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...
vtable
by freeqazDump a class's MWCC vtable from build/SZBE69_B8/obj/*.o. Shows every sub-object table (primary + each base), slot index, byte offset, and the mangled function symbol. Use when objdiff shows a `lwz r12, OFF(r12)` mismatch and you need to map the offset to a virtual method, or when verifying a header's virtual-function order against the compiled binary.
batch-check
by freeqazSweep a unit or glob of units for already-matching functions. Reads build/SZBE69_B8/report.json (no per-function objdiff invocations), auto-marks 100% matches as COMPLETE in decomp.db, and reports partial-match candidates ranked by closeness to 100%. Use this after a header change, a build-system change, or to find a unit's untouched workable functions.
stack-layout
by freeqazDiff stack-frame layouts between target and base for a function. Labels base-side slots with source variable names from a MSVC /Z7 CodeView recompile. Identifies SWAPPED pairs (decl-reorder candidates), SHIFTED slots, DIFFER (different variables in same slot), and TGT_ONLY / BASE_ONLY (extra/missing locals). Filters out callee-save slots.
xenia-gameplay
by freeqazRun DC3's original Xbox 360 debug XEX on Xenia (Linux/Vulkan) and navigate to gameplay. Captures headless frames of menus, song select, loading, and in-game venues with 3D characters. Use when testing original binary behavior, capturing IK telemetry, or comparing Xbox vs native rendering.
rb2-class
by freeqazGet class layout from RB2 DWARF debug info. Shows member offsets, sizes, types, and inheritance. Ground truth for struct layouts when DC3 headers lack offset information.
rb3-pair
by freeqazGet RB3 file pairing info for a DC3 unit. Shows compatibility score, function overlap, and optionally the RB3 source code. Use to leverage RB3 reference implementations for shared Milo engine code.
rb2-locals
by freeqazGet local variable names, types, and register/stack assignments from RB2 DWARF debug info. Shows parameters, locals (GPR/FPR/stack), and references for functions in the shared Milo engine. Ground truth for variable names/types when starting decomp.
vtable
by freeqazDump vtable layout for a class from original COFF .obj files. Maps each slot to the actual virtual function symbol AND its declaration-order name from the class header, so ICF-merged entries (OnlyReturns / merged_Returns1 / etc.) are still identifiable. Use when debugging vtable offset mismatches in objdiff.
native-build
by freeqazBuild the native port (x86_64 Linux, Clang). Targets include dc3-native, milo-viewer, render-test, milo-tests, milo2gltf. Use when verifying native compilation or running native tests.
data-diff
by freeqazDiff a DATA symbol (vtable ??_7Class@@6B@, RTTI, pointer/jump table, string pool, static initializer) between the target and the decompiled build, showing byte differences and — for each relocation slot — which function/symbol each side points to. Use when a data symbol is below 100%, or to find which vtable slot resolves to the wrong function. The MCP run_objdiff wrapper does not expose data diffs, so this calls objdiff-cli directly.
native-build
by freeqazBuild the native port (x86_64 Linux, Clang). Targets include rb3-native, milo-viewer, render-test, milo-tests. Use when verifying native compilation or running native tests.
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.