the user says "add a JFR event", "trace X with JFR", "instrument Y for flight recorder", or "emit a JFR event for Z".
camera-setup
by jbaruchOpen and warm up a cv2.VideoCapture reliably, probe for real (non-black) frames before starting the main loop, and handle macOS index enumeration quirks. Use when a VideoCapture call succeeds but returns black/stale frames, when switching between built-in and USB webcams, or when the first ~5 seconds of a pipeline produce zero face detections.
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.