Claude Market
Menu
SkillsMCPPluginsSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Claude Market
SkillsMCPPluginsSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off
Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed
Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off
Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw
Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.
Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams
Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit
Try DataForSEO free →
Reach 47,000+ AI builders
Advertise here →
Skills/wordpress/agent-skills/blueprint
blueprint logo

blueprint

wordpress/agent-skills
1K installs2K stars
Run it on Hostinger →up to 70% off + an extra 10% with code ZACAARON10Free API →

Installation

npx skills add https://github.com/wordpress/agent-skills --skill blueprint

Summary

Use when creating, editing, or reviewing WordPress Playground blueprint JSON files. Triggers on mentions of blueprints, playground configuration, or requests to set up a WordPress demo environment.

SKILL.md

WordPress Playground Blueprints

Overview

A Blueprint is a JSON file that declaratively configures a WordPress Playground instance — installing plugins/themes, setting options, running PHP/SQL, manipulating files, and more.

Core principle: Blueprints are trusted JSON-only declarations. No arbitrary JavaScript. They work on web, Node.js, and CLI.

Quick Start Template

{
  "$schema": "https://playground.wordpress.net/blueprint-schema.json",
  "landingPage": "/wp-admin/",
  "preferredVersions": { "php": "8.3", "wp": "latest" },
  "steps": [{ "step": "login" }]
}

Top-Level Properties

All optional. Only documented keys are allowed — the schema rejects unknown properties.

PropertyTypeNotes
$schemastringAlways "https://playground.wordpress.net/blueprint-schema.json"
landingPagestringRelative path, e.g. /wp-admin/
metaobject{ title, author, description?, categories? } — title and author required
preferredVersionsobject{ php, wp } — both required when present
featuresobject{ networking?: boolean, intl?: boolean } — only these two keys, nothing else. Networking defaults to true
extraLibrariesarray["wp-cli"] — auto-included when any wp-cli step is present
constantsobjectShorthand for defineWpConfigConsts. Values: string/boolean/number
pluginsarrayShorthand for installPlugin steps. Strings = wp.org slugs
siteOptionsobjectShorthand for setSiteOptions
loginboolean or objecttrue = login as admin. Object = { username?, password? } (both default to "admin"/"password")
stepsarrayMain execution pipeline. Runs after shorthands

preferredVersions Values

  • php: Major.minor only (e.g. "8.3", "7.4"), or "latest". Patch versions like "7.4.1" are invalid. Check the schema for currently supported versions.
  • wp: Recent major versions (e.g. "6.7", "6.8"), "latest", "nightly", "beta", or a URL to a custom zip. Check the schema for the full list.

Shorthands vs Steps

Shorthands (login, plugins, siteOptions, constants) are expanded and prepended to steps in an unspecified order. Use explicit steps when execution order matters.

Resource References

Resources tell Playground where to find files. Used by installPlugin, installTheme, writeFile, writeFiles, importWxr, etc.

Resource TypeRequired FieldsExample
wordpress.org/pluginsslug{ "resource": "wordpress.org/plugins", "slug": "woocommerce" }
wordpress.org/themesslug{ "resource": "wordpress.org/themes", "slug": "astra" }
urlurl{ "resource": "url", "url": "https://example.com/plugin.zip" }
git:directoryurl, refSee below
literalname, contents{ "resource": "literal", "name": "file.txt", "contents": "hello" }
literal:directoryname, filesSee below
bundledpathReferences a file within a blueprint bundle (e.g. { "resource": "bundled", "path": "/plugin.zip" })
zipinnerWraps another resource in a ZIP — use when a step expects a zip but your source isn't one (e.g. wrapping a url resource pointing to a raw directory)

git:directory — Installing from GitHub

{
  "resource": "git:directory",
  "url": "https://github.com/WordPress/gutenberg",
  "ref": "trunk",
  "refType": "branch",
  "path": "/"
}
  • When using a branch or tag name for ref, you must set refType ("branch" | "tag" | "commit" | "refname"). Without it, only "HEAD" resolves reliably.
  • path selects a subdirectory (defaults to repo root).

literal:directory — Inline File Trees

{
  "resource": "literal:directory",
  "name": "my-plugin",
  "files": {
    "plugin.php": "<?php /* Plugin Name: My Plugin */ ?>",
    "includes": {
      "helper.php": "<?php // helper code ?>"
    }
  }
}
  • files uses nested objects for subdirectories — keys are filenames or directory names, values are plain strings (file content) or objects (subdirectories). Never use resource references as values.
  • Do NOT use path separators in keys (e.g. "includes/helper.php" is wrong — use a nested "includes": { "helper.php": "..." } object).

Steps Reference

Every step requires "step": "<name>". Any step can optionally include "progress": { "weight": 1, "caption": "Installing..." } for UI feedback.

Plugin & Theme Installation

{
  "step": "installPlugin",
  "pluginData": { "resource": "wordpress.org/plugins", "slug": "gutenberg" },
  "options": { "activate": true, "targetFolderName": "gutenberg" },
  "ifAlreadyInstalled": "overwrite"
}
{
  "step": "installTheme",
  "themeData": { "resource": "wordpress.org/themes", "slug": "twentytwentyfour" },
  "options": { "activate": true, "importStarterContent": true },
  "ifAlreadyInstalled": "overwrite"
}
  • Use pluginData / themeData — NOT the deprecated pluginZipFile / themeZipFile.
  • pluginData / themeData accept any FileReference or DirectoryReference — a zip URL, a wordpress.org/plugins slug, a git:directory, or a literal:directory (no zip wrapper needed).
  • options.activate controls activation. No need for a separate activatePlugin/activateTheme step when using installPlugin/installTheme.
  • ifAlreadyInstalled: "overwrite" | "skip" | "error"

Activation (standalone)

Only needed for plugins/themes already on disk (e.g. after writeFile/writeFiles):

{ "step": "activatePlugin", "pluginPath": "my-plugin/my-plugin.php" }
{ "step": "activateTheme", "themeFolderName": "twentytwentyfour" }

File Operations

{ "step": "writeFile", "path": "/wordpress/wp-content/mu-plugins/custom.php", "data": "<?php // code" }

data accepts a plain string (as shown above) or a resource reference (e.g. { "resource": "url", "url": "https://..." }).

{
  "step": "writeFiles",
  "writeToPath": "/wordpress/wp-content/plugins/",
  "filesTree": {
    "resource": "literal:directory",
    "name": "my-plugin",
    "files": {
      "plugin.php": "<?php\n/*\nPlugin Name: My Plugin\n*/",
      "includes": {
        "helpers.php": "<?php // helpers"
      }
    }
  }
}

writeFiles requires a DirectoryReference (literal:directory or git:directory) as filesTree — not a plain object.

Other file operations: mkdir, cp, mv, rm, rmdir, unzip.

Running Code

runPHP:

{ "step": "runPHP", "code": "<?php require '/wordpress/wp-load.php'; update_option('key', 'value');" }

GOTCHA: You must require '/wordpress/wp-load.php'; to use any WordPress functions.

wp-cli:

{ "step": "wp-cli", "command": "wp post create --post_type=page --post_title='Hello' --post_status=publish" }

The step name is wp-cli (with hyphen), NOT cli or wpcli.

runSql:

{ "step": "runSql", "sql": { "resource": "literal", "name": "q.sql", "contents": "UPDATE wp_options SET option_value='val' WHERE option_name='key';" } }

Site Configuration

{ "step": "setSiteOptions", "options": { "blogname": "My Site", "blogdescription": "A tagline" } }
{ "step": "defineWpConfigConsts", "consts": { "WP_DEBUG": true } }
{ "step": "setSiteLanguage", "language": "en_US" }
{ "step": "defineSiteUrl", "siteUrl": "https://example.com" }

Other Steps

StepKey Properties
loginusername?, password? (default "admin" / "password")
enableMultisite(no required props)
importWxrfile (FileReference)
importThemeStarterContentthemeSlug?
importWordPressFileswordPressFilesZip, pathInZip? — imports a full WordPress directory from a zip
requestrequest: { url, method?, headers?, body? }
updateUserMetauserId, meta
runWpInstallationWizardoptions? — runs the WP install wizard with given options
resetData(no props)

Common Patterns

Inline mu-plugin (quick custom code)

{
  "step": "writeFile",
  "path": "/wordpress/wp-content/mu-plugins/custom.php",
  "data": "<?php\n// mu-plugins load automatically — no activation needed, no require wp-load.php\nadd_filter('show_admin_bar', '__return_false');"
}

Inline plugin with multiple files

{
  "step": "writeFiles",
  "writeToPath": "/wordpress/wp-content/plugins/",
  "filesTree": {
    "resource": "literal:directory",
    "name": "my-plugin",
    "files": {
      "my-plugin.php": "<?php\n/*\nPlugin Name: My Plugin\n*/\nrequire __DIR__ . '/includes/main.php';",
      "includes": {
        "main.php": "<?php // main logic"
      }
    }
  }
}

Then activate it with a separate step:

{ "step": "activatePlugin", "pluginPath": "my-plugin/my-plugin.php" }

Plugin from a GitHub branch

{
  "step": "installPlugin",
  "pluginData": {
    "resource": "git:directory",
    "url": "https://github.com/user/repo",
    "ref": "feature-branch",
    "refType": "branch",
    "path": "/"
  }
}

Common Mistakes

MistakeCorrect
pluginZipFile / themeZipFilepluginData / themeData
"step": "cli""step": "wp-cli"
Flat object as writeFiles.filesTreeMust be a literal:directory or git:directory resource
Path separators in files keysUse nested objects for subdirectories
runPHP without wp-load.phpAlways require '/wordpress/wp-load.php'; for WP functions
Invented top-level keysOnly documented keys work — schema rejects unknown properties
Inventing proxy URLs for GitHubUse git:directory resource type
Omitting refType with branch/tag refRequired — only "HEAD" works without it
Resource references in literal:directory files valuesValues must be plain strings (content) or objects (subdirectories) — never resource refs
features.debug or other invented feature keysfeatures only supports networking and intl — use constants: { "WP_DEBUG": true } for debug mode
require wp-load.php in mu-plugin codeOnly needed in runPHP steps — mu-plugins already run within WordPress
Schema URL with .org domainMust be playground.wordpress.net, not playground.wordpress.org

Full Reference

This skill covers the most common steps and patterns. For the complete API, see:

  • Blueprint docs: https://wordpress.github.io/wordpress-playground/blueprints
  • JSON schema: https://playground.wordpress.net/blueprint-schema.json

Additional steps not covered above: runPHPWithOptions (run PHP with custom ini settings), runWpInstallationWizard, and resource types vfs and bundled (for advanced embedding scenarios).

Blueprint Bundles

Bundles are self-contained packages that include a blueprint.json along with all the resources it references (plugins, themes, WXR files, etc.). Instead of hosting assets externally, bundle them alongside the blueprint.

Bundle Structure

my-bundle/
├── blueprint.json          ← must be at the root
├── my-plugin.zip           ← zipped plugin directory
├── theme.zip
└── content/
    └── sample-content.wxr

Plugins and themes must be zipped before bundling — installPlugin expects a zip, not a raw directory. To create the zip from a plugin directory:

cd my-bundle
zip -r my-plugin.zip my-plugin/

Referencing Bundled Resources

Use the bundled resource type to reference files within the bundle:

{
  "step": "installPlugin",
  "pluginData": {
    "resource": "bundled",
    "path": "/my-plugin.zip"
  },
  "options": { "activate": true }
}
{
  "step": "importWxr",
  "file": {
    "resource": "bundled",
    "path": "/content/sample-content.wxr"
  }
}

Creating a Bundle Step by Step

  1. Create the bundle directory and add blueprint.json at its root.
  2. Write your plugin/theme source files in a subdirectory (e.g. my-plugin/my-plugin.php).
  3. Zip the plugin directory: zip -r my-plugin.zip my-plugin/
  4. Reference it in blueprint.json using { "resource": "bundled", "path": "/my-plugin.zip" }.

Full example — a bundle that installs a custom plugin:

dashboard-widget-bundle/
├── blueprint.json
├── dashboard-widget.zip        ← zip of dashboard-widget/
└── dashboard-widget/           ← plugin source (kept for editing)
    └── dashboard-widget.php
{
  "$schema": "https://playground.wordpress.net/blueprint-schema.json",
  "landingPage": "/wp-admin/",
  "preferredVersions": { "php": "8.3", "wp": "latest" },
  "steps": [
    { "step": "login" },
    {
      "step": "installPlugin",
      "pluginData": { "resource": "bundled", "path": "/dashboard-widget.zip" },
      "options": { "activate": true }
    }
  ]
}

Distribution Formats

FormatHow to use
ZIP file (remote)Website: https://playground.wordpress.net/?blueprint-url=https://example.com/bundle.zip
ZIP file (local)CLI: npx @wp-playground/cli server --blueprint=./bundle.zip
Local directoryCLI: npx @wp-playground/cli server --blueprint=./my-bundle/ --blueprint-may-read-adjacent-files
Git repository directoryPoint blueprint-url at a repo directory containing blueprint.json

GOTCHA: Local directory bundles always need --blueprint-may-read-adjacent-files for the CLI to read bundled resources. Without it, any "resource": "bundled" reference will fail with a "File not found" error. ZIP bundles don't need this flag — all files are self-contained inside the archive.

Testing Blueprints

Inline Blueprints (quick test, no bundles)

Minify the blueprint JSON (no extra whitespace), prepend https://playground.wordpress.net/#, and open the URL in a browser:

https://playground.wordpress.net/#{"$schema":"https://playground.wordpress.net/blueprint-schema.json","preferredVersions":{"php":"8.3","wp":"latest"},"steps":[{"step":"login"}]}

Very large blueprints may exceed browser URL length limits; use the CLI instead.

Local CLI Testing

Interactive server (keeps running, opens in browser):

# Directory bundle — requires --blueprint-may-read-adjacent-files
npx @wp-playground/cli server --blueprint=./my-bundle/ --blueprint-may-read-adjacent-files

# ZIP bundle — self-contained, no extra flags needed
npx @wp-playground/cli server --blueprint=./bundle.zip

Headless validation (runs blueprint and exits):

npx @wp-playground/cli run-blueprint --blueprint=./my-bundle/ --blueprint-may-read-adjacent-files

Testing with the wordpress-playground-server Skill

Use the wordpress-playground-server skill to start a local Playground instance with --blueprint /path/to/blueprint.json, then verify the expected state with Playwright MCP. For directory bundles, pass --blueprint-may-read-adjacent-files as an extra argument.

Score

0–100
65/ 100

Grade

C

Popularity17/30

1,118 installs — growing adoption. Source repo has 1,684 GitHub stars.

Completeness27/30

Documented: full SKILL.md body, description, one-line install. Missing: category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Blueprint skill score badge previewScore badge

Markdown

[![Blueprint skill](https://www.claudemarket.ai/skills/wordpress/agent-skills/blueprint/badges/score.svg)](https://www.claudemarket.ai/skills/wordpress/agent-skills/blueprint)

HTML

<a href="https://www.claudemarket.ai/skills/wordpress/agent-skills/blueprint"><img src="https://www.claudemarket.ai/skills/wordpress/agent-skills/blueprint/badges/score.svg" alt="Blueprint skill"/></a>

Blueprint FAQ

How do I install the Blueprint skill?

Run “npx skills add https://github.com/wordpress/agent-skills --skill blueprint” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Blueprint skill do?

Use when creating, editing, or reviewing WordPress Playground blueprint JSON files. Triggers on mentions of blueprints, playground configuration, or requests to set up a WordPress demo environment. The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Blueprint skill free?

Yes. Blueprint is a free, open-source skill published from wordpress/agent-skills. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Blueprint work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Blueprint works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free →
Reach 47,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off
Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed
Launch on Hostinger →
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off
Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw
Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.
Start building free →
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams
Get it set up for you →
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit
Try DataForSEO free →
Reach 47,000+ AI builders
Advertise here →
View on GitHub

Recommended skills

Browse all →
find-skills logo

find-skills

vercel-labs/skills

2.8M installsInstall
frontend-design logo

frontend-design

anthropics/skills

731K installsInstall
grill-me logo

grill-me

mattpocock/skills

726K installsInstall
grill-with-docs logo

grill-with-docs

mattpocock/skills

616K installsInstall
agent-browser logo

agent-browser

vercel-labs/agent-browser

612K installsInstall
vercel-react-best-practices logo

vercel-react-best-practices

vercel-labs/agent-skills

598K installsInstall

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Code Review SkillsGuideBest Openclaw Skills 2026GuideHow To Evaluate Openclaw Skill Before Installing

Skills by category

FrontendBackend & APIsTesting & QASecurityDevOps & CI/CDMCP & ToolingAutomationData & Analysis+20 more

MCP servers by category

AI & MLDeveloper ToolsVector & MemoryFiles & DocsDatabasesFinance & PaymentsBrowser & ScrapingCommunication+8 more

Marketplaces by category

developmentproductivitycommunicationdesignsecuritydatabaseworkflowcompliance+34 more

Claude Market

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

Independent project, not affiliated with Anthropic.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Plugins

More

  • Submit a Tool
  • Advertise
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy

Know a company that should advertise here? Refer them and earn 10% — up to $300 per referral.

© 2026 Claude Market
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed