Agent Native

wrangler

This skill enables the agent to run Wrangler CLI commands for Cloudflare Workers projects, including local development setup, configuration management…

by CloudflareOfficial publisherNot reviewed

Identity proven by a skills index on cloudflare.com

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
Apache-2.0 (permissive)
Pin
a84b615pinned Oct 9, 2026
Context cost
about 2,700 tokenswhen the skill loads
GitHub stars
3,012on cloudflare/skills
Scripts
None found

What it does

“Run or troubleshoot Wrangler CLI commands and configure Worker projects for local development, Previews, deployment, and Cloudflare resource management.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill enables the agent to run Wrangler CLI commands for Cloudflare Workers projects, including local development setup, configuration management, deployment, and resource management. It handles project inspection, documentation retrieval, configuration editing, and deployment validation while respecting the project's existing Wrangler version and conventions.

When to use it

  • Setting up local development environments for Cloudflare Workers projects
  • Configuring bindings, secrets, and environments in wrangler.jsonc files
  • Deploying Workers and managing previews for branches or pull requests
  • Diagnosing authentication issues or managing Cloudflare account permissions

When not to

  • Project uses cloudflare.config.ts or cf CLI instead of Wrangler
  • Making hand-edits to generated TypeScript type declarations
  • User has a newer global Wrangler installation but older project version

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add cloudflare/skills --skill wrangler

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install cloudflare/skills wrangler@a84b615ff9d40e7f99755aea23d65e52d645bd42

Installs the commit we checked (a84b615).

Copy by hand

Download the folder at a84b615 and put it in .claude/skills/wrangler for Claude Code and in .agents/skills/wrangler for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at a84b615

Claude Code plugin

/plugin install cloudflare@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "wrangler" by Cloudflare.

Source, pinned to commit a84b615ff9d40e7f99755aea23d65e52d645bd42:
https://github.com/cloudflare/skills/tree/a84b615ff9d40e7f99755aea23d65e52d645bd42/skills/wrangler

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/wrangler/ for Claude Code and .agents/skills/wrangler/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/cloudflare/wrangler

SKILL.md at the pin

---
name: wrangler
description: Run or troubleshoot Wrangler CLI commands and configure Worker projects for local development, Previews, deployment, and Cloudflare resource management.
---

# Wrangler CLI

If the project has a `cloudflare.config.ts` file, or the user has asked you to use the `cf` CLI, do not use this skill. Follow the [Cloudflare CLI documentation](https://developers.cloudflare.com/cf/index.md) instead.

Use the project's Wrangler version and retrieve the relevant documentation before writing commands or configuration. CLI flags and configuration fields change; do not rely on memorized examples.

## Inspect the Project

- Find the package manager, installed Wrangler version, package scripts, framework, and Wrangler config. Run commands through the project's scripts or package manager so they use its local version. Install dependencies using the existing lockfile when needed; do not silently upgrade Wrangler to match current docs. If Wrangler is not a dependency, follow the [installation guide](https://developers.cloudflare.com/workers/wrangler/install-and-update/index.md) to add it locally.
- Identify the config used by the build or deploy command, including framework-generated config. Edit its source rather than generated output.
- Establish the target account, Worker, environment, and resource before running commands that change them. For data operations, determine whether the target is local or remote.

## Retrieve What the Task Needs

Use the Cloudflare MCP `docs` tool if available, or fetch the relevant linked page directly. Follow links to the specific command or product involved; avoid loading the entire reference. If a page moves, rediscover it through the [Wrangler command index](https://developers.cloudflare.com/workers/wrangler/commands/index.md) or Cloudflare docs search.

| Task | Source |
| --- | --- |
| Discover commands and flags, including resource management, deployments, rollback, and diagnostics | Project-local `wrangler --help` and `wrangler <command> --help`; [command reference](https://developers.cloudflare.com/workers/wrangler/commands/index.md) |
| Edit config or add a binding | Installed `wrangler/config-schema.json` (usually under `node_modules`); [configuration reference](https://developers.cloudflare.com/workers/wrangler/configuration/index.md) |
| Deploy a framework application | [Framework guides](https://developers.cloudflare.com/workers/framework-guides/index.md); follow the guide for the project's existing framework and adapter |
| Migrate an application to Workers when requested | [Pages to Workers](https://developers.cloudflare.com/workers/static-assets/migration-guides/migrate-from-pages/index.md); [Vercel to Workers](https://developers.cloudflare.com/workers/static-assets/migration-guides/vercel-to-workers/index.md) |
| Configure staging or production | [Environments](https://developers.cloudflare.com/workers/wrangler/environments/index.md) |
| Set secrets locally, in CI, or on a deployed Worker | [Secrets](https://developers.cloudflare.com/workers/configuration/secrets/index.md) |
| Generate binding and runtime types | [TypeScript](https://developers.cloudflare.com/workers/languages/typescript/index.md) |
| Run locally or choose a testing approach | [Local development](https://developers.cloudflare.com/workers/local-development/index.md); [testing](https://developers.cloudflare.com/workers/testing/index.md) |
| Choose roles, scopes, or API token permissions for Wrangler | [Roles and permissions](https://developers.cloudflare.com/workers/authorization/index.md); [Workers roles and permissions](https://developers.cloudflare.com/workers/authorization/workers/index.md#wrangler) |
| Create or manage a branch or pull request environment | [Previews overview](https://developers.cloudflare.com/workers/previews/index.md); [get started](https://developers.cloudflare.com/workers/previews/get-started/index.md); [configuration](https://developers.cloudflare.com/workers/previews/configuration/index.md) |
| Decide whether Preview resources are isolated or shared | [Resources and isolation](https://developers.cloudflare.com/workers/previews/resources/index.md), including its current limitations |
| Configure Preview URLs, access, debugging, or CI | [Custom domains](https://developers.cloudflare.com/workers/previews/custom-domains/index.md); [test and debug](https://developers.cloudflare.com/workers/previews/test-and-debug/index.md); [examples](https://developers.cloudflare.com/workers/previews/examples/index.md) |
| Choose between Previews, Version URLs, and Wrangler environments | [Compare workflows](https://developers.cloudflare.com/workers/previews/compare-workflows/index.md) |
| Diagnose authentication or select an account | [General commands](https://developers.cloudflare.com/workers/wrangler/commands/general/index.md), including `whoami`; [authentication profiles](https://developers.cloudflare.com/workers/wrangler/profiles/index.md) |
| Deploy an unauthenticated prototype | [Claim deployments](https://developers.cloudflare.com/workers/platform/claim-deployments/index.md) for eligibility, expiry, and claim URL handling; use a permanent account for production or CI |

Use installed help and schema to check whether documented features exist in the project's version. If a required feature needs an upgrade, make that dependency explicit. If retrieval is unavailable, state the gap and use available local evidence rather than inventing syntax.

## Apply the Change

- Prefer `wrangler.jsonc` for new config. Set a new project's [compatibility date](https://developers.cloudflare.com/workers/configuration/compatibility-dates/index.md) to today; review runtime changes and test when advancing an existing project's date. Preserve existing project conventions and avoid incidental format migrations.
- Check environment inheritance before adding bindings or variables. Some fields must be specified separately for each environment; a working default config does not establish that staging is configured.
- With the Cloudflare Vite plugin, select the environment via `CLOUDFLARE_ENV` at dev or build time. Deploy the resulting build; setting an environment at deploy time does not retarget its flattened config. See [Vite environments](https://developers.cloudflare.com/workers/vite-plugin/reference/cloudflare-environments/index.md).
- Reconcile dashboard changes with the config before deploying: Wrangler can overwrite dashboard variables and routes. When binding existing resources, verify their identifiers; omitted identifiers can trigger [automatic provisioning](https://developers.cloudflare.com/workers/wrangler/configuration/index.md#automatic-provisioning).
- Distinguish local simulation from remote bindings during development. A locally running Worker can still access real resources; check the selected bindings before testing writes.
- Before a remote command, identify the authenticated member or API token and retrieve the current role and scope required for the exact operation. Prefer the narrowest scope that satisfies the user's intent. The `wrangler login` OAuth flow does not support granular authorization; use an account-owned API token when granular access is required, and never ask the user to paste its value into chat.
- Keep secret values out of command arguments, source code, and logs. Use the documented interactive input or protected file/stdin mechanism for the command. Local secret files must be ignored by version control and are not automatically uploaded as deployed secrets. For missing local secrets, check file precedence and any `secrets.required` declaration in the secrets docs.
- Treat `wrangler secret put` and `secret delete` as deployments: they create a version and deploy it immediately. Use the documented `wrangler versions secret` workflow when the change must be staged.
- Before a rollback, check [rollback limitations](https://developers.cloudflare.com/workers/versions-and-deployments/rollbacks/index.md): connected resources and their data are not rolled back with Worker code.

## Work with Workers Previews

- Workers Previews requires project-local Wrangler 4.135.0 or later; project commands do not use a newer global installation. Check the project's pinned version and make any required dependency upgrade explicit.
- Use Previews for branch and pull request environments under the same Worker. Use Version URLs to inspect a specific uploaded version with production resources, and Wrangler environments for persistent, separately deployed Workers. Follow [Compare workflows](https://developers.cloudflare.com/workers/previews/compare-workflows/index.md) rather than adapting an older aliased Version URL workflow.
- First inspect how the user manages production configuration and deployments. Configure Preview domains through the same configuration system as production, such as Wrangler, the dashboard, or Terraform. Run Preview deployments through the user's existing path, such as the local CLI, Workers Builds, or external CI, unless the user requests a different workflow. Mirror the management approach, not production resource bindings or data.
- Before deploying, follow the current [configuration placement table](https://developers.cloudflare.com/workers/previews/configuration/index.md#what-goes-in-the-previews-block) and [resource matrix and limitations](https://developers.cloudflare.com/workers/previews/resources/index.md). Do not infer isolation from the Preview name or allow writes to production resources unless the user explicitly intends to share them.
- Tell the user that Preview URLs are public unless access controls are configured, then let them decide whether to protect the URLs. Follow the [custom domain and access guidance](https://developers.cloudflare.com/workers/previews/custom-domains/index.md) for the chosen setup.
- Confirm which Worker or Wrangler environment the user intends to target. When targeting a Wrangler environment, pass the same `--env` value to every Preview command; omitting it targets the top-level Worker.

## Validate

After changing config or bindings in a TypeScript project, regenerate types with the project's `wrangler types` command rather than hand-editing generated declarations. Run the relevant existing typecheck or tests.

For deployment changes, use the project's build workflow and `wrangler deploy --dry-run` where supported, with the intended config and environment. A successful dry run checks the build and packaging; it does not prove remote resources or runtime behavior work. Use task-specific local or remote checks as appropriate to the requested work.

For Previews, a returned URL does not validate behavior that depends on bindings Wrangler reports as missing. Validate the behavior the user requested, using Preview-specific logs and configuration when needed. Writes to production resources, destructive testing, and deletion of named Previews must match the user's explicit intent.

Report what changed, the target environment, checks performed, and any unresolved validation gaps. Link the documentation used when the result depends on current command or configuration behavior.

From cloudflare/skills at a84b615, shown as plain text under its license: Apache-2.0 (permissive). The license text is in LICENSE.

View SKILL.md on GitHub at a84b615

Files

1 file, 11 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at a84b615
All 18 skills from Cloudflare

More from Cloudflare

  • security-audit

    This skill guides security audits of codebases, APIs, and services by finding vulnerabilities that cross real trust boundaries.

    Contains scripts

    Claude Code · about 5.4K tokens · pinned 6 days ago

  • kumo-design

    Provides design rules for Cloudflare dashboard interfaces and Kumo UI components, covering text sizing, typography, spacing, borders, icons, animations, and…

    Claude Code, Codex, Cursor +4 · about 1.5K tokens · pinned 6 days ago

  • agents-sdk

    This skill helps build and debug Cloudflare Agents SDK applications, enabling creation of persistent agents with state management, RPC methods, scheduling…

    Claude Code, Codex, Cursor +4 · about 3K tokens · pinned 6 days ago

  • basin

    This skill helps agents build and troubleshoot Cloudflare Basin analytics workflows, which ingest events, transform data, manage Apache Iceberg tables in R2…

    Claude Code, Codex, Cursor +4 · about 600 tokens · pinned 6 days ago

  • cloudflare

    This skill helps agents discover Cloudflare products that match stated requirements and recommend the right combination for architecture and implementation.

    Claude Code, Codex, Cursor +4 · about 6.4K tokens · pinned 6 days ago

  • cloudflare-email-service

    This skill enables agents to send transactional emails and route incoming emails using Cloudflare's Email Service platform.

    Claude Code, Codex, Cursor +4 · about 1.6K tokens · pinned 6 days ago

All Cloud and DevOps skills
  • cloudflare-one-migrations

    This skill helps assess and plan migrations from VPN, SWG, or SASE platforms (Zscaler ZIA/ZPA, Palo Alto, legacy systems) to Cloudflare One.

    by CloudflareOfficial publisher

    Claude Code, Codex, Cursor +4 · about 3.1K tokens · pinned 6 days ago

  • k2

    This skill helps agents build and manage Cloudflare K2 durable logs for event streaming.

    by CloudflareOfficial publisher

    Claude Code, Codex, Cursor +4 · about 490 tokens · pinned 6 days ago

  • nextjs-on-cloudflare

    This skill guides agents to build and deploy Next.js applications on Cloudflare Workers using vinext, a Vite-based reimplementation of Next.js.

    by CloudflareOfficial publisher

    Claude Code, Codex, Cursor +4 · about 560 tokens · pinned 6 days ago

  • sandbox-migrate-to-next

    This skill migrates Cloudflare Sandbox applications from the stable @cloudflare/sandbox package to the @cloudflare/sandbox@next SDK 1.0 preview release.

    by CloudflareOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.9K tokens · pinned 6 days ago

  • sandbox-next

    This skill enables building and maintaining Cloudflare Sandbox apps using the @cloudflare/sandbox@next SDK (1.0 preview), which provides isolated Linux…

    by CloudflareOfficial publisher

    Claude Code, Codex, Cursor +4 · about 1.6K tokens · pinned 6 days ago

  • sandbox-stable

    Builds and maintains Cloudflare Sandbox applications on the stable @cloudflare/sandbox package, providing isolated Linux environments running on Cloudflare…

    by CloudflareOfficial publisher

    Claude Code, Codex, Cursor +4 · about 2.3K tokens · pinned 6 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use