Web And Browser for AI agents
100 security-reviewed web and browser listings, skills, MCP servers, and toolkits you can install into Claude Code, Cursor, and other agents with one command.
Xiaohongshu Crawler
小红书作品爬取 · 都爆鸭。按关键词爬取小红书热门作品，支持按日期范围筛选与多种排序（综合/最新/最热），终端表格展示（标题链接/作者/点赞/发布时间）并给出选题洞察。当用户需要爬取小红书作品、查小红书热门内容、搜小红书爆款笔记、做某时间段赛道盘点、竞品/选题调研时使用。触发词：小红书爬取、小红书作品、小红书爆款、小红书搜索、小红书热门、小红书笔记查询。
Html Resume
Turn resumes exported from job platforms, existing PDFs, or career notes into independently editable, recruiter-friendly HTML with exact A4 PDF output. Use for resumes, CVs, executive profiles, professional biographies, and portfolio summaries that need Chinese-English translation or same-language rewriting, factual preservation, clear information hierarchy, user-directed color styling, optional…
Observability Dotnet
Thiết lập observability metric cho service .NET — OTEL instrumentation, Prometheus scrape, Grafana dashboard, Prometheus/Alertmanager rules và vận hành. Dùng khi onboard metric mới, tạo dashboard, gắn alert, hoặc chuẩn hóa pipeline OTEL → Prometheus → Grafana.
Deep Reader
Use this skill when the user wants to deeply read, analyze, or extract insights from a web article. Triggers on: providing a URL link, or '深度阅读' or 'article analysis,' or using magic commands like /ELI5, /Challenge, /Action, /Graph, /Deep on a previously shared article. The skill fetches the article content with proper headers (mimicking WeChat browser), converts it to clean Markdown, and provide…
Browser Obscura
A Claude skill from icheer/skills.
Agent Browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to…
Artify
Build self-contained, single-file HTML artifacts and serve them with the artify CLI. Use for visualizations, interactive tools, presentations, living documents, forms and quizzes that return structured data via artify snapshot, and any browser-native replacement for static files. Prefer adapting starters when there is a close fit; otherwise build from scratch.
Browser Usage
Core agent-browser usage guide — read before running any agent-browser command. Use when the user asks to interact with, test, or automate a website — clicking, filling forms, extracting data, taking screenshots, logging in.
Web2Skill
Convert one public website URL or an explicit batch of public URLs into a reusable skill zip backed by rendered HTML snapshots and a bounded JSONL retrieval index. Use to discover a documentation directory from one URL, crawl a supplied URL set sequentially, generate a source profile, or package indexed web content as a specialized skill.
Threads Explore
Threads 內容抓取與瀏覽。觸發詞：搜索、查找、瀏覽首頁、刷一下、抓帖子、爬帖子、獲取帖子、看帖子詳情、查看用戶、用戶主頁、歷史回復、回復記錄、list-feeds、search、get-thread、user-profile、user-replies、抓取數據。
Threads Content Ops
Threads 複合運營工作流。觸發詞：競品分析、分析競爭對手、熱點追蹤、找熱門話題、批量互動、批量操作、內容策劃、運營計劃、推廣評論、定時抓帖評論、自動評論、篩選帖子並評論、醫美推廣。
Threads Interact
Threads 社交互動。觸發詞：點讚、按讚、like、轉發、repost、回覆、評論、reply、關注、follow、對這個帖子點讚、回覆這條帖子、like-thread、reply-thread、repost-thread、follow-user。
Threads
|
Threads Publish
Threads 發帖與內容發布。觸發詞：發帖、發布、寫帖子、po文、發Thread、寫一條、發一條、帶圖發帖、發圖片、post-thread、fill-thread、click-publish。
Threads Auth
Threads 認證與帳號管理。觸發詞：登錄、登出、檢查登錄、是否已登錄、登入狀態、切換帳號、退出帳號、清除Cookie、添加帳號、新增帳號、多帳號、帳號列表、設置默認帳號、刪除帳號、check-login。
Threads Skills
Threads 平台全自動化操作套件。觸發詞：登錄、登出、檢查登錄、是否已登錄、切換帳號、清除Cookie、多帳號管理、搜索、查找、瀏覽首頁、刷一下、抓帖子、獲取帖子、看帖子詳情、查看用戶、用戶主頁、歷史回復、發帖、發布、寫帖子、po文、發Thread、帶圖發帖、點讚、轉發、回覆、評論、關注、批量回覆、批量評論、GUI回覆、篩選帖子、智能篩選、熱度評分、競品分析、熱點追蹤、批量互動、運營計劃、自動評論。
Threads Batch Reply
Threads 批量回覆助手。觸發詞：批量回覆、批量評論、逐條回覆、一次回覆多個帖子、GUI回覆、彈窗回覆、reply_assistant、幫我回覆這些帖子、批量發評論。
Threads Filter
Threads 智能篩選 Skill。三源採集（Feed+關鍵詞+對標帳號）+ 三維熱度評分（互動/跨源/時效）+ AI雙關篩選（排除詞→語境判斷）。觸發詞：篩選帖子、智能篩選、找目標帖子、哪些帖子適合評論、評論目標篩選、抓帖篩選、先篩選再評論、find posts to comment、filter posts、三維評分、熱度評分。輸出按優先級排序的評論候選列表。
Agentcore Browser
|
Xianyu Monitor
Search and monitor Xianyu/Goofish (闲鱼) with private state, filters, tasks, and deduplication. Use for 搜闲鱼、闲鱼登录、上新监控、蹲二手 or recurring searches.
Security And Hardening
Harden software against security risk. Use when handling user input, authentication, authorization, sessions, secrets, file uploads, external integrations, webhooks, browser data, storage, or privileged actions.
Douyin Env
检查、安装、迁移和排查 douyin-skills 本地运行环境，包括 Python、Node.js、ws、Chrome/Chromium、图形环境和本地 Profile。用户要求安装、配置、部署、迁移、环境自检或解决依赖问题时使用。
Douyin Skills
抖音网页版与创作者中心的本地自动化技能包入口。用于组合登录、搜索、图文发布、点赞、收藏、分享链接，或解释整体能力、安全边界与多步骤流程；单一任务优先使用对应的 douyin-* 子技能。
Douyin Explore
在抖音网页版按关键词搜索公开作品，并读取 video 或 note 作品详情。用户要求搜索抖音、查找作品、查看公开作品详情或解析抖音作品链接时使用。
Douyin Interact
对明确指定的抖音公开 video 或 note 作品执行一次点赞、收藏按钮点击，或返回分享链接。用户要求点赞、收藏、取消相应状态或获取抖音作品链接时使用。
Douyin Auth
管理抖音网页版登录状态、二维码登录、短信验证码登录和本地多账号 Profile。用户要求登录、检查登录状态、添加或切换账号时使用。
Douyin Publish
在抖音创作者中心填写图文发布表单、上传本地图片、选择音乐、校验页面，并在明确复核后点击发布。用户要求发布抖音图文或检查待发布内容时使用；不用于视频、草稿或定时发布。
Multi Ai Chat Skill
Multi AI Research → Decision → Solution Generator。用户要的是一份可执行的决策/方案文档时用本技能：把问题并行分发给多个网页 AI 作答，再由主 agent 提炼成 AI Decision & Solution Document（不是 AI 回答汇总）。触发场景：技术选型/架构/产品/商业决策、需要多视角研究后形成方案决策、写方案/出方案、头脑风暴/新产品设计、新框架/新概念的系统性学习、对比几个选项选哪个。不适用：单 AI 快速一问、只要并行原始回答不要合成文档、纯总结归纳、常规问答、单次技术问答、代码 debug、简单事实/概念解释（已有明确答案只需解释时）、涉及本技能自身（评估/编写/优化 skill）——不涉及"多个网页 AI 并行 + 合成决策文档"时不需本技能。
Claudezilla
Firefox browser automation for Claude Code. No Google account required.
Dynamic Content Extraction
dynamic-content-extraction — Extract structured data from JavaScript-heavy sites where prices, text, or key fields don't appear in the standard accessibility tree. Covers browser_snapshot(full=true), TreeWalker text-node extraction, lazy-load handling, and React split-text recovery.
Browser Harness Authoring
Use when mapping a repeatable website workflow into a verified Hermes skill so later runs can follow known steps instead of rediscovering the site. Surveys browser compatibility, semantic targets, failure modes, recovery paths, decision gates, and expiry using dummy data and no irreversible submissions.
Cross Browser Typography Qa
cross-browser-typography-qa — Diagnose and verify web typography rendering defects across Chromium, WebKit, and native Safari, including clipped glyphs, broken descenders, wrapping, font metrics, gradient text, and live-cache mismatches.
Frontend Design
Design, implement, and verify production frontend interfaces for websites, applications, dashboards, components, and responsive web experiences. Use when Codex or Hermes must create or improve UI code while respecting the existing repository, accessibility, responsive behavior, interaction states, performance, and browser-based visual QA.
Seo
Perform an evidence-led SEO audit using accessible pages, source code, crawl data, and current search documentation without assuming missing plugins.
Browser Cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP, agent-browser, 浏览器操作, 操作浏览器, Chrome CDP, 复用登录态, extract token from browser.
Cmux
Drive the local cmux app — workspaces, panes, surfaces, terminal input, agent sessions, and browser surfaces.
Verify
Drive an engine app headlessly in a pty, record a video of the whole verification, and open a summary page (video + timeline + checks) with pixel open.
Xcatcher
Fetch fresh or recent public X (Twitter) posts from one or many named account handles through Xcatcher, with structured JSON results and optional x402 v2 USDC pay-per-crawl access on Base. Use for account monitoring, social intelligence, OSINT, tweet/post collection, timeline snapshots, or requests to scrape, crawl, watch, compare, or summarize specified X/Twitter handles or profile URLs.
Mcp Web Bridge
webmcp-bridge is a WebMCP-focused browser app that turns remote MCP servers into browser-usable tool context, so you can discover capabilities, execute them, and expose them through navigator.modelContext for next-gen browser AI workflows.
Rever Browser
AI agent browser for web reverse engineering
Nehemiah
On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.
Unegui Mn Mcp
MCP server for unegui.mn — Mongolia's classifieds marketplace (EN/MN)
Reverse Api Engineer
The agent that turns websites into APIs!
Bwb Browser
Browser Without Bloat — 30KB MCP browser automation server. Raw CDP, zero bloat, works on any platform (Termux, Linux, macOS, Windows). The only MCP browser with live console/network event capture.
Nuphus Mcp
Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio)
Setup Chromium
Prepare and verify Appium Chromium for Chrome, Chromium, or Edge desktop automation by validating Node/Appium, browser prerequisites, driver installation, doctor support, and a minimal browser-session smoke check. Use after the setup Skill selects Chromium. Do not use for an existing Chromium runtime failure after prerequisites pass.
Kivixa
A privacy-first cross-platform productivity workspace for notes, sketching, planning, and local AI assistance.
Director
Director: AI-first local system for producing live-app presentation videos and decks.
Bowser
Headless browser automation using Playwright CLI. Use when you need headless browsing, parallel browser sessions, UI testing, screenshots, web scraping, or browser automation that can run in the background. Keywords - playwright, headless, browser, test, screenshot, scrape, parallel.
Perplexity Webui Search
Use when the user asks to search Perplexity, query Perplexity through the web UI, perform web research with Perplexity, save a Perplexity answer as Markdown, or retrieve a Perplexity answer through browser automation.
Doska
A local-first Kanban board with Markdown cards. Runs in the browser or as a Tauri desktop app. Works offline, and syncs to a server you control.
Quantumproxies Io
Residential, datacenter, ISP & mobile proxies with 90M+ IPs in 200+ countries — plus Scraper & SERP APIs. Code examples in Python, Node.js, PHP, Go, Java, C#, Ruby and curl.
Agnt
MCP Server for Development Tooling - Project Detection, Process Management, and Reverse Proxy with Frontend Instrumentation
Figma Code To Canvas
Bring live or local web UI back into Figma as editable design layers when Figma MCP code-to-canvas or generate-design capability is available. Use this skill when the user says production, staging, localhost, or a browser-rendered page is ahead of Figma and wants to sync, capture, recreate, or convert the live UI into a Figma file while preserving privacy and evidence.
Cursor Reveal Hero
Build, repair, tune, and validate interactive cursor-trail mask reveal hero effects in frontend projects. Use when implementing canvas-based base/reveal compositing, soft radial cursor masks, fading cursor trails, reveal debug controls, full-screen hero scenes without site text, or browser smoke checks for cursor reveal, hover reveal, before/after reveal, and mask compositing effects.
Grapesjs Html Compliance
GrapesJS editor compatibility rules for HTML slide generation. Use when generating or editing HTML that will be loaded into the GrapesJS editor — covers canvas constraints, component model, script/style handling rules, and a mandatory self-check checklist. NOT for standalone browser HTML, server-rendered pages, or non-GrapesJS contexts.
Bladebro
An agentic browser driver for AI — few tools, full control, real stealth, god-tier token efficiency.
Impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, ac…
Ui Mockups
Explore a UI surface as several radically different, repository-grounded HTML mockups, render them, and converge on a locked visual specification. Use when asked to design, mock up, compare, or redesign a screen, dashboard, flow, or component before implementation.
Cbm Onboard
Register a Git repository with codebase-memory-mcp, create a managed .cbmignore baseline, install a non-clobbering post-commit reindex hook, and run the initial index. Use when asked to index, onboard, register, or keep a repository current in Codebase Memory.
Drive Local Webapp
Launch or connect to a local development web server and drive it with a reusable headless-Chromium command interface. Use when asked to render, smoke-test, interact with, verify, or screenshot a local frontend or HTML mockup.
Spin Worktree
Create an isolated Git worktree for issue, pull-request, branch, or parallel agent work without editing the control checkout. Use when starting task work from fresh remote state, avoiding a dirty or shared checkout, or preparing a dedicated worktree for another agent.
Claudeck
A browser-based UI for Claude Code — chat, run workflows, manage MCP servers, track costs, and orchestrate autonomous agents from a local web interface. Installable as a PWA.
Test Ui
Generic, stack-agnostic UI testing process for any web project — visual regression, responsive + cross-browser, WCAG 2.2 AA accessibility (axe → manual → screen reader), component/state matrix, internationalization/locale-integrity (pseudo-locale + rendered-output scan), and design-token fidelity. Use when asked to UI-test, check accessibility/a11y, run visual-regression, responsive-test, audit t…
X Presence
Run an unattended X/Twitter presence — watch topics and mentions in real time, draft posts and replies in the user's own voice, publish original posts on a schedule, and hold replies for a one-tap approval. Trigger whenever the user wants to automate their X/Twitter account, grow an audience on X, schedule or draft tweets, set up an X routine or cron job, get alerted about topics or mentions on X…
X Twitter Data
Read live X/Twitter data — a single tweet or profile, tweet and user search with the full operator set, user timelines, replies, quotes, followers and following, list and community contents, and trending topics. Trigger whenever the user wants information from X/Twitter: looking up a tweet or account, searching X for a topic or phrase, checking someone's followers or recent posts, reading a threa…
X Twitter Research
Export bulk X/Twitter datasets as downloadable files — follower and following lists, everyone who replied to or reposted or quoted a post, full threads, likers, mentions, user media, community members, list members, and people or tweet search results, across 23 extractors. Trigger whenever the user wants X data in bulk or as a file: exporting followers, analysing who engaged with a post, auditing…
X Twitter Publish
Publish to X/Twitter through an account the user connects once — draft and score post text with AI, then post, reply, quote, delete, upload media, or edit the profile. Trigger whenever the user wants to write or send something on X/Twitter: posting a tweet or thread, replying to someone, drafting or improving tweet copy, scheduling content, connecting their X account, or updating their X bio or a…
X Twitter Monitor
Watch an X/Twitter account or keyword in real time and receive events the moment they happen — new posts, replies, reposts, quotes, mentions, and profile changes — by polling a free event feed or by registering an HMAC-signed webhook. Trigger whenever the user wants to be notified about X activity, watch or track an account or topic, get alerted on mentions, stream X events to their own endpoint,…
Kasm Browser
Drive a persistent interactive browser via Chrome DevTools Protocol (KASM Chrome)
Browser Screenshot
Capture a screenshot of a URL using a headless Chromium service (Browserless)
Triage Visual Changes
Triage a UI Verify build from your coding agent via the UI Verify MCP — bucket a build's changed stories into real regressions vs cosmetic reflow vs rendering noise, summarize the real regressions for a PR comment, and accept baselines in bulk. Use after a UI Verify build reports changes and you want the agent to review, summarize, or accept from the terminal instead of clicking through the dashb…
Playwright Visual Testing
Make @uiverify/playwright (archive-replay) captures deterministic so real-page visual tests stop coming back "changed" without a real change (flaky diffs). Use when driving a real page — your app under test, a staging build, or live production — and the diff flakes. A symptom-to-lever checklist for the run-to-run variation you probably have: feature flags, live data, the clock, third-party widget…
Economical Stories
Author economical visual-test stories — full visual coverage in the fewest billable snapshots. Applies to any per-snapshot visual tool (UI Verify, Chromatic, Percy, Playwright screenshots), which all bill and diff per rendered story. Use when a component's variants/states are exploding into one story per combination, when the visual-testing bill or noise is driven by snapshot count, or when writi…
Storybook Visual Testing
Make Storybook stories deterministic for UI Verify so captures stop coming back "changed" without a real change (flaky diffs). Use when setting up story-level visual tests or debugging a story that diffs every run. Focuses only on the run-to-run variation the capturer can't neutralize from outside your app — the clock, infinite JS animations, live data, and non-Math.random randomness — and delibe…
Qa Tester
Comprehensive quality assurance testing for websites — the holistic "does this site actually work?" check. Triggers on phrases like "test my site", "QA check", "does everything work", "quality check", "smoke test", "test before launch", "site not working", "check all pages", "broken pages", "test forms", "check mobile", "cross-browser", "regression test", or "broken links".
Seo Geo Setup
Use when registering a site with search engines (Google Search Console, Naver, Bing, Daum, Pinterest), optimizing for AI search engines / GEO (ChatGPT, Perplexity, Gemini, Copilot citations, llms.txt, AI crawler access), or setting up local SEO (Google Business Profile, Naver Place, Kakao Maps, Yelp). Triggers: "SEO 세팅", "검색엔진 등록해줘", "서치콘솔", "네이버 웹마스터", "GEO", "AI 검색에 뜨게 해줘", "챗GPT가 우리를 인용 안 해",…
Visual Plan
Use when the user wants to review an implementation plan visually — "visual plan", "show me the plan in the browser", "render this plan" — or when a plan involves architecture, schema, or API changes worth reviewing before code is written. Writes the plan as markdown and serves it locally (bundled zero-dependency server) with Mermaid diagrams, rich diffs, DB migration cards, API call cards, live…
Visual Recap
Use when the user wants a visual summary of work that was done — "visual recap", "recap this PR/branch/commit visually", "show me what changed in the browser" — for a PR, branch, commit range, or uncommitted changes. Generates a markdown recap grounded in the real diff and serves it locally (bundled zero-dependency server) with Mermaid diagrams, annotated rich diffs, DB migration cards, API call…
Basketeer
Typed, pure-HTTP TypeScript SDK for your own Tesco grocery account — search, basket, nutrition, delivery slots, and orders over plain fetch. Browser only for login + payment.
Ig Card Generator
把知識素材（文章、講稿、筆記、逐字稿，或只有一個主題）提煉成 IG 輪播知識圖卡：封面 hook → 每卡一概念 → 結尾 CTA。以約定 Markdown DSL 撰寫，經 lint（criteria 全過）後由 build script 產出 1080×1350 PNG 系列圖（支援深／淺色主題）。當使用者說「做 IG 圖卡」「知識圖卡」「輪播圖」「carousel」「把這篇做成圖卡」「IG 貼文圖」「圖卡系列」時使用。出圖完成後可銜接 promo-writer 產生貼文 caption。
Godot Stagehand
Playwright inspired tool for testing Godot games
Opentakeoff
Open-source (Apache-2.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP, not bolted on. One-click room detection, materials + quantities, built for preconstruction. Runs entirely in your browser.
PyScrappy
Python web scraping toolkit and MCP server that gives AI agents clean, structured web data from any URL or built-in scrapers.
Playwright
>
Emscripten Env Audit
Static analysis of Emscripten build flags targeting AudioWorkletGlobalScope. Parses a Makefile or build script, extracts emcc flags, and cross-references against a known list of APIs unavailable in the worklet environment. Flags configuration patterns that will cause runtime failures in the browser.
Wasm Worklet Smoke
Headless Playwright smoke test for an Emscripten + AudioWorklet WASM build. Builds the WASM target, serves it locally, launches headless Chrome, clicks Start Audio, verifies the engine initialises without console errors, and checks for non-silent audio output.
Google Flow Mcp
MCP server that drives Google Flow (Veo / Nano Banana) through its internal tRPC API, with a hard credit-cost gate
Openrouter Register
OpenRouter 全链路自动化 — Outlook 注册 → OpenRouter 注册 → API Key 创建 → 邮件通知 → Web 管理
Mcp Realbrowser
A persistent browser profile for your AI — log in once, sessions stay forever. 20 MCP tools for Claude Code,auto-detects your default browser.
Rendering Spec Docs
Use when asked to render, view in a browser, or share a spec / plan / design / brainstorm / handoff / notes markdown file as HTML — including superpowers specs and plans (docs/superpowers/specs, docs/superpowers/plans), or any *-design.md / *-plan.md. Triggers on "show me the doc in html", "render this spec/plan", "make an html version".
Vigia
Use when you need to audit a website or a local build for responsiveness, cross-browser rendering (including WebKit/Safari), broken layout, smoke errors (JS exceptions, failed assets, broken images), HTTP delivery config (compression, caching, security headers, redirects), and performance (Lighthouse budget). vigia diagnoses and never edits code. Trigger when the user asks "is my site broken / re…
Argus
Autonomous QA MCP that tests web and macOS apps like a real testing engineer—and verifies every bug it reports.
Browser Engine
Build browser games that are actually PLAYABLE — 2D or 3D — not tech demos. Use for ANY request to build, prototype, or fix a game that runs in a web browser (canvas/WebGL/WebGPU) — top-down, platformer, shooter, puzzle, 3D. Kills the #1 AI-game failure where "solid" objects are just drawn and the player walks straight through them. Routes to game-collision (make it solid) and game-optimization (…
Game Collision
Make browser-game objects ACTUALLY solid — the fix for the #1 AI-game failure where a rock is drawn but the player walks straight through it. Use whenever anything in a game must block, hit, stand on, or push anything else. Covers the sprite≠body rule, footprint hitboxes (collide at the base, not the whole picture), tilemap collision layers, y-sort depth (walk behind the tree), axis-separated res…
Brainstorm Game Design
Brainstorm-mode for designing a browser game's CONCEPT before any code — pillars, core loop, player fantasy, mechanics, scope, win/loss. Use when the user wants to design a new game, rethink an existing one, or figure out "what is this game." Facilitates the brainstorm AND writes every accepted decision into game-design/GDD.md in the user's project so no agent (Claude, Cursor, Antigravity) ever l…
Game Optimization
Make a browser game hold a rock-solid 60fps (or 120+) under real load, in 2D or 3D. Use whenever a game stutters, slows as entities spawn, runs at different speeds on different machines, or before claiming a game is "done." Covers the fixed-timestep game loop (framerate-independent, deterministic physics), object pooling (zero-GC steady state), sprite batching / texture atlases (fewer draw calls)…
Brainstorm Level Design
Brainstorm-mode for designing a browser game's LEVELS and encounters — layout, pacing, difficulty curve, teaching mechanics, critical path, secrets. Use when designing a level, stage, room, arena, or wave, or planning a game's progression. Reads game-design/GDD.md for the game's pillars, then writes each level to game-design/levels/<name>.md so no agent loses the design. Kills flat, arbitrary lev…
Framejs
Create, modify, and share interactive browser apps and visualizations from JavaScript via framejs.io. The app is encoded into a shareable URL that runs instantly — no build, server, or account. Use when the user wants a chart, graph, plot, dashboard, animation, simulation, creative coding sketch, data visualization, or small interactive web tool; when they reference a framejs.io short URL (/j/<sh…
Write Tests
Write Vitest unit/integration tests OR Playwright e2e tests for an existing source file (server action, page, component, query). Reads the project''s wired test framework from `.workflow/meta.json#stack.test`, follows the mocking patterns already present in `vitest.setup.ts` and any sibling test files. Use when the user says "scrivi i test per X", "test per la server action Y", "e2e per /clienti"…