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...
mongez-supportive-is-environment
by hassanzohdyDocuments the browser and device-environment predicates — `isMobile`, `isMac`, `isDesktop`, `isBrowser`, `isChrome`, `isFirefox`, `isSafari`, `isOpera`, `isIE`, and `isEdge` — including SSR safety rules and known bugs. TRIGGER when: code imports `isMobile`, `isMac`, `isDesktop`, `isBrowser`, `isChrome`, `isFirefox`, `isSafari`, `isOpera`, `isIE`, or `isEdge` from `@mongez/supportive-is`; user asks "how do I detect mobile / iOS / Android", "Cmd vs Ctrl on Mac", "browser sniff for Safari/Chrome/Firefox", or "is this code running in browser vs SSR"; typical import is `import { isMobile, isMac } from "@mongez/supportive-is"` (or `Is.mobile.android()` via the legacy default export — note this package commonly exposes methods through the `Is` object too). SKIP: server-side user-agent parsing from request headers — use a dedicated UA parser library on `request.headers.get("user-agent")`; React-Native or Capacitor device-info APIs; CSS media queries for responsive layout; feature-detection beyond what these vendor pr
mongez-react-router-lazy-loading
by hassanzohdyCode-splitting via apps and modules, module manifests, loader wiring, loading UI, and chunk-error recovery in @mongez/react-router. TRIGGER when: code calls `setApps`, configures `lazyLoading` (`loaders.app` / `loaders.module`, `loadingComponent`, `renderOverPage`, `chunkErrorHandler`) via `setRouterConfigurations`, references `App`, `PublicApp`, `Module`, `Loaders`, `LazyLoadingOptions`, `LazyLoadingProps`, `ChunkErrorHandler`, or `ChunkErrorStrategy`, writes a `*-modules.json` manifest, or listens to `routerEvents.onChunkLoadError`; user asks "how do I lazy-load modules", "configure app/module loaders", "show a loading spinner over the previous page", "recover from chunk-load errors after a deploy". SKIP: this is @mongez's router, distinct from upstream `react-router-dom` — skip when the file uses bare `React.lazy` + `<Suspense>` without `@mongez/react-router` apps/modules, or `react-router`'s `loader`/`lazy` route options; registering individual routes — use `mongez-react-router-routes`; per-route `suspens
mongez-collection-sort-group
by hassanzohdyHow to sort, group, partition, deduplicate, and reorder items in an `ImmutableCollection` — `sort`, `sortBy`, `sortByDesc`, `groupBy`, `partition`, `unique`, `uniqueList`, `swap`, `move`, `reorder`, `reverse`, `flip`. Covers stability, multi-key `sortBy({...})`, the `unique` vs `uniqueList` shape difference, and which sort variants mutate. TRIGGER when: code calls `c.sort`, `c.sortBy`, `c.sortByDesc`, `c.groupBy`, `c.partition`, `c.unique`, `c.uniqueList`, `c.swap`, `c.move`, `c.reorder`, `c.reverse`, or `c.flip` on an `ImmutableCollection`; user asks "how do I sort by a field / multiple keys", "ascending vs descending", "how to group by role / category", "how to split active vs inactive", "how to dedupe by email", "how to swap two positions / reorder a list". SKIP: mutation safety details for `sort` / `reverse` / `sortByDesc` — use `mongez-collection-mutation` for the in-depth matrix; column projection after grouping — see `mongez-collection-transforming` for `pluck` / `select`; standalone `groupBy` / `uniqu
mongez-collection-mutation
by hassanzohdyDefinitive matrix of which `ImmutableCollection` methods mutate in place — `sort`, `reverse` / `flip`, `sortByDesc`, `shift`, `pop` — versus which return a new collection. Covers `clone` / `copy` workarounds and the `toArray()` / `all()` live-reference hazard. TRIGGER when: code calls `c.sort`, `c.reverse`, `c.flip`, `c.sortByDesc`, `c.shift`, `c.pop`, `c.clone`, or `c.copy` on an `ImmutableCollection`; user asks "is sort/reverse/shift/pop safe", "why is my original collection changing", "do I need to clone before sorting", "which methods mutate in @mongez/collection", "is toArray a copy"; debugging an unexpected mutation bug on a shared collection. SKIP: non-mutating sort by key (`sortBy(key)` and `sortBy({...})`) — use `mongez-collection-sort-group`; insert / remove / replace operations that always return new — use `mongez-collection-overview` for the global picture; understanding what `@mongez/reinforcements` does on its own — that package has no wrapper to mutate.
mongez-collection-pagination
by hassanzohdyHow to paginate, chunk, skip, and take items from an `ImmutableCollection` — `take`, `limit`, `takeLast`, `takeUntil`, `takeWhile`, `skip`, `skipTo`, `skipLast`, `skipUntil`, `skipLastUntil`, `skipLastWhile`, `skipWhile`, `slice`, `splice`, `chunk`, `random`, `shuffle` — plus the `(page-1)*perPage` recipe and the fact that there's no built-in `paginate` with totals. TRIGGER when: code calls `c.take`, `c.limit`, `c.takeLast`, `c.takeUntil`, `c.takeWhile`, `c.skip`, `c.skipTo`, `c.skipLast`, `c.skipUntil`, `c.skipLastUntil`, `c.skipLastWhile`, `c.skipWhile`, `c.slice`, `c.splice`, `c.chunk`, `c.random`, or `c.shuffle` on an `ImmutableCollection`; user asks "how do I paginate a collection", "how to take the first N / last N / page N", "how to batch into chunks of 100", "how to grab a random sample / shuffle". SKIP: page metadata (total / hasNext / totalPages) — not built-in, manually compute from `.length`; chunk a plain array without a wrapper — use `chunk` from `mongez-reinforcements-arrays`; sorting before pa
mongez-collection-math-aggregation
by hassanzohdyTutorial-style "when to use which math method" guide for `@mongez/collection` — totaling, averaging, finding min/max/median, counting by predicate or by key, applying per-item arithmetic (`plus`/`minus`/`multiply`/`divide`/`modulus`/`increment`/`decrement`/`double`/`half`), parity filters (`even`/`odd`/`evenIndexes`/`oddIndexes`). TRIGGER when: user asks "how do I total / aggregate / sum up / average a field across items", "how to apply a markup / discount to every item", "how to count items matching a condition", "what's the difference between count / countValue / countBy"; user explores math methods without a specific method name in mind; code shapes look like aggregating monetary or analytic fields with `collect(...)`. SKIP: lookup-style "what does method X do" — use `mongez-collection-math` for the exact reference; one-shot aggregation without a chain — use `mongez-reinforcements-arrays`' standalone `sum`/`average`/`min`/`max`/`median`/`count`/`countBy` instead; filtering or sorting downstream of math — s
mongez-vite-recipes
by hassanzohdyReady-to-use vite.config.ts compositions for common @mongez/vite scenarios including minimal SPA setup, CDN base URL, Apache deploy with prerender, multi-stage builds, and more. TRIGGER when: user wants a working starting-point `vite.config.ts` / `vite.config.js` that composes `mongezVite()` with multiple options (`htaccess`, `preRender`, `productionEnvName`, `envBaseUrlKey`, `compressedFileName`, `htmlEnvPrefix`/`htmlEnvSuffix`, `linkTsconfigPaths`); user asks "give me a `vite.config.ts` example for @mongez/vite", "how do I set up multi-stage builds with mongezVite", "show me an Apache deploy pipeline with mongezVite + prerender + zip". SKIP: single-feature deep dives — route to the matching feature skill instead (`mongez-vite-env-loading`, `mongez-vite-env-in-html`, `mongez-vite-production-base-url`, `mongez-vite-build-zip`, `mongez-vite-htaccess`, `mongez-vite-prerender`, `mongez-vite-tsconfig-aliases`, `mongez-vite-auto-open-browser`); first-time orientation (use `mongez-vite-overview`); generic Vite conf
mongez-reinforcements-random
by hassanzohdyRandom value generation via the Random namespace class from @mongez/reinforcements — integers, floats, booleans, strings, UUIDs, nanoids, dates, colors, weighted picks, and seedable deterministic mode.
mongez-reinforcements-arrays
by hassanzohdy@mongez/reinforcements array helpers — chunking, ranges, unique/dedupe, pluck, groupBy, countBy, stats (sum/avg/median/min/max), even/odd parity filters, and mutating pushUnique/unshiftUnique. One function per section: description, signature, example.
mongez-reinforcements-async
by hassanzohdyAsync/Promise utilities from @mongez/reinforcements — sleep, retry with backoff, timeout racing, pProps/pAll/pMap/pSeries/pFilter for concurrent work, defer, and debounceAsync.
mongez-reinforcements-functions
by hassanzohdyFunction utilities from @mongez/reinforcements — debounce, throttle, memoize, once/after/before call-count gating, pipe/compose composition, curry/partial application, and FP primitives.
mongez-reinforcements-numbers
by hassanzohdyNumber utilities from @mongez/reinforcements — rounding, clamping, range helpers, safe arithmetic (safeDivide, percentage, parseNumber), and formatting (formatBytes, formatNumber).
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.