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...
legacy-ibmi-flow-analyzer
by wwa-labAnalyze a complete IBM i call chain — one business transaction end-to-end across all programs it touches. Supports seven trigger models (batch job, interactive menu, subfile dispatch, F-key branch, DB trigger, scheduler, API/remote). Produces a flow analysis covering trigger context, sequence, cross-program data flow, error propagation, commit boundaries, UI surfaces, and business-capability seeds. Use when a single program analysis is insufficient because the business event spans multiple programs. Layer 1.5 (platform-specific) skill of the Legacy Spec Factory reverse chain.
legacy-ibmi-inventory
by wwa-labInventory IBM i / AS400 legacy assets for modernization. Use when collecting or reviewing RPGLE, CLLE, COBOL, DDS, DB2 for i, jobs, screens, reports, spool, and runtime evidence before generating an evidence-backed spec. Layer 1 (platform-specific) skill of the Legacy Spec Factory reverse chain.
legacy-ibmi-module-analyzer
by wwa-labAssemble and validate an IBM i business module from approved flow analyses or a ready module-first context package, producing the evidence-backed module overview plus Program Flow and Data Flow artifacts. Operation Flow and System Flow are no longer default outputs because they require stronger SME or architecture evidence than most code-backed runs provide. Use when multiple flows belong to the same business module, or when `legacy-module-context-intake` has normalized external RAG / human context and you need evidence-bounded module assembly before BRD writing and review. Layer 1.5 (platform-specific) skill. Implements the model defined in `docs/module-analysis-model.md`.
legacy-ibmi-program-analyzer
by wwa-labAnalyze individual IBM i programs (RPGLE, CLLE, COBOL) to extract control flow, file I/O, external calls, and error handling with evidence backing. Use when diving deep into one program's behavior from an approved inventory, or in standalone exploratory mode when the user only wants to inspect a skill output before BRD/spec chain readiness. Layer 1 (platform-specific) skill of the Legacy Spec Factory reverse chain.
legacy-ibmi-runtime-evidence-miner
by wwa-labExtract structured `observed_in_runtime` evidence from approved IBM i job logs and spool/report files into `runtime-evidence.jsonl`. Use after `legacy-ibmi-evidence-intake` has approved the evidence manifest and `legacy-ibmi-inventory` can map runtime artifacts to `OBJ-*` IDs. Blocks on missing approval, unredacted confidential evidence, or missing inventory mappings; never infers business rules or modernization decisions from runtime logs.
legacy-ibmi-screen-report-analyzer
by wwa-labAnalyze IBM i DSPF, PRTF, menus, subfiles, function keys, indicators, screen samples, spool/report samples, and presentation-layer behavior with evidence backing. Use when screen/report artifacts need structured analysis before or alongside program/flow analysis. Layer 1 (platform-specific) skill of the Legacy Spec Factory reverse chain.
legacy-ibmi-batch-digest
by wwa-labAggregate every per-program analysis under one module into a single SME-friendly batch digest table (`programs-batch-digest.md`). Reduces SME review friction for medium/large modules — a 50-program module turns from 50 files to one scannable page grouped by criticality (critical / standard / low_risk), with one-line roles, key pending decisions, TBD counts, and links to detail. Trigger when the user says "give me the SME-facing program review", "我要给 SME 看程序清单", "batch review the programs in this module", or after a batch of new program-analysis.md files lands. Supplemental skill — does not advance the linear stage_id; co-exists with `legacy-ibmi-program-analyzer` (which produces the detail) and `legacy-sme-review-facilitator` (which builds the active decision queue).
legacy-ibmi-data-model-analyzer
by wwa-labAnalyze IBM i data models from DDS physical/logical files, DB2 for i metadata, SQL DDL, approved inventory, and program/flow evidence to produce an evidence-backed data model package with dictionary, access paths, CRUD matrix, and SME review checklist. Use when reverse-engineering a business domain's data structure to support modernization. Layer 1.5 (platform-specific) skill of the Legacy Spec Factory reverse chain.
legacy-ibmi-evidence-intake
by wwa-labRegister, classify, assign evidence IDs, and record source-path authorization or redaction governance for IBM i modernization evidence. Use when preparing source code, DB metadata, job logs, spool files, screen samples, reports, transactions, or runtime evidence before inventory analysis. This skill records intake metadata, source paths, internal review decisions, and redaction approvals when required. Precedes legacy-ibmi-inventory.
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.