mcpField

Skills

99,951 packaged capabilities and playbooks for agents. Install any of them with one command.

All

T
threat-modeling
threat-modeling
briiirussell / cybersecurity-skills

Run a structured threat-modeling session for a new feature, system, or architecture—STRIDE, attack trees, data flow diagrams, and abuse cases. Use when the user mentions “threat model,” “threat modeling,” “STRIDE,” “attack tree,” “abuse case,” “data flow diagram,” “DFD,” “security architecture review,” “design review,” “pre-implementation security,” “shift left,” “what could go wrong,” or needs strategic security thinking before code is written

Security484
T
tldr-deep
tldr-deep
parcadei / continuous-claude-v3

Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.

Development484
V
vast-gpu
vast-gpu
wanshuiyin / auto-claude-code-research-in-sleep

Rent, manage, and destroy GPU instances on vast.ai. Use when user says “rent gpu”, “vast.ai”, “rent a server”, “cloud gpu”, or needs on-demand GPU without owning hardware

Cloud & DevOps484
V
video-script
video-script
sugarforever / 01coder-agent-skills

Create video scripts and publishing materials for YouTubers/UP主. Use when user wants to prepare a video, write a script (口播稿), generate video title, description, tags, or chapter timestamps. Triggers on "写视频脚本", "视频口播稿", "video script", "prepare video", "视频发布素材", or mentions creating content for YouTube/Bilibili.

Creative & media484
V
vitest-skill
vitest-skill
lambdatest / agent-skills

Generates Vitest tests in JavaScript/TypeScript with Vite-native speed. Jest-compatible API with ESM support and HMR. Use when user mentions "Vitest", "vi.mock", "vitest.config". Triggers on: "Vitest", "vi.mock", "vi.fn", "Vite test", "vitest config".

Testing & quality484
W
wallet-profiling
wallet-profiling
agiprolabs / claude-trading-skills

Behavioral classification, performance analysis, and trading style detection for Solana wallets

Data & databases484
A
agent-package-manager
agent-package-manager
webmaxru / ai-native-dev

Installs, configures, audits, and operates Agent Package Manager (APM) in repositories. Use when initializing apm.yml, installing or updating packages, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, or packaging resolved context for CI and team distribution. Don't use for writing a single skill by hand, generic package managers like npm or pip, or non-APM agent configuration systems.

Agent workflows483
A
apidog-cli

Manage Apidog project resources through Apidog CLI. Trigger scenarios - running API automation tests/test suites, querying/creating/updating/deleting endpoints, environments, schemas, mocks, branches and other project resources, importing/exporting API documentation, viewing test reports, managing runners, scheduled tasks, notifications and CI/CD configuration. CLI output is structured JSON and often includes agentHints.nextSteps; all commands support --help.

Development483
B
bug-fix
bug-fix
bobmatnyc / claude-mpm-skills

Systematic workflow for verifying bug fixes to ensure quality and prevent regres...

Testing & quality483
C
copywriting
copywriting
mblode / agent-skills

Writes and edits product and marketing copy using the brand voice, house vocabulary, awareness-stage frameworks, and product-state contracts. Use when asked to "write copy", "improve this CTA", "remove AI writing patterns", or name an error or empty state. For behavior decisions use product-design; for docs use docs-writing.

Marketing & growth483
D
dns-management
dns-management
aj-geddes / useful-ai-prompts

Manage DNS records, routing policies, and failover configurations for high availability and disaster recovery.

Cloud & DevOps483
G
gpt-taste
gpt-taste
tasteskill / tasteskill

Elite UX/UI & GSAP Motion Engineer. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

Design & UI483
I
image-video-gen

Generate videos from text descriptions, a workflow skill for generating images and videos. Depends on skills: byted-web-search, image-generate, video-generate. Note: This workflow has no executable scripts; it is only descriptive documentation.

Creative & media483
M
mcp-chaining
mcp-chaining
parcadei / continuous-claude-v3

Research-to-implement pipeline chaining 5 MCP tools with graceful degradation

Agent workflows483
M
migrate
migrate
parcadei / continuous-claude-v3

Migration workflow - research → analyze → plan → implement → review

Development483
N
no-polling-agents
no-polling-agents
parcadei / continuous-claude-v3

No Polling for Background Agents

Agent workflows483
O
observe-before-editing
observe-before-editing
parcadei / continuous-claude-v3

Observe Before Editing

Development483
O
obsidian
obsidian
gapmiss / obsidian-plugin-skill

Comprehensive guidelines for Obsidian.md plugin development including ESLint rules from eslint-plugin-obsidianmd v0.4.2, TypeScript best practices, memory management, API usage (requestUrl vs fetch), UI/UX standards, popout window compatibility, community.obsidian.md submission process, and Scorecard optimization. Use when working with Obsidian plugins, main.ts files, manifest.json, Plugin class, MarkdownView, TFile, vault operations, or any Obsidian API development.

Development483
P
photoshop-automator
photoshop-automator
abdul-karim-mia / photoshop-automator

Professional Adobe Photoshop automation via COM/ExtendScript bridge. Supports text updates, filters, and action playback.

Creative & media483
Q
qlty-during-development
qlty-during-development
parcadei / continuous-claude-v3

QLTY During Development

Testing & quality483
R
release
release
parcadei / continuous-claude-v3

Release preparation workflow - security audit → E2E tests → review → changelog → docs

Development483
R
render-cron-jobs
render-cron-jobs
render-oss / skills

Configures and troubleshoots scheduled tasks on Render using cron job services. Use when the user needs to run something on a schedule, write a cron expression, set up a periodic job, migrate from Heroku Scheduler, choose between cron jobs and background workers, or fix a cron that isn't firing. Trigger terms: cron job, scheduled task, periodic job, cron expression, schedule, run every, timer, Heroku Scheduler migration.

Cloud & DevOps483
R
report-regressions
report-regressions
trailofbits / skills

Use when assembling or refreshing an evidence-linked regression report from saved campaign decisions

Testing & quality483
S
ship-gate
ship-gate
alirezarezvani / claude-skills

Use before deploying or going live (“am I ready to ship”, “can I deploy”, “preflight check”). Scans the codebase with ship_gate_scanner.py across security, database, deploy, AI, dependencies and observability, and blocks on critical items

Testing & quality483
S
skill-creator
skill-creator
freestylefly / canghe-skills

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Agent workflows483
S
skill-creator
skill-creator
webmaxru / ai-native-dev

Authors and structures professional-grade agent skills following the agentskills.io spec. Use when creating new skill directories, drafting procedural instructions, or optimizing metadata for discoverability. Don't use for general documentation, non-agentic library code, or README files.

Agent workflows483
S
specsfy-specialist-shadcn-ui
specsfy-specialist-shadcn-ui
promovaweb / specsfy

Instalar, compor e adaptar shadcn/ui com registry, Radix, theming, formulários, tabelas, gráficos, sidebars e componentes acessíveis. Use quando houver components.json, componentes shadcn ou pedido explícito por shadcn; trate o código copiado como código do projeto.

Design & UI483
S
spring-boot-skill
spring-boot-skill
sivaprasadreddy / sivalabs-agent-skills

Build Spring Boot 4.x applications following the best practices. Use this skill: * When developing Spring Boot applications using Spring MVC, Spring Data JPA, Spring Modulith, Spring Security * To create recommended Spring Boot package structure * To implement REST APIs, entities/repositories, service layer, modular monoliths * To use Thymeleaf view templates for building web applications * To write tests for REST APIs and Web applications * To write ArchUnit tests for testing architecture * To configure the recommended plugins and configurations to improve code quality, and testing while using Maven. * To use Spring Boot's Docker Compose support for local development * To create Taskfile for easier execution of common tasks while working with a Spring Boot application

Development483
V
vip-test

No description yet

Other483
W
write-landing
write-landing
openclaudia / openclaudia-skills

Create high-converting landing page copy and structure. Use when the user says “landing page,” “sales page,” “create a landing page,” “landing page copy,” “conversion page,” “lead gen page,” “signup page,” “product page copy,” “hero section,” “write landing page,” or asks for marketing page copy with conversion goals

Marketing & growth483
X
xss-prevention
xss-prevention
aj-geddes / useful-ai-prompts

Prevent Cross-Site Scripting (XSS) attacks through input sanitization, output encoding, and Content Security Policy. Use when handling user-generated content in web applications.

Security483
A
aeo
aeo
alirezarezvani / claude-skills

Use before rewriting content that should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization). Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py

Marketing & growth482
A
agent-deep-links
agent-deep-links
composio-community / awesome-codex-skills

Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools. Use when users ask for clickable links (especially in Slack) that open threads, files, folders, or app settings

Productivity482
A
api-gateway-patterns
api-gateway-patterns
manutej / luxor-claude-marketplace

Comprehensive API gateway patterns skill covering Kong, routing, rate limiting, authentication, load balancing, traffic management, and production gateway architecture

Cloud & DevOps482
A
auth0-android
auth0-android
auth0 / agent-skills

Use when adding Auth0 login, logout, or credential management to an Android app in Kotlin or Java. Covers Web Auth, biometric-protected CredentialsManager, and MFA — even if the user just says "add login to my Android app" without mentioning Auth0. Integrates com.auth0.android:auth0.

Security482
C
code-review:review-pr
code-review:review-pr
neolabhq / context-engineering-kit

Comprehensive pull request review using specialized agents

Testing & quality482
C
conversational-flow-management
conversational-flow-management
louisblythe / sales-skills

When the user wants to build or improve a sales bot's ability to keep exchanges natural while progressing toward outcomes. Also use when the user mentions "conversation design," "dialog flow," "bot conversations," "natural conversations," or "guided conversations."

Marketing & growth482
C
core-animation
core-animation
prisma-labs-dev / apple-skills

API reference: Core Animation (QuartzCore). Query for CALayer, CAAnimation, CABasicAnimation, CAKeyframeAnimation, CASpringAnimation, CATransaction, CAShapeLayer, CAGradientLayer, CAEmitterLayer, CATransform3D, CADisplayLink.

Development482
C
create-component
create-component
incluud / astro-agent-skills

Create Astro components, pages, and layouts with accessible markup and minimal client-side JavaScript.

Development482
D
django-drf
django-drf
prowler-cloud / prowler

Django REST Framework patterns. Trigger: When implementing generic DRF APIs (ViewSets, serializers, routers, permissions, filtersets). For Prowler API specifics (RLS/RBAC/Providers), also use prowler-api.

Development482
H
hook-voice-patterns
hook-voice-patterns
motion-team / creative-strategy-skills

A living swipe file of scroll-stopping hook templates collected from the wild — real sentence structures and native voice patterns that have proven they stop the scroll. Use this whenever writing hooks, opening lines, or scroll-stoppers, especially when combined with hook-writing and hook-tactics. Trigger any time the user wants hooks that feel native to the feed rather than constructed. These templates are the raw structural DNA of hooks that work — plug in the brand, persona, and pain to execute.

Marketing & growth482
K
kafka-stream-processing
kafka-stream-processing
manutej / luxor-claude-marketplace

Complete guide for Apache Kafka stream processing including producers, consumers, Kafka Streams, connectors, schema registry, and production deployment

Data & databases482
M
meta-ad-creative-generation
meta-ad-creative-generation
eachlabs / skills

Generate Meta (Facebook & Instagram) ad creatives using each::sense AI. Create feed ads, stories, reels, carousel images, and video ads optimized for Meta's ad formats and best practices.

Marketing & growth482
P
performing-web-application-vulnerability-triage
performing-web-application-vulnerability-triage
mukul975 / anthropic-cybersecurity-skills

Triages web application vulnerability findings from DAST/SAST scanners

Security482
P
pp-booking-com
pp-booking-com
mvanhorn / printing-press-library

Every Booking.com workflow, plus offline price history, wishlist drop alerts, and multi-leg planning no other... Trigger phrases: `search booking.com for hotels in`, `what's the cheapest week to stay in`, `track price drops on my booking.com wishlist`, `compare these two hotels`, `are any of my booking trips about to lose free cancellation`, `plan a multi-city trip on booking.com`, `use booking-com`, `run booking-com`.

Other482
P
prepare-regression
prepare-regression
trailofbits / skills

Use when pinning before/after sources and collecting PR or commit context for a regression investigation

Testing & quality482
R
reference-sdk
reference-sdk
parcadei / continuous-claude-v3

Check reference SDK implementations using btca ask

Development482
R
reflexion:critique
reflexion:critique
neolabhq / context-engineering-kit

Comprehensive multi-perspective review using specialized judges with debate and consensus building

Agent workflows482
S
sandbox-guard
sandbox-guard
useai-pro / openclaw-skills-security

Generate Docker sandbox configurations for safely running untrusted OpenClaw skills. Isolates filesystem, network,

Security482
S
setup
setup
subframeapp / subframe

Initialize Subframe in a new or existing project. Sets up the CLI, syncs components, configures Tailwind and fonts.

Development482
S
supabase-backend-platform
supabase-backend-platform
bobmatnyc / claude-mpm-skills

Supabase open-source Firebase alternative with Postgres, authentication, storage, and realtime subscriptions. Use when building full-stack applications requiring integrated backend services with Next.js, React, or Vue.

Cloud & DevOps482
S
symfony:api-platform-versioning
symfony:api-platform-versioning
dev-toolings / superpowers-symfony

Evolve API Platform APIs via deprecation (deprecationReason/sunset, RFC 8594/9745), the recommended alternative to versioning; plus path/header strategies

Development482
T
tour
tour
parcadei / continuous-claude-v3

Friendly onboarding when users ask about capabilities

Agent workflows482
U
ugc-ad
ugc-ad
postplusai / postplus-skills

Design or review creator-led product ads, testimonials, demos, tutorials, unboxings, or POV concepts with believable interaction and approved proof.

Marketing & growth482
W
write-code-eval
write-code-eval
ai-evals-course / evals-skills

Write code evaluators for known failure modes with objective rules. Use when code can check the rule from a trace, with or without a reference answer. Use `write-judge-prompt` when the rule requires interpretation.

Testing & quality482
W
writing-tests
writing-tests
remotion-dev / remotion

Guidance for explicitly requested new tests and for updating or reviewing existing tests in the Remotion repository.

Testing & quality482
Z
zenstack-querying
zenstack-querying
zenstackhq / skills

Query and mutate data with the ZenStack V3 client. Use when creating a ZenStackClient (SQLite/Postgres/MySQL dialect), using the Prisma-compatible ORM API (findMany/create/update/etc.), relation queries (select/include), computed fields, polymorphic models, strongly-typed JSON, data validation on writes (@email/@length/@@validate), transactions, the Kysely query-builder escape hatch ($qb / $expr), custom procedures, raw SQL, logging, or handling ORMError.

Data & databases482
A
adjudicate-regression
adjudicate-regression
trailofbits / skills

Use when deciding whether source and live reproduction evidence establish a new regression or an exclusion

Testing & quality481
A
agent-package-manager
agent-package-manager
webmaxru / enonic-agent-skills

Installs, configures, audits, and operates Agent Package Manager (APM) in repositories. Use when initializing apm.yml, installing or updating packages, validating manifests, managing lockfiles, compiling agent context, browsing MCP servers, setting up runtimes, or packaging resolved context for CI and team distribution. Don't use for writing a single skill by hand, generic package managers like npm or pip, or non-APM agent configuration systems.

Agent workflows481
A
apache-spark-data-processing
apache-spark-data-processing
manutej / luxor-claude-marketplace

Complete guide for Apache Spark data processing including RDDs, DataFrames, Spark SQL, streaming, MLlib, and production deployment

Data & databases481
21181–21240 of 99,951

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.