mcpField

Skills

99,064 packaged capabilities and playbooks for agents. Install any of them with one command.

Development

N
ns-docs-writer
ns-docs-writer
nextstage-brasil / skills

(NS) Human-facing project docs — README, docs/ guides, runbooks, contributor markdown. Use whenever the user asks for documentation, README updates, how-to guides, or docs/ content — even if they say \"explain how to use\" instead of \"write docs\". Do NOT use for code comments, API docblocks, requirements.md, or SDD version artifacts (use PM skills).

Documents140
O
observability
observability
maddhruv / absolute

Absolute skills to 10x your development lifecycle

Cloud & DevOps140
O
onchain-randomness
onchain-randomness
mystenlabs / skills

Onchain randomness on Sui. Use when generating random values in Move smart contracts, working with the Random object (0x8) or RandomGenerator, securing randomness-consuming functions against composition attacks, PTB attacks, or state leakage, implementing commit-reveal patterns, balancing gas across execution paths, or integrating randomness from TypeScript. For general Move security patterns, see the `move-security` skill. For Move language fundamentals, see the `sui-move` skill. For TypeScript SDK patterns, see the `sui-sdks` skill.

Development140
P
performance-engineering
performance-engineering
travisjneuman / .claude

Web Vitals, bundle optimization, CDN, caching, and load analysis. Use when diagnosing slow pages or APIs, reducing bundle size, or designing caching and performance budgets.

Development140
P
pythia-impact
pythia-impact
thaildhe172591 / pythia

Use before proposing or writing any change to an Oracle object - a procedure, package, function, trigger, view, or table. Impact analysis comes first, because what depends on an object decides how careful the change must be, and Oracle invalidates dependents in cascade.

Data & databases140
R
ray-common-develop-skill

Provides index-first documentation navigation and implementation constraints for Ray mini program development. Use when building pages or UI, encapsulating and refactoring components, integrating Ray APIs and device capabilities, working with lifecycles and routing, converting images to code, handling i18n and styles, or troubleshooting and upgrading. Before implementing, locate capabilities via references/ray/INDEX.md and the routing docs; never invent APIs or lifecycle hooks.

Development140
R
react-hook-form
react-hook-form
thongdn-it / react-agent-skills

React Hook Form performance optimization for client-side form validation using useForm, useWatch, useController, and useFieldArray. This skill should be used when building client-side controlled forms with React Hook Form library. This skill does NOT cover React 19 Server Actions, useActionState, or server-side form handling (use react-19 skill for those).

Development140
R
remotion-best-practices
remotion-best-practices
remotion-dev / claude-code-plugin

Router for all Remotion skills

Creative & media140
R
repo-guidance
repo-guidance
composiohq / composio

Navigate the Composio SDK monorepo, branch and PR workflow, repo layout, generated-file boundaries, changesets, and shared maintenance rules. Use when work spans multiple packages, when deciding where code belongs, when preparing a PR, or when the user asks about repository conventions rather than a specific SDK implementation.

Development140
R
roblox-quest-progression-systems
roblox-quest-progression-systems
ashexplained / roblox-skills

Design and implement Roblox quests, achievements, collections, unlocks, prestige, daily/weekly goals, progression pacing, reward claims, and objective tracking. Use for short-term and long-term goals tied to retention.

Development140
S
ssot
ssot
venhdev / zenforge

Audit documentation authority, reconcile conflicting specifications, and maintain canonical Single Source of Truth records across repository documentation.

Documents140
T
task-automation
task-automation
seb1n / awesome-ai-agent-skills

Automate repetitive tasks and workflows using scripting, file watchers, scheduled jobs, CI triggers, and API polling to eliminate manual toil. Use when the user requests task automation or provides relevant inputs for this workflow.

Productivity140
T
telnyx-webrtc-client-js

Build browser-based VoIP calling apps using the Telnyx WebRTC JavaScript SDK. Covers authentication, voice calls, events, debugging, call quality metrics, and AI Agent integration. Use for web-based real-time communication

Development140
T
textual-builder
textual-builder
ypares / agent-skills

Build Text User Interface (TUI) applications using the Textual Python framework (v0.86.0+). Use when creating terminal-based applications, prototyping card games or interactive CLIs, or when the user mentions Textual, TUI, or terminal UI. Includes comprehensive reference documentation, card game starter template, and styling guides.

Development140
T
to-tasks
to-tasks
venhdev / zenforge

Decompose settled changesets into a verifiable DAG and persist tasks to the configured tracker via split-tasks and track-tasks.

Agent workflows140
T
triage
triage
leandrocfe / skills

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Development140
T
twilio-taskrouter-routing

Route tasks to agents using Twilio TaskRouter. Covers Workers, Task Queues, Workflows, Reservations, skills-based routing, and common gotchas (hyphen attributes, HAS operator, reservation cascade). Use this skill for any multi-agent contact center, support queue, or AI agent escalation routing.

Development140
T
typescript-advanced-patterns
typescript-advanced-patterns
curiositech / some_claude_skills

'Advanced TypeScript type system patterns for production codebases. [What: branded types for nominal typing, discriminated unions, template literal types, conditional types, the infer keyword,

Development140
T
typescript-providers
typescript-providers
composiohq / composio

Implement, modify, test, or document TypeScript provider packages under ts/packages/providers, including framework adapters for OpenAI, Anthropic, Google, LangChain, Mastra, Vercel, LlamaIndex, Cloudflare, Claude Agent SDK, and TypeSafe. Use for provider-specific TS work; do not use for core-only changes.

Development140
U
umbraco-version-guard
umbraco-version-guard
umbraco / umbraco-cms-backoffice-skills

Deterministically verify that the Umbraco major of the site you are working on matches the major these skills target. Run this FIRST, before any Umbraco backoffice work, to avoid mixing guidance across Umbraco majors (e.g. 17 vs 18 vs 19). Trigger on the first Umbraco task in a session, or whenever the site's version is uncertain.

Development140
U
using-crabnebula-cloud-with-tauri
using-crabnebula-cloud-with-tauri
dchuk / claude-code-tauri-skills

Guides the user through distributing Tauri applications via CrabNebula Cloud, including pipeline setup, cloud configuration, auto-updates integration, and CI/CD workflows for seamless app distribution.

Cloud & DevOps140
U
using-strong-skipping-correctly
using-strong-skipping-correctly
skydoves / compose-performance-skills

Use this skill to reason about Jetpack Compose's Strong Skipping Mode — the default since Kotlin 2.0.20 — including what it changes about skippability, when it does and does not auto-`remember` lambdas, and which escape hatches (`@DontMemoize`, `@NonSkippableComposable`, `@NonRestartableComposable`, `@ReadOnlyComposable`) apply where. Covers verifying the mode is active, auditing lambda capture sites, and the gaps where strong skipping does not memoize (`LazyListScope.items {}`, `Modifier.pointerInput {}`, object expressions, non-@Composable scopes). Use when the developer asks "do I still need @Stable?", "does this composable skip?", "why does this still recompose despite strong skipping", "when do I need @DontMemoize or @NonSkippableComposable?", is migrating from older Compose, or sees auto-remembered lambdas in compiler output.

Development140
V
vibe-techdesign
vibe-techdesign
khazp / vibe-coding-prompt-template

Writes an MVP technical design from agreed requirements, including architecture choices and relevant tradeoffs.

Development140
V
vite
vite
partme-ai / full-stack-skills

Guidance for Vite using the official Guide, Config Reference, and Plugins pages. Use when the user needs Vite setup, configuration, or plugin selection details

Development140
W
windows-app-developer
windows-app-developer
404kidwiz / claude-supercode-skills

Expert in building modern Windows applications using WinUI 3, WPF, and the Windows App SDK. Specializes in MSIX packaging, XAML styling, and MVVM architecture.

Development140
A
ai-steering-files
ai-steering-files
lvtd-llc / ai-steering

Use when creating, auditing, or updating AI steering files such as AGENTS.md, CLAUDE.md, GEMINI.md, .github/copilot-instructions.md, .cursor/rules/*.mdc, PRODUCT.md, ANALYTICS.md, TECH.md, STRUCTURE.md, VISION.md, or DESIGN.md in a software repository.

Agent workflows139
A
aps-docs-portal
aps-docs-portal
autodesk-platform-services / skills

Navigate the Autodesk Platform Services (APS) documentation portal — find the right API docs, decode glossary terms, index table-of-contents JSON trees, extract content from static HTML pages, and build valid aps.autodesk.com portal links. Covers ACC, BIM 360, Model Derivative, Data Management, Viewer, Design Automation, Authentication, Webhooks, and all related APS APIs.

Development139
A
auth-ops
auth-ops
0xdarkmatter / claude-mods

Authentication and authorization patterns — JWT, OAuth2, sessions, RBAC, ABAC, passkeys, MFA, identity-aware proxies, and Better Auth. Use for: authentication, jwt, oauth2, session, login, rbac, abac, passkey, mfa, totp, api key, token, cookie, csrf, bearer token, refresh token, oidc, cloudflare access, zero trust, Cf-Access-Jwt-Assertion, AUD tag, service auth, better auth.

Security139
B
backend-best-practices

Best practices for backend development including API design, database patterns, authentication, error handling, performance, and security. Use when reviewing backend code, building APIs, designing database schemas, or enforcing backend coding standards.

Development139
B
backend-security-coder
backend-security-coder
rmyndharis / antigravity-skills

Expert in secure backend coding practices specializing in input

Security139
B
bagisto-payment-method-development
bagisto-payment-method-development
bagisto / agent-skills

Use when creating or changing a Bagisto payment method — a payment class, the payment methods config, the checkout redirect and callback flow, or integrating a gateway such as Stripe or PayPal. Trigger phrases include "payment", "payment method", "payment gateway", "Stripe", "PayPal", "Razorpay", "checkout payment", "redirect", "webhook".

Development139
B
binary-analysis
binary-analysis
laurigates / claude-plugins

Binary analysis: strings, binwalk, hexdump, xxd, file, objdump. Use when identifying unknown files, extracting strings, hunting credentials, or entropy analysis.

Security139
B
break-req
break-req
chanakya-net / maestro-ai

Requirements discovery, dependency mapping, and technical constraint capture before implementation planning.

Development139
B
bruno-collection-generator
bruno-collection-generator
bruno-collections / bruno-agent-skills

Generate Bruno API collections, request files, environments, and request documentation from backend source code, route definitions, OpenAPI snippets, pasted API docs, curl commands, or endpoint lists. Use when a user asks to create, scaffold, convert, organize, or improve Bruno collections, opencollection YAML files, .bru files, folders, request docs, request metadata, environments, or API-client collections for Bruno.

Development139
B
build-prd
build-prd
fellowship-dev / dogfooded-skills

Use when creating a PRD, writing requirements, or transforming a feature request into an implementation-ready GitHub issue

Development139
C
c4-codebase-architecture
c4-codebase-architecture
lmammino / c4-codebase-architecture-skill

Helps an agent inspect a repository and produce C4 architecture documentation. Use this when reverse engineering a codebase, documenting system context, containers, components, or clarifying architecture from code and infrastructure.

Development139
C
camunda-dmn
camunda-dmn
camunda / skills

Use this skill when the business, not developers, should own decision rules—eligibility, risk, routing, discounts—and change them without a code release or audit which rule fired, even if DMN or decision tables aren't mentioned. Authors and validates DMN decision tables for Camunda 8. Not for requests to write a function or script in a programming language

Development139
C
catlass-operator-dev
catlass-operator-dev
ascend / agent-skills

An end-to-end Catlass operator development orchestrator. Based on ascend-kernel (csrc/ops), it connects catlass design, catlass-operator-code-gen, and the ascendc sub-skill to complete the cycle from project initialization through documentation, accuracy, and performance. Keywords: Catlass, end-to-end, ascend-kernel, operator development, workflow orchestration.

Development139
C
chrome-devtools
chrome-devtools
oakoss / agent-skills

Browser automation via Chrome extension and DevTools MCP. Use when controlling a logged-in Chrome browser, automating workflows, filling forms, extracting data, debugging web apps, reading console logs, or running scheduled browser tasks. Use for browser testing, form automation, data extraction, web scraping, authenticated browsing.

Productivity139
C
claude-agent-sdk
claude-agent-sdk
secondsky / claude-skills

Anthropic Claude Agent SDK for autonomous agents and multi-step workflows. Use for subagents, tool orchestration, MCP servers, or encountering CLI not found, context length exceeded errors.

Agent workflows139
C
cli-reference
cli-reference
even-realities / everything-evenhub

Even Hub CLI command reference — login, init, qr, and pack commands with all options. Use when running CLI commands, generating QR codes, initializing projects, or packaging apps

Development139
C
code-clone-assistant
code-clone-assistant
terrylica / cc-skills

Detect and refactor code duplication with PMD CPD. TRIGGERS - code clones, DRY violations, duplicate code

Development139
C
code-review
code-review
luongnv89 / skills

Review or improve code — one skill, four modes: bug/security review (default), performance, clean-code audit, slop cleanup. Pass mode:review|perf|clean|cleanup or infer. Don't use for writing features or generating tests (use test-coverage).

Testing & quality139
C
comark

Comark (Components in Markdown) parser: syntax, AST, Vue/React/Svelte/Angular renderers, plugins, and LLM streaming with auto-close.

Development139
C
configuring-lazy-prefetch
configuring-lazy-prefetch
skydoves / compose-performance-skills

Use this skill to tune Jetpack Compose lazy-layout prefetch with LazyLayoutCacheWindow (Compose Foundation 1.9+, @ExperimentalFoundationApi) and pausable composition in prefetch (Compose Foundation 1.10+, default on). Covers configurable Dp-based ahead/behind cache windows plumbed through rememberLazyListState(cacheWindow = ...), NestedPrefetchScope for items containing inner lazy layouts (HorizontalPager inside a LazyColumn row), version requirements, and the trade-off between memory pressure and idle-frame work. Use when the developer mentions dropped frames at high scroll velocity, prefetch window, ahead/behind extents, LazyLayoutCacheWindow, NestedPrefetchScope, pausable composition for prefetch, or wants composition retained for items briefly scrolled past. Item-level fixes (keys, contentType) live in a sibling skill.

Development139
C
copilot-sdk
copilot-sdk
hoodini / ai-agents-skills

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

Agent workflows139
C
create-git-issue
create-git-issue
chanakya-net / maestro-ai

Create a PRD from resolved requirements, break it into tracer-bullet implementation issues, and publish via GitHub when available or local files when not.

Development139
D
debug
debug
openai / symphony

Investigate stuck runs and execution failures by tracing Symphony and Codex logs with issue/session identifiers; use when runs stall, retry repeatedly, or fail unexpectedly.

Development139
D
debug-tools
debug-tools
adeonir / agent-skills

Evidence-led debugging for unexpected, silent, intermittent, or regressed behavior, including slowdowns and leaks. Use when tracing a bug to its root cause, finding what broke something that used to work, adding or removing targeted debug logs, or verifying a fix. Not for known one-line fixes, code review of a diff, runtime review of deployed services, or PM bug triage.

Development139
D
develop-web-game
develop-web-game
davila7 / claude-code-templates

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

Development139
D
developer-growth-analysis
developer-growth-analysis
davepoon / buildwithclaude

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs

Development139
D
doca-dpa
doca-dpa
nvidia / skills

Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app image (`doca_dpa_app`), creating DPA threads, launching kernels via `doca_dpa_kernel_launch_update_*`, draining `doca_dpa_completion`, running `doca_dpa_cap_*` discovery, choosing between the DPA comm component (inter-DPA messaging) and the DPA verbs component (in-kernel RDMA), or debugging `DOCA_ERROR_*` from `doca_dpa_*`. Trigger even without "DOCA DPA" or "Data-Path Accelerator": "run compute on the DPA from my host", "DPA kernel hangs, no completion", "DOCA_ERROR_DRIVER on launch", "DOCA/DPACC version skew", or "does this BlueField expose a DPA". Route elsewhere for DPA-side kernel programming itself, DPACC compiler internals, host↔DPU messaging (doca-comch), host-side RDMA (doca-rdma), and GPU-initiated networking (doca-gpunetio).

Development139
D
docker
docker
oakoss / agent-skills

Docker containerization for development and production. Covers Dockerfiles, multi-stage builds, layer caching, Compose services, networking, volumes, health checks, security hardening, and production deployment patterns. Use when writing Dockerfiles, optimizing image size, configuring Compose services, debugging container networking, setting up health checks, hardening containers for production, or troubleshooting build cache issues.

Cloud & DevOps139
D
dwe

Use when the current working directory is inside a DWE project — a Docker-based developer environment manager. Detect one by walking up from cwd to a directory containing `workspace.yml`; that directory is the project root. A populated project also has a `workspace/` subdirectory (services, pipelines), but its absence does not disqualify it (e.g. a freshly-initialized project). Applies anywhere beneath the root, including service folders like `workspace/services/<name>/` and their source subtrees. The skill is both a navigator — which `dwe` commands to use for inspection vs mutation, and how to look up everything else via the built-in `dwe docs` subsystem — and an authoring guide for extending a project (scaffolding from git repos, adding services and tools, authoring commands and daemons, wiring render packs and vars, customizing deploy/lifecycle pipelines, integration tests). Activates on the word "dwe", on editing any file under `workspace/`, or when working inside a service directory.

Development139
E
editframe-create
editframe-create
editframe / skills

Scaffold a new Editframe video project from a template. This generates the project structure, installs dependencies, and sets up composition tooling to start immediately.

Creative & media139
E
executing-univer-plans
executing-univer-plans
dream-num / skills

Use when executing a written Univer SaC workbook plan, implementing Facade Migration Packs, repairing plan gaps, or coordinating plan-driven assertion and migration work

Documents139
E
extract-openapi-from-code
extract-openapi-from-code
speakeasy-api / sdk-generation-skills

Use when extracting or generating an OpenAPI spec from existing API code. Triggers on "extract OpenAPI", "code first", "generate spec from code", "FastAPI OpenAPI", "Spring Boot OpenAPI", "NestJS swagger", "Django OpenAPI", "Flask OpenAPI", "Rails swagger", "Laravel OpenAPI", "existing API code"

Development139
F
factory-product
factory-product
tikalk / adlc-team-skills

Use when orchestrating a product lifecycle (specify/init → clarify → implement → analyze) to generate or verify PRD.md.

Agent workflows139
F
fastapi-router-py
fastapi-router-py
sickn33 / agentic-awesome-skills

Create FastAPI routers following established patterns with proper authentication, response models, and HTTP status codes.

Development139
F
feature-flags-nextjs
feature-flags-nextjs
posthog / skills

PostHog feature flags for Next.js applications

Development139
16921–16980 of 37,923

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.