mcpField

Skills

96,981 packaged capabilities and playbooks for agents. Install any of them with one command.

Development

I
injective-evm-developer
injective-evm-developer
injectivelabs / agent-skills

Develop EVM smart contracts and dApps on Injective

Development41
I
injective-mcp-servers
injective-mcp-servers
injectivelabs / agent-skills

Set up and run Injective MCP servers. Needed by multiple Injective skills which perform MCP tool calls.

Development41
I
inkblot-branch-naming
inkblot-branch-naming
inkblot-therapy / ai-skills

Inkblot git branch naming convention. Use when creating a branch, checking out a feature/bugfix branch, naming a PR branch, or when the user asks to start work on a Jira ticket.

Development41
I
inngest-local
inngest-local
joelhooks / joelclaw

Set up self-hosted Inngest on macOS as a durable background task manager for AI agents. Interactive Q&A to match intent — from Docker one-liner to full k8s deployment with persistent state. Use when: 'set up inngest', 'background tasks', 'durable workflows', 'self-host inngest', 'event-driven functions', 'cron jobs', or any request for a local workflow engine.

Cloud & DevOps41
I
integrate-payroc-cloud
integrate-payroc-cloud
payroc / skills

Guides developers through running in-person, card-present sales and refunds through Payroc Cloud—the semi-integrated cloud-to-device API where a POS sends an instruction to the Payroc gateway and the gateway relays it to a physical payment device. Use this skill whenever the user mentions Payroc Cloud, “pay by cloud”, semi-integrated card-present payments, sending a sale/refund/signature to a terminal or card reader via the API, payment-instructions / refund-instructions / signature-instructions, polling an instruction, cloud device payments—even if they don't say “skill” explicitly. Covers the async submit → poll → follow-link → retrieve flow, idempotency, cancelling an in-progress instruction, referenced vs unreferenced refunds, reversals, signature capture, closed-loop reads, and finding a device serialNumber via GET /devices. Do NOT use this skill for card-not-present / e-commerce flows, for Hosted Fields, Hosted Payment Pages, or Payment Links (browser-based—separate skills), or for physically configuring or pairing a payment device (that is hardware setup, out of scope). If the user wants to set up or pair a device, say that is out of scope and that this skill picks up once a device serial number exists.

Development41
I
Internationalizing Websites
Internationalizing Websites
mavscui / agent-skills-hunter

Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.

Development41
I
Internationalizing Websites
Internationalizing Websites
zhanlincui / agent-skills-hunter

Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content. Use when adding new languages, setting up i18n, optimizing for international SEO, or when user mentions localization, translation, multi-language, or specific languages like Japanese, Korean, Chinese.

Development41
I
interop-promise
interop-promise
openharmonyinsight / openharmony-skills

ETS-JavaScript interop Promise bridging system in ArkCompiler. Use this skill when working on cross-language Promise conversion between ETS (ArkTS) and JavaScript, including JSConvertPromise Wrap/Unwrap, EtsPromise proxy creation, EtsPromiseRef bridging, CreatePromiseLink, OnJsPromiseCompleted callbacks, connectPromise, SettleJsPromise, PromiseInteropResolve/Reject, EtsAwaitPromise/AwaitProxyPromise, callback queue management, or any code under js_convert.h (Promise section), js_job_queue, ets_promise, ets_promise_ref, std_core_Promise.cpp, or PromiseInterop.ets. Also use when debugging cross-VM Promise state synchronization, coroutine suspension/resumption during await, or napi_deferred lifecycle issues.

Development41
I
intlayer-cli
intlayer-cli
aymericzip / intlayer-skills

Manages Intlayer dictionaries and configuration via the Command Line Interface. Use when the user asks to "audit translations", "build dictionaries", "sync content", or run "intlayer" commands.

Development41
I
ios
ios
alphaonedev / openclaw-graph

iOS root: SDK, app lifecycle scene-based, permissions NSUsageDescription, HIG guidelines

Development41
I
ios-swift
ios-swift
full-stack-skills / mobile-native-skills

Provides comprehensive guidance for iOS development with Swift including view controllers, views, navigation, lifecycle, and iOS app development. Use when the user asks about iOS Swift, needs to create iOS applications, implement iOS components, or work with Swift in iOS.

Development41
I
issue-flow
issue-flow
notedit / happy-skills

AI-Native Issue-Driven development workflow. From GitHub Issue to merged PR: parse issue, explore codebase, design technical plan, execute with agent team, create PR, and cleanup. Use when a user wants to implement a GitHub Issue end-to-end: `/issue-flow #123` or `/issue-flow` to pick from open issues.

Development41
J
java-springboot
java-springboot
vekzz-dev / opencode-skills

Comprehensive best practices for developing high-quality Spring Boot applications with production-ready patterns. Trigger: When developing Spring Boot applications, need best practices, or working with Spring framework.

Development41
J
javascript
javascript
htlin222 / dotfiles

Write modern JavaScript with ES6+, async patterns, and Node.js. Use for JS development, async debugging, or optimization.

Development41
J
javascript-sdk
javascript-sdk
qu-skills / superpowers

JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate with all models. Package: @inferencesh/sdk (npm install). Full TypeScript support, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, human approval. Use for: JavaScript integration, TypeScript, Node.js, React, Next.js, frontend apps. Triggers: javascript sdk, typescript sdk, npm install, node.js api, js client, react ai, next.js ai, frontend sdk, @inferencesh/sdk, typescript agent, browser sdk, js integration

Development41
K
kita-html

Write and edit `.tsx` or `.jsx` for Kita Html instead of React. Use this whenever the user mentions Kita, KitaJS, `@kitajs/html`, `safe` attributes, `kita-html check`, `xss-scan`, `reply.html()`, `res.html()`, Suspense `rid`, async components that return HTML strings, or asks for JSX in a server-rendered templating context where JSX compiles to strings rather than a virtual DOM. Also use it when the project contains Kita config such as `jsxImportSource: "@kitajs/html"`, `@kitajs/html-cli` or `@kitajs/ts-html-plugin`, even if the user only says "TSX" or "JSX".

Development41
K
kotlin-idiomatic-refactorer-spring-aware
kotlin-idiomatic-refactorer-spring-aware
jetbrains / skills

Refactor Kotlin code toward clearer, more idiomatic design without breaking Spring behavior, serialization, persistence, or public contracts. Use when Java-flavored Kotlin needs cleanup, domain modeling should become more expressive, or boilerplate should be reduced, but the refactoring must remain safe for proxies, Jackson, JPA, configuration binding, and existing tests

Development41
L
langchain
langchain
alphaonedev / openclaw-graph

Framework for building applications with large language models and chains.

Development41
L
laravel-actions
laravel-actions
leeovery / claude-laravel

Action-oriented architecture for Laravel. Invokable classes that contain domain logic. Use when working with business logic, domain operations, or when user mentions actions, invokable classes, or needs to organize domain logic outside controllers.

Development41
L
laravel-controllers
laravel-controllers
leeovery / claude-laravel

Thin HTTP layer controllers. Controllers contain zero domain logic, only HTTP concerns. Use when working with controllers, HTTP layer, web vs API patterns, or when user mentions controllers, routes, HTTP responses.

Development41
L
learn
learn
fancyboi999 / ai-engineering-from-scratch-zh

An interactive course tutor for the AI Engineering from Scratch course. Reads LEARNING.md, finds the next lesson, teaches it section by section in the terminal, then quizzes you and records progress. Works in a cloned repository or entirely through raw.githubusercontent.com — no setup required. Trigger phrases: “下一课”, “教我”, “继续课程”, “我们来学习”, “继续学习”, or “next lesson”, “teach me”, “continue the course”, “let's learn”, “resume learning”.

Development41
L
linear-batch-close
linear-batch-close
lkshrk / linear-ai

Batch-orchestrate Linear closeout: find llm-review issues, confirm the queue and bounded parallelism, and dispatch linear-close subagents while closeout mutations stay with linear-close.

Agent workflows41
L
linear-batch-implement
linear-batch-implement
lkshrk / linear-ai

Batch-orchestrate ready Linear implementation work: find llm-ready issues with newest valid ready plans, confirm the queue and parallelism, and dispatch isolated linear-implement subagents.

Agent workflows41
L
linear-batch-refine
linear-batch-refine
lkshrk / linear-ai

Batch-orchestrate Linear refinement: find llm-refine and llm-blocked issues, show the queue, process one issue at a time with linear-refine subagents, and aggregate questions and feedback.

Agent workflows41
L
linear-deliver-feature
linear-deliver-feature
lkshrk / linear-ai

Run the full Linear AI workflow for one feature or bug: create issue, refine plan, implement work, verify, prepare review handoff, and close after merge. Use when the user wants one feature delivered through all Linear AI steps end to end.

Agent workflows41
L
linear-status
linear-status
lkshrk / linear-ai

Inspect a Linear issue and report the current workflow phase, missing evidence, state inconsistencies, and recommended next skill. Use when the user asks what is next, where the issue stands, whether work can resume, or why labels/comments disagree.

Agent workflows41
L
litestar-logging
litestar-logging
alti3 / litestar-skills

Configure Litestar logging with `LoggingConfig`, `queue_listener`, exception logging policy, selective stack-trace suppression, standard logging, picologging, Structlog, and custom logging config subclasses. Use when establishing or refactoring application logging behavior, request-level logs, or production-safe error logging in Litestar. Do not use for metrics/tracing instrumentation or exception-response contract design.

Development41
L
livekit-skills
livekit-skills
fcakyon / claude-codex-settings

Build voice AI agents with LiveKit Agents SDK. Use when the user asks to "build a voice agent", "create a LiveKit agent", "add voice AI", "implement handoffs", "structure agent workflows", or is working with LiveKit Agents SDK. Covers both LiveKit Cloud and self-hosted deployments using lk CLI.

Agent workflows41
L
local-server
local-server
aiagentwithdhruv / skills

Run Claude orchestrator locally with Cloudflare tunneling. Use when user asks to run locally, start local server, or test webhooks locally.

Cloud & DevOps41
L
local-wp-cli
local-wp-cli
aslamdoctor / local-wp-cli

Run WP-CLI commands against any Local by Flywheel site. Use when the user says 'wp-cli', 'run wp', 'use wp-cli', 'activate plugin', 'deactivate plugin', 'flush cache', 'wp option', 'wp transient', 'wp db', 'wp eval', 'wp cron', 'wp rewrite', or any request involving WordPress CLI commands.

Development41
L
log-analysis
log-analysis
naodeng / awesome-qa-skills

Use this skill when you need to analyze logs into evidence, timelines, anomalies, and follow-up hypotheses; triggers include log analysis.

Development41
L
lovrabet
lovrabet
lovrabet / lovrabet-skill

Use when a user request involves development capabilities of the Lovrabet/云兔/yuntoo platform. Trigger words: 数据集, 数据表, 自定义 SQL, filter, sql.execute, bff.execute, @lovrabet/sdk, MCP SQL 工作流, 多表关联, lovrabet 开发.

Data & databases41
M
m365-agents-dotnet
m365-agents-dotnet
sickn33 / agentic-awesome-skills

Microsoft 365 Agents SDK for .NET. Build multichannel agents for Teams/M365/Copilot Studio with ASP.NET Core hosting, AgentApplication routing, and MSAL-based auth.

Agent workflows41
M
makefile-update
makefile-update
hiromaily / go-crypto-wallet

Makefile development workflow. Use when modifying Makefile or files in make/ directory.

Development41
M
matlab-generate-code
matlab-generate-code
matlab / matlab-agentic-toolkit

Generate, verify, refine, and accelerate C/C++ or CUDA code from MATLAB with MATLAB Coder, Embedded Coder, GPU Coder, or MATLAB Test. Also covers writing codegen-ready MATLAB code: language constraints, coder.* directives, and optimization patterns. Triggers on: codegen, MEX, deploy MATLAB as C/C++, GPU Coder, coder.screener, coder.config, coder.gpuConfig, coder.typeof, coder.runTest, matlabtest.coder.TestCase, SIL, embedded config, no dynamic memory, EnableMexProfiling, coder.timeit, coder.perfCompare, %#codegen, writing codegen-ready MATLAB, code generation readiness, coder.varsize, coder.unroll, coder.noImplicitExpansionInFunction, coder.ceval, coder.inline, coder.extrinsic, coder.const, coder.classSignature, class codegen limitations, temporal types codegen, DMA-off, stack-only, host-target InstructionSetExtensions, SIMDAcceleration, OptimizeReductions, host SIMD tuning, host OpenMP, codegen performance

Development41
M
matrixscan-batch-ios
matrixscan-batch-ios
scandit / skills

MatrixScan Batch (MatrixScan, BarcodeBatch, legacy BarcodeTracking) — tracking and scanning multiple barcodes at once in iOS (Swift, UIKit/SwiftUI) projects. Use for integration, settings and symbologies, tracked-barcode handling, basic/advanced overlay customization, lifecycle, or troubleshooting.

Development41
M
matrixscan-count-capacitor
matrixscan-count-capacitor
scandit / skills

Capacitor MatrixScan Count (BarcodeCount) — plugin scandit-capacitor-datacapture-barcode. Multi-barcode counting and receiving workflows (scan-and-count, inventory count, capture list, status mode) with BarcodeCountView on a DOM element in Capacitor apps, iOS/Android native only. For React Native use matrixscan-count-rn. Use for integration, symbology configuration, result handling, view customization, or troubleshooting counting workflows.

Development41
M
matrixscan-count-flutter
matrixscan-count-flutter
scandit / skills

MatrixScan Count (BarcodeCount) in Flutter projects — scandit_flutter_datacapture_barcode_count package. Multi-barcode counting and receiving workflows (scan-and-count, counting against a target list, status providers) with the BarcodeCountView widget. Use for integration, scan settings, result handling, UI customization, SDK version migration, or troubleshooting counting workflows.

Development41
M
maui-ui-best-practices
maui-ui-best-practices
rimblehelm / .net-maui-skills

Defines recommended UI/UX patterns, layout strategies, styling conventions, accessibility rules, and performance guidelines for .NET MAUI applications.

Design & UI41
M
mb-map-codebase
mb-map-codebase
mrvladd-d / memobank

Map an existing codebase into an as-is Memory Bank without inventing roadmap items.

Development41
M
mcp-builder
mcp-builder
21307369 / superpowers-zh

MCP server construction methodology — systematically build production-grade MCP tools so AI assistants can connect to external capabilities

Development41
M
mcp-spy
mcp-spy
johnlindquist / claude

Debug MCP server communication. Use for troubleshooting MCP integrations, viewing traffic, and analyzing latency.

Development41
M
mcporter
mcporter
alphaonedev / openclaw-graph

MCP server management: install, configure, bridge external tools, protocol handling

Agent workflows41
M
melech-plan-review
melech-plan-review
adird / agent-shell-hamelech

Review a solution before approving it, like a GitHub changes tab: show a file tree of red and green pseudo-code for inline comments, then respond with Approve, Commented, or Rejected. Use when the user wants to see what would change, a git-like diff, or the PR as if it were ready.

Agent workflows41
M
merge-pr
merge-pr
lwlee2608 / agent-skills

Merge a GitHub PR, close linked issues, and delete the branch

Development41
M
mermaid-architecture
mermaid-architecture
afonsoft / skills

Use when generating, documenting, or updating architecture diagrams, flowcharts, sequence, ER, class, or state diagrams using Mermaid in docs/architecture/.

Development41
M
microservices
microservices
krzysztofsurdy / code-virtuoso

Microservices and distributed systems patterns: service boundaries, sagas, CQRS, resilience, and monolith trade-offs. Use to decompose a monolith or design service communication.

Development41
M
miniapp-devtools-cli-repair
miniapp-devtools-cli-repair
sun-sunshine06 / miniprogram-skills

Diagnose WeChat DevTools failures through the official CLI instead of relying only on GUI screenshots. Use when Codex needs to run `open`, `preview`, or related commands, discover the live service port, classify whether a failure is CLI-visible, host-side, or outside preview scope, and apply or suggest only safe repo-level fixes.

Development41
M
miniapp-devtools-recovery
miniapp-devtools-recovery
sun-sunshine06 / miniprogram-skills

Recover a WeChat Mini Program repository after wrong-root import, DevTools template residue, stale compile conditions, or TypeScript-recognition drift. Use when Codex needs to restore the intended repo shape, remove generated clutter, or tell the user exactly what to fix inside DevTools.

Development41
M
miniapp-official-scaffold-alignment
miniapp-official-scaffold-alignment
sun-sunshine06 / miniprogram-skills

Validate or design a WeChat Mini Program scaffold, repository layout, or TypeScript setup against official platform rules. Use when Codex needs to review `project.config.json`, `app.json`, `miniprogramRoot`, page or component file sets, or the initial repo skeleton before feature work begins.

Development41
M
mistral-api
mistral-api
alphaonedev / openclaw-graph

Mistral AI API for models like large/medium/small, with function calling and code generation.

Development41
M
mongodb-search-and-ai
mongodb-search-and-ai
fcakyon / claude-codex-settings

Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG applications), or combined approaches. Also use when users need text containment, substring matching ('contains', 'includes', 'appears in'), case-insensitive or multi-field text search, or filtering across many fields with variable combinations. Provides workflows for selecting the right search type, creating indexes, constructing queries, and optimizing performance using the MongoDB MCP server.

Data & databases41
M
mosaicml
mosaicml
membranedev / application-skills

MosaicML integration. Manage data, records, and automate workflows. Use when the user wants to interact with MosaicML data.

Cloud & DevOps41
N
n8n-binary-and-data
n8n-binary-and-data
czlonkowski / n8n-mcp

Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send the image", Merge losing binary, or a CDN for chat images. Covers the $binary vs $json split, reading/writing binary, keeping binary alive across transforms with Merge, the agent-tool binary boundary, and the CDN/URL requirement for chat surfaces.

Data & databases41
N
n8n-subworkflows
n8n-subworkflows
czlonkowski / n8n-mcp

Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over ~10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs, waitForSubWorkflow, mode each vs all, or exposing a workflow as an agent tool. Covers typed sub-workflow inputs, all-vs-each execution, verb-first naming for discovery, stateless vs stateful design, and splitting by input shape.

Development41
N
n8n:ui-design
n8n:ui-design
n8n-io / n8n

Guidelines on designing and building UI. Use when working in editor-ui or design-system packages. Triggers for tasks that include refactoring components, styling changes, or feature work

Design & UI41
N
nft-blockchain
nft-blockchain
dcl-regenesislabs / opendcl

NFT display and blockchain interaction in Decentraland. NftShape (framed NFT artwork), wallet checks (getPlayer, isGuest), signedFetch (authenticated requests), smart contract interaction (eth-connect, createEthereumProvider), and RPC calls. Use when the user wants NFTs, blockchain, wallet, smart contracts, Web3, crypto, or token gating. Do NOT use for player avatar data or emotes (see player-avatar).

Development41
N
node-packaging
node-packaging
paldom / node-skills

Configures npm package artifacts - package.json exports maps, ESM-first vs dual format decisions, tsdown/tsup bundling, publint and arethetypeswrong gates, files whitelist, engines. Use when the user asks to package a library for npm, fix consumer import or type-resolution errors, or check publish-readiness. Not for version bumps, changelogs, releases, or registry auth

Development41
N
novu
novu
novuhq / skills

Build multi-channel notification systems with Novu. Trigger notifications across email, SMS, push, chat, and in-app channels. Manage subscribers, integrate the inbox component, and configure notification preferences.

Development41
O
odoo_coding_guidelines
odoo_coding_guidelines
odoo-ps / ps-ai-skills

"Official Odoo coding standards for reviewing, checking, or writing Python, XML, JavaScript, and CSS/SCSS, plus module structure and a full-review checklist."

Development41
34441–34500 of 37,145

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.