wp-playground
Use as the WordPress Playground routing wrapper for ambiguous Playground work, local CLI runs with @wp-playground/cli, playground.wordpress.net share links, browser previews, WebMCP site tools, snapshots, mounts, version switching, and Xdebug. For Blueprint JSON authoring or review, use the blueprint skill directly.
- Installs
- 4.7K
- Last 24h
- +28
- Trending rank
- #4518
- Security
- Warn
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/wordpress/agent-skills --skill wp-playground- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads wp-playground automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
Security audits
Independent scans of the skill's instructions and bundled files.
SKILL.md
The instructions your agent reads when the skill is triggered.
WordPress Playground
This is a thin routing wrapper. Use it to pick the right Playground workflow, then load only the focused reference or skill needed for the task.
Procedure
- Identify the user intent: Blueprint authoring/review, local CLI execution, browser-only website/share link workflow, Xdebug/stuck CLI run, or a mixed Playground request.
- Route to the focused source below, loading more than one only when the request has multiple distinct parts.
- For mixed requests, delegate Blueprint JSON work to
blueprint, then return here for runtime, CLI, debugging, or sharing guidance.
- Blueprint JSON, schema, steps, resources, bundles, or Blueprint review: use the
blueprintskill directly. Do not duplicate Blueprint schema details here. - Local CLI execution: read
references/cli.mdfor@wp-playground/cliserver,run-blueprint,build-snapshot, mounts, version switching, and local validation. - Xdebug or stuck CLI runs: read
references/debugging.mdfor Xdebug, runtime logs, worker flags, and stuck CLI runs. - Browser-only Playground website workflows: read
references/website.mdfor Query API and Blueprint URL setup, share links, and browser limitations. It routes existing-site operations to separate WebMCP, Playground MCP, and Sites API references; load only the selected method. Unless the user requests a specific connection method, prefer available WebMCP tools for supported browser operations.
Inputs required
- The intended workflow: Blueprint authoring, local CLI run, website/share link, snapshot, or debugging.
- Project or bundle path if local code must be mounted or packaged.
- Desired WordPress/PHP versions if compatibility matters.
- Port preference if a local server is needed.
- Whether browser-only sharing or local filesystem access is required.
Guardrails
- Playground instances are disposable, SQLite-backed environments; never point them at production data.
- Keep Blueprint JSON guidance in
blueprintso the schema and examples have one source of truth. - For local CLI work, verify Node.js 20.18+ and
npm/npxbefore running commands. - Browser-only Playground cannot read local filesystem paths; use public URLs, hosted ZIP bundles, or inline Blueprint JSON.
Verification
- For Blueprint content, validate against the published schema and follow the
blueprintskill verification. - For local CLI runs, verify the mounted plugin/theme or Blueprint side effects in the Playground instance.
- For share links, open the generated URL and confirm the expected landing page and installed assets load.
Failure modes
- Blueprint work routed here: stop and use the
blueprintskill for schema keys, steps, resources, bundles, validation, or Blueprint review. - Local filesystem needed in a browser-only workflow: use
references/cli.md;playground.wordpress.netcannot read local filesystem paths. - Shareable browser link requested from a local CLI workflow: use
references/website.md; local server URLs are not portable share links. - Debugging treated as a second-hop reference: read
references/debugging.mddirectly for Xdebug, logs, worker flags, and stuck CLI runs.
Escalation
- If the task needs PHP extensions, native database access, persistence, or production-like infrastructure that Playground cannot provide, use a full WordPress stack such as wp-env, Docker, or the project-provided environment.
FAQ
What does the wp-playground skill do?
Use as the WordPress Playground routing wrapper for ambiguous Playground work, local CLI runs with @wp-playground/cli, playground.wordpress.net share links, browser previews, WebMCP site tools, snapshots, mounts, version switching, and Xdebug. For Blueprint JSON authoring or review, use the blueprint skill directly.
How do I install wp-playground?
Run npx skills add https://github.com/wordpress/agent-skills --skill wp-playground in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/wp-playground/ (personal) or .claude/skills/wp-playground/ (project).
Which AI agents can use wp-playground?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is wp-playground safe to install?
Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk flagged items to review; Runlayer flagged items to review; ZeroLeaks passed. As with any skill, read the SKILL.md and bundled scripts before installing.
Who maintains wp-playground?
It is published by wordpress in wordpress/agent-skills, and it is an official skill from the maker of the technology it covers. It has 4,727 recorded installs.
More from wordpress/agent-skills
wp-plugin-development
wordpress/agent-skills
Use when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security (nonces/capabilities/sanitization/escaping), and release packaging.
wp-performance
wordpress/agent-skills
Use when investigating or improving WordPress performance (backend-only agent): profiling and measurement (WP-CLI profile/doctor, Server-Timing, Query Monitor via REST headers), database/query optimization, autoloaded options, object caching, cron, HTTP API calls, and safe verification.
wp-rest-api
wordpress/agent-skills
Use when building, extending, or debugging WordPress REST API endpoints/routes: registerrestroute, WPRESTController/controller classes, schema/argument validation, permissioncallback/authentication, response shaping, registerrestfield/registermeta, or exposing CPTs/taxonomies via showinrest.
wp-block-themes
wordpress/agent-skills
Use when developing WordPress block themes: theme.json (global settings/styles), templates and template parts, patterns, style variations, and Site Editor troubleshooting (style hierarchy, overrides, caching).
wordpress-router
wordpress/agent-skills
Use when the user asks about WordPress codebases (plugins, themes, block themes, Gutenberg blocks, WP core checkouts) and you need to quickly classify the repo and route to the correct workflow/skill (blocks, theme.json, REST API, WP-CLI, performance, security, testing, release packaging).
wp-block-development
wordpress/agent-skills
Use when developing WordPress (Gutenberg) blocks: block.json metadata, registerblocktype(frommetadata), attributes/serialization, supports, dynamic rendering (render.php/rendercallback), deprecations/migrations, viewScript vs viewScriptModule, and @wordpress/scripts/@wordpress/create-block build and test workflows.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available