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...
jujutsu
by systeminitTrack changes, rebase modifications, resolve conflicts, and manage bookmarks with Jujutsu (jj). Use when committing changes, navigating history, squashing/splitting commits, or pushing to Git remotes.
swamp-troubleshooting
by systeminitDiagnose swamp problems and verify health through a layered diagnostic loop — health checks, error inspection, tracing, and source reading. Do NOT use for smoke testing extensions (swamp-extension) or setting up repos (swamp-repo). Triggers on "swamp error", "failing", "not working", "crash", "timeout", "bug", "debug", "troubleshoot", "root cause", "slow", "performance", "latency", "erroring", "workflow error", "step error", "is swamp working", "health check", "diagnose swamp", "audit log empty", "hooks not firing", "extension not loading", "swamp-warning", "preflight", "doctor audit", "doctor extensions", "internals", "under the hood".
swamp-getting-started
by systeminitInteractive getting-started walkthrough for new swamp users. Guides through understanding the user's goals, creating and running a first model, inspecting output, and choosing next steps. Uses a state-machine checklist with verification at each step. Triggers on "getting started", "get started", "new to swamp", "first time", "tutorial", "walkthrough", "onboarding", "how do I start", "what do I do first", "quickstart", "quick start", "hello world", "first model", "just installed swamp", "show me how swamp works", "intro to swamp", "new user", "set up swamp", "learn swamp".
swamp-report
by systeminitRun, configure, and view reports for swamp models and workflows. Use when running reports via CLI, configuring report selection in definition YAML, viewing report output, or filtering reports by label. Do NOT use for creating report extensions (that is swamp-extension) or debugging report failures (that is swamp-troubleshooting). Triggers on "run report", "swamp report", "model report", "report output", "report label", "skip report", "report results", "cost report", "audit report", "workflow report", "report get", "report filtering".
swamp-repo
by systeminitManage swamp repositories, datastores, extension sources, and the audit integration — initializing repos (single or multi-tool), upgrading swamp, syncing data, releasing stuck locks, loading extensions from external paths, and installing swamp in CI. Do NOT use for diagnosing health check failures or doctor command output (that is swamp-troubleshooting). Triggers on "repo", "repository", "init", "setup swamp", "upgrade swamp", ".swamp folder", "datastore", "datastore sync", "datastore lock", "stuck lock", "install swamp", "CI/CD", "extension source", ".swamp-sources.yaml", "source add", "source rm", "multi-tool repo", "multiple tools", "--tool", "enroll tool", "primary tool", "marker.tools".
issue-lifecycle
by systeminitDrive the @swamp/issue-lifecycle model for interactive issue triage and plan iteration against swamp-club lab issues. Use when the user wants to triage a swamp-club issue, generate an implementation plan, or iterate on a plan with feedback. Triggers on "triage issue", "triage #", "issue plan", "review plan", "iterate plan", "approve plan", "issue lifecycle".
terminal-output
by systeminitTerminal output design system for swamp CLI commands. Use when creating or modifying any CLI command output, render function, or presentation layer code. Ensures consistent formatting, coloring, and structure across all swamp commands in both "log" (human-readable) and "json" (structured) output modes. Triggers on output files in src/presentation/output/, render functions, writeOutput usage, OutputMode handling, or any CLI command that produces terminal output.
swamp-workflow
by systeminitWork with swamp workflows for AI-native automation — define jobs and steps in YAML, wire models together with dependencies, validate DAGs, and inspect run history. Use when searching for workflows, creating new workflows, validating workflow definitions, running workflows, or viewing run history. Triggers on "swamp workflow", "swamp workflow create", "swamp workflow run", "swamp workflow validate", "workflow YAML", "workflow DAG", "wire models together", "model_method step", "workflows/*.yaml", "swamp run history", "swamp workflow logs", "debug swamp workflow". Use ONLY for swamp's declarative YAML workflow artifacts created via swamp workflow create — NOT for the Claude Code Workflow tool, multi-step agent task lists, worktrees, or cron/scheduled agent runs.
swamp-vault
by systeminitManage swamp vaults for secure secret storage — create vault instances, store and retrieve secrets, list keys, and use vault expressions in workflows. Use when working with existing vault types through the CLI. Do NOT use for creating custom vault TypeScript implementations (that is swamp-extension). Triggers on "vault", "secret", "secrets", "swamp vault", "store secret", "get secret", "vault expression", "aws secrets manager", "credential storage", "vault create", "vault put", "vault read-secret", "vault list-keys", "vault migrate", "vault annotate", "vault inspect", "annotation", "annotate secret", "inspect secret".
swamp-issue
by systeminitFetch, edit, search, and submit issues to swamp Lab — view details, edit title/body, search/list issues, file bugs/features/security reports, post ripples (comments) with close/reopen, route to extension publishers. Triggers on "bug report", "feature request", "security report", "report bug", "file bug", "submit bug", "swamp bug", "swamp feature", "feedback", "report issue", "file issue", "extension bug", "ripple", "comment on issue", "close issue", "reopen issue", "get issue", "view issue", "fetch issue", "show issue", "edit issue", "update issue", "change issue title", "search issues", "list issues", "find issue", "issue search".
swamp-extension
by systeminitCreate, test, and develop swamp extensions — models, vaults, drivers, datastores, and reports. Covers Zod schemas, smoke testing, manifest.yaml, and the quality scorecard. Do NOT use for running existing models (swamp-model), using vaults (swamp-vault), workflows (swamp-workflow), debugging (swamp-troubleshooting), or publishing (swamp-extension-publish). Triggers on "create model", "custom model", "extension model", "zod schema", "build integration", "extensions/models", "implement model", "smoke test extension", "test extension", "manifest.yaml", "custom vault", "VaultProvider", "extensions/vaults", "custom driver", "ExecutionDriver", "extensions/drivers", "custom datastore", "DatastoreProvider", "extensions/datastores", "create report extension", "extensions/reports", "quality score", "scorecard", "improve my extension", "extension quality", "rubric", "fast-check", "extension grade", "symbols-docs".
swamp-extension-publish
by systeminitPublish swamp extensions to the registry and manage post-publication lifecycle (deprecation). Enforces a state-machine checklist that verifies repo initialization, authentication, manifest validation, collective ownership, version bumping, formatting, and dry-run before allowing a push. Also covers deprecating and undeprecating published extensions. Do NOT use for creating extensions (that is swamp-extension), improving quality scores (that is swamp-extension), or smoke testing extensions before push (that is swamp-extension). Use when publishing, pushing, releasing, deprecating, or undeprecating extensions. Triggers on "publish extension", "push extension", "extension push", "publish to registry", "swamp extension push", "release extension", "prepare for publishing", "extension-publish", "deprecate extension", "undeprecate extension", "mark extension deprecated", "remove deprecation", "extension deprecated", "superseded by".
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.