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...
rcj-soccer-coach
by IITA-ProyectosUse when working in the IITA Soccer Open repo to give technical feedback to students. Frames feedback as tema-a-analizar with risk-no-fix / risk-fix / tiempo, prioritizes P0/P1/P2, and demands a hardware-real test plan. Activates the senior-coach lens (RoboCupJunior Soccer Open + Middle Size League experience).
advanced-pid-optimization
by IITA-ProyectosTécnicas avanzadas de optimización de controladores PID para robótica de competencia — más allá del tuning empírico básico. Cubre gain scheduling por régimen, derivative filtering (D-on-measurement, D-low-pass), anti-windup con back-calculation, feedforward del modelo, two-degree-of-freedom (setpoint weighting), control bang-bang en saturación, deadband, métricas formales (ITAE, ISE, IAE), gain scheduling adaptativo, y consideraciones de tiempo de muestreo. Usar SIEMPRE que se requiera optimizar un PID que ya funciona pero hay que pulirlo, exprimir velocidad sin perder estabilidad, manejar régimenes muy distintos (recta vs curva), saturación de actuadores, ruido alto en la medición, o se mencione 'gain scheduling', 'derivative kick', 'D-on-measurement', 'derivative filter', 'back-calculation anti-windup', 'feedforward', 'two-degree-of-freedom PID', 'setpoint weighting', 'ITAE', 'ISE', 'control optimizado', 'PID adaptativo'. NO usar para el primer tuning empírico básico (eso es robotics-control-theory).
robotics-control-theory
by IITA-ProyectosTeoría de control aplicada a robótica de competición — PID tuning con métodos sistemáticos (Ziegler-Nichols), feedforward, filtros de señal (low-pass, complementary, Kalman simple), state machines y máquinas de estado finito para comportamiento robótico. Usar SIEMPRE que se trabaje en sintonización profesional de PID, métodos formales de tuning, fusión de sensores con filtros, diseño de state machines para robots, control teorico aplicado, o se mencione 'PID tuning', 'Ziegler-Nichols', 'feedforward', 'low-pass filter', 'complementary filter', 'Kalman', 'state machine', 'FSM', 'control loop', 'transfer function'. Aplica a Pybricks, Arduino, ROS, Raspberry Pi y cualquier plataforma de robótica. Es transversal a todas las categorías de competición.
sensor-calibration-logger
by IITA-Proyectoscalibrate spike sensors and analyze logs for pybricks competition robots. use when the user wants black and white thresholds, color detection, distance cutoffs, imu-based headings, or interpretation of reflection and timing data from repeated tests.
openmv-vision-tuning
by IITA-ProyectosUse when calibrating or troubleshooting OpenMV cameras (H7 / H7 Plus) for the soccer robot — LAB color thresholds for orange golf ball (passive IR ball 2026) and cyan/magenta goals, exposure lock under varying field lighting, FOV and mount tuning, multi-camera consistency, frame rate vs accuracy trade-offs. Critical for Incheon where lighting differs from the IITA Salta lab.
wro-football
by IITA-ProyectosEstrategia y patrones para WRO Football (RoboSport Football) — competición de fútbol robótico 2v2 con bola IR pulsada. Usar SIEMPRE que se trabaje en WRO Football, fútbol robótico, soccer robot, IR ball tracking, sensor de bola infrarroja, posicionamiento en cancha de fútbol robótico, roles goalkeeper/striker, omnidirectional drive, kicker mechanism, o se mencione 'WRO Football', 'soccer', 'IR ball', 'pulsed infrared', 'goalkeeper', 'striker', 'kicker', 'goal post', 'penalty area', 'RCJ Soccer'. La bola es siempre IR pulsada según estándar RoboCup. NO usar para WRO RoboMission (eso va en wro-robomission-strategy) ni Future Engineers.
attachment-cycle-optimizer
by IITA-Proyectosdesign and code reliable attachment cycles for lego spike competition robots using pybricks. use when the user needs motorized arms, lifts, claws, sliders, homing, synchronization with drive motion, or safe reset positions between autonomous runs.
drivebase-tuner
by IITA-Proyectostune straight driving and turning accuracy for lego spike pybricks drive bases. use when the user wants to measure wheel diameter, axle track, drift, overshoot, drivebase settings, or convert test results into corrected constants for competition robots.
line-follower-tuner
by IITA-Proyectosbuild and tune fast, stable line following for lego spike robots programmed with pybricks. use when the user asks for proportional or pd control, gap recovery, intersections, edge selection, rescue line behavior, or precision line following on black or colored tracks.
wro-robomission-strategist
by IITA-Proyectosplan wro robomission runs for lego spike robots programmed with pybricks. use when the user wants to convert the yearly mission rules into scoring strategy, route order, attachments, risk analysis, run segmentation, or code priorities for autonomous wro attempts.
wro-future-engineers
by IITA-ProyectosEstrategia y arquitectura para WRO Future Engineers — la categoría de auto autónomo de WRO con vehículo Ackermann, cámara, y misiones de circuit + obstacle avoidance + parking. Usar SIEMPRE que se trabaje en WRO Future Engineers, FE, autonomous car competition, vehículo Ackermann, steering servo, computer vision con Raspberry Pi/OpenCV para detección de obstáculos por color, parking paralelo autónomo, navegación por circuito cerrado con paredes, o se mencione 'Future Engineers', 'autonomous car', 'Ackermann steering', 'parallel parking', 'pillars', 'red green pillar', 'OpenCV ROI', 'PiCamera'. NO usar para WRO RoboMission (eso va en wro-robomission-strategy) ni Football (wro-football). Esta categoría usa Raspberry Pi + Pi Camera, NO Spike Prime.
vibe-mechanical-design
by IITA-ProyectosUse when designing or iterating mechanical parts for the robot (chassis, dribbler, kicker, sensor mounts, omni wheel hubs) using AI-accelerated CAD pipelines. Goes from sketch/intent to printable STL/STEP with verification gates (clearance, motor torque match, manufacturability, BOM check). Specialised for RoboCup-class robots with 3D-printed + manually-fabricated parts.
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.