Next.js Skills: official workflows for Next.js apps
vercel/next.js
Six step-by-step playbooks from the Next.js team for your AI coding assistant. They help it switch your Next.js app to newer speed features, find what makes pages slow to load, and check every change in a real browser. The same repo also holds 21 skills for people who work on Next.js itself; you can ignore those.
Pack description by its author: “Six step-by-step playbooks from the Next.js team for your AI coding assistant. They help it switch your Next.js app to newer speed features, find what makes pages slow to load, and check every change in a real browser. The same repo also holds 21 skills for people who work on Next.js itself; you can ignore those.”
Marketing, SEO and writingKnowledge and rules for your assistantGives your assistant new abilities with scripts
1. Changes your files
Skills that write or edit files: next-bundle-optimizer, next-cache-components-adoption, next-cache-components-optimizer, next-partial-prefetching-adoption, next-partial-prefetching-optimizer, authoring-skills, backport-pr, create-pr.
github.com/vercel/next.js/blob/6352f41/2. Runs code on your machine
Install of the app skills: Markdown files only. No hooks, no scripts, no plugin hooks key. App skills at work: They tell your assistant to run commands in your project: next dev, next build, next start, next analyze, Playwright tests and official codemods (npx @next/codemod). These change files in your app.
github.com/vercel/next.js/blob/6352f41/3. Sends data
Install only from github.com/vercel/next.js (folders skills/ and .agents/skills/) or with the skills tool pointing there. The app skills install other tools (agent-browser, more Next.js skills, codemods) and run production builds with your real secrets; keep the testing option off in real production builds. Skills are instructions your agent follows: read them before installing.
github.com/vercel/next.js/blob/6352f41/4. Commercial use
MIT: keep the copyright and permission notice
github.com/vercel/next.js/blob/6352f41/Checked against the pack's files at commit 6352f41, on Oct 27, 2026. Tap a verdict to see its source.How we checkedReport an error
The pack has changed since AgentGid checked it on Oct 27, 2026. Some details may be out of date.
Good for you if
- You build a site or app with Next.js and use an AI coding assistant such as Claude Code, Codex or Cursor
- You want to turn on Cache Components or Partial Prefetching and have the assistant fix the pages it flags
- Your pages feel slow on first load or when clicking links, and you want a report of why
- You want the assistant to check each change in a running app, not only that the code builds
Probably not for you if
- Your app uses only the older pages/ folder: the Cache Components skill stops and says that move is a separate project
- You are on Next.js older than 16.3: most skills ask you to upgrade first
- You don't use Next.js: the skills are about Next.js only
What its answer looks like
Prompts from the official docs
Each app skill has a ready prompt on the Next.js AI Coding Agents page; they are the say lines above.
The skill's own example, from docs/01-app/02-guides/ai-agents.mdx. More examples
What you'll notice
- Questions before big changes: one branch, or a series of smaller reviews? It checks in after each part of the app
- Your assistant starts the app, opens pages in a hidden browser and reports what loads at once and what streams in
- New browser tests in your project that keep a fast page fast, plus a short setup note (instant-nav.rig.md)
- A plain-language click-through list at the end: which page to open and what to look for
What you need
- Claude Code, Codex, Cursor, GitHub Copilot, any agent that reads skills
- Free, MIT license
- One command per skill: npx skills add vercel/next.js --skill <name>
- Needs a Next.js app on 16.3 or later. next-dev-loop also needs the agent-browser tool installed on your computer and Turbopack (the default since 16.3). The two optimizers and Partial Prefetching adoption need Playwright browser tests and a production build of your app, with its real database and secrets.
Words on this page
- Skill
- A set of written instructions your AI assistant follows. Installing one is like giving it a playbook.
- Plugin
- A package your assistant installs that can bring skills, commands and hooks together.
- Repository
- A project folder on GitHub with its files and history.
- CLI
- A program you run by typing commands in a terminal.
- MCP
- A standard way to connect an AI assistant to outside tools and data.
| Repository | vercel/next.js · website |
|---|---|
| GitHub stars | 143,605 (the Next.js repository: these skills ship inside the product, so the stars are the product's) |
| Skills | 27 (27 SKILL.md in the repo, 6 in skills/) · 3 with scripts |
| Category | Marketing, SEO and writing |
| License | MIT |
| Last updated | Nov 22, 2026 · card checked Oct 27, 2026 at commit 6352f41 |
| Install counts | vercel/next.js on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
vercel/next.js popularity over time
What Next.js Skills does
- Check every edit in the running app: next-dev-loop asks Next.js itself (its built-in /_next/mcp endpoint) and a real Chrome (agent-browser) whether the page compiles, runs without errors and looks right.
- Work in small, checked steps: one part of the app at a time, a passing dev check and a passing build before moving on.
- Prove speed with a test, not a stopwatch: the optimizers first write a Playwright instant() test that fails, fix the page until it passes, and keep the test.
- Follow the official docs: each error links a docs page, and the skills tell the assistant to read it before fixing.
- Audit before fixing: next-bundle-optimizer only reports unless you ask it to change the app.
- Hand-offs between skills: adoption first, then the optimizers; each skill says which one comes next.
Never cut, per the skill: your app's existing data source, freshness, login and permission checks, redirects and error states; the optimizers must leave the page looking and behaving the same.
From the pack's SKILL.md files, summarised by AgentGid.
The 6 skills, explained
next-dev-loop
Checks each change in your running app through Next.js and a real browser
You give
- Your app running with next dev (Next.js 16.3+, Turbopack)
- The page address to check
- Your login in a visible browser window, if the page needs one
You get
- A list of the app's pages
- Build errors, server and browser errors for the page
- What a user actually sees, checked in the browser
- Component tree, props and render counts from React DevTools
next-bundle-optimizer
Finds what makes your pages heavy to load; reports by default, fixes only when you ask
You give
- The whole app, or one page, package or feature to look at
- Audit (report only) or fix
You get
- Saved before and after snapshots from the Next.js bundle analyzer
- Ranked candidates with the exact file that pulls each one in
- In fix mode: one small change at a time, kept only if the number improves and the page still works
- A report that separates facts from guesses
next-cache-components-adoption
Turns on Cache Components and fixes the pages that block it, one part of the app at a time
You give
- An App Router app on Next.js 16.3+ that starts
- Your choice: one branch, or a first safe change then one review per feature
You get
- cacheComponents switched on
- Pages marked with a to-do opt-out, then fixed one feature at a time (incremental path)
- A passing build after each feature
- A table per feature: which page to open and what to look for
next-cache-components-optimizer
Makes the useful part of one page appear at once, and adds a test that keeps it that way
You give
- The page and how users reach it (direct visit or a link click)
- What should show at once, for example the header and project list
- Next.js 16.3+ with Cache Components already on
You get
- A setup note for your project's test build (instant-nav.rig.md)
- A failing instant() test, then the fix that makes it pass
- Proof: undo the fix and the test fails again
- One line per page: what shows at once and what streams in
next-partial-prefetching-adoption
Moves your links to Partial Prefetching without losing what they already load ahead of the click
You give
- Next.js 16.3+ with Cache Components on and a passing build
- A production-like build it can run, with the real environment
- One branch, or one review per page
You get
- An audit of every link that prefetches today, as a table
- Browser tests that pass before and after the switch
- partialPrefetching switched on and leftover settings removed by the official codemod
- Marked candidates for extra per-link prefetching, decided with you later
next-partial-prefetching-optimizer
Decides what a chosen link loads before the click, and locks it in with a test
You give
- The link and the page it opens
- What must be ready before the click and what can wait
- Cache Components and Partial Prefetching already on
You get
- One test per link that clicks it and checks the result
- The smallest change that makes it pass
- A click-through list: what is ready before the click, what waits, when prefetching starts
See it in action
The skill defines what its answer looks like. Its own example:
// TODO: Cache Components adoption. Refactor this route so this opt-out can be removed. // See: https://nextjs.org/docs/app/guides/migrating-to-cache-components export const instant = false
The skill defines what its answer looks like. Its own example:
A Playwright test that logs in as the test user, clicks a real link inside instant(), and checks that a fixed part of the destination page (SHELL_MARKER) shows under the lock. Full template in the file (over 15 lines).
From skills/next-cache-components-optimizer/test-template.md.
The skill defines what its answer looks like. Its own example:
Each app skill has a ready prompt on the Next.js AI Coding Agents page; they are the say lines above.
When to reach for it
| You want | Use |
|---|---|
| Your assistant should check each change in the browser | next-dev-loop |
| A report on why pages are heavy to load | next-bundle-optimizer (audit is the default) |
| To turn on Cache Components in an existing app | next-cache-components-adoption |
| One page should show its header and main content at once | next-cache-components-optimizer (after adoption) |
| To switch links to Partial Prefetching | next-partial-prefetching-adoption (after Cache Components) |
| A chosen link should load more before the click | next-partial-prefetching-optimizer (after both adoptions) |
| To work on Next.js itself | the internal skills in .agents/skills/, loaded inside a Next.js checkout |
Skills in vercel/next.js
| Skill | In plain words | Changes files? | What it does (author) |
|---|---|---|---|
| next-bundle-optimizer | Finds what makes your pages heavy to load; reports by default, fixes only when you ask | Yes | Audit and reduce Next.js browser initial-load work. Use for slow route startup, oversized client bundles, duplicate browser dependencies, or features that can wait for interaction.npx skills add vercel/next.js --skill next-bundle-optimizer |
| next-cache-components-adoption | Turns on Cache Components and fixes the pages that block it, one part of the app at a time | Yes | Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the `cacheComponents` flag, work through a flood of blocking-prerender / instant validation errors, run the…npx skills add vercel/next.js --skill next-cache-components-adoption |
| next-cache-components-optimizer | Makes the useful part of one page appear at once, and adds a test that keeps it that way | Yes | Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped…npx skills add vercel/next.js --skill next-cache-components-optimizer |
| next-dev-loop | Checks each change in your running app through Next.js and a real browser | No | Verify Next.js runtime behavior after editing app code. Use this skill to confirm a change actually works in a running app — not just that it compiles or type-checks. Combines /_next/mcp (Next.js's view) with agent-browser (the browser's view). Requires a running `next dev`.npx skills add vercel/next.js --skill next-dev-loop |
| next-partial-prefetching-adoption | Moves your links to Partial Prefetching without losing what they already load ahead of the click | Yes | Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the `partialPrefetching` flag, opt routes in with `export const prefetch = 'partial'`, audit `Link prefetch={true}` behavior, preserve…npx skills add vercel/next.js --skill next-partial-prefetching-adoption |
| next-partial-prefetching-optimizer | Decides what a chosen link loads before the click, and locks it in with a test | Yes | Optimize what selected Next.js client navigations include before the click under Partial Prefetching. Use after Cache Components and Partial Prefetching are adopted when the user wants selected URL-specific UI to be instant, wants reusable content to wait for navigation, or needs to choose between…npx skills add vercel/next.js --skill next-partial-prefetching-optimizer |
| authoring-skills | How to write new skills for the Next.js codebase | Yes | How to create and maintain agent skills in .agents/skills/. Use when creating a new SKILL.md, writing skill descriptions, choosing frontmatter fields, or deciding what content belongs in a skill vs AGENTS.md. Covers the supported spec fields, description writing, naming conventions, and the…npx skills add vercel/next.js --skill authoring-skills |
| backport-pr | Copies a merged fix to an older long-term-support release line | Yes | Backport a merged Next.js pull request from canary to an LTS release branch (releases/lts/active or releases/lts/maintenance). Use when the user asks to backport, cherry-pick, or open a backport PR from a PR number to an older Next.js version. Covers finding the merged PR commit, creating a…npx skills add vercel/next.js --skill backport-pr |
| create-pr | Makes a branch, pushes it and opens a draft pull request on GitHub | Yes | Create Git branches, commits, pushes, and GitHub pull requests for Next.js. Use when the user asks to create a branch, commit current changes, open a PR or draft PR, publish a pull request, or recover from gh pr create / PR template issues. Covers .github/pull_request_template.md, --body…npx skills add vercel/next.js --skill create-pr |
| dce-edge | Rules for framework code that must also work in the lightweight edge build | Yes | DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render / stream-utils for edge builds. Covers if/else branching for webpack DCE, TypeScript definite…npx skills add vercel/next.js --skill dce-edge |
| deploy-release-test | Starts the full deployment test suite on GitHub Actions from an internal branch | Unclear | Validate a commit-specific Next.js preview package and manually trigger the entire Next.js deployment test suite through the test_e2e_deploy_release.yml GitHub Actions workflow. Use only when asked to run the full deploy test suite or this workflow specifically from an internal vercel/next.js PR…npx skills add vercel/next.js --skill deploy-release-test |
docs-diagrams/docs-diagrams only (never starts by itself) |
Draws light and dark diagrams for the Next.js docs with headless Chrome, no AI images | Yes | Draw diagrams for the Next.js docs in the style of the ones already published there: the light/dark PNGs an mdx references with `<Image srcLight="/docs/light/<name>.png" srcDark="/docs/dark/<name>.png">`. Use when a guide or API reference needs a new diagram or an existing one needs a change.… has scriptsnpx skills add vercel/next.js --skill docs-diagrams |
| flags | How to add an experimental feature flag through every layer of the framework | Yes | How to add or modify Next.js experimental feature flags end-to-end. Use when editing config-shared.ts, config-schema.ts, define-env-plugin.ts, next-server.ts, export/worker.ts, or module.compiled.js. Covers type declaration, zod schema, build-time injection, runtime env plumbing, and the decision…npx skills add vercel/next.js --skill flags |
| gate-tests | Marks known-failing tests with @gate instead of quietly skipping them | Yes | How to use the `@gate` / `@force-gate` test directives instead of `it.skip` or fake-green skip patterns. Use when a test is known-failing under some test-matrix dimension (dev mode, a bundler, an experimental flag like cacheComponents), when converting `if (isNextDev) return` guards or env-var…npx skills add vercel/next.js --skill gate-tests |
| gh-stack | Splits work into stacked pull requests with GitHub's gh-stack tool (copied from GitHub) | Yes | Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or isolate work for review; whenever a user mentions a stack, branch layers, dependent PRs, or gh…npx skills add vercel/next.js --skill gh-stack |
| insight-error-page | Writes or checks error help pages for the Next.js dev overlay | Yes | Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new `errors/<slug>.mdx` page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets,…npx skills add vercel/next.js --skill insight-error-page |
| next-rspack | Keeps the Rspack bundler packages and their Rust versions up to date | Yes | Maintain @next/rspack-core and @next/rspack-binding packages. Use when editing rspack/package.json, rspack/crates/binding/Cargo.toml, rspack/rust-toolchain.toml, or packages/next-rspack/package.json. Covers upgrading @rspack/core npm version, rspack_* crate versions, Rust toolchain version,…npx skills add vercel/next.js --skill next-rspack |
| pr-status-triage | Sorts failing checks and review comments on a pull request, worst first | Unclear | Triage CI failures and PR review comments using scripts/pr-status.js. Use when investigating failing CI jobs, flaky tests, or PR review feedback. Covers blocker-first prioritization (build > lint > types > tests), CI env var matching for local reproduction, and the Known Flaky Tests distinction.npx skills add vercel/next.js --skill pr-status-triage |
| react-sync | Builds a local React checkout and copies it into Next.js for testing | Yes | Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration. Use when working on React changes that need validation in Next.js, or when asked to run buildForNext, pnpm sync-react, or synchronize a React checkout… has scriptsnpx skills add vercel/next.js --skill react-sync |
| react-vendoring | Rules for the copy of React bundled inside Next.js | Yes | React vendoring and react-server layer boundaries. Use when editing entry-base.ts, $$compiled.internal.d.ts, compiled/react* packages, or taskfile.js copy_vendor_react. Covers the entry-base.ts boundary (all react-server-dom-webpack/* imports must go through it), vendored React channels, type…npx skills add vercel/next.js --skill react-vendoring |
| router-act | How to write end-to-end tests that control prefetch timing | Yes | How to write end-to-end tests using createRouterAct and LinkAccordion. Use when writing or modifying tests that need to control the timing of internal Next.js requests (like prefetches) or assert on their responses. Covers the act API, fixture patterns, prefetch control via LinkAccordion, fake…npx skills add vercel/next.js --skill router-act |
| runtime-debug | Steps to track down bundle size and module loading regressions | Unclear | Debug and verification workflow for runtime-bundle and module-resolution regressions. Use when diagnosing unexpected module inclusions, bundle size regressions, or CI failures related to NEXT_SKIP_ISOLATE, nft.json traces, or runtime bundle selection (module.compiled.js). Covers CI env mirroring,…npx skills add vercel/next.js --skill runtime-debug |
| sandbox-bench | Speed comparison of two versions of React or Next.js on paid Vercel Sandbox machines | Unclear | Benchmark React or Next.js changes on Vercel Sandbox VMs with paired A/B statistics: react PR/commit vs base, or Next.js PR/commit vs base, measured end-to-end through the bench/render-pipeline app (rps, latency, p95; TTFB, RSS and document/Flight bytes when the Next side captures them) and, for… has scriptsnpx skills add vercel/next.js --skill sandbox-bench |
| update-docs | Updates the Next.js documentation to match a code change | Yes | This skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what docs need updating", "sync docs with code", "scaffold docs for this feature", "document this feature", "review docs completeness", "add docs for this change", "what documentation…npx skills add vercel/next.js --skill update-docs |
| v8-jit | Patterns for fast JavaScript in busy server code paths | Yes | V8 JIT optimization patterns for writing high-performance JavaScript in Next.js server internals. Use when writing or reviewing hot-path code in app-render, stream-utils, routing, caching, or any per-request code path. Covers hidden classes / shapes, monomorphic call sites, inline caches,…npx skills add vercel/next.js --skill v8-jit |
| write-api-reference | Drafts a Next.js reference page for a function or option | Yes | Produces API reference documentation for Next.js APIs: functions, components, file conventions, directives, and config options. **Auto-activation:** User asks to write, create, or draft an API reference page. Also triggers on paths like `docs/01-app/03-api-reference/`, or keywords like "API…npx skills add vercel/next.js --skill write-api-reference |
| write-guide | Drafts a step-by-step Next.js guide with growing examples | Yes | Generates technical guides that teach real-world use cases through progressive examples. **Auto-activation:** User asks to write, create, or draft a guide or tutorial. Also use when converting feature documentation, API references, or skill knowledge into step-by-step learning content. **Input…npx skills add vercel/next.js --skill write-guide |
The author's descriptions come from each skill's SKILL.md; the plain-words column is AgentGid's.
Good to know before you install
- Two audiences in one repo: only the six skills in skills/ are meant for your app. The 21 in .agents/skills/ are tagged internal and help with work on Next.js itself; installing them into your app does nothing useful.
- The Cache Components adoption skill tells your assistant to install next-dev-loop without asking you first, also in unattended runs. It only says to tell you if you are present.
- next-dev-loop needs the agent-browser tool installed globally on your computer, and it saves the browser's cookies and local storage so you stay logged in between checks.
- The optimizers and Partial Prefetching adoption run your app as a production build with its real database and secrets, and switch on a testing option. The skills say to keep that option off for real production builds.
- Saving to git stays with you: the adoption skill suggests a save point after each feature but never makes one without your yes.
- Feedback to the Next.js team: next-dev-loop joins Next.js's agent feedback only when you turned that feature on; it is off by default and nothing is sent until you press Send feedback.
Before you start
Works in
- Claude Code: plugin
- Any agent with a skills folder: skills CLI
- Codex: skills folder
You will need
- Next.js 16.3 or later: All six app skills need it
- Turbopack: next-dev-loop's compile check works only on Turbopack
- agent-browser 0.31.1 or later: next-dev-loop drives Chrome through it
- @next/playwright: The optimizers and Partial Prefetching adoption write instant() browser tests with it
- The app's real environment (database, auth, secrets): Partial Prefetching is verified on a production run
Steps only you can do
- Choose one branch, or a first pull request plus one review per feature, when the adoption skill asks (skills/next-cache-components-adoption/SKILL.md)
Then: The agent follows that plan and checks in after each feature - Log in to your app in the visible browser window when a page needs a login (skills/next-dev-loop/SKILL.md)
Then: The agent continues checks in the same saved browser session - Provide the app's real environment (database, auth, secrets) for the production run (skills/next-partial-prefetching-adoption/SKILL.md)
Then: The agent builds and starts the app and verifies prefetching against it - Approve each commit the adoption skill suggests (skills/next-cache-components-adoption/SKILL.md)
Then: The agent commits only after your yes - Contributors only: name the Vercel team and project for sandbox-bench, which bills sandbox machines (.agents/skills/sandbox-bench/SKILL.md)
Then: The scripts start the benchmark machines under that team and project
Mistakes to avoid
Install the skills from .agents/skills/ into your own app
Install only the six skills in skills/ (the "nextjs" plugin); the rest are for work on Next.js itself
The .agents/skills/ ones are tagged internal and describe the Next.js codebase, not your appRun an optimizer on an app that has not adopted Cache Components or Partial Prefetching yet
Run the adoption skill first, then the optimizer
The optimizers assume the features are already on and send you back to adoption otherwiseUse next-dev-loop on an app whose dev script runs webpack
Switch to Turbopack, or use the adoption skill's build-only check if you must stay on webpack
next-dev-loop needs Turbopack's compile check and stops on webpackTreat the instant-false codemod's "0 ok" result as a finished adoption
Read the file count and rerun with the correct app directory if it is zero
A wrong path does not raise an errorDelete or move the .next folder while next dev is running
Leave .next in place; give a separate production build its own distDir
The dev server loses its generated state and caches
Which one to pick
| If you need | Pick |
|---|---|
| You want step-by-step workflows to adopt Cache Components or Partial Prefetching and check them in a running Next.js app | This pack |
| You want rule books for React, Next.js and React Native code plus page and docs reviews and Vercel deploys | vercel-labs/agent-skills |
| You want a speed, accessibility, search and security audit of any website, not only Next.js | addyosmani/web-quality-skills |
Works well with
- next: The skills work only on Next.js apps, version 16.3 or later
- agent-browser: next-dev-loop drives the browser through agent-browser
- skills: The docs install each skill with npx skills add
- claude-code: The repo ships a Claude Code plugin marketplace with the six app skills
May I use it like this?
| Use | Answer | Condition |
|---|---|---|
| In a commercial app | Yes | MIT: keep the copyright and permission notice |
| Passing the files on | Yes | MIT: include the copyright and permission notice in copies; gh-stack is copied from GitHub's own pack, check its source for its terms |
| Work for clients | Yes | MIT allows use in work for others |
| Shipped inside your app | Yes | The plugin manifest also states MIT; keep the notice |
What leaves your machine
- Requests for Next.js docs pages linked from each error → nextjs.org, During adoption, for every distinct error. Opt out: No opt-out in the skill; the fetch is part of the workflow
- Package downloads for agent-browser, codemods and other Next.js skills → The npm registry and GitHub (through npm and npx skills add), When the agent installs tools the skills need. Opt out: Install the tools yourself at fixed versions before starting
- An anonymized report about a Next.js issue, which you review first → The Next.js team, through a review form opened in your browser, Only if experimental.agentFeedback is on and you press Send feedback. Opt out: Leave agentFeedback off (the default)
- Contributors only: React or Next.js builds and benchmark runs → Vercel Sandbox machines under your Vercel team (billed), When sandbox-bench runs. Opt out: Do not use sandbox-bench
- Contributors only: a font request while rendering docs diagrams → Google Fonts, When docs-diagrams renders. Opt out: Do not use docs-diagrams
Install Next.js Skills
Official commands from the repository
npx skills add vercel/next.js --skill next-dev-loop npx skills add vercel/next.js --skill next-bundle-optimizer npx skills add vercel/next.js --skill next-cache-components-adoption npx skills add vercel/next.js --skill next-cache-components-optimizer npx skills add vercel/next.js --skill next-partial-prefetching-adoption npx skills add vercel/next.js --skill next-partial-prefetching-optimizer
One command per skill; install only the ones you need. The Next.js docs list these commands on the AI Coding Agents page.
npx skills add https://github.com/vercel/next.js/tree/canary/skills/next-dev-loop
The form the skills themselves use when one skill needs another.
The repo ships a Claude Code plugin marketplace named "nextjs" with one plugin, "nextjs", that holds the six app skills. The repo does not print the install commands for it.
The 21 internal skills load from .agents/skills/ (with .claude/skills pointing there) when an agent works inside a Next.js checkout. No install.
Or with the open-source skills CLI: npx skills add vercel/next.js. Skills are instructions your agent follows: read them before installing.
What it installs and runs on your machine
Read in the code at commit 6352f41, Oct 27, 2026
| When | What happens |
|---|---|
| Install of the app skills | Markdown files only. No hooks, no scripts, no plugin hooks key. |
| App skills at work | They tell your assistant to run commands in your project: next dev, next build, next start, next analyze, Playwright tests and official codemods (npx @next/codemod). These change files in your app. |
| App skills at work (network) | Your assistant installs tools (agent-browser globally, other Next.js skills, codemods through npx) and fetches Next.js docs pages from nextjs.org for each error. |
| next-dev-loop | Talks to your local dev server at /_next/mcp and drives a headless Chrome through agent-browser, which saves cookies and local storage per checkout so the next check stays logged in. |
| next-bundle-optimizer | Writes analyzer snapshots and exports them to /tmp/analyze-app-before.jsonl.gz (example path); in Codex it must capture outside the sandbox because it opens a network port. |
| Contributor: docs-diagrams | A shell script runs Node and headless Chrome to render diagrams to PNG; the pages load the Inter font from Google Fonts. |
| Contributor: react-sync | A shell script builds React from a local React checkout into build/oss-stable and build/oss-experimental. |
| Contributor: sandbox-bench | Node scripts start billed Vercel Sandbox machines through the Vercel command line tool and store team and project in ~/.config/sandbox-bench/config.json and a cache in ~/.cache/sandbox-bench. |
The author's numbers, as reported
AgentGid did not run these tests
- In the Next.js team's agent evaluations, bundled docs in AGENTS.md reached a 100% pass rate, compared with up to 79% for skill-based approaches (Vercel research linked from the docs; the Next.js docs therefore keep framework knowledge in bundled docs and use skills only for multi-step workflows). Source
Settings
NEXT_MCP_URL: Address of the dev server's /_next/mcp endpoint when next dev does not run on port 3000 (next-dev-loop)AGENT_BROWSER_SESSION: agent-browser session id for this checkout (next-dev-loop)AGENT_BROWSER_RESTORE: agent-browser key for saved login state (next-dev-loop)experimental.exposeTestingApiInProductionBuild: next.config option the optimizers switch on for test builds onlySANDBOX_BENCH_CACHE: cache folder for the contributor sandbox-bench scripts
Quick answers
- Are these skills free?
- Yes. The plugin manifest and the Next.js repo use the MIT license.
- Which skills do I need for my own app?
- Only the six in skills/: next-dev-loop, next-bundle-optimizer and the four Cache Components and Partial Prefetching skills. The rest are internal tools for Next.js contributors.
- Will it change my code without asking?
- The bundle optimizer only reports unless you ask for fixes. The adoption skills edit your app, but check in after each feature and never save to git without your yes.
- What Next.js version do I need?
- 16.3 or later for all six app skills; the skills tell your assistant to upgrade first if you are below that.
- Does it work with webpack instead of Turbopack?
- next-dev-loop refuses on webpack. The adoption skills fall back to driving a browser directly or a build-only check.
- Should I install the skills for framework knowledge?
- The Next.js docs say no: framework knowledge comes from the docs bundled with Next.js; the skills are for multi-step workflows.
Checked by AgentGid on Oct 27, 2026 against commit 6352f41 of the pack's own files. Related: vercel-labs/agent-browser, github/gh-stack. agent.md for AI agents · Report a mistake
More marketing, seo and writing skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
mvanhorn/last30days-skill You type /last30days and a topic: a person, a company, a product or "this vs that". Your assistant runs a bundled search program …
|
1 | 72.3K | 2026-11-22 |
| 2 |
blader/humanizer An editing guide for your AI assistant. Give it text that sounds machine-written and it rewrites it so it reads like a person wro…
|
1 | 72.1K | 2026-11-19 |
| 3 |
coreyhaines31/marketingskills A library of 52 marketing playbooks for your AI assistant. Ask for page copy, an SEO check, emails, ads or a launch plan. The mat…
|
53 | 61.9K | 2026-11-20 |
| 4 |
Imbad0202/academic-research-skills A full research-to-paper workflow for Claude Code. Your assistant can research a topic, plan and draft a paper, check its citatio…
|
5 | 58K | 2026-11-22 |
| 5 |
alirezarezvani/claude-skills A very large library of add-ons for AI assistants, grouped by area: software, marketing, product, finance, executive advice, comp…
|
473 | 30.3K | 2026-11-21 |
| 6 |
phuryn/pm-skills A large set of product management playbooks for your AI assistant: discovery, strategy, PRDs, OKRs, launches, metrics, research a…
|
72 | 28.2K | 2026-11-08 |