Cloud platform
Vercel agent skills for Claude Code, Codex and other agents.
- skills
- 284
- official
- 75
- Type
- Cloud platform
- Website
- vercel.com
- Official GitHub
- vercel, vercel-labs
- Reviews
- See Vercel on Enlisted
Vercel skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking… | vercel-labs/ | 44k | 24 repos | ~864 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 2 | Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations. | vercel-labs/ | 32k | 8 repos | ~4.3k | Automated safety check: Pass | No licence | 1 mo ago |
| 3 | Answer questions about the AI SDK and help build AI-powered features. | vercel-labs/ | 168 | 21 repos | ~1.2k | Automated safety check: Pass | No licence | 5 mo ago |
| 4 | Deploys applications to Vercel as previews by default, picking a deploy method from the project's link state, git remote and team. | vercel-labs/ | 32k | 11 repos | ~2.9k | Automated safety check: Notes | No licence | 1 mo ago |
| 5 | React and Next.js performance optimization guidelines from Vercel Engineering. | sanity-io/ | 6.4k | 130 repos | ~1.6k | Automated safety check: Pass | MIT | today |
| 6 | Add existing screenshots or screen recordings to a GitHub pull request as a before/after or preview block. | sanity-io/ | 6.4k | 1 repo | ~2.1k | Automated safety check: Pass | MIT | today |
| 7 | Deploys and manages Vercel projects through the CLI using an access token from the environment or a .env file instead of interactive login. | vercel-labs/ | 32k | 7 repos | ~2.6k | Automated safety check: Notes | No licence | 1 mo ago |
| 8 | Next.js 16 Cache Components - PPR, use cache directive, cacheLife, cacheTag, updateTag | vercel-labs/ | 1.7k | 9 repos | ~2.3k | Automated safety check: Pass | No licence | 7 mo ago |
| 9 | Runs deepsec's AI-powered security scan over a repository's uncommitted changes, its diff to main, or the whole codebase, using a regex pass followed by agent investigation. | vercel-labs/ | 8.1k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 10 | Set up a Codex monitor for Vercel deployments and preview URLs. | remotion-dev/ | 62k | — | ~1.2k | Automated safety check: Pass | Unknown | today |
| 11 | Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling | vercel-labs/ | 1.7k | 18 repos | ~1k | Automated safety check: Pass | No licence | 7 mo ago |
| 12 | Points the agent at deepsec's own docs to answer questions about initializing, configuring, resuming, scanning with and extending the vulnerability scanner. | vercel-labs/ | 8.1k | — | ~956 | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 13 | Upgrade Next.js to the latest version following official migration guides and codemods | vercel-labs/ | 1.7k | 6 repos | ~502 | Automated safety check: Pass | No licence | 7 mo ago |
| 14 | Vercel deployment and CI/CD expert guidance. An agent skill from vercel/vercel-plugin. | vercel/ | 301 | 1 repo | ~3k | Automated safety check: Pass | Unknown | today |
| 15 | Audit vercel-plugin performance on real-world projects. An agent skill from vercel/vercel-plugin. | vercel/ | 301 | — | ~739 | Automated safety check: Pass | Unknown | today |
| 16 | Give an AI agent GitHub access via @github-tools/sdk. An agent skill from vercel-labs/github-tools. | vercel-labs/ | 131 | — | ~2.8k | Automated safety check: Pass | MIT | 8 days ago |
| 17 | Run DeepSec against a Vercel project checkout from dev3000. An agent skill from vercel-labs/dev3000. | vercel-labs/ | 1.6k | — | ~985 | Automated safety check: Notes | MIT | yesterday |
| 18 | Opens Vercel deployments behind Deployment Protection in agent-browser, using a short-lived OIDC token instead of a static bypass secret or a public exception. | vercel-labs/ | 44k | — | ~1.7k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 19 | Vercel CLI expert guidance. An agent skill from vercel/vercel-plugin. | vercel/ | 301 | 1 repo | ~2.5k | Automated safety check: Pass | Unknown | today |
| 20 | Writes, reviews and edits developer documentation for SDKs, libraries and frameworks, from getting-started guides and API references to migration guides. | vercel-labs/ | 131 | — | ~3.9k | Automated safety check: Pass | MIT | 8 days ago |
| 21 | Runs agent-browser with headless Chrome inside Vercel Sandbox microVMs so Vercel-deployed apps can automate a browser without binary size limits. | vercel-labs/ | 44k | — | ~2k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 22 | Apply dashboard-grade chat UX patterns in the Eve chat template. | vercel-labs/ | 137 | — | ~2.1k | Automated safety check: Pass | No licence | 1 mo ago |
| 23 | Channel webhook triage for vercel-openclaw Slack/Telegram/Discord/WhatsApp issues: prove deployment state, collect admin readiness endpoints, build evidence-first handoff before fixes. | vercel-labs/ | 117 | — | ~2k | Automated safety check: Notes | MIT | 4 mo ago |
| 24 | Work safely on eve-specific internals in the eve chat template. | vercel-labs/ | 137 | — | ~1.1k | Automated safety check: Pass | No licence | 1 mo ago |
| 25 | Cron and watchdog debugging for vercel-openclaw: Vercel Cron auth, persisted OpenClaw jobs, cron wake keys, token refresh, restore oracle, hot spare, and watchdog reports. | vercel-labs/ | 117 | — | ~1.6k | Automated safety check: Pass | MIT | 4 mo ago |
| 26 | Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and… | vercel/ | 301 | — | ~4.4k | Automated safety check: Notes | Unknown | today |
| 27 | Configure and troubleshoot Vercel Services for multiple frontends and backends in one project. | vercel/ | 301 | — | ~3k | Automated safety check: Pass | Unknown | today |
| 28 | Deploy applications and websites to Vercel. An agent skill from JetBrains/skills. | JetBrains/ | 363 | 5 repos | ~716 | Automated safety check: Pass | MIT | 3 mo ago |
| 29 | Auth and store debugging for vercel-openclaw: admin-secret mode, Sign in with Vercel, session cookies, CSRF, LOCALREADONLY, Redis vs memory store, keyspace namespacing, and metadata shape migrations. | vercel-labs/ | 117 | — | ~465 | Automated safety check: Pass | MIT | 4 mo ago |
| 30 | Firewall and Vercel AI Gateway debugging for vercel-openclaw: network policy allowlists, OIDC token refresh, AI Gateway transform rules, firewall learning/enforcement, and sandbox.update… | vercel-labs/ | 117 | — | ~550 | Automated safety check: Pass | MIT | 4 mo ago |
| 31 | Access and test Vercel deployments protected by Vercel Authentication, SSO, or Deployment Protection. | vercel/ | 301 | — | ~1.9k | Automated safety check: Notes | Unknown | today |
| 32 | Gateway and proxy debugging for vercel-openclaw: /gateway routing, HTML injection, WebSocket rewrite, gateway-token handoff, waiting page, status heartbeat, sandbox port URL cache, and proxy auth. | vercel-labs/ | 117 | — | ~573 | Automated safety check: Pass | MIT | 4 mo ago |
| 33 | Project bootstrapping orchestrator for repos that depend on Vercel-linked resources (databases, auth, and managed integrations). | vercel/ | 301 | — | ~2.1k | Automated safety check: Notes | Unknown | today |
| 34 | OpenClaw bootstrap, bundle, config, and restore-asset debugging for vercel-openclaw: openclaw.bundle sidecars, plugin discovery, channel catalog, restart scripts, config hashes, dynamic resume… | vercel-labs/ | 117 | — | ~494 | Automated safety check: Pass | MIT | 4 mo ago |
| 35 | Default guidance for building AI agents. An agent skill from vercel/vercel-plugin. | vercel/ | 301 | — | ~1.4k | Automated safety check: Pass | Unknown | today |
| 36 | Sandbox lifecycle debugging for vercel-openclaw: create, resume, stop, snapshotting, reset, stale-running reconciliation, persistent Sandbox v2 behavior, hot spares, and lifecycle locks. | vercel-labs/ | 117 | — | ~809 | Automated safety check: Pass | MIT | 4 mo ago |
| 37 | Emit and query Vercel Custom Metrics. An agent skill from vercel/vercel-plugin. | vercel/ | 301 | — | ~1.6k | Automated safety check: Pass | Unknown | today |
| 38 | Search, register, connect, transfer, and renew domain names on Vercel using the CLI or Domains Registrar API. | vercel/ | 301 | — | ~2.2k | Automated safety check: Pass | Unknown | today |
| 39 | Vercel Sandbox v2 lifecycle expertise for vercel-openclaw: named persistent OpenClaw sandbox create/resume/stop/delete, persistent auto-save truth, manual snapshot diagnostics, short-lived worker… | vercel-labs/ | 117 | — | ~788 | Automated safety check: Pass | MIT | 4 mo ago |
| 40 | Vercel environment variable expert guidance. An agent skill from vercel/vercel-plugin. | vercel/ | 301 | — | ~3k | Automated safety check: Notes | Unknown | today |
| 41 | Vercel Workflow SDK expert guidance. An agent skill from vercel/vercel-plugin. | vercel/ | 301 | 1 repo | ~12k | Automated safety check: Pass | Unknown | today |
| 42 | Admin UI and operator surface debugging for vercel-openclaw: command shell design, admin actions, request core, status panels, launch verification UI, channel readiness UI, and local read-only… | vercel-labs/ | 117 | — | ~404 | Automated safety check: Pass | MIT | 4 mo ago |
| 43 | Use Redis over HTTP from serverless and edge runtimes with @upstash/redis, and add rate limiting with @upstash/ratelimit. | github/ | 40k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 44 | Set up and use feature flags and A/B tests with the Flags SDK (flags npm package) and Vercel Flags. | vercel/ | 301 | — | ~6.9k | Automated safety check: Notes | Unknown | today |
| 45 | Launch verification and remote smoke debugging for vercel-openclaw: preflight, queue ping, ensureRunning, chatCompletions, wakeFromSleep, restorePrepared, channelReadiness, NDJSON progress, and… | vercel-labs/ | 117 | — | ~457 | Automated safety check: Pass | MIT | 4 mo ago |
| 46 | Vercel Queues guidance — durable topics with at-least-once delivery, independent consumer groups, retries, delays, and idempotency keys via @vercel/queue (JS) or vercel-queue (Python). | vercel/ | 301 | — | ~2.4k | Automated safety check: Pass | Unknown | today |
| 47 | Release vercel-plugin — run gates, bump version, generate artifacts, commit, and push. | vercel/ | 301 | — | ~551 | Automated safety check: Pass | Unknown | today |
| 48 | Vercel Routing Middleware guidance — request interception before cache, rewrites, redirects, personalization. | vercel/ | 301 | — | ~2.8k | Automated safety check: Pass | Unknown | today |
Questions, answered from the data.
What is the best Vercel skill?
Agent Browser CLI (official) from vercel-labs/agent-browser ranks first of the 284 Vercel skills listed here, with the highest score: its repository has 44k GitHub stars, 24 other GitHub owners carry a copy, its SKILL.md loads about 864 tokens and it passes the automated safety check with no findings. Next come Vercel Optimize Audit and AI SDK.
Is there an official Vercel skill?
75 of the 284 Vercel skills are official, published by the vendor's own GitHub organization: Agent Browser CLI, Vercel Optimize Audit, AI SDK, Deploy to Vercel, Vercel React Best Practices and 70 more.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.