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...
simulink-layout-tidy
by calebzuTidy the layout of an already-built Simulink model — make it compact and readable, remove block overlaps and lines that cut through blocks, and honestly minimize line-line crossings without ever falsely promising zero. Quantifies block overlaps, line-through-block hits, line-line crossings, model extent, and graph planarity (K3,3/K5 detection) before and after arranging, then exports a screenshot for human sign-off. Use when a Simulink or .slx block diagram looks messy, cluttered, overlapping, or tangled; when asked to clean up, arrange, beautify, declutter, or improve the readability of a Simulink diagram; or after auto-building a model that needs visual polish. General-purpose across any domain (not motor-specific). Local MATLAB only. Skip for non-Simulink diagrams, pure simulation or numerical questions, or any request that changes model behavior or port connections.
motor-dtc-pmsm
by calebzuPMSM Direct Torque Control Builder. Build a Direct Torque Control (DTC) outer-loop torque/flux controller for a three-phase voltage-source-inverter-driven PMSM (SPMSM/IPMSM via parameterization) in Simulink using Sutikno 6-state switching table, αβ stationary frame, 2-level hysteresis on (T, ψ), with outer-loop Speed PI providing Te_ref. Use when constructing, reproducing, porting, or extending a DTC simulation in Simulink (keywords DTC, direct torque control, Takahashi DTC, Sutikno DTC, hysteresis-based torque control, switching table, 磁链滞环, 转矩滞环). Skip for FCS-MPC, FOC, sensorless, scalar V/Hz, BLDC trapezoidal, induction-motor DTC, DTC-SVM, MP-DTC, or pure theory questions. Layered on motor-pmsm-base.
motor-fcs-mpc-dualvector
by calebzuPMSM Dual-Vector Finite-Control-Set MPC Builder. Build an inner-loop two-vectors-per-period finite-control-set MPC current controller for a three-phase voltage-source-inverter-driven PMSM (SPMSM / mild-saliency IPMSM via parameterization) in Simulink, with an outer speed PI providing iq_ref. Two vectors per control period (V_opt1 + V_j) with q-axis-deadbeat time allocation cut switching-cycle current ripple ~3-5x below single-vector FCS-MPC. Use when constructing, reproducing, porting, or extending a dual-vector / two-vector FCS-MPC current-control simulation in Simulink (keywords dual-vector MPC, two-vector MPC, double-vector MPCC, deadbeat time allocation, duty-cycle MPC, 双矢量模型预测, 占空比 MPC). Skip for single-vector FCS-MPC (use motor-fcs-mpc), FOC, DTC, SMC, sensorless, scalar V/Hz, BLDC trapezoidal, induction-motor MPC, three-or-more-vector / multi-step-horizon MPC, strong-saliency IPMSM MTPA, weak-field, or pure theory questions. Layered on motor-pmsm-base.
motor-fcs-mpc
by calebzuPMSM Single-Vector Finite-Control-Set MPC Builder. Build an inner-loop finite-control-set MPC current controller for a three-phase voltage-source-inverter-driven PMSM (SPMSM/IPMSM via parameterization) in Simulink, with optional outer speed PI providing iq_ref. Use when constructing, reproducing, porting, or extending an FCS-MPC simulation in Simulink (keywords FCS-MPC, finite control set MPC, single-vector MPC, 7-vector / 8-vector MPC, predictive current control). Skip for FOC, DTC, sensorless, scalar control, BLDC trapezoidal, induction-motor MPC, multi-step horizon, weak-field, MTPA optimization, or pure theory questions. Layered on motor-pmsm-base.
motor-pmsm-base
by calebzuPMSM Simulation Modeling Base — entry-point skill for building three-phase voltage-source-inverter-driven PMSM (SPMSM/IPMSM) control simulations in Simulink. Provides plant build standard, dq frame conventions, building blocks library SOP, sanity-check templates, broken-FOC defense checklist, and visual review standards. Method-specific skills (motor-fcs-mpc / motor-dtc-pmsm / motor-smc-pmsm) layer their control law on this base. Use when starting a new PMSM control method study, designing a build script skeleton, or debugging broken-FOC symptoms (motor stalled, abc DC-locked). Skip for non-PMSM motors (induction / BLDC / SRM) or pure theory questions.
motor-smc-pmsm
by calebzuPMSM Sliding Mode Control Speed-Loop Builder. Build a Sliding Mode Control (SMC) speed-loop outer controller (PD-type sliding surface + Super-Twisting Algorithm reaching law) + dq current-loop PI inner controller with cross-decoupling feedforward + Anti_Park library block + SVPWM library block + Universal Bridge IGBT inverter + PMSM Discrete plant for a three-phase voltage-source-inverter-driven PMSM in Simulink. v1 baseline supports SPMSM and mild-saliency IPMSM (id_ref=0). Use when constructing, reproducing, porting, or extending an SMC-based PMSM speed-loop simulation in Simulink (keywords SMC, sliding mode control, super-twisting, STA, PD-type sliding, boundary layer SMC, 滑模控制, 滑模面). Skip for FCS-MPC, FOC, DTC, sensorless, scalar V/Hz, BLDC trapezoidal, induction-motor SMC, observer-based / adaptive / disturbance-observer / neural-network / fuzzy SMC variants, strong-saliency IPMSM MTPA, weak-field, or pure theory questions. Layered on motor-pmsm-base.
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.