By agent

Top Skills for Cursor

AI-first IDE. SKILL.md works via the Cursor plugin layer; per-skill compatibility verified here.

88 verified skills · vendor: Cursor · via compatibility layerInstall docs

About Cursor

Cursor is the AI-first IDE — a fork of VS Code with deep Claude, GPT and Gemini integration — and it adopted SKILL.md support through its plugin layer. Skills on Cursor sit alongside Cursor's own rules system (`.cursorrules` and `.cursor/rules/`), and the best-published Cursor Skills work well in both contexts.

The install model is repository-scoped or user-scoped. Drop the Skill folder under `.cursor/skills/` for a per-project install, or place it in the global Cursor config directory for user-wide availability. Cursor's plugin marketplace is the easiest route — search for the Skill and install with one click.

Cursor is the right target for engineers who prefer an IDE over a CLI workflow but want the same Skill-driven discipline. Compatibility with Claude Code Skills is high for any Skill that does not depend on Claude Code's specific Bash and subagent primitives. We rank Cursor Skills with provenance, install count, and the verified-compatibility filter — Skills tested in both Cursor and Claude Code rank above those tested in only one.

Verified for this agent

Best Skills for Cursor

Every skill below is verified to work with Cursor. Ranked by composite score.

Escape generic AI-generated UIs. Forces a bold, distinctive design direction before any code is written.

ReactTailwindDesign
All surfaces

Stripe's own integration playbook: pick the right API, set up Connect and billing, and handle keys and webhooks securely.

StripePaymentsSubscriptions
Code

Provision a Postgres, Redis, auth, or LLM provider through the Stripe Projects catalog rather than signing up by hand.

StripeProvisioningInfra
Code

Resend's deliverability playbook: SPF/DKIM/DMARC, spam avoidance, bounce handling, and CAN-SPAM/GDPR/CASL compliance.

EmailDeliverabilitySPF/DKIM/DMARC
Code

Build cross-client HTML emails as React components, with a visual editor and Resend-ready rendering.

React EmailTemplatesTransactional
Code

Stripe's version-upgrade guide: move API versions and SDKs without breaking your integration.

StripeMigrationSDK
Code

Find vendors and partners for a job-to-be-done — and, where supported, let the agent purchase and consume the service.

StripeDiscoveryPayments
Code

Hookdeck's webhook playbook: 40 provider-specific skills covering signature verification, idempotency, and event handling — each with runnable examples.

WebhooksSignature VerificationIdempotency
Code

Resend's own API skill: send transactional and batch email, handle inbound webhooks, and manage domains, templates, and keys.

ResendEmailTransactional
Code

Give an agent a webhook-driven inbox with the sender-allowlist and content-filtering patterns that block prompt injection from inbound email.

Inbound EmailAgent SecurityWebhooks
Code

Structured multi-step development. Brainstorm → spec → plan → build → review → merge — TDD baked in.

TDDMulti-agentPlans
Code

Paddle's own integration playbook: ten skills for Checkout, webhooks, pricing pages, and subscription lifecycle on the merchant-of-record platform.

PaddleSubscriptionsMerchant of Record
Code

Open-source marketing stack for AI coding agents. SEO, content, email, ads, analytics in one bundle.

SEOContentGrowth
Code

Twilio's official Developer Kit: 55 skills across SMS, WhatsApp, Voice, Verify, SendGrid, and compliance — plus the Twilio MCP. Public beta.

TwilioSMSWhatsAppVoice
Code

Composio's official skill for connecting agents to 1000+ external apps: auth configs, per-user connections, tool execution, and triggers.

ComposioTool RouterIntegrations
Code

Full-stack WorkOS implementation with auth provider migration paths.

WorkOSAuthSSO
Code

1,000+ SaaS integrations as one skill. OAuth lifecycle, scoped credentials, structured actions.

OAuthSaaSAction-taking
All surfaces

ADR authoring + design review. Trade-offs, consequences, alternatives.

ADRArchitectureDesign
All surfaces

Disciplined debugging loop. Reproduce, isolate, diagnose, fix.

DebugDiagnosisTroubleshooting
All surfaces

Technical writing that engineers will actually read and update.

DocumentationWritingREADME
All surfaces

Incident triage + comms + blameless postmortem in one harness.

IncidentPostmortemOn-call
All surfaces

System design from requirements. APIs, data, boundaries, scale.

System DesignArchitectureAPI
All surfaces

Honest tech-debt audit with a prioritized cleanup backlog.

Tech DebtRefactorAudit
All surfaces

Layered test plan sized to the change's risk profile.

TestingStrategyCoverage
All surfaces
Official

Real feature verification — run the app, drive it, prove it works.

VerifyPreviewE2E
Code

Self-contained HTML artifacts with React + shadcn/ui — no build step, just paste and run.

Reactshadcn/uiArtifacts
All surfaces
Official

Extract, fill, merge. PDF manipulation with bundled scripts so Claude does not waste tokens generating them.

PDFFormsRead-write
All surfaces

Senior-designer feedback on demand. Hierarchy, usability, consistency, motion.

DesignCritiqueReview
All surfaces

Turn a final design into a spec engineers can implement directly.

HandoffSpecsTokens
All surfaces

Design-system hygiene at speed. Audit, document, extend.

Design SystemAuditDocumentation
All surfaces

Microcopy that respects the user. Errors, empty states, CTAs, onboarding.

UX CopyMicrocopyWriting
All surfaces

Supabase done right. RLS policies, edge functions, realtime, auth — in idiomatic patterns.

PostgresRLSRealtime
Code

Stripe done right. Checkout, subscriptions, webhooks, idempotency, metered billing.

StripePaymentsWebhooks
All surfaces

Shopify Storefront API: cart, checkout, metafields, customer accounts, Hydrogen patterns.

ShopifyCommerceHydrogen
Code

Sentry the right way. Source maps, releases, breadcrumbs, performance, structured tags.

SentryErrorsObservability
Code

Single seed prompt → cohesive token system. Tokens that look intentional, not generated.

TokensDesign systemTheming
All surfaces

Test local webapps with Playwright. Generation, run, report — end-to-end.

PlaywrightE2ETesting
Code

Review for reuse, quality, efficiency. Catches over-abstraction and dead code before merge.

ReviewRefactorDRY
Code

Security audits run by a real security firm. CodeQL + Semgrep + audit workflows.

CodeQLSemgrepAudit
Code

Web scraping, search, and browser automation built to be agent-friendly.

ScrapingSearchWeb
All surfaces

Web search + 36 authoritative data sources. SEC, PubMed, ChEMBL, FRED — agent-grade research.

SearchSECPubMed
All surfaces

PlanetScale's schema branching and index-aware queries, packaged for agents.

SchemaMigrationsMySQL
Code

shadcn/ui context: components, patterns, and the right composition by default.

shadcnComponents
Code

Next.js App Router by the book. Server components, streaming, parallel routes.

Next.jsReactApp Router
Code

Boolean prop hell → compound components. Cleaner React component APIs by construction.

ReactPatternsAPI design
Code

20 SEO + GEO skills in one bundle. Keyword research, audits, rank tracking, AI search optimization.

SEOGEOContent
Code

Expo workflows: navigation, EAS, OTA, native modules.

ExpoReact NativeEAS
Code
Community

TDD with red/green/refactor as a concrete TypeScript walkthrough.

TDDTypeScript
Code

32+ marketing skills in one bundle. CRO, copywriting, SEO, analytics, email, growth.

CROCopywritingEmail
Code

Strip the AI tells. Multi-pass editing for content that reads opinionated, not generated.

EditingVoiceAEO
Code

Prisma migrations and queries by the book. Index-aware, migration-safe, type-correct.

PrismaTypeScriptMigrations
Code

Caching without the bugs. Invalidation, write-through, cache-aside, distributed locks.

RedisCachePerformance
Code

CRO patterns from real teardowns. Hero copy, social proof, friction audits, test design.

CROA/B testingFunnel
Code

Full email sequences with branching, exit conditions, and copy that does not read like an AI wrote it.

EmailLifecycleDrip
Code

Dockerfiles done right. Multi-stage, cache-friendly, distroless, hardened.

DockerContainersSecurity
Code

GitHub Actions workflows with matrix, reusable jobs, OIDC, secrets done right.

GitHub ActionsCI/CDYAML
Code

TypeScript strict mode by default. Discriminated unions, branded types, exhaustive switches.

TypeScriptTypesStrict
Code

Vitest patterns: snapshots, mocks, parallel runs, in-source tests, coverage.

VitestUnit testingTypeScript
Code

Terraform expertise on tap. State inspection, module validators, safety-first IaC.

TerraformIaCAWS
Code

Senior DevOps engineer persona — CI/CD, containers, blue-green/canary, IaC across clouds.

CI/CDContainersAWS
Code

Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions.

BrowserAutomationAction-taking
Code

Headless browser as an agent tool. Navigate JS-heavy pages, fill forms, extract content.

HeadlessBrowserJS
Code

Playwright patterns: clicks, fills, waits, retries. The do-it-right defaults.

PlaywrightAutomation
Code

D3.js patterns for interactive viz that does not look stock.

D3.jsVizInteractive
Code

HTML slide decks from prose. Easy to embed, version, and edit later.

SlidesHTMLPresentations
Code

Standup updates from recent commits, PRs, and ticket moves. Yesterday/today/blockers.

StandupReports
Code

MongoDB aggregations and indexing without the foot-guns.

MongoDBAggregationNoSQL
Code

Mermaid diagrams from prose with self-validating syntax. Sequence, flowchart, ER, state.

MermaidDiagramsMarkdown
All surfaces

LinkedIn posts that read human. Hook patterns, voice modeling, carousel scripts.

LinkedInSocialContent
All surfaces

AWS CDK in TypeScript with stack composition, drift detection, cost-tagged resources.

AWSCDKIaC
Code

Cypress E2E with page objects, custom commands, network stubs, a11y checks.

CypressE2EFrontend testing
Code

Kubernetes hardening by the book. NetworkPolicies, RBAC, OPA, service mesh.

KubernetesRBACOPA
Code

FAQ

Frequently asked

How do Cursor Skills compare to .cursorrules?

Cursor rules are global to the project; Skills are loaded conditionally based on triggering. Best teams use both — rules for invariant coding conventions, Skills for task-specific workflows.

How do I install a Skill in Cursor?

Drop the folder under `.cursor/skills/` for project-scoped, or the global Cursor config dir for user-wide. The marketplace gives one-click install for popular Skills.

Do Claude Code Skills work in Cursor?

Most do — the SKILL.md spec is shared. Skills that depend on Claude Code's specific Bash, Workflow or subagent primitives may need adaptation; per-Skill compatibility is listed on each Skill page.

Can Cursor Skills drive the editor?

Yes — through Cursor's built-in tools (apply code change, run terminal command, etc.). Skills can edit files, run commands and read diagnostics like a human engineer would.

Which model is best in Cursor?

Claude Opus 4.7+ for the high-effort Skills (review, refactor, architecture); Claude Sonnet 4.6 for fast iteration. GPT-5 and Gemini are also supported but Anthropic Skills are tuned for Claude.

Switch agent

Other supported agents