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...
marmot
by 941designMarmot Protocol implementation advisor — MDK (Rust), marmot-ts (TypeScript), and the wn CLI/daemon. Authoritative source for MDK API shape, MIP specifications, MLS-on-Nostr behavior, and WhiteNoise architecture. TRIGGER when: about to reference MDK / marmot-ts / wn APIs in code, comments, specs, proposals, PR descriptions, or documentation; about to claim a method exists or has a given signature; uncertain or guessing about an MDK / marmot-ts / wn API shape or an MIP / MLS-on-Nostr behavior; user mentions Marmot, MDK, MLS-on-Nostr, WhiteNoise, or wn; about to write or modify a file that imports `mdk-core`, `marmot-ts`, or wn bindings. Fire even if the user did not explicitly ask an MDK-specific question — agent self-detected uncertainty about an in-domain API alone is a sufficient trigger. SKIP when: plain Nostr work with no MLS / no group encryption — use nostr-skills:nostr instead; rmcp / JSON-RPC transport plumbing that does not touch group state; pure SQLite / storage work with no protocol-level concern
cross-environment
by 941designDiagnose and resolve issues when a single project tree is developed from two architectures at once (e.g. macOS host + Linux VM/container sharing a mounted directory). Covers native node_modules bindings, Playwright browser caches, and Claude Code session environment variables. Trigger on cross-platform install errors ("Cannot find module @next/swc-...", "Cannot find module @rollup/rollup-..."), Playwright "Executable doesn't exist at chrome-headless-shell-..." errors, ENOENT errors against CLAUDE_PLUGIN_DATA, questions about platform stamps in Makefiles, PLAYWRIGHT_BROWSERS_PATH, and any "after switching from mac to linux..." troubleshooting.
backlog
by 941designOwns `BACKLOG.json` — the project-level coordination file consumed by `/base:orient`, `/base:next`, `base:project-curator`, `/base:feature`, and `/base:bug`. Single authority for the file's format (`plugins/base/schemas/backlog.schema.json`) and the canonical write path (`scripts/`). Operations: `init` (scaffold + `CLAUDE.md` pointer + one-shot epic seeding), `add-finding`, `add-archive`, `mark-archive-adr`, `resolve <slug>`, `defer-stamp <slug>`, `add-epic`, `list`, `get`, `pick-next`, `render`, `query`, `migrate-v3` (one-shot v2-MD → v3-JSON conversion). Use when the user wants to bootstrap a backlog, append a finding outside a `/feature` or `/bug` run, close a finding inter-run, query backlog state, or migrate a legacy v2 BACKLOG.md. **All BACKLOG.json mutations from `/base:feature`, `/base:bug`, `/base:next`, `/base:triage`, `base:project-curator`, `triage` agent, `/base:orient`, and `/base:next-epic` MUST go through this skill via the `Skill` tool — direct shell-outs to the underlying scripts are a contr
agent-memory
by 941designExpert knowledge on AI agent memory systems, architectures, and implementations. Covers episodic/semantic/procedural/causal memory, RAG, vector stores, embeddings, context window management, knowledge graphs, memory persistence, multi-agent memory patterns, self-improvement memory (Evolver), and implementations in MemGPT/Letta, LangChain, CrewAI, Mem0, Zep, Cognee, and more. Use when designing, comparing, or debugging agent memory systems.
agent-design
by 941designExpert knowledge on AI agent design patterns — architecture, multi-agent coordination, tool use, prompt engineering, evaluation, safety, observability, and deployment. Covers router, supervisor, blackboard patterns, MCP, agent evaluation benchmarks, guardrails, observability platforms, and implementations across Claude Code, LangGraph, CrewAI, AutoGen, Semantic Kernel, and more. Use when designing, evaluating, or architecting agent systems.
metrics
by 941designWorkflow metrics aggregation. Reads per-epic artifacts, writes per-epic metrics.json. Mirrors base:backlog/base:retros/base:learnings layout.
mutation-audits
by 941designOwns `${CLAUDE_PLUGIN_DATA}/mutation-audits/<consumer-slug>/audits.json` — the durable, per-module record of mutation-testing runs produced by `base:mutation-testing` and consumed by `base:next-mutation`, `/base:orient`, and the AC-linkage step of `base:property-based-testing`. Single authority for the file format (`plugins/base/schemas/mutation-audit.schema.json`) and the canonical write path (`scripts/`). Operations: `add-audit`, `get`, `list`, `query`. Sibling concern to `base:learnings` (technical knowledge) and `base:metrics` (per-epic workflow rollups); mutation audits are per-module diagnostic state used to phase coverage toward the full project and to derive spec-gap findings from unspecced behavior.
next-mutation
by 941designPick the next module to audit with `base:mutation-testing` and dispatch it. Walks `${CLAUDE_PLUGIN_DATA}/mutation-audits/<consumer-slug>/audits.json` plus git as ground truth and ranks candidates by three signals — changed since last audit, dependency-affected (lockfile changed since the audit captured its fingerprint), and stale (audit older than N days). Reached as a sub-mode of `/base:next` via `/base:next mutation [<hint>] [auto]`, or invoked directly as `/base:next-mutation [<hint>] [auto]`. Always auto-dispatches the top candidate without confirmation; detail mode renders top-3 rationale first, auto mode prints a single notice line.
nostr-update
by 941designMaintenance skill that refreshes the nak CLI knowledge base by fetching the latest README, release notes, and command documentation from the nak repository. Updates agent memory with new findings and timestamps.
playwright-update
by 941designMaintenance skill that refreshes the Playwright browser automation knowledge base by fetching the latest Playwright MCP documentation, changelog, and best practices. Updates agent memory with new findings and timestamps.
reference
by 941designReference project knowledge advisor. Answers questions about tracked GitHub repos — their architecture, API surfaces, implementation patterns, and evolution. Draws on accumulated per-project knowledge and cross-project insights. Invoke for questions about reference projects, pattern comparisons, or API lookups across tracked repos.
nostr-sdks
by 941designCross-language Nostr SDK selection and usage advisor. Helps pick the right library for the user's language and platform across nostr-tools (TS), NDK, rust-nostr, fiatjaf.com/nostr (Go), nostr-java, nostr4j, nostr-sdk-jvm, nostr-sdk-ios (native Swift), nostr-sdk-swift (UniFFI), pynostr, and more. Covers event publishing, subscriptions, NIP support, project status, cross-SDK interop, and bindings vs native trade-offs. Invoke when the user is choosing or learning a Nostr SDK in any language beyond pure NIP-46 signing (use the remote-signing skill for that).
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.