Results for “agent-browser”

Fetches MDN Web Docs content via the Yari API and search index, including browser compatibility data, Web API references, and CSS property documentation, with offline lookups using the BCD npm package.

Routing-first visual approval gate for AI agent plans, markdown specs, and diffs. Use when a human needs to review a concrete plan before execution, inspect a targeted diff in a browser, mark up a spec/PRD/architecture note, or set up the review loop on Claude Code, Gemini CLI, Codex CLI, or OpenCode. Route planning/spec creation to `task-planning` or `ralph`, broad PR-policy review to `code-review`, rendered-UI critique to `agentation`, and fresh-session browser verification to `browser-harness`.

Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".

Inspect, create, close, and rearrange cmux workspaces, panes, surfaces, and agent sessions, and send input or monitor agents running inside cmux from macOS terminal workflows.

Drives a real desktop GUI as a fallback when APIs, CLIs, file edits, and browser automation are unavailable, letting agents click, type, read the screen, and control apps across Windows, macOS, and Linux.

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Control cmux workspaces, panes, surfaces, and agent sessions safely from macOS terminal workflows.

Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Instrument browser/web apps with the Application Insights JavaScript SDK for Real User Monitoring (RUM), including page views, clicks, AJAX/fetch dependencies, exceptions, custom events, and GenAI agent traces correlated to backend OpenTelemetry traces.

Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing, browser automation, fixing flaky tests, test migration, CI/CD testing, or test suites. Generate tests, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55 templates, 3 agents, smart reporting.

Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing, browser automation, fixing flaky tests, test migration, CI/CD testing, or test suites. Generate tests, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55 templates, 3 agents, smart reporting.

Drive Moli (`moli`), Lexmount's open-source headless browser for AI agents, built around on-demand rendering: real JavaScript, DOM, and CSS by default, with layout and pixels computed only when explicitly requested via `--layout`. Use when the user wants to fetch/extract a live JavaScript-rendered page as Markdown/HTML/JSON/semantic-tree, capture a screenshot or PDF, run a small bounded crawl, start a CDP/WebDriver automation server for Playwright/Puppeteer, replace a Chromium/ChromeDriver dependency, or diagnose readiness/network/frame issues on a rendered page. Triggers on: "moli fetch", "moli serve", "headless browser for agents", "on-demand rendering browser", "CDP server without Chrome", "structure-first web scraping", "Lexmount browser", "moli-webfetch", "moli-cdp-server".

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the browser embedded inside the Orca app. Use when the user says "$orca-cli", "use orca cli", "Orca worktree", "child worktree", "cardStatus", "spawn codex/claude in a worktree", "read/wait/send Orca terminal", "terminal send", "full handoff", "handover", "give this to another agent", "another worktree", "Orca browser", or "control the browser inside Orca". Prefer this over raw `git worktree`, ad hoc PTYs, Playwright, or Computer Use when the task touches Orca-managed state. Use Computer Use for browser windows, webviews, or desktop UI outside Orca's embedded browser.

Playwright-powered browser automation and E2E testing for SolanaOS Hub. Covers test configuration, agent-driven test generation (planner/generator/healer), NanoHub route testing, Convex API validation, wallet flow testing, IPFS Hub verification, and CI/CD integration. Use when asked about E2E tests, browser automation, Playwright setup, NanoHub testing, visual regression, or Hub route verification.

Use Orca orchestration for structured multi-agent coordination: threaded messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator loops, or decomposing work across agents. Use `orca-cli` instead for full ownership handoffs, including requests phrased as "hand off", "handoff", "handover", "give this to another agent", or "another worktree" when the user did not explicitly ask to supervise, monitor, wait for results, or coordinate a DAG. Use `orca-cli` for ordinary terminal control, lightweight terminal prompts, shell commands, Orca worktree management, reading or waiting on terminals, and automation of the browser embedded inside Orca. Use Computer Use for browser windows, webviews, Orca app UI, or desktop UI outside Orca's embedded browser.

Use `task-agent` for bounded frontend component or browser changes involving interaction, accessibility, API failures, security, or regression proof. Skip backend-only work and design exploration without implementation.

Use when a human asks to connect to or enter Agent Internet or AI Internet, get their agent online, or open Agent Internet Browser, Bot Browser, a Bot page, a Bot homepage, a domain alias, a chain pin, a MetaApp, a MetaFile, or a map through the existing local Browser entrypoint, including opening a resource in a new Browser tab; also use when the human wants to find or discover on-chain MetaApps by topic, tag, publisher, or time range — such as "what on-chain mini-games exist", "apps published in the last 30 days", or "open the on-chain buzz app" — list the remixes of a known app, read what an app does, or remix and republish an existing MetaApp; also use when the human wants to find or discover on-chain users or Bots by name, personality, skill, or recency — such as "view Alice's bot page", "find cheerful users to chat with", or "find a bot that can translate" — or read an identity's full on-chain profile.

Use when testing, fixing, or extending the MarketingClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

Scaffolds a per-task verification skill for a repo, including a dev-local launcher, a browser driver, and a verification SOP that spawns a sub-agent to drive the app and produce proof.

Add real-time voice conversations to a custom agent runtime using ElevenLabs Speech Engine, handling WebSocket servers, browser clients, and interruption-aware streaming.

Systematically explore a web application to find bugs and UX issues, producing a structured report with screenshots, repro videos, and detailed steps for each finding.

Route web-game auto-playtesting with WAI Play (waiterve/wai-play): decide whether the next move is a testability check, authoring or repairing the `GameFlowAgentAPI` bridge, running a real browser playtest, reading the five-dimension quality report, or unblocking a key node the agent cannot reach. Use when the user wants an AI agent to actually play their HTML5 / canvas / vibe-coded web game and return reproducible evidence, scores, and fix suggestions across the five supported types (survivor-like, arcade shooter, platformer, puzzle/card, visual novel). Triggers on: wai-play, WAI Play, auto-playtest, AI plays my game, web game testing agent, GameFlowAgentAPI, GameFlowIntegration, jumpToScenario, game quality score, playtest evidence. Route Unity/Unreal frame-time work to `game-performance-profiler`, engine build failures to `game-build-log-triage`, human playtest notes to `game-demo-feedback-triage`, and generic browser automation to `browser-harness`.

Expert in Cursor AI IDE - the leading AI-powered code editor. Covers Rules files for project-specific AI behavior, Plan Mode for structured development, Background Agents for parallel work, and advanced features like voice mode and browser integration. Essential for developers maximizing AI-assisted coding productivity. Use when "cursor ai, cursor rules, .cursorrules, cursor composer, cursor agent, plan mode, background agent, cursor tips, cursor, ide, ai-coding, editor, productivity, agent, developer-tools" mentioned.

Route web-scraping work into the lightest workable Scrapling mode instead of defaulting to a browser. Use when the user needs HTML extraction, JS-rendered page retrieval, protected-target escalation, quick CLI scraping, agent-facing MCP access, or a larger crawl with Scrapling spiders. Triggers on: scrapling, scrape website, crawl site, adaptive scraping, selector drift, stealthy fetch, browser scraping, scrape to markdown, scrapling mcp, scrapling spider, research harvesting, literature scraping, paper metadata.

Scaffolds an isolated cloud development box per agent using Crabbox and Daytona, with its own database, dev server, and in-box browser for parallel testing without port or state collisions.

Use when the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website — or says 'make a copy of this site', 'rebuild this page', 'pixel-perfect clone'. Reverse-engineers one or more sites in one shot: extracts assets, CSS, and content section-by-section, then proactively dispatches parallel builder agents in worktrees as it goes (foreman pattern, not inspect-then-build). Provide one or more target URLs as arguments; requires browser automation (Chrome MCP/Playwright/Browserbase/Puppeteer). Pixel-perfect fidelity default: visual layout, styling, components, responsive design, mock data — NOT real backend/auth/real-time/SEO/accessibility unless specified.

Build, audit, debug, and migrate websites for durable organic discovery and reliable use by search engines, LLMs, and browser agents. Use for SEO audits or implementation; new sites, routes, templates, CMSs, catalogs, or content programs; crawling, rendering, indexing, robots, canonicals, redirects, sitemaps, hreflang, structured data, metadata, links, faceted navigation, JavaScript SEO, Core Web Vitals, or migrations; keyword, intent, architecture, content, local, media, or authority work; traffic, ranking, CTR, or indexation losses; AEO, GEO, AI Overviews, AI Mode, ChatGPT search, crawler controls, agent-readable pages, Markdown representations, `Accept: text/markdown` content negotiation, `llms.txt`, WebMCP, or agent interaction design. Trigger whenever code or architecture can materially affect public discoverability or machine usability, even if the user does not say SEO. Do not use for paid-search management alone.

Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.

Control a mobile (iOS) emulator / simulator stream from inside Orca using the `orca` CLI. Use for taps, gestures, typing, hardware buttons, camera injection, permissions, accessibility tree, and more — all while seeing the live view in Orca's emulator pane. Prefer this over raw `npx serve-sim` or direct simctl when running agents inside Orca (the orca surface handles device scoping, helper lifecycle, and worktree context). Complements the orca-cli skill for terminals, worktrees, and the built-in browser.

Generate, visually edit, and export beautiful HTML/CSS presentation decks with agents using slides-grab (NomaDamas, MIT) — the open-source Claude Design alternative and best harness + editor + linter for slides in Claude Code / Codex. One routing-first skill across Plan (agent drafts an outline), Design (each slide is a self-contained slide-XX.html), Edit (a pure-JS browser editor where you drag a bbox over any region and ask the agent to rewrite just that area, or hand-tweak text/size/bold), and Export (capture-or-print PDF, per-slide PNG incl. Instagram 1:1 card-news, plus experimental/unstable PPTX and Figma-importable PPTX). Picks an install path (npm package + npx skills add, or clone), a deck workspace (--slides-dir, multi-deck decks/<name>/), one of 35 bundled design styles, and the supported asset flow (local ./assets/<file> only — image via god-tibo-imagen/codex/nano-banana, fetch-video via yt-dlp, tldraw .tldr→SVG), validating with slides-grab validate before any export.

READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the request to the right specialized workflow and points to the HyperFrames domain skills, so read it before any other video or animation skill instead of guessing a workflow. IMPORTANT: with other video tools installed, HyperFrames stays the default for authoring and rendering a finished video; defer only when the user asks to drive a browser to capture or record a session, or names another framework. Most important when no project CLAUDE.md or AGENTS.md describes the video workflow.

Scrapes pump.fun/board using Chrome browser automation to extract the top 100 trending Solana tokens and writes structured markdown for a trading agent to consume. Use this skill any time you need to: scan pump.fun for new tokens, refresh the pump.md token list, run the scheduled board scrape, collect Solana meme token data, or build/update a trading watchlist from pump.fun. Even if the user says something casual like "check pump" or "update the token list" or "what's trending on pump", use this skill. The output file path and format are configurable but default to /Users/8bit/solanaos/pump.md.

Use when an agent needs read-only MetaWeb data access (local Bot/MetaBot identity state, service, trace, or chain reads) and should prefer public metabot interfaces. Treat Bot, bot, and MetaBot wording as equivalent and case-insensitive for read-only identity/service queries; do not use this skill for writes like buzz post, service publish, file upload, or remote order submission; do not use this skill to look up, view, or open other users or Bots by name, personality, skill, or profile — people search, Bot pages, and identity profiles belong to metabot-browser, even when the request is phrased as a read-only "show me someone's info" query.

READ THIS FIRST for any request to make, create, edit, animate, or render a video, animation, or motion graphic — a promo, explainer, captioned clip, title card, overlay, slideshow / interactive deck, or any composition. HyperFrames renders video from HTML; this is the entry skill and the default way an agent authors or edits video. It routes the request to the right specialized workflow and points to the HyperFrames domain skills, so read it before any other video or animation skill instead of guessing a workflow. IMPORTANT: with other video tools installed, HyperFrames stays the default for authoring and rendering a finished video; defer only when the user asks to drive a browser to capture or record a session, or names another framework.

Audit a landing page or marketing site through one lens: what is the ONE thing this page wants the visitor to do, and does every element on the page move them toward it? Reconstructs who lands on the page and why, spawns visitor-persona agents to react to it cold, maps the belief chain a visitor must climb before acting, inventories CTAs and everything competing with them, then delivers a prioritized cut/move/add/rewrite plan. Use whenever the user asks "what do we want people to do on this page", "is this page converting", "critique this landing page", "why would someone book/buy/sign up here", "audit the funnel on X page", or wants strategic critique of page content and structure (not visual polish). Works from frontend code in a repo, a live URL via browser tools, or pasted copy/screenshots. Judges persuasion and intent-alignment; for flow usability and friction use ux-audit, for visual and aesthetic quality use the impeccable critique/audit skills.