GitHub organization
Agent skills by vercel-labs
- skills
- 51
- official
- 51
- repositories
- 13
Repositories by vercel-labs
- vercel-openclaw-archivedOfficialDeploy OpenClaw on Vercel117 stars · 16 skills
- agent-browserOfficialBrowser automation CLI for AI agents44k stars · 10 skills
- openreviewOfficialAn open-source, self-hosted AI code review bot powered by Vercel.1.7k stars · 6 skills
- agent-skillsOfficialVercel's official collection of agent skills32k stars · 4 skills
- dev3000OfficialCaptures your web app's complete development timeline - server logs, browser events, console messages, network requests, and automatic screenshots - in a unified, timestamped feed for AI debugging.1.6k stars · 3 skills
- deepsecOfficialDeepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents8.1k stars · 2 skills
- eve-chat-templateOfficial137 stars · 2 skills
- github-toolsOfficialGitHub tools and agents for the Vercel AI SDK, wrap GitHub's API as AI SDK tools ready to plug into any agent131 stars · 2 skills
- issue-graphOfficialFind related issues, competing changes, and unresolved follow-ups before you start work.125 stars · 2 skills
- ai-factsOfficialReal-time fact checking on spoken statements with the AI SDK, Perplexity and DeepGram168 stars · 1 skill
- autoshipOfficialCLI tool to automate changeset-based releases162 stars · 1 skill
- next-beatsOfficialA Next.js 16.3 music player demo showcasing Instant Navigations with Cache Components and Partial Prefetching.167 stars · 1 skill
- skillsOfficialThe open agent skills tool - npx skills33k stars · 1 skill
Skills by vercel-labs, 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 | today |
| 2 | Explores a web app with the agent-browser CLI to find bugs and UX problems, then writes a report with screenshots, repro videos and step-by-step reproduction for each issue. | vercel-labs/ | 44k | 8 repos | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Rules for structuring React components with composition instead of boolean props, covering compound components, lifted state, variants and React 19 changes. | vercel-labs/ | 1.7k | 58 repos | ~721 | Automated safety check: Pass | MIT | 7 mo ago |
| 4 | Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or… | vercel-labs/ | 1.7k | 98 repos | ~308 | Automated safety check: Pass | No licence | 7 mo ago |
| 5 | A prioritized rule set for React Native and Expo apps covering list performance, animation, navigation, UI patterns, state, rendering, monorepos and configuration. | vercel-labs/ | 1.7k | 17 repos | ~1.1k | Automated safety check: Pass | MIT | 7 mo ago |
| 6 | Automates Electron desktop apps such as VS Code, Slack or Discord by connecting agent-browser to their Chrome DevTools Protocol port. | vercel-labs/ | 44k | 5 repos | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | 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 |
| 8 | 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 |
| 9 | Drives the Slack web app with the agent-browser CLI to check unread channels, search, read channel details and extract information, with screenshots as evidence. | vercel-labs/ | 44k | 1 repo | ~2.1k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | Core usage guide for the agent-browser CLI: the snapshot-and-ref workflow for navigating, clicking, filling forms, extracting data and running parallel sessions. | vercel-labs/ | 44k | 4 repos | ~9.5k | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Guides implementing animated page and state transitions in React with the native View Transition API, covering shared elements, list reorders and directional navigation. | vercel-labs/ | 167 | 10 repos | ~3.1k | Automated safety check: Pass | MIT | 8 days ago |
| 12 | 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 |
| 13 | 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 |
| 14 | 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 |
| 15 | 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 |
| 16 | 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 |
| 17 | Labels a pull request in the skills CLI repo as bug, documentation or enhancement based on its description and patch, leaving existing labels untouched. | vercel-labs/ | 33k | — | ~310 | Automated safety check: Pass | MIT | today |
| 18 | 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 |
| 19 | Records a site's browser traffic into a HAR file, then builds a standalone client or CLI that calls its internal endpoints directly with no browser. | vercel-labs/ | 44k | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 20 | Review docs/prose for Writing Guidelines compliance. An agent skill from vercel-labs/agent-skills. | vercel-labs/ | 32k | 7 repos | ~309 | Automated safety check: Pass | No licence | 1 mo ago |
| 21 | Builds and validates experimental WebMCP tools that expose a web page's real workflows to agents, with a manifest, init script and evals compared against accessibility-tree automation. | vercel-labs/ | 44k | 1 repo | ~752 | Automated safety check: Pass | Apache-2.0 | today |
| 22 | 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 |
| 23 | CLI tool for automated changeset-based releases with AI-generated descriptions. | vercel-labs/ | 162 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 20 days ago |
| 24 | Convert Next.js bundle analyzer data to NDJSON and explore it | vercel-labs/ | 1.6k | — | ~617 | Automated safety check: Pass | MIT | yesterday |
| 25 | Runs agent-browser on cloud browser sessions hosted by AWS Bedrock AgentCore, with credentials taken from the environment or the AWS CLI. | vercel-labs/ | 44k | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
| 26 | 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 |
| 27 | A skill your agent uses when the user asks to use d3k, run/dev/test/debug a web project with d3k, or reproduce a browser issue. | vercel-labs/ | 1.6k | — | ~1.5k | Automated safety check: Warn | MIT | yesterday |
| 28 | 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 |
| 29 | 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 | today |
| 30 | 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 |
| 31 | 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 | today |
| 32 | 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 |
| 33 | 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 |
| 34 | Writing and maintaining lat.md documentation files — structured markdown that describes a project's architecture, design decisions, and test specs. | vercel-labs/ | 117 | 1 repo | ~1.2k | Automated safety check: Pass | MIT | 4 mo ago |
| 35 | Status-first routing, bounded evidence collection, and safety guidance for issue-graph. | vercel-labs/ | 125 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 36 | 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 |
| 37 | 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 |
| 38 | Read-only context for issues, pull requests, and backlogs. An agent skill from vercel-labs/issue-graph. | vercel-labs/ | 125 | — | ~275 | Automated safety check: Pass | Apache-2.0 | 6 days ago |
| 39 | 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 |
| 40 | 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 |
| 41 | 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 |
| 42 | 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 |
| 43 | 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 |
| 44 | 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 |
| 45 | 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 |
| 46 | 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 |
| 47 | Discord channel specialist workflow: debug interaction webhooks, Ed25519 signatures, deferred replies, workflow forwarding to /discord-webhook, integration reconcile, and token expiry. | vercel-labs/ | 117 | — | ~464 | Automated safety check: Pass | MIT | 4 mo ago |
| 48 | Slack channel specialist workflow: debug Slack OAuth vs delivery-ready, /slack/events fast path, raw-body signatures, route repair, boot-message cleanup, and lastForward. | vercel-labs/ | 117 | — | ~484 | Automated safety check: Pass | MIT | 4 mo ago |
Questions, answered from the data.
What is the best skill by vercel-labs?
Agent Browser CLI (official) from vercel-labs/agent-browser ranks first of the 51 skills by vercel-labs 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 Dogfood Exploratory QA and React Composition Patterns.
Are vercel-labs's skills official?
51 of the 51 skills by vercel-labs are official, published by the vendor's own GitHub organization: Agent Browser CLI, Dogfood Exploratory QA, React Composition Patterns, Web Interface Guidelines Reviewer, React Native Best Practices and 46 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.