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...
ms-office-graph-python
by joogy06Use when calling Microsoft Graph from Python for mail (Outlook), calendar, contacts, Teams chat / channels / meetings, SharePoint sites / lists / documents, OneDrive files, or Microsoft 365 user / group administration. Libraries — msgraph-sdk (primary, Microsoft-blessed, Kiota-generated), O365 (community wrapper, friendlier API), exchangelib (on-prem Exchange Server only — EWS retires for Exchange Online per Microsoft's announced schedule, disabled-by-default 2026-10-01 with permanent shutdown 2027-04-01; verify before relying), extract-msg / libpff-python (offline .msg / .pst parsing), botbuilder-* (full Teams bots), adaptive-cards-py (Adaptive Cards 1.5+). Covers delegated vs application permissions, RSC, throttling, paging, change-tracking, webhook validation. Part of the ms-office-python-* skill family.
ibm-mainframe
by joogy06Use when working with IBM z/OS mainframe systems — JCL (Job Control Language) syntax and patterns, dataset types (sequential/PDS/PDSE/VSAM), IDCAMS utility, DFSORT/ICETOOL, ISPF navigation, TSO/REXX scripting, system utilities (IEBCOPY/IEBGENER/IEFBR14), RACF security basics, GDG (Generation Data Groups), SMS (Storage Management Subsystem), and z/OS fundamentals. Part of the ibm-mainframe skill family.
ibm-mq
by joogy06Use when installing, configuring, or managing IBM MQ on RHEL 9 — queue manager creation and administration, queues (local/remote/alias/model), channels (sender/receiver/server-conn/client-conn), listeners, triggers, clustering, publish/subscribe, MQ security (TLS, channel auth rules, OAM), dead-letter queue handling, MQ Explorer, runmqsc commands, MQ developer patterns (JMS, MQI, Python/pymqi, .NET), performance tuning, systemd services, SELinux contexts, and firewalld rules. Part of the ibm-* skill family.
ibm-websphere
by joogy06Use when installing, configuring, or managing IBM WebSphere Application Server on RHEL 9 — WAS traditional (8.5.5/9.0) profiles and deployment, WebSphere Liberty/Open Liberty configuration and development, application deployment (WAR/EAR), security (SSL/TLS, LTPA, LDAP/AD integration, SAML/OIDC), JVM tuning (heap, GC policies), clustering and ND topology, JDBC data sources, JMS/MQ integration, wsadmin scripting (Jython), systemd services, SELinux contexts, and firewalld rules. Part of the ibm-* skill family.
ms-office-word-python
by joogy06Use when reading, writing, transforming, or converting Word documents from Python — .docx (python-docx, docx2txt, mammoth, pypandoc), .docm (macro-enabled — handled with explicit user intent), .doc legacy (LibreOffice headless or antiword), or generating PDF (docx2pdf on Windows/macOS, LibreOffice headless on Linux, pypandoc + xelatex/wkhtmltopdf). Covers OOXML XXE defence, full-fidelity caveats (python-docx is NOT a 100% renderer), and macro handling. Part of the ms-office-python-* skill family.
datastage-developer
by joogy06Use when developing or administering IBM DataStage — parallel job design, server job patterns, stage types (Transformer/Join/Lookup/Aggregator/Sort/Funnel/Merge), connectors (DB2/Oracle/ODBC/Sequential File/Complex Flat File), parallel framework configuration, job sequencing, performance tuning, scheduling, DataStage on Cloud Pak for Data, and migration from legacy versions. Part of the data-* skill family.
legacy-code-intel
by joogy06Use when you want a PERSISTENT, queryable, SCIP-inspired code-intelligence library over legacy artifacts — COBOL, DataStage .dsx (XML), ETL scripts (shell/SQL/Python), and Pick/MultiValue BASIC (UniVerse/UniData/D3/jBASE/OpenQM) — built ONCE into a content-addressed store and exposed via a deterministic graph-query layer + a self-contained HTML navigator. An LLM-as-parser framework (mirrors lineage-extract-static): model-neutral prompts the in-session AI CLI uses to extract symbols/occurrences/relationships, NOT per-format AST parsers. Triggerable as a single skill (ingest one artifact/dir) and via agent-teams (batch, one worker per artifact — NO new agent). Static analysis only (v1). Also trigger on "index this COBOL", "symbol graph for DataStage jobs", "where is this paragraph called", "impact of changing this copybook", "index this Pick/MultiValue BASIC", "code intelligence for legacy", "build a navigator for this mainframe code".
antigravity-cli
by joogy06Use when delegating to or working with the Antigravity CLI (`agy`) — headless single-prompt orchestration (`agy -p`), interactive/resume modes, plugins, sandbox, and auth. `agy` is this host's PRIMARY second-opinion / challenger / research delegate; the gemini CLI (v0.45.0) remains an available fallback until Google retires the gemini CLI on 2026-06-18. Covers Antigravity CLI 1.0.5 (verified locally 2026-06-05 from `agy --help`).
db2-rhel
by joogy06Use when installing, configuring, or managing IBM DB2 LUW on RHEL 9 (and AlmaLinux/Rocky 9) — instance creation, database administration, buffer pool and tablespace management, backup/restore with HADR, performance tuning (db2advis, db2pd, MON functions), runstats/reorg, SELinux contexts, firewalld rules, and DB2 pureScale. Part of the db2-* skill family.
rhel-databases
by joogy06Use when installing, configuring, or managing databases on RHEL 9 (and AlmaLinux/Rocky 9) — PostgreSQL 15/16 via module streams, MySQL 8/MariaDB 10.11, Redis 7, performance tuning, backup/restore, replication, connection pooling, user/role management, SELinux contexts, and firewalld rules. Part of the rhel-* skill family.
ansible
by joogy06Use when automating infrastructure with Ansible — playbook development (tasks, handlers, variables, templates, conditionals, loops), role design (Galaxy structure, defaults, dependencies), inventory management (static/dynamic, groups, host_vars/group_vars), collections (ansible.builtin, community, custom), Ansible Vault (encryption), AWX/Ansible Automation Platform (job templates, workflows, RBAC, surveys), module development, testing (Molecule, ansible-lint), and performance tuning (forks, pipelining, async). Part of the automation-* skill family.
python-enterprise-connectors
by joogy06Use when connecting Python to enterprise databases (DB2, Oracle, SQL Server, Teradata), mainframe systems (z/OS, CICS, IMS, MQ), or building custom database connectors. Covers ibm_db, Zowe SDK, pyodbc, python-oracledb, EBCDIC handling, credential management, and connection security.
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.