{ "$schema": "https://top-agent-skills.com/schemas/catalog.v1.json", "type": "vertical-category", "slug": "engineering", "title": "Engineering", "shortTitle": "Engineering", "description": "Skills for software engineers: code review, refactoring, testing, debugging, infra.", "canonical": "https://top-agent-skills.com/top-skills-for-engineering", "alternates": { "html": "https://top-agent-skills.com/top-skills-for-engineering", "markdown": "https://top-agent-skills.com/top-skills-for-engineering.md", "json": "https://top-agent-skills.com/top-skills-for-engineering.json" }, "rubricVersion": "1.0", "methodology": "https://top-agent-skills.com/about/methodology", "contentLastUpdated": "2026-09-06", "count": 126, "topPick": { "slug": "frontend-design", "name": "frontend-design", "score": 92, "tagline": "Escape generic AI-generated UIs. Forces a bold, distinctive design direction before any code is written.", "url": "https://top-agent-skills.com/skill/frontend-design" }, "ranking": [ { "rank": 1, "slug": "frontend-design", "name": "frontend-design", "score": 92, "tagline": "Escape generic AI-generated UIs. Forces a bold, distinctive design direction before any code is written.", "bestFor": "Greenfield landing pages, marketing sites, and any UI that should feel intentional rather than templated.", "notIdealFor": "Ports of an existing design system — frontend-design pushes a bold direction that may overwrite established tokens.", "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "claude-ai", "claude-api", "cursor", "codex", "gemini-cli", "antigravity" ], "install": "npx skills add github.com/anthropics/skills --skill frontend-design", "url": "https://top-agent-skills.com/skill/frontend-design", "json": "https://top-agent-skills.com/skill/frontend-design.json" }, { "rank": 2, "slug": "docling", "name": "docling", "score": 66, "tagline": "One skill covering every document format the category exists for — including scanned PDFs and RAG chunking — from the maintainers of the parser itself.", "bestFor": "Reading or converting documents the agent cannot open directly, at 65K stars and MIT: scanned PDFs, Office formats, tables, and chunking a corpus for retrieval.", "notIdealFor": "Producing polished Office files. Docling is a reader and converter — for generating a styled DOCX, XLSX or PPTX, the Anthropic document skills are the better fit.", "provenance": "verified-org", "publisher": "Docling project (LF AI & Data)", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "pip install docling && uvx library-skills --claude", "url": "https://top-agent-skills.com/skill/docling", "json": "https://top-agent-skills.com/skill/docling.json" }, { "rank": 3, "slug": "hyperframes", "name": "hyperframes", "score": 64, "tagline": "Write HTML, render video. Agent-native, deterministic, no build step.", "bestFor": "Programmatic video an agent can iterate on — release clips, motion graphics, captioned explainers.", "notIdealFor": "Generative video from a text prompt; that is a model API, not a renderer.", "provenance": "verified-org", "publisher": "HeyGen", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "npx skills add heygen-com/hyperframes --skill hyperframes", "url": "https://top-agent-skills.com/skill/hyperframes", "json": "https://top-agent-skills.com/skill/hyperframes.json" }, { "rank": 4, "slug": "superpowers", "name": "superpowers", "score": 61, "tagline": "Structured multi-step development. Brainstorm → spec → plan → build → review → merge — TDD baked in.", "bestFor": "Long-running engineering tasks where you want each phase to handoff cleanly.", "notIdealFor": "Quick one-shot tasks — the orchestration overhead is not worth it.", "provenance": "community", "publisher": "obra", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add obra/superpowers", "url": "https://top-agent-skills.com/skill/superpowers", "json": "https://top-agent-skills.com/skill/superpowers.json" }, { "rank": 5, "slug": "firebase-hosting", "name": "firebase-hosting-basics", "score": 61, "tagline": "Firebase-authored. Init, configure, and one-step deploy to Firebase Hosting / App Hosting.", "bestFor": "Web apps already in the Google/Firebase ecosystem (Firestore, Auth) that want the agent to handle hosting setup and the deploy step without leaving chat.", "notIdealFor": "Static-only sites with no Firebase dependency — a generic static host (Pages, Netlify) is simpler and avoids the Firebase project requirement.", "provenance": "verified-org", "publisher": "Firebase (Google)", "license": "Apache-2.0", "compatibility": [ "claude-code", "cursor", "codex", "gemini-cli", "antigravity" ], "install": "claude plugin marketplace add firebase/agent-skills", "url": "https://top-agent-skills.com/skill/firebase-hosting", "json": "https://top-agent-skills.com/skill/firebase-hosting.json" }, { "rank": 6, "slug": "zeabur-agent-skills", "name": "zeabur-agent-skills", "score": 61, "tagline": "Deploy and register the domain in the same session — Zeabur is its own registrar, so both are one CLI.", "bestFor": "Shipping a service and buying the domain it will live on in one flow, without a separate registrar account.", "notIdealFor": "Domains outside Zeabur's nine supported TLDs (.com, .net, .org, .io, .dev, .app, .co, .me, .xyz), or DNS for zones registered elsewhere.", "provenance": "verified-org", "publisher": "Zeabur", "license": "MIT", "compatibility": [ "claude-code", "codex" ], "install": "npx skills add zeabur/agent-skills --skill zeabur-domain-register --yes", "url": "https://top-agent-skills.com/skill/zeabur-agent-skills", "json": "https://top-agent-skills.com/skill/zeabur-agent-skills.json" }, { "rank": 7, "slug": "playwright-cli", "name": "playwright-cli", "score": 60, "tagline": "Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required.", "bestFor": "Driving a real browser from the agent and working with an existing Playwright suite — navigation, assertions, tracing, video, request mocking, and test generation.", "notIdealFor": "Hosted scraping at scale. It drives a local browser, so rate limiting and anti-bot handling are your problem — reach for a hosted extraction skill when the target fights back.", "provenance": "verified-org", "publisher": "Microsoft", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "playwright-cli install --skills", "url": "https://top-agent-skills.com/skill/playwright-cli", "json": "https://top-agent-skills.com/skill/playwright-cli.json" }, { "rank": 8, "slug": "stripe-best-practices", "name": "stripe-best-practices", "score": 59, "tagline": "Stripe's own integration playbook: pick the right API, set up Connect and billing, and handle keys and webhooks securely.", "bestFor": "Building, modifying, or reviewing any Stripe integration — payments, marketplaces, subscriptions, secure key management.", "notIdealFor": "Non-Stripe payment processors (Adyen, Braintree, PayPal) — the rules are Stripe-specific.", "provenance": "verified-org", "publisher": "Stripe", "license": "MIT", "compatibility": [ "claude-code", "cursor", "gemini-cli" ], "install": "/plugin marketplace add stripe/ai", "url": "https://top-agent-skills.com/skill/stripe-best-practices", "json": "https://top-agent-skills.com/skill/stripe-best-practices.json" }, { "rank": 9, "slug": "stripe-projects", "name": "stripe-projects", "score": 59, "tagline": "Provision a Postgres, Redis, auth, or LLM provider through the Stripe Projects catalog rather than signing up by hand.", "bestFor": "Letting an agent provision and wire up cloud services (DB, cache, auth, email, model providers) with credentials returned inline.", "notIdealFor": "Teams that must provision through their own IaC (Terraform, Pulumi) or a locked-down cloud account.", "provenance": "verified-org", "publisher": "Stripe", "license": "MIT", "compatibility": [ "claude-code", "cursor", "gemini-cli" ], "install": "/plugin marketplace add stripe/ai", "url": "https://top-agent-skills.com/skill/stripe-projects", "json": "https://top-agent-skills.com/skill/stripe-projects.json" }, { "rank": 10, "slug": "resend-email", "name": "resend", "score": 59, "tagline": "Resend's own API skill: send transactional and batch email, handle inbound webhooks, and manage domains, templates, and keys.", "bestFor": "Wiring Resend into an app — transactional sends, batch sends, inbound webhook handling, and domain/template/key management.", "notIdealFor": "Non-Resend providers (SendGrid, Postmark, SES) — the SDK calls and webhook signatures are Resend-specific.", "provenance": "verified-org", "publisher": "Resend", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add resend/resend-skills", "url": "https://top-agent-skills.com/skill/resend-email", "json": "https://top-agent-skills.com/skill/resend-email.json" }, { "rank": 11, "slug": "email-best-practices", "name": "email-best-practices", "score": 59, "tagline": "Resend's deliverability playbook: SPF/DKIM/DMARC, spam avoidance, bounce handling, and CAN-SPAM/GDPR/CASL compliance.", "bestFor": "Diagnosing deliverability problems and setting up authentication, compliance, and accessible markup before email goes to production.", "notIdealFor": "Writing the campaign copy itself — pair it with a copywriting skill like email-sequence for the words.", "provenance": "verified-org", "publisher": "Resend", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add resend/resend-skills", "url": "https://top-agent-skills.com/skill/email-best-practices", "json": "https://top-agent-skills.com/skill/email-best-practices.json" }, { "rank": 12, "slug": "react-email", "name": "react-email", "score": 59, "tagline": "Build cross-client HTML emails as React components, with a visual editor and Resend-ready rendering.", "bestFor": "Authoring transactional email templates (welcome, reset, receipt, notification) as type-safe React components that render across email clients.", "notIdealFor": "Plain-text-only sends or teams not using React — the value is the React Email component model.", "provenance": "verified-org", "publisher": "Resend", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add resend/resend-skills", "url": "https://top-agent-skills.com/skill/react-email", "json": "https://top-agent-skills.com/skill/react-email.json" }, { "rank": 13, "slug": "agent-email-inbox", "name": "agent-email-inbox", "score": 59, "tagline": "Give an agent a webhook-driven inbox with the sender-allowlist and content-filtering patterns that block prompt injection from inbound email.", "bestFor": "Letting an agent receive and act on email safely — support triage, email-to-task pipelines, automated replies with content-safety guards.", "notIdealFor": "Outbound-only sending — use the resend skill; this one is about securely processing inbound mail.", "provenance": "verified-org", "publisher": "Resend", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add resend/resend-skills", "url": "https://top-agent-skills.com/skill/agent-email-inbox", "json": "https://top-agent-skills.com/skill/agent-email-inbox.json" }, { "rank": 14, "slug": "azure-resource-visualizer", "name": "azure-resource-visualizer", "score": 59, "tagline": "Diagrams generated from live infrastructure rather than from a prompt — it reads the actual resource group and draws what is really there.", "bestFor": "Documenting an Azure estate you inherited, where the useful diagram is the one that matches reality rather than the one in the original design doc.", "notIdealFor": "Any cloud that is not Azure, and any diagram of a system that does not exist yet — it reads deployed resources, so there is nothing to read before you deploy.", "provenance": "verified-org", "publisher": "Microsoft", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add microsoft/skills --skill azure-resource-visualizer", "url": "https://top-agent-skills.com/skill/azure-resource-visualizer", "json": "https://top-agent-skills.com/skill/azure-resource-visualizer.json" }, { "rank": 15, "slug": "azure-document-translation", "name": "azure-ai-translation-document-py", "score": 59, "tagline": "Batch document translation that preserves layout — the part that breaks when you translate a PDF by extracting text and re-flowing it.", "bestFor": "Translating a corpus of Word, PDF, Excel or PowerPoint files where the formatting has to survive the round trip.", "notIdealFor": "A single short document, or anything that cannot leave your infrastructure — it is a cloud batch service with Azure credentials attached.", "provenance": "verified-org", "publisher": "Microsoft", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add microsoft/skills --skill azure-ai-translation-document-py", "url": "https://top-agent-skills.com/skill/azure-document-translation", "json": "https://top-agent-skills.com/skill/azure-document-translation.json" }, { "rank": 16, "slug": "browserbase-browser", "name": "browser", "score": 58, "tagline": "Local browser with no credentials, or a hosted Browserbase session with CAPTCHA solving and residential proxies when the target is protected.", "bestFor": "Sites that resist automation. The local mode works with zero setup; the remote mode adds verified browsers, CAPTCHA handling, and proxies for pages that block plain headless traffic.", "notIdealFor": "Licence-strict procurement. The repository has no LICENSE file — MIT is declared only in the skill frontmatter, so confirm that is sufficient for your compliance rules before adopting it.", "provenance": "verified-org", "publisher": "Browserbase", "license": "MIT (declared in SKILL.md frontmatter; no repo LICENSE file)", "compatibility": [ "claude-code" ], "install": "npx skills add browserbase/skills", "url": "https://top-agent-skills.com/skill/browserbase-browser", "json": "https://top-agent-skills.com/skill/browserbase-browser.json" }, { "rank": 17, "slug": "browserbase-ui-test", "name": "ui-test", "score": 58, "tagline": "Diff-aware adversarial QA: it reads the git diff and tests only what changed, across correctness, accessibility, layout and UX.", "bestFor": "QA on a pull request, where testing the whole app is too slow and testing nothing is what actually happens.", "notIdealFor": "Deterministic regression suites. It explores and spawns sub-agents with step budgets, so results vary between runs — use it alongside a fixed suite, not instead of one.", "provenance": "verified-org", "publisher": "Browserbase", "license": "MIT (declared in SKILL.md frontmatter; no repo LICENSE file)", "compatibility": [ "claude-code" ], "install": "npx skills add browserbase/skills", "url": "https://top-agent-skills.com/skill/browserbase-ui-test", "json": "https://top-agent-skills.com/skill/browserbase-ui-test.json" }, { "rank": 18, "slug": "stripe-connect-recommend", "name": "connect-recommend", "score": 58, "tagline": "The marketplace architecture decision, made with a compatibility matrix that blocks invalid Connect configurations instead of describing them.", "bestFor": "Choosing a Stripe Connect charge pattern and account type before you build — the decision that is expensive to reverse once money is flowing.", "notIdealFor": "Writing the integration. This produces a recommendation document; stripe-payments is the implementation skill once the design is settled.", "provenance": "verified-org", "publisher": "Stripe", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add stripe/ai --skill connect-recommend", "url": "https://top-agent-skills.com/skill/stripe-connect-recommend", "json": "https://top-agent-skills.com/skill/stripe-connect-recommend.json" }, { "rank": 19, "slug": "drawio-diagram-generator", "name": "drawio", "score": 58, "tagline": "The only vendor-official skill from a major diagramming product — and it emits editable .drawio files rather than a throwaway image.", "bestFor": "Producing a diagram someone will later edit. Output is native .drawio XML (or an app.diagrams.net link), so the diagram stays maintainable instead of becoming a screenshot.", "notIdealFor": "Diagrams that must live inside Markdown. Mermaid stays in the file; .drawio is a separate artefact, which is the trade for editability.", "provenance": "verified-org", "publisher": "draw.io (JGraph)", "license": "Apache-2.0", "compatibility": [ "claude-code", "codex" ], "install": "/plugin marketplace add jgraph/drawio-mcp", "url": "https://top-agent-skills.com/skill/drawio-diagram-generator", "json": "https://top-agent-skills.com/skill/drawio-diagram-generator.json" }, { "rank": 20, "slug": "upgrade-stripe", "name": "upgrade-stripe", "score": 57, "tagline": "Stripe's version-upgrade guide: move API versions and SDKs without breaking your integration.", "bestFor": "Migrating a Stripe integration to a newer API version or SDK with a clear backward-compatibility map.", "notIdealFor": "Greenfield integrations with no existing Stripe version to upgrade from — start with stripe-best-practices.", "provenance": "verified-org", "publisher": "Stripe", "license": "MIT", "compatibility": [ "claude-code", "cursor", "gemini-cli" ], "install": "/plugin marketplace add stripe/ai", "url": "https://top-agent-skills.com/skill/upgrade-stripe", "json": "https://top-agent-skills.com/skill/upgrade-stripe.json" }, { "rank": 21, "slug": "stripe-link-checkout", "name": "create-payment-credential", "score": 57, "tagline": "Stripe's answer to agentic checkout: one-time payment credentials so an agent can buy without ever seeing the underlying card.", "bestFor": "Letting an agent complete a real purchase on a merchant site, with the human approving each transaction and the real credentials never exposed.", "notIdealFor": "Anything resembling a sandbox. This spends real money on live merchant sites — treat it as a production capability with a human in the loop, never as a dev-time convenience.", "provenance": "verified-org", "publisher": "Stripe", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add stripe/link-cli --skill create-payment-credential", "url": "https://top-agent-skills.com/skill/stripe-link-checkout", "json": "https://top-agent-skills.com/skill/stripe-link-checkout.json" }, { "rank": 22, "slug": "hostinger-agent-skills", "name": "hostinger-agent-skills", "score": 57, "tagline": "The registrar half of the stack: buy the domain, set the DNS, stand up the site — from one plugin.", "bestFor": "Registering a domain and pointing its DNS at a site without leaving the terminal, on an account you already own.", "notIdealFor": "Anyone not hosting at Hostinger — every endpoint is Hostinger-account-scoped, so it manages your portfolio there and nothing else.", "provenance": "verified-org", "publisher": "Hostinger", "license": "MIT", "compatibility": [ "claude-code", "codex" ], "install": "npx skills add hostinger/hostinger-agent-skills --skill domains --yes", "url": "https://top-agent-skills.com/skill/hostinger-agent-skills", "json": "https://top-agent-skills.com/skill/hostinger-agent-skills.json" }, { "rank": 23, "slug": "chrome-devtools", "name": "chrome-devtools", "score": 57, "tagline": "Chrome's own team, giving agents the DevTools protocol: drive it, inspect it, debug it.", "bestFor": "Debugging a live page — performance, accessibility, memory, or why a flow breaks in a real browser.", "notIdealFor": "Large-scale scraping of blocked sites; that is what the proxy-based scraping skills exist for.", "provenance": "verified-org", "publisher": "Chrome DevTools (Google)", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add ChromeDevTools/chrome-devtools-mcp", "url": "https://top-agent-skills.com/skill/chrome-devtools", "json": "https://top-agent-skills.com/skill/chrome-devtools.json" }, { "rank": 24, "slug": "hookdeck-webhook-skills", "name": "webhook-skills", "score": 56, "tagline": "Hookdeck's webhook playbook: 40 provider-specific skills covering signature verification, idempotency, and event handling — each with runnable examples.", "bestFor": "Building a webhook receiver for a specific provider with correct signature verification, idempotency, and retry handling — the part most teams get subtly wrong.", "notIdealFor": "Outbound API consumption or OAuth flows — this is receiver-side webhook handling, not a general REST client.", "provenance": "verified-org", "publisher": "Hookdeck", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add github.com/hookdeck/webhook-skills --skill stripe-webhooks", "url": "https://top-agent-skills.com/skill/hookdeck-webhook-skills", "json": "https://top-agent-skills.com/skill/hookdeck-webhook-skills.json" }, { "rank": 25, "slug": "dbhub", "name": "dbhub", "score": 56, "tagline": "One skill across Postgres, MySQL, SQL Server, MariaDB and SQLite — and its actual job is forcing explore-before-query on real schemas.", "bestFor": "Querying an unfamiliar production-shaped schema, where the agent guessing table and column names is the failure you are trying to prevent.", "notIdealFor": "Setups without MCP. It requires the DBHub MCP server plus a DSN, and it can execute SQL — so scope the connection to a read-only role unless writes are the point.", "provenance": "verified-org", "publisher": "Bytebase", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx @bytebase/dbhub@latest --transport http --port 8080 --dsn \"postgres://user:password@localhost:5432/dbname\"", "url": "https://top-agent-skills.com/skill/dbhub", "json": "https://top-agent-skills.com/skill/dbhub.json" }, { "rank": 26, "slug": "azure-content-understanding", "name": "azure-ai-contentunderstanding-py", "score": 56, "tagline": "Multimodal extraction across documents, images, audio and video through one Azure client — Microsoft-authored, with an explicit trigger list.", "bestFor": "Teams already on Azure that need structured extraction from mixed media, not just PDFs — the case where a single-format parser leaves half the corpus unread.", "notIdealFor": "Local or offline processing. It teaches an agent to write correct Azure SDK code, so it needs Azure credentials and sends content to the service.", "provenance": "verified-org", "publisher": "Microsoft", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add microsoft/skills --skill azure-ai-contentunderstanding-py", "url": "https://top-agent-skills.com/skill/azure-content-understanding", "json": "https://top-agent-skills.com/skill/azure-content-understanding.json" }, { "rank": 27, "slug": "elevenlabs-speech-to-text", "name": "speech-to-text", "score": 56, "tagline": "Transcription and subtitle generation as a first-class skill — the media job agents are asked for most and could not previously do well.", "bestFor": "Turning recorded audio or video into text you can act on: subtitles, meeting notes, or a searchable transcript of a media archive.", "notIdealFor": "Confidential audio that cannot leave your infrastructure — it is a hosted API, so the audio is uploaded.", "provenance": "verified-org", "publisher": "ElevenLabs", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add elevenlabs/skills --skill speech-to-text", "url": "https://top-agent-skills.com/skill/elevenlabs-speech-to-text", "json": "https://top-agent-skills.com/skill/elevenlabs-speech-to-text.json" }, { "rank": 28, "slug": "composio", "name": "composio", "score": 55, "tagline": "1,000+ SaaS integrations as one skill. OAuth lifecycle, scoped credentials, structured actions.", "bestFor": "Any agent that needs to act on real SaaS systems — Slack, Notion, GitHub, Stripe, Salesforce.", "notIdealFor": "Read-only research where MCPs would be lighter.", "provenance": "verified-org", "publisher": "Composio", "license": "Apache-2.0", "compatibility": [ "claude-code", "claude-ai", "claude-api", "cursor", "codex", "gemini-cli", "antigravity" ], "install": "npx skills add composiohq/skills", "url": "https://top-agent-skills.com/skill/composio", "json": "https://top-agent-skills.com/skill/composio.json" }, { "rank": 29, "slug": "postgres-aiguide", "name": "postgres", "score": 55, "tagline": "The generalist Postgres skill the ecosystem was missing — schema, indexing, extensions and migrations, from a Postgres company.", "bestFor": "Any Postgres decision where the default answer is wrong: choosing between B-tree and GIN, partitioning a large table, or picking an index type for pgvector at your data size.", "notIdealFor": "MySQL or SQL Server work. It is Postgres-specific by design, including the extension ecosystem (pgvector, PostGIS, TimescaleDB) that makes Postgres advice non-transferable.", "provenance": "verified-org", "publisher": "TigerData (Timescale)", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "npx skills add timescale/pg-aiguide --skill postgres", "url": "https://top-agent-skills.com/skill/postgres-aiguide", "json": "https://top-agent-skills.com/skill/postgres-aiguide.json" }, { "rank": 30, "slug": "postgres-migrations", "name": "postgres-database-migration", "score": 55, "tagline": "Zero-downtime Postgres migrations, with the locking behaviour spelled out — which ALTER TABLE takes an AccessExclusiveLock and what to do instead.", "bestFor": "A schema change on a live table where the failure mode is a lock that takes production down, not a syntax error.", "notIdealFor": "Greenfield schemas with no data and no traffic — the whole value here is in the constraints that only exist once a table is live.", "provenance": "verified-org", "publisher": "TigerData (Timescale)", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "npx skills add timescale/pg-aiguide --skill postgres-database-migration", "url": "https://top-agent-skills.com/skill/postgres-migrations", "json": "https://top-agent-skills.com/skill/postgres-migrations.json" }, { "rank": 31, "slug": "postgres-table-design", "name": "design-postgres-tables", "score": 55, "tagline": "Schema design decisions made explicitly: data types, key strategy, JSONB versus columns, and when partitioning earns its complexity.", "bestFor": "Designing a new schema, or reviewing one before it accumulates the data that makes changing it expensive.", "notIdealFor": "Applying a migration to an existing live table — reach for the migration skill instead, which covers the locking behaviour this one does not.", "provenance": "verified-org", "publisher": "TigerData (Timescale)", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "npx skills add timescale/pg-aiguide --skill design-postgres-tables", "url": "https://top-agent-skills.com/skill/postgres-table-design", "json": "https://top-agent-skills.com/skill/postgres-table-design.json" }, { "rank": 32, "slug": "qdrant-advisor", "name": "qdrant-advisor", "score": 55, "tagline": "A self-updating vector-database skill: it fetches current Qdrant guidance at run time instead of shipping a snapshot that rots.", "bestFor": "Diagnosing a Qdrant deployment that is slow, memory-hungry, or returning poor results — the failure modes where stale advice is worse than none.", "notIdealFor": "Air-gapped environments. It needs network access to skills.qdrant.tech to load current guidance, which is exactly the design that keeps it fresh.", "provenance": "verified-org", "publisher": "Qdrant", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "npx skills add qdrant/skills/meta/qdrant-advisor", "url": "https://top-agent-skills.com/skill/qdrant-advisor", "json": "https://top-agent-skills.com/skill/qdrant-advisor.json" }, { "rank": 33, "slug": "composio-tool-router", "name": "composio", "score": 54, "tagline": "Composio's official skill for connecting agents to 1000+ external apps: auth configs, per-user connections, tool execution, and triggers.", "bestFor": "Building a multi-user agent or app that needs per-user OAuth connections to many third-party services (Gmail, Slack, GitHub, Notion) without hand-rolling each integration.", "notIdealFor": "A single, deep integration with one provider — a provider-specific skill (e.g. the Stripe or Twilio skills) gives sharper, vendor-authored guidance than a broad tool router.", "provenance": "verified-org", "publisher": "Composio", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add composiohq/skills", "url": "https://top-agent-skills.com/skill/composio-tool-router", "json": "https://top-agent-skills.com/skill/composio-tool-router.json" }, { "rank": 34, "slug": "dodo-payments-skills", "name": "dodo-payments-skills", "score": 54, "tagline": "The deepest MoR skill coverage after Stripe: 17 skills from checkout to go-live.", "bestFor": "SaaS and digital-product teams integrating a merchant of record with usage- or credit-based billing models.", "notIdealFor": "Card-processing-only setups where you keep merchant-of-record duties yourself — that is Stripe territory.", "provenance": "verified-org", "publisher": "Dodo Payments", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add dodopayments/skills --skill checkout-integration", "url": "https://top-agent-skills.com/skill/dodo-payments-skills", "json": "https://top-agent-skills.com/skill/dodo-payments-skills.json" }, { "rank": 35, "slug": "loops-skills", "name": "loops-skills", "score": 54, "tagline": "SaaS email as skills: Loops API, CLI, LMX markup, deliverability practice.", "bestFor": "Product teams on Loops automating contacts, events, transactional sends, and campaign content from code or agents.", "notIdealFor": "High-volume raw SMTP or non-Loops stacks — this is platform-specific by design.", "provenance": "verified-org", "publisher": "Loops", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add loops-so/skills --skill loops-api", "url": "https://top-agent-skills.com/skill/loops-skills", "json": "https://top-agent-skills.com/skill/loops-skills.json" }, { "rank": 36, "slug": "workos", "name": "workos", "score": 54, "tagline": "Full-stack WorkOS implementation with auth provider migration paths.", "bestFor": "Adding WorkOS auth to a new app, or migrating from Auth0/Clerk/Cognito/Firebase/Supabase/Stytch/Descope/Better Auth.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "Built into Claude Code. Invoke with /workos.", "url": "https://top-agent-skills.com/skill/workos", "json": "https://top-agent-skills.com/skill/workos.json" }, { "rank": 37, "slug": "workos-widgets", "name": "workos-widgets", "score": 54, "tagline": "Drop-in WorkOS widgets with backend token wiring across every major framework.", "bestFor": "Embedding WorkOS user-management UI in an existing app without rebuilding auth screens.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "Built into Claude Code. Invoke with /workos-widgets.", "url": "https://top-agent-skills.com/skill/workos-widgets", "json": "https://top-agent-skills.com/skill/workos-widgets.json" }, { "rank": 38, "slug": "paddle-agent-skills", "name": "paddle-agent-skills", "score": 53, "tagline": "Paddle's own integration playbook: ten skills for Checkout, webhooks, pricing pages, and subscription lifecycle on the merchant-of-record platform.", "bestFor": "Building or reviewing a Paddle Billing integration — catalog, Checkout, webhooks, customer portal, and subscription upgrade/downgrade/cancel — where Paddle handles payments, tax, and compliance as merchant of record.", "notIdealFor": "Paddle Classic (these skills target Paddle Billing only) and non-Paddle processors such as Stripe or Lemon Squeezy.", "provenance": "verified-org", "publisher": "Paddle", "license": "Apache-2.0", "compatibility": [ "claude-code", "codex", "cursor", "gemini-cli" ], "install": "/plugin marketplace add PaddleHQ/paddle-agent-skills", "url": "https://top-agent-skills.com/skill/paddle-agent-skills", "json": "https://top-agent-skills.com/skill/paddle-agent-skills.json" }, { "rank": 39, "slug": "twilio-skills", "name": "twilio", "score": 53, "tagline": "Twilio's official Developer Kit: 55 skills across SMS, WhatsApp, Voice, Verify, SendGrid, and compliance — plus the Twilio MCP. Public beta.", "bestFor": "Wiring Twilio messaging or voice into an app — SMS/WhatsApp sends, verification flows, and the A2P 10DLC compliance setup most teams skip until it blocks them.", "notIdealFor": "Production-critical work that needs a support SLA — the kit is Public Beta, not covered by Twilio Support Terms or SLA, and some features are unimplemented. For transactional email alone, the focused Resend skill is lighter.", "provenance": "verified-org", "publisher": "Twilio", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "/plugin marketplace add twilio/ai", "url": "https://top-agent-skills.com/skill/twilio-skills", "json": "https://top-agent-skills.com/skill/twilio-skills.json" }, { "rank": 40, "slug": "turso-db", "name": "turso-db", "score": 53, "tagline": "The SQLite slot, filled by Turso — and unusually, a skill that actively steers the agent off the stale API surface web search returns.", "bestFor": "Building on Turso or embedded SQLite where the agent would otherwise reach for the deprecated @libsql/client API that dominates search results.", "notIdealFor": "Managed Turso Cloud concerns — provisioning, JWT and fine-grained tokens live in the separate turso-cloud skill.", "provenance": "verified-org", "publisher": "Turso", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add tursodatabase/agent-skills --skill turso-db", "url": "https://top-agent-skills.com/skill/turso-db", "json": "https://top-agent-skills.com/skill/turso-db.json" }, { "rank": 41, "slug": "liteparse", "name": "liteparse", "score": 53, "tagline": "Local document extraction with no API key — read the file, not the whole file.", "bestFor": "Looking up a figure or table inside a large document without burning context on the parts you do not need.", "notIdealFor": "Complex layout reconstruction or scanned-image OCR — the hosted llamaparse skill in the same repo is the heavier option for that.", "provenance": "verified-org", "publisher": "LlamaIndex", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add run-llama/llamaparse-agent-skills --skill liteparse", "url": "https://top-agent-skills.com/skill/liteparse", "json": "https://top-agent-skills.com/skill/liteparse.json" }, { "rank": 42, "slug": "box-for-ai", "name": "box", "score": 53, "tagline": "Box as an agent surface, plus the contract-review workflows nothing else in the catalog covers.", "bestFor": "Teams whose documents already live in Box, especially contract review and diligence over files stored there.", "notIdealFor": "Anyone not on Box — every skill routes through Box auth and its MCP or CLI.", "provenance": "verified-org", "publisher": "Box", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add box/box-for-ai --skill box", "url": "https://top-agent-skills.com/skill/box-for-ai", "json": "https://top-agent-skills.com/skill/box-for-ai.json" }, { "rank": 43, "slug": "web-artifacts-builder", "name": "web-artifacts-builder", "score": 52, "tagline": "Self-contained HTML artifacts with React + shadcn/ui — no build step, just paste and run.", "bestFor": "Demos, prototypes, and one-off interactive artifacts.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "claude-ai", "claude-api", "cursor", "codex" ], "install": "npx skills add github.com/anthropics/skills --skill web-artifacts-builder", "url": "https://top-agent-skills.com/skill/web-artifacts-builder", "json": "https://top-agent-skills.com/skill/web-artifacts-builder.json" }, { "rank": 44, "slug": "semgrep-scan", "name": "semgrep", "score": 52, "tagline": "Semgrep's own scanning skill: run the industry-standard SAST engine across 30+ languages, and author custom rules for your codebase's patterns.", "bestFor": "Pattern-based vulnerability scanning across a polyglot codebase, and writing custom YAML rules to enforce a house convention the linter cannot express.", "notIdealFor": "Teams that need a permissive licence. This ships under the Semgrep Rules License v1.0, not MIT or Apache — read it before vendoring the rules into a commercial product.", "provenance": "verified-org", "publisher": "Semgrep", "license": "Semgrep Rules License v1.0", "compatibility": [ "claude-code" ], "install": "npx skills add semgrep/skills", "url": "https://top-agent-skills.com/skill/semgrep-scan", "json": "https://top-agent-skills.com/skill/semgrep-scan.json" }, { "rank": 45, "slug": "semgrep-code-security", "name": "code-security", "score": 52, "tagline": "A vendor-maintained rule corpus for secure code review — one reference file per vulnerability class, from SQL injection to Terraform misconfiguration.", "bestFor": "Secure-code review with real depth behind each finding: the skill ships separate references for SQL injection, XSS, SSRF, XXE, CSRF, secrets, regex DoS, memory safety, Docker, Kubernetes, and Terraform on AWS and GCP.", "notIdealFor": "Running an actual scan — this is guidance, not a scanner. Pair it with the semgrep skill when you need findings rather than review standards.", "provenance": "verified-org", "publisher": "Semgrep", "license": "Semgrep Rules License v1.0", "compatibility": [ "claude-code" ], "install": "npx skills add semgrep/skills", "url": "https://top-agent-skills.com/skill/semgrep-code-security", "json": "https://top-agent-skills.com/skill/semgrep-code-security.json" }, { "rank": 46, "slug": "weaviate-skill", "name": "weaviate", "score": 52, "tagline": "The vector-database skill that ships executable scripts rather than prose — the agent runs the query instead of describing it.", "bestFor": "Actually operating a Weaviate instance from the agent: creating collections, importing files, and running semantic, keyword, and hybrid queries.", "notIdealFor": "Read-only exploration with no credentials. It needs WEAVIATE_URL, an API key, and a vectorizer provider key, and it creates collections and imports data — so point it at a scratch instance first.", "provenance": "verified-org", "publisher": "Weaviate", "license": "BSD-3-Clause", "compatibility": [ "claude-code" ], "install": "npx skills add weaviate/agent-skills --skill weaviate", "url": "https://top-agent-skills.com/skill/weaviate-skill", "json": "https://top-agent-skills.com/skill/weaviate-skill.json" }, { "rank": 47, "slug": "accessibility-review", "name": "accessibility-review", "score": 52, "tagline": "Pre-handoff a11y audit that catches what design QA misses.", "bestFor": "Reviewing a design or live page against WCAG 2.1 AA before engineering handoff or production deploy.", "notIdealFor": "Replacing manual screen-reader testing with assistive tech in real environments.", "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "claude-ai", "claude-api", "cursor", "codex", "antigravity" ], "install": "claude plugin install design", "url": "https://top-agent-skills.com/skill/accessibility-review", "json": "https://top-agent-skills.com/skill/accessibility-review.json" }, { "rank": 48, "slug": "supabase-skill", "name": "supabase-skill", "score": 51, "tagline": "Supabase done right. RLS policies, edge functions, realtime, auth — in idiomatic patterns.", "bestFor": "Teams on Supabase who want the agent to write RLS-correct queries by default.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Supabase", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add supabase/agent-skills", "url": "https://top-agent-skills.com/skill/supabase-skill", "json": "https://top-agent-skills.com/skill/supabase-skill.json" }, { "rank": 49, "slug": "neon-postgres", "name": "neon-postgres", "score": 51, "tagline": "Neon serverless Postgres done right — branching, pooling, and scale-to-zero, from Neon.", "bestFor": "Teams on Neon who want the agent to use branch-per-PR databases and Neon-native connection handling by default.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Neon", "license": "Apache-2.0", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add neondatabase/agent-skills", "url": "https://top-agent-skills.com/skill/neon-postgres", "json": "https://top-agent-skills.com/skill/neon-postgres.json" }, { "rank": 50, "slug": "stripe-payments", "name": "stripe-payments", "score": 51, "tagline": "Stripe done right. Checkout, subscriptions, webhooks, idempotency, metered billing.", "bestFor": "Teams adding Stripe where webhook handling and idempotency are easy to get wrong.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Stripe", "license": "MIT", "compatibility": [ "claude-code", "claude-api", "cursor", "codex" ], "install": "npx skills add stripe/skills", "url": "https://top-agent-skills.com/skill/stripe-payments", "json": "https://top-agent-skills.com/skill/stripe-payments.json" }, { "rank": 51, "slug": "shopify-storefront", "name": "shopify-storefront", "score": 51, "tagline": "Shopify Storefront API: cart, checkout, metafields, customer accounts, Hydrogen patterns.", "bestFor": "Headless Shopify storefronts where you want the agent to build commerce flows correctly.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Shopify", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add shopify/skills", "url": "https://top-agent-skills.com/skill/shopify-storefront", "json": "https://top-agent-skills.com/skill/shopify-storefront.json" }, { "rank": 52, "slug": "slack-block-kit", "name": "block-kit", "score": 51, "tagline": "Slack's own Block Kit skill — and the rare vendor skill that needs no token, because it validates against Slack's public API.", "bestFor": "Composing Slack messages, modals and Home tabs where hand-written Block Kit JSON is the thing that keeps breaking — it validates output against Slack rather than guessing.", "notIdealFor": "Actually sending the message. It generates and validates layouts; delivery is the sibling slack-api skill, which does need a token.", "provenance": "verified-org", "publisher": "Slack Technologies", "license": "MIT", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add slackapi/slack-skills-plugin", "url": "https://top-agent-skills.com/skill/slack-block-kit", "json": "https://top-agent-skills.com/skill/slack-block-kit.json" }, { "rank": 53, "slug": "openai-visualize-data", "name": "visualize-data", "score": 51, "tagline": "OpenAI's chart-design skill: the judgement layer that decides which chart the question actually needs before any plotting code is written.", "bestFor": "Getting a chart that answers the question rather than one that displays the data — chart-type choice, encoding, and a QA pass on a figure you already have.", "notIdealFor": "Library-specific implementation help. It carries visual judgement, not D3 or Vega syntax, so pair it with a plotting library skill when the code is the hard part.", "provenance": "verified-org", "publisher": "OpenAI", "license": "MIT", "compatibility": [ "codex" ], "install": "npx skills add openai/role-specific-plugins --skill openai-visualize-data", "url": "https://top-agent-skills.com/skill/openai-visualize-data", "json": "https://top-agent-skills.com/skill/openai-visualize-data.json" }, { "rank": 54, "slug": "openai-build-dashboard", "name": "build-dashboard", "score": 51, "tagline": "Dashboards with source definitions and a QA step — the parts that separate a monitoring view from a wall of charts nobody trusts.", "bestFor": "A dashboard people will make decisions from, where every metric needs a stated definition and source rather than an unexplained number.", "notIdealFor": "One-off exploratory charts. The structure it imposes — metric definitions, filters, QA — is overhead when you are just looking at data once.", "provenance": "verified-org", "publisher": "OpenAI", "license": "MIT", "compatibility": [ "codex" ], "install": "npx skills add openai/role-specific-plugins --skill openai-build-dashboard", "url": "https://top-agent-skills.com/skill/openai-build-dashboard", "json": "https://top-agent-skills.com/skill/openai-build-dashboard.json" }, { "rank": 55, "slug": "railway-skills", "name": "railway-skills", "score": 51, "tagline": "All of Railway in one skill: provision, deploy, debug — listed in the official plugin marketplace.", "bestFor": "Deploying and operating full-stack apps and databases on Railway without touching the dashboard.", "notIdealFor": "Teams not on Railway — the skill assumes the Railway CLI and an authenticated account.", "provenance": "verified-org", "publisher": "Railway", "license": "MIT", "compatibility": [ "claude-code" ], "install": "/plugin install railway@claude-plugins-official", "url": "https://top-agent-skills.com/skill/railway-skills", "json": "https://top-agent-skills.com/skill/railway-skills.json" }, { "rank": 56, "slug": "architecture-adr", "name": "architecture", "score": 51, "tagline": "ADR authoring + design review. Trade-offs, consequences, alternatives.", "bestFor": "Choosing between technologies, documenting a design decision, or reviewing a proposal.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/architecture-adr", "json": "https://top-agent-skills.com/skill/architecture-adr.json" }, { "rank": 57, "slug": "debug", "name": "debug", "score": 51, "tagline": "Disciplined debugging loop. Reproduce, isolate, diagnose, fix.", "bestFor": "When behavior diverges from expected and the cause is not obvious from a quick read.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/debug", "json": "https://top-agent-skills.com/skill/debug.json" }, { "rank": 58, "slug": "deploy-checklist", "name": "deploy-checklist", "score": 51, "tagline": "The pre-ship checklist that catches the embarrassing stuff.", "bestFor": "Shipping a release with migrations, feature flags, or anything that needs a documented rollback path.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/deploy-checklist", "json": "https://top-agent-skills.com/skill/deploy-checklist.json" }, { "rank": 59, "slug": "documentation", "name": "documentation", "score": 51, "tagline": "Technical writing that engineers will actually read and update.", "bestFor": "Writing the docs nobody on the team has time to write but everyone needs.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/documentation", "json": "https://top-agent-skills.com/skill/documentation.json" }, { "rank": 60, "slug": "incident-response", "name": "incident-response", "score": 51, "tagline": "Incident triage + comms + blameless postmortem in one harness.", "bestFor": "Active production incidents and the postmortem afterward.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/incident-response", "json": "https://top-agent-skills.com/skill/incident-response.json" }, { "rank": 61, "slug": "system-design", "name": "system-design", "score": 51, "tagline": "System design from requirements. APIs, data, boundaries, scale.", "bestFor": "Greenfield service design or designing a new feature that crosses service boundaries.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/system-design", "json": "https://top-agent-skills.com/skill/system-design.json" }, { "rank": 62, "slug": "tech-debt", "name": "tech-debt", "score": 51, "tagline": "Honest tech-debt audit with a prioritized cleanup backlog.", "bestFor": "Quarterly planning, post-incident review, or any moment the team agrees something has to give.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/tech-debt", "json": "https://top-agent-skills.com/skill/tech-debt.json" }, { "rank": 63, "slug": "testing-strategy", "name": "testing-strategy", "score": 51, "tagline": "Layered test plan sized to the change's risk profile.", "bestFor": "Greenfield features when you need a real plan before writing the first test.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex", "antigravity" ], "install": "claude plugin install engineering", "url": "https://top-agent-skills.com/skill/testing-strategy", "json": "https://top-agent-skills.com/skill/testing-strategy.json" }, { "rank": 64, "slug": "webapp-testing", "name": "webapp-testing", "score": 50, "tagline": "Test local webapps with Playwright. Generation, run, report — end-to-end.", "bestFor": "Filling test gaps in a webapp, smoke-testing UIs after a change.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add github.com/anthropics/skills --skill webapp-testing", "url": "https://top-agent-skills.com/skill/webapp-testing", "json": "https://top-agent-skills.com/skill/webapp-testing.json" }, { "rank": 65, "slug": "simplify", "name": "simplify", "score": 50, "tagline": "Review for reuse, quality, efficiency. Catches over-abstraction and dead code before merge.", "bestFor": "Pre-merge review pass on a feature branch.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "Bundled with Claude Code by default — invoke with /simplify.", "url": "https://top-agent-skills.com/skill/simplify", "json": "https://top-agent-skills.com/skill/simplify.json" }, { "rank": 66, "slug": "gitguardian-secret-scanning", "name": "scan-secrets", "score": 50, "tagline": "GitGuardian's own secret-detection skill — scans history, images and packages, and ships a written remediation doctrine rather than just a list of hits.", "bestFor": "Catching a credential before it reaches a remote, and knowing what to do about one already committed — the bundled doctrine covers rotation triggers and history rewriting, not just detection.", "notIdealFor": "Zero-setup use. It requires the ggshield CLI and an authenticated GitGuardian account, and the skill explicitly forbids substituting the GitGuardian MCP scan tool for the CLI.", "provenance": "verified-org", "publisher": "GitGuardian", "license": "MIT", "compatibility": [ "claude-code", "codex" ], "install": "/plugin marketplace add GitGuardian/agent-skills", "url": "https://top-agent-skills.com/skill/gitguardian-secret-scanning", "json": "https://top-agent-skills.com/skill/gitguardian-secret-scanning.json" }, { "rank": 67, "slug": "postmark-skills", "name": "postmark-skills", "score": 50, "tagline": "Transactional email the Postmark way: send, inbound, templates, webhooks.", "bestFor": "Teams on Postmark wiring transactional sends, inbound processing, and template management from an agent.", "notIdealFor": "Marketing broadcast campaigns — Postmark is transactional-first; last upstream commit is Feb 2026, so check freshness against API changes.", "provenance": "verified-org", "publisher": "ActiveCampaign (Postmark)", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add ActiveCampaign/postmark-skills --skill postmark", "url": "https://top-agent-skills.com/skill/postmark-skills", "json": "https://top-agent-skills.com/skill/postmark-skills.json" }, { "rank": 68, "slug": "verify", "name": "verify", "score": 50, "tagline": "Real feature verification — run the app, drive it, prove it works.", "bestFor": "Pre-merge verification for UI changes when type checks and unit tests verify code, not feature correctness.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "Built into Claude Code. Invoke with /verify.", "url": "https://top-agent-skills.com/skill/verify", "json": "https://top-agent-skills.com/skill/verify.json" }, { "rank": 69, "slug": "setup-cowork", "name": "setup-cowork", "score": 50, "tagline": "Bootstrap the right plugin stack for your role in one guided pass.", "bestFor": "New teams onboarding to Claude Code or Cowork who want a role-fitted plugin bundle.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "antigravity" ], "install": "Built into Claude Code. Invoke with /setup-cowork.", "url": "https://top-agent-skills.com/skill/setup-cowork", "json": "https://top-agent-skills.com/skill/setup-cowork.json" }, { "rank": 70, "slug": "vercel-web-design-guidelines", "name": "vercel-web-design-guidelines", "score": 49, "tagline": "100+ accessibility and UX rules from Vercel, applied as a structural audit on your UI code.", "bestFor": "Pre-PR audits, accessibility compliance, design system enforcement.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Vercel", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add github.com/vercel-labs/agent-skills --skill web-design-guidelines", "url": "https://top-agent-skills.com/skill/vercel-web-design-guidelines", "json": "https://top-agent-skills.com/skill/vercel-web-design-guidelines.json" }, { "rank": 71, "slug": "vercel-react-best-practices", "name": "vercel-react-best-practices", "score": 49, "tagline": "57 React/Next.js performance rules, applied as a structural review on your code.", "bestFor": "Performance reviews on React/Next.js codebases.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Vercel", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add github.com/vercel-labs/agent-skills --skill vercel-react-best-practices", "url": "https://top-agent-skills.com/skill/vercel-react-best-practices", "json": "https://top-agent-skills.com/skill/vercel-react-best-practices.json" }, { "rank": 72, "slug": "trail-of-bits", "name": "trail-of-bits", "score": 49, "tagline": "Security audits run by a real security firm. CodeQL + Semgrep + audit workflows.", "bestFor": "Pre-release vulnerability scans, ongoing security review.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Trail of Bits", "license": "Apache-2.0", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add trailofbits/skills", "url": "https://top-agent-skills.com/skill/trail-of-bits", "json": "https://top-agent-skills.com/skill/trail-of-bits.json" }, { "rank": 73, "slug": "planetscale-skills", "name": "planetscale-skills", "score": 49, "tagline": "PlanetScale's schema branching and index-aware queries, packaged for agents.", "bestFor": "Teams already on PlanetScale who want migrations to feel like Git.", "notIdealFor": null, "provenance": "verified-org", "publisher": "PlanetScale", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add planetscale/skills", "url": "https://top-agent-skills.com/skill/planetscale-skills", "json": "https://top-agent-skills.com/skill/planetscale-skills.json" }, { "rank": 74, "slug": "shadcn-context", "name": "shadcn-context", "score": 49, "tagline": "shadcn/ui context: components, patterns, and the right composition by default.", "bestFor": "Teams using shadcn/ui who want the agent to honor component conventions.", "notIdealFor": null, "provenance": "verified-org", "publisher": "shadcn", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add shadcn/ui", "url": "https://top-agent-skills.com/skill/shadcn-context", "json": "https://top-agent-skills.com/skill/shadcn-context.json" }, { "rank": 75, "slug": "prisma-orm", "name": "prisma-orm", "score": 49, "tagline": "Prisma migrations and queries by the book. Index-aware, migration-safe, type-correct.", "bestFor": "TypeScript backends on Prisma where schema migrations should be reviewable and safe.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Prisma", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add prisma/skills", "url": "https://top-agent-skills.com/skill/prisma-orm", "json": "https://top-agent-skills.com/skill/prisma-orm.json" }, { "rank": 76, "slug": "next-js-app-router", "name": "next-js-app-router", "score": 49, "tagline": "Next.js App Router by the book. Server components, streaming, parallel routes.", "bestFor": "Next.js 13+ teams that want App Router patterns idiomatic and not Pages-Router-flavored.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Vercel", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add github.com/vercel-labs/agent-skills --skill next-js-app-router", "url": "https://top-agent-skills.com/skill/next-js-app-router", "json": "https://top-agent-skills.com/skill/next-js-app-router.json" }, { "rank": 77, "slug": "notion-api-skill", "name": "notion-api-skill", "score": 49, "tagline": "Notion API: page/database CRUD, block hierarchies, rich text, schema sync.", "bestFor": "Teams using Notion as a CMS or knowledge base where the agent needs to read and write.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Notion", "license": "MIT", "compatibility": [ "claude-code", "claude-api", "cursor", "codex" ], "install": "npx skills add makenotion/skills", "url": "https://top-agent-skills.com/skill/notion-api-skill", "json": "https://top-agent-skills.com/skill/notion-api-skill.json" }, { "rank": 78, "slug": "vercel-deploy-claimable", "name": "vercel-deploy-claimable", "score": 49, "tagline": "Ship to a live Vercel URL from chat — auto-detects the framework, returns a claim link.", "bestFor": "Quickly getting a prototype onto a live URL from a conversation, then claiming it into your own Vercel account when you want to keep it.", "notIdealFor": "Teams that need a deploy tied to an existing project, CI pipeline, or custom domain on the first deploy — the claim flow assumes a fresh, transferable deploy.", "provenance": "verified-org", "publisher": "Vercel", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add github.com/vercel-labs/agent-skills --skill vercel-deploy-claimable", "url": "https://top-agent-skills.com/skill/vercel-deploy-claimable", "json": "https://top-agent-skills.com/skill/vercel-deploy-claimable.json" }, { "rank": 79, "slug": "owasp-security-skills", "name": "code-review-security", "score": 49, "tagline": "OWASP-published review, SCA, secrets and threat-modelling skills — the most citable provenance available for security review vocabulary.", "bestFor": "Pre-merge security gates mapped to a standard a reviewer can cite, and threat modelling multi-agent systems against the OWASP Multi-Agentic guide and CSA MAESTRO layers.", "notIdealFor": "Vendoring into a product. The bundle is CC-BY-4.0 — a content licence, not a software licence — so check your obligations before redistributing the rules.", "provenance": "verified-org", "publisher": "OWASP Foundation", "license": "CC-BY-4.0", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add OWASP/secure-agent-playbook", "url": "https://top-agent-skills.com/skill/owasp-security-skills", "json": "https://top-agent-skills.com/skill/owasp-security-skills.json" }, { "rank": 80, "slug": "knock-notifications", "name": "knock-notification-best-practices", "score": 49, "tagline": "The multi-channel notification slot nothing else covers: push, in-app and chat alongside email, with copy guidance per channel. No credentials required.", "bestFor": "Designing a notification system rather than a single send — which channel carries what, how the copy differs per channel, and when to batch or digest.", "notIdealFor": "Sending anything. This is guidance only; the sibling knock-setup skill handles workflows and requires the Knock MCP server and an API key.", "provenance": "verified-org", "publisher": "Knock", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add knocklabs/skills --skill knock-notification-best-practices", "url": "https://top-agent-skills.com/skill/knock-notifications", "json": "https://top-agent-skills.com/skill/knock-notifications.json" }, { "rank": 81, "slug": "mapbox-data-visualization", "name": "mapbox-data-visualization-patterns", "score": 49, "tagline": "The geospatial gap, filled by the vendor that defines it: data on a map, done properly.", "bestFor": "Any visualization where location is the dimension that matters, and the dataset is large enough to need tuning.", "notIdealFor": "Charts and diagrams — this is cartography, not a plotting library.", "provenance": "verified-org", "publisher": "Mapbox", "license": "MIT", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add mapbox/mapbox-agent-skills", "url": "https://top-agent-skills.com/skill/mapbox-data-visualization", "json": "https://top-agent-skills.com/skill/mapbox-data-visualization.json" }, { "rank": 82, "slug": "design-handoff", "name": "design-handoff", "score": 49, "tagline": "Turn a final design into a spec engineers can implement directly.", "bestFor": "The moment a design is approved and engineering needs implementation-ready specs.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "claude-ai", "cursor", "antigravity" ], "install": "claude plugin install design", "url": "https://top-agent-skills.com/skill/design-handoff", "json": "https://top-agent-skills.com/skill/design-handoff.json" }, { "rank": 83, "slug": "design-system", "name": "design-system", "score": 49, "tagline": "Design-system hygiene at speed. Audit, document, extend.", "bestFor": "Teams maintaining a real design system that has grown organically.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "cursor", "antigravity" ], "install": "claude plugin install design", "url": "https://top-agent-skills.com/skill/design-system", "json": "https://top-agent-skills.com/skill/design-system.json" }, { "rank": 84, "slug": "mcp-builder", "name": "mcp-builder", "score": 48, "tagline": "Build new MCP servers. The official scaffold + design walkthrough.", "bestFor": "When you need a new MCP and want it built right.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add github.com/anthropics/skills --skill mcp-builder", "url": "https://top-agent-skills.com/skill/mcp-builder", "json": "https://top-agent-skills.com/skill/mcp-builder.json" }, { "rank": 85, "slug": "claude-api", "name": "claude-api", "score": 48, "tagline": "Always-current Claude API reference and SDK docs. Bundled with Claude Code.", "bestFor": "Building Claude API apps that should not lag the docs.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Bundled with Claude Code by default. To re-install: npx skills add github.com/anthropics/skills --skill claude-api", "url": "https://top-agent-skills.com/skill/claude-api", "json": "https://top-agent-skills.com/skill/claude-api.json" }, { "rank": 86, "slug": "internal-comms", "name": "internal-comms", "score": 48, "tagline": "Internal comms that read consistent. Newsletters, status reports, FAQs, updates.", "bestFor": "Recurring internal comms — weekly updates, all-hands prep, FAQ pages.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code", "claude-ai" ], "install": "npx skills add github.com/anthropics/skills --skill internal-comms", "url": "https://top-agent-skills.com/skill/internal-comms", "json": "https://top-agent-skills.com/skill/internal-comms.json" }, { "rank": 87, "slug": "sentry-error-handling", "name": "sentry-error-handling", "score": 48, "tagline": "Sentry the right way. Source maps, releases, breadcrumbs, performance, structured tags.", "bestFor": "Teams adding or improving error monitoring with Sentry.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Sentry", "license": "Apache-2.0", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "/plugin marketplace add getsentry/skills", "url": "https://top-agent-skills.com/skill/sentry-error-handling", "json": "https://top-agent-skills.com/skill/sentry-error-handling.json" }, { "rank": 88, "slug": "snyk-fix", "name": "snyk-fix", "score": 48, "tagline": "The remediation half of security work: scan, fix, validate the fix, open the PR. Batch mode handles a whole backlog of CVEs in one pass.", "bestFor": "Closing the loop from finding to validated fix to pull request, rather than producing another list of vulnerabilities nobody has time to triage.", "notIdealFor": "Environments without Snyk. It requires the Snyk MCP server and an authenticated account, plus the GitHub CLI for PR creation — and it edits files, so review its diffs like any other agent-authored change.", "provenance": "verified-org", "publisher": "Snyk", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "curl -fsSL 'https://raw.githubusercontent.com/snyk/studio-recipes/main/installer/dist/snyk-studio-install.sh' -o snyk-studio-install.sh", "url": "https://top-agent-skills.com/skill/snyk-fix", "json": "https://top-agent-skills.com/skill/snyk-fix.json" }, { "rank": 89, "slug": "pretty-mermaid", "name": "pretty-mermaid", "score": 48, "tagline": "Actually renders Mermaid to SVG or ASCII instead of emitting text and hoping something downstream draws it. Bundles the render scripts.", "bestFor": "Turning Mermaid source into a finished SVG or a terminal-friendly ASCII diagram, with themes applied and batches handled in one pass.", "notIdealFor": "Anything needing a recent upstream. This is community-maintained and its last release predates most of the current agent tooling — useful, but not actively tracking the ecosystem.", "provenance": "community", "publisher": "imxv", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add https://github.com/imxv/pretty-mermaid-skills --skill pretty-mermaid", "url": "https://top-agent-skills.com/skill/pretty-mermaid", "json": "https://top-agent-skills.com/skill/pretty-mermaid.json" }, { "rank": 90, "slug": "markdown-exporter", "name": "markdown-exporter", "score": 48, "tagline": "The widest format matrix of any conversion skill we catalogue, and it executes the conversion rather than describing it.", "bestFor": "Turning agent-authored Markdown into whatever format the recipient actually needs — a deck, a spreadsheet, a PDF — without hand-writing a converter each time.", "notIdealFor": "Reliable auto-triggering. Its description is a bare capability list with no trigger phrasing, so it often needs to be invoked by name rather than firing on its own.", "provenance": "community", "publisher": "bowenliang123", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add bowenliang123/markdown-exporter", "url": "https://top-agent-skills.com/skill/markdown-exporter", "json": "https://top-agent-skills.com/skill/markdown-exporter.json" }, { "rank": 91, "slug": "brightdata-skills", "name": "brightdata", "score": 48, "tagline": "The anti-bot problem, handled: proxies, SERP, and structured extraction at scale.", "bestFor": "Price comparison, competitive intelligence, and RAG pipelines over sites that fight scrapers.", "notIdealFor": "Simple public-page fetching, where a crawl-to-markdown skill is lighter and free.", "provenance": "verified-org", "publisher": "Bright Data", "license": "MIT", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add brightdata/skills", "url": "https://top-agent-skills.com/skill/brightdata-skills", "json": "https://top-agent-skills.com/skill/brightdata-skills.json" }, { "rank": 92, "slug": "run", "name": "run", "score": 48, "tagline": "One-command app launch tailored to your project type.", "bestFor": "Confirming a change works in the real app rather than only in tests.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /run.", "url": "https://top-agent-skills.com/skill/run", "json": "https://top-agent-skills.com/skill/run.json" }, { "rank": 93, "slug": "security-review", "name": "security-review", "score": 48, "tagline": "Pre-merge security sweep on the current branch's diff.", "bestFor": "Every PR before merge — catches the mechanical security issues a hurried human review misses.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /security-review.", "url": "https://top-agent-skills.com/skill/security-review", "json": "https://top-agent-skills.com/skill/security-review.json" }, { "rank": 94, "slug": "code-review-builtin", "name": "code-review", "score": 48, "tagline": "The canonical Anthropic code review. Effort levels from quick to ultra.", "bestFor": "Every change before merge, with effort sized to the change's risk.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /code-review.", "url": "https://top-agent-skills.com/skill/code-review-builtin", "json": "https://top-agent-skills.com/skill/code-review-builtin.json" }, { "rank": 95, "slug": "init-skill", "name": "init", "score": 48, "tagline": "Bootstrap a CLAUDE.md so future sessions start informed.", "bestFor": "First time using Claude Code on a project — gives the agent the context it needs.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /init.", "url": "https://top-agent-skills.com/skill/init-skill", "json": "https://top-agent-skills.com/skill/init-skill.json" }, { "rank": 96, "slug": "review-pr", "name": "review", "score": 48, "tagline": "PR review with inline GitHub comments via gh.", "bestFor": "Reviewing teammates' PRs without leaving the terminal.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /review.", "url": "https://top-agent-skills.com/skill/review-pr", "json": "https://top-agent-skills.com/skill/review-pr.json" }, { "rank": 97, "slug": "update-config", "name": "update-config", "score": 48, "tagline": "Edit settings.json safely. Hooks, perms, env, behaviors.", "bestFor": "Setting up hooks, managing permissions, and any \"from now on, when X\" automation.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /update-config.", "url": "https://top-agent-skills.com/skill/update-config", "json": "https://top-agent-skills.com/skill/update-config.json" }, { "rank": 98, "slug": "keybindings-help", "name": "keybindings-help", "score": 48, "tagline": "Rebind keys and add chords without reading the keymap docs.", "bestFor": "Customizing Claude Code keyboard shortcuts to your existing terminal muscle memory.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /keybindings-help.", "url": "https://top-agent-skills.com/skill/keybindings-help", "json": "https://top-agent-skills.com/skill/keybindings-help.json" }, { "rank": 99, "slug": "fewer-permission-prompts", "name": "fewer-permission-prompts", "score": 48, "tagline": "Cuts the permission-prompt friction by learning your safe-tool patterns.", "bestFor": "Teams running Claude Code daily and tired of approving the same read-only commands.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /fewer-permission-prompts.", "url": "https://top-agent-skills.com/skill/fewer-permission-prompts", "json": "https://top-agent-skills.com/skill/fewer-permission-prompts.json" }, { "rank": 100, "slug": "loop", "name": "loop", "score": 48, "tagline": "Recurring task runner. Self-paced or interval-based.", "bestFor": "Polling for status, monitoring a deploy, repeating a check at intervals.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /loop.", "url": "https://top-agent-skills.com/skill/loop", "json": "https://top-agent-skills.com/skill/loop.json" }, { "rank": 101, "slug": "schedule", "name": "schedule", "score": 48, "tagline": "Cron for remote Claude Code agents. Set it and forget it.", "bestFor": "Automated daily/weekly tasks — standup, status reports, monitoring, batch jobs.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Built into Claude Code. Invoke with /schedule.", "url": "https://top-agent-skills.com/skill/schedule", "json": "https://top-agent-skills.com/skill/schedule.json" }, { "rank": 102, "slug": "composition-patterns", "name": "composition-patterns", "score": 47, "tagline": "Boolean prop hell → compound components. Cleaner React component APIs by construction.", "bestFor": "Component library refactoring, API design improvements.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Vercel", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add github.com/vercel-labs/agent-skills --skill composition-patterns", "url": "https://top-agent-skills.com/skill/composition-patterns", "json": "https://top-agent-skills.com/skill/composition-patterns.json" }, { "rank": 103, "slug": "expo-skills", "name": "expo-skills", "score": 47, "tagline": "Expo workflows: navigation, EAS, OTA, native modules.", "bestFor": "React Native + Expo teams.", "notIdealFor": null, "provenance": "verified-org", "publisher": "Expo", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add expo/skills", "url": "https://top-agent-skills.com/skill/expo-skills", "json": "https://top-agent-skills.com/skill/expo-skills.json" }, { "rank": 104, "slug": "paypal-ai-toolkit", "name": "paypal-ai-toolkit", "score": 47, "tagline": "The largest payment processor, first-party: checkout to disputes to payouts.", "bestFor": "Building or auditing PayPal integrations — checkout flows, subscriptions, invoicing, and webhook handling with vendor-canonical guidance.", "notIdealFor": "Non-PayPal processors — for Stripe use the Stripe official skills already in this category.", "provenance": "verified-org", "publisher": "PayPal", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "/plugin install paypal@claude-plugins-official", "url": "https://top-agent-skills.com/skill/paypal-ai-toolkit", "json": "https://top-agent-skills.com/skill/paypal-ai-toolkit.json" }, { "rank": 105, "slug": "tdd-skill", "name": "tdd-skill", "score": 46, "tagline": "TDD with red/green/refactor as a concrete TypeScript walkthrough.", "bestFor": "New features with clear requirements, bug fixes, complex business logic.", "notIdealFor": "UI layout changes, simple CRUD, exploratory code.", "provenance": "community", "publisher": "obra", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "npx skills add obra/superpowers --skill tdd", "url": "https://top-agent-skills.com/skill/tdd-skill", "json": "https://top-agent-skills.com/skill/tdd-skill.json" }, { "rank": 106, "slug": "duckdb-skills", "name": "duckdb-skills", "score": 46, "tagline": "In-process analytical SQL over CSV, Parquet, and Excel — no warehouse, no server.", "bestFor": "Ad-hoc analytics over local data files (CSV, Parquet, JSON, Excel) where standing up a warehouse is overkill.", "notIdealFor": "High-concurrency transactional workloads — DuckDB is an analytical (OLAP) engine, not an OLTP database.", "provenance": "verified-org", "publisher": "DuckDB", "license": "MIT", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add duckdb/duckdb-skills", "url": "https://top-agent-skills.com/skill/duckdb-skills", "json": "https://top-agent-skills.com/skill/duckdb-skills.json" }, { "rank": 107, "slug": "netlify-deploy", "name": "netlify-deploy", "score": 46, "tagline": "Netlify-authored deploy flow. Auth, site linking, Deploy Previews, production promotes.", "bestFor": "Teams shipping static sites and serverless functions to Netlify who want the agent to follow the platform's own deploy and preview conventions.", "notIdealFor": "Bare-metal or VM hosting — this is Netlify-platform-specific and assumes the Netlify CLI.", "provenance": "verified-org", "publisher": "Netlify", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add netlify/context-and-tools --skill netlify-deploy --yes", "url": "https://top-agent-skills.com/skill/netlify-deploy", "json": "https://top-agent-skills.com/skill/netlify-deploy.json" }, { "rank": 108, "slug": "cloudflare-platform", "name": "cloudflare", "score": 46, "tagline": "Cloudflare-authored. Workers and Pages deploys, Wrangler config, KV/D1/R2 from chat.", "bestFor": "Edge-first teams deploying Workers and Pages who want the agent to use Wrangler correctly and follow Cloudflare's own platform patterns.", "notIdealFor": "Projects that never touch the Cloudflare edge — the Skill is Cloudflare-platform-specific.", "provenance": "verified-org", "publisher": "Cloudflare", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add cloudflare/skills", "url": "https://top-agent-skills.com/skill/cloudflare-platform", "json": "https://top-agent-skills.com/skill/cloudflare-platform.json" }, { "rank": 109, "slug": "agentic-seo-skill", "name": "agentic-seo-skill", "score": 46, "tagline": "The heavyweight audit machine: 88 evidence scripts so SEO findings come from data, not vibes.", "bestFor": "Deep site audits where you want reproducible, script-collected evidence behind every SEO finding.", "notIdealFor": "Quick single-page checks — this is a full audit apparatus, not a lint pass.", "provenance": "community", "publisher": "Bhanu Namikaze", "license": "MIT", "compatibility": [ "claude-code" ], "install": "git clone https://github.com/Bhanunamikaze/Agentic-SEO-Skill", "url": "https://top-agent-skills.com/skill/agentic-seo-skill", "json": "https://top-agent-skills.com/skill/agentic-seo-skill.json" }, { "rank": 110, "slug": "carbone-templates", "name": "carbone", "score": 46, "tagline": "Data-driven document generation: one template, a thousand filled documents.", "bestFor": "Invoices, contracts, certificates, and reports produced at volume from structured data and a designed template.", "notIdealFor": "One-off documents — authoring a single file is what the Anthropic docx and xlsx skills are for.", "provenance": "verified-org", "publisher": "Carbone.io", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add carboneio/carbone-skill", "url": "https://top-agent-skills.com/skill/carbone-templates", "json": "https://top-agent-skills.com/skill/carbone-templates.json" }, { "rank": 111, "slug": "code-review-plugin", "name": "code-review-plugin", "score": 45, "tagline": "Structured PR reviews with severity-tagged findings — bugs, security, perf, style.", "bestFor": "Pre-merge review with consistent format that PR comments can quote directly.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "Bundled with Claude Code — invoke with /review.", "url": "https://top-agent-skills.com/skill/code-review-plugin", "json": "https://top-agent-skills.com/skill/code-review-plugin.json" }, { "rank": 112, "slug": "github-pages-deploy", "name": "github-pages", "score": 45, "tagline": "Repo-to-live-URL on GitHub Pages: Actions workflow, custom domain, Jekyll, troubleshoot.", "bestFor": "Free static hosting for docs, portfolios, and project sites straight from a GitHub repo, including apex/subdomain custom-domain setup and Actions-based builds.", "notIdealFor": "Server-rendered apps or anything needing serverless functions — GitHub Pages serves static output only.", "provenance": "community", "publisher": "julianobarbosa", "license": "MIT", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add julianobarbosa/claude-code-skills", "url": "https://top-agent-skills.com/skill/github-pages-deploy", "json": "https://top-agent-skills.com/skill/github-pages-deploy.json" }, { "rank": 113, "slug": "apify-skills", "name": "apify", "score": 45, "tagline": "Run the marketplace's scrapers, or turn your own scraper into a deployable Actor.", "bestFor": "Reaching for an existing scraper instead of writing one, or packaging your own scraper for reuse.", "notIdealFor": "Anything needing a local-only pipeline — Actors run on the Apify platform.", "provenance": "verified-org", "publisher": "Apify", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add apify/apify-claude-code-plugin", "url": "https://top-agent-skills.com/skill/apify-skills", "json": "https://top-agent-skills.com/skill/apify-skills.json" }, { "rank": 114, "slug": "cowork-plugin-customizer", "name": "cowork-plugin-customizer", "score": 45, "tagline": "Tailor a plugin to your org's stack in one pass.", "bestFor": "Teams that have installed a plugin but need it to match their tools, naming and workflows.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "claude plugin install cowork-plugin-management", "url": "https://top-agent-skills.com/skill/cowork-plugin-customizer", "json": "https://top-agent-skills.com/skill/cowork-plugin-customizer.json" }, { "rank": 115, "slug": "create-cowork-plugin", "name": "create-cowork-plugin", "score": 45, "tagline": "Scaffold a new plugin from scratch with guided prompts.", "bestFor": "Engineering leads building org-specific plugins for their team to use in Claude Code.", "notIdealFor": null, "provenance": "anthropic", "publisher": "Anthropic", "license": "MIT", "compatibility": [ "claude-code" ], "install": "claude plugin install cowork-plugin-management", "url": "https://top-agent-skills.com/skill/create-cowork-plugin", "json": "https://top-agent-skills.com/skill/create-cowork-plugin.json" }, { "rank": 116, "slug": "fhir-developer-skill", "name": "fhir-developer-skill", "score": 44, "tagline": "The standalone FHIR skill: modeling, validation, SMART on FHIR — without the full healthcare plugin.", "bestFor": "Developers building against FHIR who want one lean skill instead of the whole Anthropic healthcare plugin.", "notIdealFor": "Clinical coding or prior-auth workflows — this is developer tooling for the FHIR standard itself.", "provenance": "verified-org", "publisher": "PhenoML", "license": "Apache-2.0", "compatibility": [ "claude-code" ], "install": "/plugin marketplace add PhenoML/ClaudeFHIRSkill", "url": "https://top-agent-skills.com/skill/fhir-developer-skill", "json": "https://top-agent-skills.com/skill/fhir-developer-skill.json" }, { "rank": 117, "slug": "render-deploy", "name": "render-deploy", "score": 44, "tagline": "Deploy, debug, and scale on Render: Blueprint generation with validation built in.", "bestFor": "Teams deploying web services and databases on Render who want render.yaml generated and validated from the codebase.", "notIdealFor": "Non-Render stacks; star count is near zero because the repo is weeks old — provenance here is the official org plus Anthropic marketplace listing, not adoption.", "provenance": "verified-org", "publisher": "Render", "license": "MIT", "compatibility": [ "claude-code" ], "install": "/plugin install render@claude-plugins-official", "url": "https://top-agent-skills.com/skill/render-deploy", "json": "https://top-agent-skills.com/skill/render-deploy.json" }, { "rank": 118, "slug": "tufte-charts", "name": "tufte", "score": 44, "tagline": "A named design canon for charts, not another plotting wrapper.", "bestFor": "Charts that will be published or presented, where the default library output looks like the default library output.", "notIdealFor": "Interactive dashboards and live data — this is about how a chart is designed, not how it is served.", "provenance": "community", "publisher": "aref-vc", "license": "MIT", "compatibility": [ "claude-code" ], "install": "git clone https://github.com/aref-vc/tufte-claude-skill.git ~/.claude/skills/tufte", "url": "https://top-agent-skills.com/skill/tufte-charts", "json": "https://top-agent-skills.com/skill/tufte-charts.json" }, { "rank": 119, "slug": "terraform-claude-skill", "name": "terraform-claude-skill", "score": 43, "tagline": "Terraform expertise on tap. State inspection, module validators, safety-first IaC.", "bestFor": "Terraform-heavy infra teams that want fewer foot-guns.", "notIdealFor": null, "provenance": "community", "publisher": "lgbarn", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add lgbarn/devops-skills --skill terraform", "url": "https://top-agent-skills.com/skill/terraform-claude-skill", "json": "https://top-agent-skills.com/skill/terraform-claude-skill.json" }, { "rank": 120, "slug": "devops-engineer", "name": "devops-engineer", "score": 43, "tagline": "Senior DevOps engineer persona — CI/CD, containers, blue-green/canary, IaC across clouds.", "bestFor": "Generalist DevOps work where you want a higher-quality default than the agent gives unprompted.", "notIdealFor": null, "provenance": "community", "publisher": "jeffallan", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add jeffallan/claude-skills --skill devops-engineer", "url": "https://top-agent-skills.com/skill/devops-engineer", "json": "https://top-agent-skills.com/skill/devops-engineer.json" }, { "rank": 121, "slug": "system-architecture-diagrams", "name": "system-architecture-diagrams", "score": 42, "tagline": "C4, deployment, sequence-of-events architecture diagrams generated from natural-language descriptions.", "bestFor": "Engineering reviews, ADRs, onboarding docs.", "notIdealFor": null, "provenance": "community", "publisher": "cheriftj", "license": "MIT", "compatibility": [ "claude-code", "cursor", "codex" ], "install": "/plugin marketplace add cheriftj/c4-model-skill", "url": "https://top-agent-skills.com/skill/system-architecture-diagrams", "json": "https://top-agent-skills.com/skill/system-architecture-diagrams.json" }, { "rank": 122, "slug": "publishing-astro-websites", "name": "publishing-astro-websites", "score": 42, "tagline": "Astro from scaffold to live site — content collections, search, i18n, multi-host deploy.", "bestFor": "Content and docs sites built on Astro that need the agent to handle the full path from project structure to a deployed static build.", "notIdealFor": "Non-Astro stacks, or apps that need server-rendered runtime rather than a static build.", "provenance": "community", "publisher": "SpillwaveSolutions", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add github.com/spillwavesolutions/publishing-astro-websites-agentic-skill", "url": "https://top-agent-skills.com/skill/publishing-astro-websites", "json": "https://top-agent-skills.com/skill/publishing-astro-websites.json" }, { "rank": 123, "slug": "ios-simulator-skill", "name": "ios-simulator-skill", "score": 41, "tagline": "Drive the iOS Simulator from the agent loop. Build and test iOS apps.", "bestFor": "iOS dev where the agent should compile, run, and test in the simulator.", "notIdealFor": null, "provenance": "community", "publisher": "conorluddy", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add conorluddy/ios-simulator-skill", "url": "https://top-agent-skills.com/skill/ios-simulator-skill", "json": "https://top-agent-skills.com/skill/ios-simulator-skill.json" }, { "rank": 124, "slug": "web-asset-generator", "name": "web-asset-generator", "score": 41, "tagline": "Favicons, app icons, social cards — generated at all the right sizes.", "bestFor": "Pre-launch asset generation, social-card production at scale.", "notIdealFor": null, "provenance": "community", "publisher": "alonw0", "license": "MIT", "compatibility": [ "claude-code" ], "install": "npx skills add alonw0/web-asset-generator", "url": "https://top-agent-skills.com/skill/web-asset-generator", "json": "https://top-agent-skills.com/skill/web-asset-generator.json" }, { "rank": 125, "slug": "k8s-security-policies", "name": "k8s-security-policies", "score": 40, "tagline": "Kubernetes hardening by the book. NetworkPolicies, RBAC, OPA, service mesh.", "bestFor": "Hardening k8s clusters before they ship.", "notIdealFor": null, "provenance": "community", "publisher": "jeffallan", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add jeffallan/claude-skills --skill k8s-security-policies", "url": "https://top-agent-skills.com/skill/k8s-security-policies", "json": "https://top-agent-skills.com/skill/k8s-security-policies.json" }, { "rank": 126, "slug": "excalidraw-generator", "name": "excalidraw-generator", "score": 40, "tagline": "Excalidraw JSON diagrams from prose, with rendering self-checks.", "bestFor": "Architecture diagrams, conceptual mappings, whiteboarding outputs.", "notIdealFor": null, "provenance": "community", "publisher": "coleam00", "license": "MIT", "compatibility": [ "claude-code", "cursor" ], "install": "npx skills add coleam00/excalidraw-diagram-skill", "url": "https://top-agent-skills.com/skill/excalidraw-generator", "json": "https://top-agent-skills.com/skill/excalidraw-generator.json" } ], "faqs": [ { "question": "Which Skills ship with Claude Code by default?", "answer": "code-review, simplify, verify, init, security-review, run, and several others. They cover the core engineering loop — review, simplify, verify, init, secure, run." }, { "question": "Are these Skills useful for Cursor and Codex?", "answer": "Most are — the SKILL.md spec was adopted by Cursor, Codex, Gemini CLI and Antigravity in late 2025. Per-Skill compatibility is verified on each skill's page." }, { "question": "Do these Skills work in a monorepo?", "answer": "Most handle monorepos cleanly — they respect workspace boundaries and run scoped to the changed package. A few generic Skills assume single-project layout; their pages flag this." }, { "question": "How do I pick between Opus and Sonnet for engineering Skills?", "answer": "Opus 4.7+ for high-effort review, architecture and complex refactors. Sonnet 4.6 for routine review and quick fixes. Several Skills auto-select based on the work's effort level." }, { "question": "Can I bundle several engineering Skills into a plugin?", "answer": "Yes — Claude Code plugins package multiple Skills together. The plugin-customizer Skill helps tailor a bundle for your org's stack." } ], "license": "https://creativecommons.org/licenses/by/4.0/", "attribution": "Top Agent Skills (https://top-agent-skills.com)" }