Vercel Agent Skills
Vercel Labs' official Agent Skills collection for AI coding agents working on Vercel deployments, React and Next.js performance, React Native, web design guidelines, writing guidelines, composition patterns, view transitions, CLI token workflows, and Vercel optimization audits.
Open the source and read safety notes before installing.
Safety notes
- The deploy-to-vercel and Vercel CLI token skills can guide agents toward git pushes, preview deployments, Vercel project linking, environment variable changes, and account-scoped CLI calls; keep human approval on those actions.
- The vercel-cli-with-tokens skill includes token-handling workflows. Prefer environment variables over command-line token flags and avoid echoing secrets into prompts, logs, screenshots, or public PRs.
- The vercel-optimize skill reads Vercel metrics, usage, project configuration, and code scan results; verify the linked project and team scope before collecting or acting on recommendations.
- The web-design-guidelines and writing-guidelines skills fetch current upstream rule documents at use time, so review fetched guidance before treating output as policy.
- React, Next.js, and React Native performance rules are strong defaults, but agents still need local tests, framework-version checks, and product-specific review before broad refactors.
Privacy notes
- Deployment and optimization workflows may expose project names, team slugs, deployment URLs, routes, metrics, usage details, billing signals, source paths, build configuration, environment variable names, and CLI account context.
- Keep VERCEL_TOKEN, VERCEL_ORG_ID, VERCEL_PROJECT_ID, API keys, environment values, claim URLs, deployment logs, and private preview URLs out of public artifacts unless intentionally disclosed.
- Design, writing, React, and performance reviews can reveal proprietary UI, product copy, documentation strategy, source code, routes, and business priorities to the configured model provider.
Prerequisites
- An Agent Skills compatible host or local installer that can install GitHub-hosted skills.
- A Vercel, React, Next.js, React Native, design-review, writing-review, or deployment task where Vercel's guidance applies.
- Vercel CLI and an authenticated account or token only for skills that deploy, inspect, or optimize a Vercel project.
- Explicit approval before an agent commits, pushes, deploys, links a project, modifies environment variables, or runs account-scoped Vercel commands.
Schema details
- Install type
- package
- Reading time
- 7 min
- Difficulty score
- 76
- Troubleshooting
- Yes
- Breaking changes
- No
- Scope
- Source repo
- Skill type
- capability-pack
- Skill level
- expert
- Verification
- validated
- Verified at
- 2026-06-18
| Platform | Support | Install path |
|---|---|---|
| claude-code | Native | .claude/skills/<skill-name>/SKILL.md |
| codex | Native | .agents/skills/<skill-name>/SKILL.md |
| windsurf | Native | .windsurf/skills/<skill-name>/SKILL.md |
| gemini | Native | .gemini/skills/<skill-name>/SKILL.md or .agents/skills/<skill-name>/SKILL.md |
| cursor | Adapter | .cursor/rules/<skill-name>.mdc |
| cli | Manual | AGENTS.md or tool-specific context file |
Full copyable content
npx skills add vercel-labs/agent-skills
# Focused examples when your installer supports --skill
npx skills add vercel-labs/agent-skills --skill vercel-optimize
npx skills add vercel-labs/agent-skills --skill deploy-to-vercel
npx skills add vercel-labs/agent-skills --skill vercel-react-best-practicesAbout this resource
Vercel Agent Skills
vercel-labs/agent-skills is Vercel Labs' official collection of Agent Skills
for AI coding agents. The repository packages reusable instructions and helper
assets for React, Next.js, React Native, Vercel deployment, token-safe Vercel
CLI use, Vercel project optimization, UI review, writing review, composition
patterns, and React view transitions.
Use this listing for the skill collection itself. Use separate Vercel platform, React, or Next.js entries when evaluating a runtime, framework, or service rather than installable agent instructions.
Knowledge Freshness
Vercel platform behavior, CLI flags, deployment flows, Observability features, React and Next.js APIs, React Native patterns, and Vercel's design and writing guidelines can change quickly. The skills are durable workflow instructions, but exact CLI behavior, metrics availability, and framework APIs should be checked against current docs, installed tool versions, and fetched guideline sources before implementation.
For Vercel optimization tasks, verify the linked project, team scope, Vercel CLI version, and metric availability before collecting data or recommending changes. For web and writing reviews, fetch the current upstream guideline documents referenced by those skills.
Retrieval Sources
This listing is grounded in:
- The upstream
vercel-labs/agent-skillsREADME. - The
skills.sh.jsongrouping manifest. - Representative
SKILL.mdfiles forvercel-optimize,vercel-react-best-practices,deploy-to-vercel,vercel-cli-with-tokens,web-design-guidelines, andwriting-guidelines. - The public skills.sh listing for the collection.
- Current GitHub repository metadata.
Core Workflow
Install the full skill collection:
npx skills add vercel-labs/agent-skills
When your installer supports focused installs, choose the task-specific skill:
npx skills add vercel-labs/agent-skills --skill vercel-optimize
npx skills add vercel-labs/agent-skills --skill deploy-to-vercel
npx skills add vercel-labs/agent-skills --skill vercel-react-best-practices
Then invoke the relevant skill by task:
Review this Next.js page with Vercel React best practices.
Audit this linked Vercel project for cost and performance issues.
Deploy this app to Vercel as a preview after I approve the push/deploy step.
Capability Scope
The README and manifest describe these skill areas:
| Area | Example Skills |
|---|---|
| React and Next.js | vercel-react-best-practices, vercel-composition-patterns, vercel-react-view-transitions |
| Vercel platform | vercel-optimize, deploy-to-vercel, vercel-cli-with-tokens |
| Interface quality | web-design-guidelines |
| Documentation and prose | writing-guidelines |
| Mobile apps | vercel-react-native-skills |
The collection can help an agent review performance rules, structure UI components, run Vercel optimization audits, choose a safe deployment path, and apply Vercel writing or interface standards. It does not provide account credentials, replace Vercel support, guarantee current API behavior, or remove the need for user approval before writes, pushes, deploys, or billing-relevant project actions.
Production Rules
- Confirm the Vercel project and team scope before linking, deploying, reading metrics, or applying account-level changes.
- Never put Vercel tokens in command-line flags, public logs, committed files, screenshots, or PR bodies.
- Treat git pushes, project linking, production deploys, environment-variable changes, and billing or usage recommendations as approval-gated actions.
- Verify React, Next.js, React Native, and Vercel CLI versions before applying large performance or deployment refactors.
- Fetch current web-design and writing guideline sources before using those review skills as policy.
- Run local tests, preview builds, or deployment checks before treating an agent-guided change as production-ready.
Use Cases
- Ask Claude Code or Codex to review a React component against Vercel's performance guidance.
- Have an agent run a Vercel optimization audit that starts from metrics rather than repo-wide guessing.
- Use token-safe Vercel CLI guidance in non-interactive CI or remote coding environments.
- Ask an agent to deploy a preview while keeping production deploys and git pushes behind explicit approval.
- Review UI code or documentation against Vercel's current guideline sources.
Source Review
Verified on 2026-06-18:
- The README describes the repository as a collection of Agent Skills for AI
coding agents and documents installation with
npx skills add vercel-labs/agent-skills. - The README lists Vercel, React, React Native, web design, writing, composition, view-transition, deployment, and optimization skills.
skills.sh.jsongroups skills into React, Vercel, and Design categories.vercel-optimize/SKILL.mdrequires metrics-first Vercel optimization, explicit project/scope handling, Vercel CLI prerequisites, and Observability-related caveats.deploy-to-vercel/SKILL.mdsays preview deployments are the default unless production is explicitly requested and includes approval gates before git push deploys.vercel-cli-with-tokens/SKILL.mdwarns against passing tokens as CLI flags and prefers theVERCEL_TOKENenvironment variable.- The README states the collection follows the Agent Skills format and lists MIT under License; individual skills also include Vercel-authored metadata.
Duplicate Review
Checked current content/skills/, content/tools/, content/mcp/,
content/agents/, open pull requests, and repository-wide content for
vercel-labs/agent-skills, Vercel Agent Skills, Vercel skills,
vercel-optimize, deploy-to-vercel, vercel-react-best-practices, Vercel
CLI token skill, and web design guidelines skill. Existing content includes
React, Next.js, Vercel, and deployment-related skills, but no dedicated Vercel
Labs Agent Skills collection entry, exact source URL duplicate, target file, or
open duplicate PR was found.
Disclosure
Editorial listing. No paid placement or affiliate link is used. The collection is maintained by Vercel Labs; Vercel also offers hosted commercial platform services.
Source citations
Add this badge to your README
How it compares
Vercel Agent Skills side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Vercel Agent Skills Vercel Labs' official Agent Skills collection for AI coding agents working on Vercel deployments, React and Next.js performance, React Native, web design guidelines, writing guidelines, composition patterns, view transitions, CLI token workflows, and Vercel optimization audits. Open dossier | Flutter Agent Skills Official Flutter team Agent Skills for AI coding agents building Flutter apps, fixing layout issues, adding widget and integration tests, creating widget previews, applying layered architecture, routing, localization, JSON serialization, and HTTP workflows. Open dossier | Dart Agent Skills Official Dart team Agent Skills for AI coding agents working on Dart unit tests, CLI apps, coverage, runtime errors, mocks, package conflicts, static analysis, Native Assets, FFI, ffigen, and pattern matching. Open dossier | Google Cloud Agent Skills Google Agent Skills catalog for AI agents working with Google Cloud, Gemini Enterprise Agent Platform, Gemini APIs, Skill Registry, Cloud Run, BigQuery, Firebase, GKE, Cloud SQL, AlloyDB, gcloud, auth, onboarding, and Well-Architected Framework guidance. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | skills | skills | skills | skills |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | Vercel Labs | Flutter Team | Dart Team | |
| Added | 2026-06-18 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI | Claude CodeCodexWindsurfGeminiCursorCLI |
| Source repo | — | — | — | — |
| Safety notes | ✓The deploy-to-vercel and Vercel CLI token skills can guide agents toward git pushes, preview deployments, Vercel project linking, environment variable changes, and account-scoped CLI calls; keep human approval on those actions. The vercel-cli-with-tokens skill includes token-handling workflows. Prefer environment variables over command-line token flags and avoid echoing secrets into prompts, logs, screenshots, or public PRs. The vercel-optimize skill reads Vercel metrics, usage, project configuration, and code scan results; verify the linked project and team scope before collecting or acting on recommendations. The web-design-guidelines and writing-guidelines skills fetch current upstream rule documents at use time, so review fetched guidance before treating output as policy. React, Next.js, and React Native performance rules are strong defaults, but agents still need local tests, framework-version checks, and product-specific review before broad refactors. | ✓Flutter skills can modify application code, tests, pubspec dependencies, routing, localization files, serialization code, architecture boundaries, and app entry points. Integration-test workflows may enable Flutter Driver extensions, add keys to widgets, launch apps through MCP tools, interact with running UI, and create driver scripts. Do not run device, emulator, browser, Firebase Test Lab, or network-backed integration tests against production services without explicit approval and test credentials. Architecture and routing changes can alter navigation, state management, API access, caching, offline behavior, and user-visible app flows. Use project-local conventions and Flutter version constraints before applying generated examples. | ✓Dart skills can modify source code, tests, pubspec dependencies, analysis options, generated mocks, coverage output, native hooks, FFI bindings, and package constraints. `dart fix --apply`, formatter runs, mock generation, build_runner, ffigen, and Native Assets hooks can create broad mechanical diffs; inspect changes before committing. Native Assets and FFI workflows may compile C/C++ code, run local toolchains, download precompiled binaries, and link dynamic or static libraries. Downloaded binaries should use cryptographic hash validation and offline fallbacks as the skill describes. Package conflict fixes can upgrade or downgrade dependencies and affect transitive package behavior across Dart and Flutter projects. | ✓Google Cloud skills can create, update, delete, deploy, query, or configure cloud resources, datasets, IAM policies, service accounts, APIs, containers, jobs, and networking. The gcloud skill requires command validation and safety guardrails before invoking Google Cloud CLI commands; do not let agents improvise cloud commands from memory. Skill Registry guidance includes skill lifecycle management such as upload, update, and permanent delete operations; validate environment and approval before use. Cloud Run, GKE, BigQuery, Firebase, Cloud SQL, AlloyDB, and Gemini API workflows can create cost, expose endpoints, alter data, or change production behavior. The repository notes active development, so verify exact commands, product names, API availability, and launch-stage limits before production use. |
| Privacy notes | ✓Deployment and optimization workflows may expose project names, team slugs, deployment URLs, routes, metrics, usage details, billing signals, source paths, build configuration, environment variable names, and CLI account context. Keep VERCEL_TOKEN, VERCEL_ORG_ID, VERCEL_PROJECT_ID, API keys, environment values, claim URLs, deployment logs, and private preview URLs out of public artifacts unless intentionally disclosed. Design, writing, React, and performance reviews can reveal proprietary UI, product copy, documentation strategy, source code, routes, and business priorities to the configured model provider. | ✓Flutter projects may contain API URLs, Firebase project IDs, mobile bundle IDs, analytics keys, user fixtures, screenshots, test traces, device logs, crash output, and integration-test artifacts. MCP app exploration can expose widget trees, screen text, test data, typed inputs, navigation paths, and screenshots from the running app. HTTP, JSON, localization, and repository-layer work may touch private API schemas, user data models, translations, product copy, and backend payloads. Keep credentials, private endpoints, screenshots with user data, device logs, Firebase tokens, and proprietary UI flows out of public prompts, issues, PRs, and examples. | ✓Dart projects may contain private package names, API schemas, service URLs, test fixtures, generated mocks, coverage paths, stack traces, native library names, and build logs. Runtime-error workflows can expose stack traces, local paths, active app state, logs, and user-input data from the running program. FFI and Native Assets workflows may include proprietary C/C++ source, platform-specific build settings, binary hashes, and downloaded artifact URLs. Keep credentials, private package registries, source paths when sensitive, proprietary native code, test data, and generated coverage reports out of public prompts, issues, PRs, and examples. | ✓Google Cloud workflows may expose project IDs, service account emails, OAuth tokens, API keys, ADC credentials, Terraform state, dataset names, table schemas, query text, logs, traces, prompts, model outputs, embeddings, and customer data. BigQuery, Firebase, Cloud SQL, AlloyDB, GKE, and Agent Platform workflows may process regulated or proprietary data; review data residency, IAM, retention, audit logging, and sharing rules before use. Gemini API and Agent Platform skills can send prompts, files, images, audio, video, tool inputs, structured outputs, cached contexts, and batch datasets to Google services. Keep credentials, project IDs when sensitive, private queries, logs, trace payloads, Terraform state, customer data, and generated datasets out of public prompts, issues, PRs, and screenshots. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | — | — | — | — |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Featured in
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.