[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DA05G3YR5JP17KJ2TY7H2E":3,"skill-same:01M7DA05G3YR5JP17KJ2TY7H2E":84},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":14,"repositoryHtmlUrl":65,"repositoryHomepageUrl":6,"ownerHtmlUrl":66,"ownerBlogUrl":67,"ownerDescription":68,"updatedAt":69,"install":70,"resources":83},"01M7DA05G3YR5JP17KJ2TY7H2E","Vibe Check - Browser Automation",null,"Browser automation for AI agents. Navigate pages, fill forms, click elements, take screenshots, and manage tabs — all through simple CLI commands. 2.6k+ GitHub stars.","GrupoANDevelopment-m\u002Falberto-ai","GrupoANDevelopment-m","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F257455179?v=4","01M7D69X2N2KEVN0SJF6WGM6SH","Antônio  Ndombe","01M7D69X3P5JTT8H8S904N3888",0,"MIT","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fvibe-check\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"Vibe Check - Browser Automation\"\ndescription: \"Browser automation for AI agents. Navigate pages, fill forms, click elements, take screenshots, and manage tabs — all through simple CLI commands. 2.6k+ GitHub stars.\"\nversion: 1.0.0\nauthor: vibiumdev\nlicense: MIT\ntags: [browser-automation, vibe-coding, ai-agent, chrome, cli, testing, web-scraping]\ntestingTypes: [e2e, visual, accessibility]\nframeworks: [playwright]\nlanguages: [typescript, javascript, python, go]\ndomains: [web, mobile]\nagents: [claude-code, cursor, github-copilot, windsurf, codex, aider, continue, cline, zed, bolt, opencode, gemini-cli, amp]\n---\n\n# Vibium Browser Automation — CLI Reference\n\nThe `vibium` CLI automates Chrome via the command line. The browser auto-launches on first use (daemon mode keeps it running between commands).\n\n```\nvibium go \u003Curl> && vibium map && vibium click @e1 && vibium map\n```\n\n## Core Workflow\n\nEvery browser automation follows this pattern:\n\n1. **Navigate**: `vibium go \u003Curl>`\n2. **Map**: `vibium map` (get element refs like `@e1`, `@e2`)\n3. **Interact**: Use refs to click, fill, select — e.g. `vibium click @e1`\n4. **Re-map**: After navigation or DOM changes, get fresh refs with `vibium map`\n\n## Binary Resolution\n\nBefore running any commands, resolve the `vibium` binary path once:\n\n1. Try `vibium` directly (works if globally installed via `npm install -g vibium`)\n2. Fall back to `.\u002Fclicker\u002Fbin\u002Fvibium` (dev environment, in project root)\n3. Fall back to `.\u002Fnode_modules\u002F.bin\u002Fvibium` (local npm install)\n\nRun `vibium --help` (or the resolved path) to confirm. Use the resolved path for all subsequent commands.\n\n**Windows note:** Use forward slashes in paths (e.g. `.\u002Fclicker\u002Fbin\u002Fvibium.exe`) and quote paths containing spaces.\n\n## Command Chaining\n\nChain commands with `&&` to run them sequentially. The chain stops on first error:\n\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium map && vibium click @e3 && vibium diff map\n```\n\n**When to chain:** Use `&&` for sequences that should happen back-to-back (navigate → interact → verify). Run commands separately when you need to inspect output between steps.\n\n**When NOT to chain:** Don't chain commands that depend on parsing the previous output (e.g. reading map output to decide what to click). Run those separately so you can analyze the result first.\n\n## Commands\n\n### Discovery\n- `vibium map` — map interactive elements with @refs (recommended before interacting)\n- `vibium map --selector \"nav\"` — scope map to elements within a CSS subtree\n- `vibium diff map` — compare current vs last map (see what changed)\n\n### Navigation\n- `vibium go \u003Curl>` — go to a page\n- `vibium back` — go back in history\n- `vibium forward` — go forward in history\n- `vibium reload` — reload the current page\n- `vibium url` — print current URL\n- `vibium title` — print page title\n\n### Reading Content\n- `vibium text` — get all page text\n- `vibium text \"\u003Cselector>\"` — get text of a specific element\n- `vibium html` — get page HTML (use `--outer` for outerHTML)\n- `vibium find \"\u003Cselector>\"` — find element, return `@e1` ref (clickable with `vibium click @e1`)\n- `vibium find --text \"Sign In\"` — find element by text content → `@e1`\n- `vibium find --label \"Email\"` — find input by label → `@e1`\n- `vibium find --placeholder \"Search\"` — find by placeholder → `@e1`\n- `vibium find --testid \"submit-btn\"` — find by data-testid → `@e1`\n- `vibium find --xpath \"\u002F\u002Fdiv[@class]\"` — find by XPath → `@e1`\n- `vibium find --alt \"Logo\"` — find by alt attribute → `@e1`\n- `vibium find --title \"Settings\"` — find by title attribute → `@e1`\n- `vibium find-all \"\u003Cselector>\"` — find all matching elements → `@e1`, `@e2`, ... (`--limit N`)\n- `vibium find --role \u003Crole>` — find element by ARIA role → `@e1` (combine with `--text`, `--label`, etc.)\n- `vibium eval \"\u003Cjs>\"` — run JavaScript and print result (`--stdin` to read from stdin)\n- `vibium count \"\u003Cselector>\"` — count matching elements\n- `vibium screenshot -o file.png` — capture screenshot (`--full-page`, `--annotate`)\n- `vibium a11y-tree` — accessibility tree (`--everything` for all nodes)\n\n### Interaction\n- `vibium click \"\u003Cselector>\"` — click an element (also accepts `@ref` from map)\n- `vibium dblclick \"\u003Cselector>\"` — double-click an element\n- `vibium type \"\u003Cselector>\" \"\u003Ctext>\"` — type into an input (appends to existing value)\n- `vibium fill \"\u003Cselector>\" \"\u003Ctext>\"` — clear field and type new text (replaces value)\n- `vibium press \u003Ckey> [selector]` — press a key on element or focused element\n- `vibium focus \"\u003Cselector>\"` — focus an element\n- `vibium hover \"\u003Cselector>\"` — hover over an element\n- `vibium scroll [direction]` — scroll page (`--amount N`, `--selector`)\n- `vibium scroll-into-view \"\u003Cselector>\"` — scroll element into view (centered)\n- `vibium keys \"\u003Ccombo>\"` — press keys (Enter, Control+a, Shift+Tab)\n- `vibium select \"\u003Cselector>\" \"\u003Cvalue>\"` — pick a dropdown option\n- `vibium check \"\u003Cselector>\"` — check a checkbox\u002Fradio (idempotent)\n- `vibium uncheck \"\u003Cselector>\"` — uncheck a checkbox (idempotent)\n\n### Mouse Primitives\n- `vibium mouse-click [x] [y]` — click at coordinates or current position (`--button 0|1|2`)\n- `vibium mouse-move \u003Cx> \u003Cy>` — move mouse to coordinates\n- `vibium mouse-down` — press mouse button (`--button 0|1|2`)\n- `vibium mouse-up` — release mouse button (`--button 0|1|2`)\n- `vibium drag \"\u003Csource>\" \"\u003Ctarget>\"` — drag from one element to another\n\n### Element State\n- `vibium value \"\u003Cselector>\"` — get input\u002Ftextarea\u002Fselect value\n- `vibium attr \"\u003Cselector>\" \"\u003Cattribute>\"` — get HTML attribute value\n- `vibium is-visible \"\u003Cselector>\"` — check if element is visible (true\u002Ffalse)\n- `vibium is-enabled \"\u003Cselector>\"` — check if element is enabled (true\u002Ffalse)\n- `vibium is-checked \"\u003Cselector>\"` — check if checkbox\u002Fradio is checked (true\u002Ffalse)\n\n### Waiting\n- `vibium wait \"\u003Cselector>\"` — wait for element (`--state visible|hidden|attached`, `--timeout ms`)\n- `vibium wait-for-url \"\u003Cpattern>\"` — wait until URL contains substring (`--timeout ms`)\n- `vibium wait-for-load` — wait until page is fully loaded (`--timeout ms`)\n- `vibium wait-for-text \"\u003Ctext>\"` — wait until text appears on page (`--timeout ms`)\n- `vibium wait-for-fn \"\u003Cexpression>\"` — wait until JS expression returns truthy (`--timeout ms`)\n- `vibium sleep \u003Cms>` — pause execution (max 30000ms)\n\n### Capture\n- `vibium screenshot -o file.png` — capture screenshot (`--full-page`, `--annotate`)\n- `vibium pdf -o file.pdf` — save page as PDF\n\n### Dialogs\n- `vibium dialog accept [text]` — accept dialog (optionally with prompt text)\n- `vibium dialog dismiss` — dismiss dialog\n\n### Emulation\n- `vibium set-viewport \u003Cwidth> \u003Cheight>` — set viewport size (`--dpr` for device pixel ratio)\n- `vibium viewport` — get current viewport dimensions\n- `vibium window` — get OS browser window dimensions and state\n- `vibium set-window \u003Cwidth> \u003Cheight> [x] [y]` — set window size and position (`--state`)\n- `vibium emulate-media` — override CSS media features (`--color-scheme`, `--reduced-motion`, `--forced-colors`, `--contrast`, `--media`)\n- `vibium set-geolocation \u003Clat> \u003Clng>` — override geolocation (`--accuracy`)\n- `vibium set-content \"\u003Chtml>\"` — replace page HTML (`--stdin` to read from stdin)\n\n### Frames\n- `vibium frames` — list all iframes on the page\n- `vibium frame \"\u003CnameOrUrl>\"` — find a frame by name or URL substring\n\n### File Upload\n- `vibium upload \"\u003Cselector>\" \u003Cfiles...>` — set files on input[type=file]\n\n### Tracing\n- `vibium trace start` — start recording (`--screenshots`, `--snapshots`, `--name`)\n- `vibium trace stop` — stop recording and save ZIP (`-o path`)\n\n### Cookies\n- `vibium cookies` — list all cookies\n- `vibium cookies set \u003Cname> \u003Cvalue>` — set a cookie\n- `vibium cookies clear` — clear all cookies\n\n### Storage State\n- `vibium storage-state` — export cookies + localStorage + sessionStorage (`-o state.json`)\n- `vibium restore-storage \u003Cpath>` — restore state from JSON file\n\n### Downloads\n- `vibium download set-dir \u003Cpath>` — set download directory\n\n### Tabs\n- `vibium tabs` — list open tabs\n- `vibium tab-new [url]` — open new tab\n- `vibium tab-switch \u003Cindex|url>` — switch tab\n- `vibium tab-close [index]` — close tab\n\n### Debug\n- `vibium highlight \"\u003Cselector>\"` — highlight element visually (3 seconds)\n\n### Session\n- `vibium quit` — close the browser (daemon keeps running)\n- `vibium close` — alias for quit\n- `vibium daemon start` — start background browser\n- `vibium daemon status` — check if running\n- `vibium daemon stop` — stop daemon\n\n## Common Patterns\n\n### Ref-based workflow (recommended for AI)\n```sh\nvibium go https:\u002F\u002Fexample.com\nvibium map\nvibium click @e1\nvibium map  # re-map after interaction\n```\n\n### Verify action worked\n```sh\nvibium map\nvibium click @e3\nvibium diff map  # see what changed\n```\n\n### Read a page\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium text\n```\n\n### Fill a form (end-to-end)\n```sh\nvibium go https:\u002F\u002Fexample.com\u002Flogin\nvibium map\n# Look at map output to identify form fields\nvibium fill @e1 \"user@example.com\"\nvibium fill @e2 \"secret\"\nvibium click @e3\nvibium wait-for-url \"\u002Fdashboard\"\nvibium screenshot -o after-login.png\n```\n\n### Scoped map (large pages)\n```sh\nvibium map --selector \"nav\"        # Only map elements in \u003Cnav>\nvibium map --selector \"#sidebar\"   # Only map elements in #sidebar\nvibium map --selector \"form\"       # Only map form controls\n```\n\n### Semantic find (no CSS selectors needed)\n```sh\nvibium find --text \"Sign In\"           # → @e1 [button] \"Sign In\"\nvibium find --label \"Email\"            # → @e1 [input] placeholder=\"Email\"\nvibium click @e1                       # Click the found element\nvibium find --placeholder \"Search...\"  # → @e1 [input] placeholder=\"Search...\"\nvibium find --testid \"submit-btn\"      # → @e1 [button] \"Submit\"\nvibium find --alt \"Company logo\"       # → @e1 [img] alt=\"Company logo\"\nvibium find --title \"Close\"            # → @e1 [button] title=\"Close\"\nvibium find --xpath \"\u002F\u002Fa[@href='\u002Fabout']\"  # → @e1 [a] \"About\"\n```\n\n### Authentication with state persistence\n```sh\n# Log in once and save state\nvibium go https:\u002F\u002Fapp.example.com\u002Flogin\nvibium fill \"input[name=email]\" \"user@example.com\"\nvibium fill \"input[name=password]\" \"secret\"\nvibium click \"button[type=submit]\"\nvibium wait-for-url \"\u002Fdashboard\"\nvibium storage-state -o auth.json\n\n# Restore in a later session (skips login)\nvibium restore-storage auth.json\nvibium go https:\u002F\u002Fapp.example.com\u002Fdashboard\n```\n\n### Extract structured data\n```sh\nvibium go https:\u002F\u002Fexample.com\nvibium eval \"JSON.stringify([...document.querySelectorAll('a')].map(a => ({text: a.textContent.trim(), href: a.href})))\"\n```\n\n### Check page structure without rendering\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium a11y-tree\n```\n\n### Multi-tab workflow\n```sh\nvibium tab-new https:\u002F\u002Fdocs.example.com\nvibium text \"h1\"\nvibium tab-switch 0\n```\n\n### Annotated screenshot\n```sh\nvibium screenshot -o annotated.png --annotate\n```\n\n### Inspect an element\n```sh\nvibium attr \"a\" \"href\"\nvibium value \"input[name=email]\"\nvibium is-visible \".modal\"\n```\n\n### Save as PDF\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium pdf -o page.pdf\n```\n\n## Eval \u002F JavaScript\n\n`vibium eval` is the escape hatch for any DOM query or mutation the CLI doesn't cover directly.\n\n**Simple expressions** — use single quotes:\n```sh\nvibium eval 'document.title'\nvibium eval 'document.querySelectorAll(\"li\").length'\n```\n\n**Complex scripts** — use `--stdin` with a heredoc:\n```sh\nvibium eval --stdin \u003C\u003C'EOF'\nconst rows = [...document.querySelectorAll('table tbody tr')];\nJSON.stringify(rows.map(r => {\n  const cells = r.querySelectorAll('td');\n  return { name: cells[0].textContent.trim(), price: cells[1].textContent.trim() };\n}));\nEOF\n```\n\n**JSON output** — use `--json` to get machine-readable output:\n```sh\nvibium eval --json 'JSON.stringify({url: location.href, title: document.title})'\n```\n\n## Timeouts and Waiting\n\nAll interaction commands (`click`, `fill`, `type`, etc.) auto-wait for the target element to be actionable. You usually don't need explicit waits.\n\nUse explicit waits when:\n- **Waiting for navigation:** `vibium wait-for-url \"\u002Fdashboard\"` — after clicking a link that navigates\n- **Waiting for content:** `vibium wait-for-text \"Success\"` — after form submission, wait for confirmation\n- **Waiting for element:** `vibium wait \".modal\"` — wait for a modal to appear\n- **Waiting for page load:** `vibium wait-for-load` — after navigation to a slow page\n- **Waiting for JS condition:** `vibium wait-for-fn \"window.appReady === true\"` — wait for app initialization\n- **Fixed delay (last resort):** `vibium sleep 2000` — only when no better signal exists (max 30s)\n\nAll wait commands accept `--timeout \u003Cms>` (default varies by command).\n\n## Ref Lifecycle\n\nRefs (`@e1`, `@e2`) are invalidated when the page changes. Always re-map after:\n- Clicking links or buttons that navigate\n- Form submissions\n- Dynamic content loading (dropdowns, modals)\n\n## Global Flags\n\n| Flag | Description |\n|------|-------------|\n| `--headless` | Hide browser window |\n| `--json` | Output as JSON |\n| `-v, --verbose` | Debug logging |\n\n## Tips\n\n- All click\u002Ftype\u002Fhover\u002Ffill actions auto-wait for the element to be actionable\n- All selector arguments also accept `@ref` from `vibium map`\n- Use `vibium map` before interacting to discover interactive elements\n- Use `vibium map --selector` to reduce noise on large pages\n- Use `vibium fill` to replace a field's value, `vibium type` to append to it\n- Use `vibium find --text` \u002F `--label` \u002F `--testid` for semantic element lookup (more reliable than CSS selectors)\n- Use `vibium find --role` for ARIA-role-based lookup\n- Use `vibium a11y-tree` to understand page structure without visual rendering\n- Use `vibium text \"\u003Cselector>\"` to read specific sections\n- Use `vibium diff map` after interactions to see what changed\n- `vibium eval` is the escape hatch for complex DOM queries\n- `vibium check`\u002F`vibium uncheck` are idempotent — safe to call without checking state first\n- Screenshots save to the current directory by default (`-o` to change)\n- Use `vibium storage-state` \u002F `vibium restore-storage` to persist auth across sessions\n","# Vibium Browser Automation — CLI Reference\n\nThe `vibium` CLI automates Chrome via the command line. The browser auto-launches on first use (daemon mode keeps it running between commands).\n\n```\nvibium go \u003Curl> && vibium map && vibium click @e1 && vibium map\n```\n\n## Core Workflow\n\nEvery browser automation follows this pattern:\n\n1. **Navigate**: `vibium go \u003Curl>`\n2. **Map**: `vibium map` (get element refs like `@e1`, `@e2`)\n3. **Interact**: Use refs to click, fill, select — e.g. `vibium click @e1`\n4. **Re-map**: After navigation or DOM changes, get fresh refs with `vibium map`\n\n## Binary Resolution\n\nBefore running any commands, resolve the `vibium` binary path once:\n\n1. Try `vibium` directly (works if globally installed via `npm install -g vibium`)\n2. Fall back to `.\u002Fclicker\u002Fbin\u002Fvibium` (dev environment, in project root)\n3. Fall back to `.\u002Fnode_modules\u002F.bin\u002Fvibium` (local npm install)\n\nRun `vibium --help` (or the resolved path) to confirm. Use the resolved path for all subsequent commands.\n\n**Windows note:** Use forward slashes in paths (e.g. `.\u002Fclicker\u002Fbin\u002Fvibium.exe`) and quote paths containing spaces.\n\n## Command Chaining\n\nChain commands with `&&` to run them sequentially. The chain stops on first error:\n\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium map && vibium click @e3 && vibium diff map\n```\n\n**When to chain:** Use `&&` for sequences that should happen back-to-back (navigate → interact → verify). Run commands separately when you need to inspect output between steps.\n\n**When NOT to chain:** Don't chain commands that depend on parsing the previous output (e.g. reading map output to decide what to click). Run those separately so you can analyze the result first.\n\n## Commands\n\n### Discovery\n- `vibium map` — map interactive elements with @refs (recommended before interacting)\n- `vibium map --selector \"nav\"` — scope map to elements within a CSS subtree\n- `vibium diff map` — compare current vs last map (see what changed)\n\n### Navigation\n- `vibium go \u003Curl>` — go to a page\n- `vibium back` — go back in history\n- `vibium forward` — go forward in history\n- `vibium reload` — reload the current page\n- `vibium url` — print current URL\n- `vibium title` — print page title\n\n### Reading Content\n- `vibium text` — get all page text\n- `vibium text \"\u003Cselector>\"` — get text of a specific element\n- `vibium html` — get page HTML (use `--outer` for outerHTML)\n- `vibium find \"\u003Cselector>\"` — find element, return `@e1` ref (clickable with `vibium click @e1`)\n- `vibium find --text \"Sign In\"` — find element by text content → `@e1`\n- `vibium find --label \"Email\"` — find input by label → `@e1`\n- `vibium find --placeholder \"Search\"` — find by placeholder → `@e1`\n- `vibium find --testid \"submit-btn\"` — find by data-testid → `@e1`\n- `vibium find --xpath \"\u002F\u002Fdiv[@class]\"` — find by XPath → `@e1`\n- `vibium find --alt \"Logo\"` — find by alt attribute → `@e1`\n- `vibium find --title \"Settings\"` — find by title attribute → `@e1`\n- `vibium find-all \"\u003Cselector>\"` — find all matching elements → `@e1`, `@e2`, ... (`--limit N`)\n- `vibium find --role \u003Crole>` — find element by ARIA role → `@e1` (combine with `--text`, `--label`, etc.)\n- `vibium eval \"\u003Cjs>\"` — run JavaScript and print result (`--stdin` to read from stdin)\n- `vibium count \"\u003Cselector>\"` — count matching elements\n- `vibium screenshot -o file.png` — capture screenshot (`--full-page`, `--annotate`)\n- `vibium a11y-tree` — accessibility tree (`--everything` for all nodes)\n\n### Interaction\n- `vibium click \"\u003Cselector>\"` — click an element (also accepts `@ref` from map)\n- `vibium dblclick \"\u003Cselector>\"` — double-click an element\n- `vibium type \"\u003Cselector>\" \"\u003Ctext>\"` — type into an input (appends to existing value)\n- `vibium fill \"\u003Cselector>\" \"\u003Ctext>\"` — clear field and type new text (replaces value)\n- `vibium press \u003Ckey> [selector]` — press a key on element or focused element\n- `vibium focus \"\u003Cselector>\"` — focus an element\n- `vibium hover \"\u003Cselector>\"` — hover over an element\n- `vibium scroll [direction]` — scroll page (`--amount N`, `--selector`)\n- `vibium scroll-into-view \"\u003Cselector>\"` — scroll element into view (centered)\n- `vibium keys \"\u003Ccombo>\"` — press keys (Enter, Control+a, Shift+Tab)\n- `vibium select \"\u003Cselector>\" \"\u003Cvalue>\"` — pick a dropdown option\n- `vibium check \"\u003Cselector>\"` — check a checkbox\u002Fradio (idempotent)\n- `vibium uncheck \"\u003Cselector>\"` — uncheck a checkbox (idempotent)\n\n### Mouse Primitives\n- `vibium mouse-click [x] [y]` — click at coordinates or current position (`--button 0|1|2`)\n- `vibium mouse-move \u003Cx> \u003Cy>` — move mouse to coordinates\n- `vibium mouse-down` — press mouse button (`--button 0|1|2`)\n- `vibium mouse-up` — release mouse button (`--button 0|1|2`)\n- `vibium drag \"\u003Csource>\" \"\u003Ctarget>\"` — drag from one element to another\n\n### Element State\n- `vibium value \"\u003Cselector>\"` — get input\u002Ftextarea\u002Fselect value\n- `vibium attr \"\u003Cselector>\" \"\u003Cattribute>\"` — get HTML attribute value\n- `vibium is-visible \"\u003Cselector>\"` — check if element is visible (true\u002Ffalse)\n- `vibium is-enabled \"\u003Cselector>\"` — check if element is enabled (true\u002Ffalse)\n- `vibium is-checked \"\u003Cselector>\"` — check if checkbox\u002Fradio is checked (true\u002Ffalse)\n\n### Waiting\n- `vibium wait \"\u003Cselector>\"` — wait for element (`--state visible|hidden|attached`, `--timeout ms`)\n- `vibium wait-for-url \"\u003Cpattern>\"` — wait until URL contains substring (`--timeout ms`)\n- `vibium wait-for-load` — wait until page is fully loaded (`--timeout ms`)\n- `vibium wait-for-text \"\u003Ctext>\"` — wait until text appears on page (`--timeout ms`)\n- `vibium wait-for-fn \"\u003Cexpression>\"` — wait until JS expression returns truthy (`--timeout ms`)\n- `vibium sleep \u003Cms>` — pause execution (max 30000ms)\n\n### Capture\n- `vibium screenshot -o file.png` — capture screenshot (`--full-page`, `--annotate`)\n- `vibium pdf -o file.pdf` — save page as PDF\n\n### Dialogs\n- `vibium dialog accept [text]` — accept dialog (optionally with prompt text)\n- `vibium dialog dismiss` — dismiss dialog\n\n### Emulation\n- `vibium set-viewport \u003Cwidth> \u003Cheight>` — set viewport size (`--dpr` for device pixel ratio)\n- `vibium viewport` — get current viewport dimensions\n- `vibium window` — get OS browser window dimensions and state\n- `vibium set-window \u003Cwidth> \u003Cheight> [x] [y]` — set window size and position (`--state`)\n- `vibium emulate-media` — override CSS media features (`--color-scheme`, `--reduced-motion`, `--forced-colors`, `--contrast`, `--media`)\n- `vibium set-geolocation \u003Clat> \u003Clng>` — override geolocation (`--accuracy`)\n- `vibium set-content \"\u003Chtml>\"` — replace page HTML (`--stdin` to read from stdin)\n\n### Frames\n- `vibium frames` — list all iframes on the page\n- `vibium frame \"\u003CnameOrUrl>\"` — find a frame by name or URL substring\n\n### File Upload\n- `vibium upload \"\u003Cselector>\" \u003Cfiles...>` — set files on input[type=file]\n\n### Tracing\n- `vibium trace start` — start recording (`--screenshots`, `--snapshots`, `--name`)\n- `vibium trace stop` — stop recording and save ZIP (`-o path`)\n\n### Cookies\n- `vibium cookies` — list all cookies\n- `vibium cookies set \u003Cname> \u003Cvalue>` — set a cookie\n- `vibium cookies clear` — clear all cookies\n\n### Storage State\n- `vibium storage-state` — export cookies + localStorage + sessionStorage (`-o state.json`)\n- `vibium restore-storage \u003Cpath>` — restore state from JSON file\n\n### Downloads\n- `vibium download set-dir \u003Cpath>` — set download directory\n\n### Tabs\n- `vibium tabs` — list open tabs\n- `vibium tab-new [url]` — open new tab\n- `vibium tab-switch \u003Cindex|url>` — switch tab\n- `vibium tab-close [index]` — close tab\n\n### Debug\n- `vibium highlight \"\u003Cselector>\"` — highlight element visually (3 seconds)\n\n### Session\n- `vibium quit` — close the browser (daemon keeps running)\n- `vibium close` — alias for quit\n- `vibium daemon start` — start background browser\n- `vibium daemon status` — check if running\n- `vibium daemon stop` — stop daemon\n\n## Common Patterns\n\n### Ref-based workflow (recommended for AI)\n```sh\nvibium go https:\u002F\u002Fexample.com\nvibium map\nvibium click @e1\nvibium map  # re-map after interaction\n```\n\n### Verify action worked\n```sh\nvibium map\nvibium click @e3\nvibium diff map  # see what changed\n```\n\n### Read a page\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium text\n```\n\n### Fill a form (end-to-end)\n```sh\nvibium go https:\u002F\u002Fexample.com\u002Flogin\nvibium map\n# Look at map output to identify form fields\nvibium fill @e1 \"user@example.com\"\nvibium fill @e2 \"secret\"\nvibium click @e3\nvibium wait-for-url \"\u002Fdashboard\"\nvibium screenshot -o after-login.png\n```\n\n### Scoped map (large pages)\n```sh\nvibium map --selector \"nav\"        # Only map elements in \u003Cnav>\nvibium map --selector \"#sidebar\"   # Only map elements in #sidebar\nvibium map --selector \"form\"       # Only map form controls\n```\n\n### Semantic find (no CSS selectors needed)\n```sh\nvibium find --text \"Sign In\"           # → @e1 [button] \"Sign In\"\nvibium find --label \"Email\"            # → @e1 [input] placeholder=\"Email\"\nvibium click @e1                       # Click the found element\nvibium find --placeholder \"Search...\"  # → @e1 [input] placeholder=\"Search...\"\nvibium find --testid \"submit-btn\"      # → @e1 [button] \"Submit\"\nvibium find --alt \"Company logo\"       # → @e1 [img] alt=\"Company logo\"\nvibium find --title \"Close\"            # → @e1 [button] title=\"Close\"\nvibium find --xpath \"\u002F\u002Fa[@href='\u002Fabout']\"  # → @e1 [a] \"About\"\n```\n\n### Authentication with state persistence\n```sh\n# Log in once and save state\nvibium go https:\u002F\u002Fapp.example.com\u002Flogin\nvibium fill \"input[name=email]\" \"user@example.com\"\nvibium fill \"input[name=password]\" \"secret\"\nvibium click \"button[type=submit]\"\nvibium wait-for-url \"\u002Fdashboard\"\nvibium storage-state -o auth.json\n\n# Restore in a later session (skips login)\nvibium restore-storage auth.json\nvibium go https:\u002F\u002Fapp.example.com\u002Fdashboard\n```\n\n### Extract structured data\n```sh\nvibium go https:\u002F\u002Fexample.com\nvibium eval \"JSON.stringify([...document.querySelectorAll('a')].map(a => ({text: a.textContent.trim(), href: a.href})))\"\n```\n\n### Check page structure without rendering\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium a11y-tree\n```\n\n### Multi-tab workflow\n```sh\nvibium tab-new https:\u002F\u002Fdocs.example.com\nvibium text \"h1\"\nvibium tab-switch 0\n```\n\n### Annotated screenshot\n```sh\nvibium screenshot -o annotated.png --annotate\n```\n\n### Inspect an element\n```sh\nvibium attr \"a\" \"href\"\nvibium value \"input[name=email]\"\nvibium is-visible \".modal\"\n```\n\n### Save as PDF\n```sh\nvibium go https:\u002F\u002Fexample.com && vibium pdf -o page.pdf\n```\n\n## Eval \u002F JavaScript\n\n`vibium eval` is the escape hatch for any DOM query or mutation the CLI doesn't cover directly.\n\n**Simple expressions** — use single quotes:\n```sh\nvibium eval 'document.title'\nvibium eval 'document.querySelectorAll(\"li\").length'\n```\n\n**Complex scripts** — use `--stdin` with a heredoc:\n```sh\nvibium eval --stdin \u003C\u003C'EOF'\nconst rows = [...document.querySelectorAll('table tbody tr')];\nJSON.stringify(rows.map(r => {\n  const cells = r.querySelectorAll('td');\n  return { name: cells[0].textContent.trim(), price: cells[1].textContent.trim() };\n}));\nEOF\n```\n\n**JSON output** — use `--json` to get machine-readable output:\n```sh\nvibium eval --json 'JSON.stringify({url: location.href, title: document.title})'\n```\n\n## Timeouts and Waiting\n\nAll interaction commands (`click`, `fill`, `type`, etc.) auto-wait for the target element to be actionable. You usually don't need explicit waits.\n\nUse explicit waits when:\n- **Waiting for navigation:** `vibium wait-for-url \"\u002Fdashboard\"` — after clicking a link that navigates\n- **Waiting for content:** `vibium wait-for-text \"Success\"` — after form submission, wait for confirmation\n- **Waiting for element:** `vibium wait \".modal\"` — wait for a modal to appear\n- **Waiting for page load:** `vibium wait-for-load` — after navigation to a slow page\n- **Waiting for JS condition:** `vibium wait-for-fn \"window.appReady === true\"` — wait for app initialization\n- **Fixed delay (last resort):** `vibium sleep 2000` — only when no better signal exists (max 30s)\n\nAll wait commands accept `--timeout \u003Cms>` (default varies by command).\n\n## Ref Lifecycle\n\nRefs (`@e1`, `@e2`) are invalidated when the page changes. Always re-map after:\n- Clicking links or buttons that navigate\n- Form submissions\n- Dynamic content loading (dropdowns, modals)\n\n## Global Flags\n\n| Flag | Description |\n|------|-------------|\n| `--headless` | Hide browser window |\n| `--json` | Output as JSON |\n| `-v, --verbose` | Debug logging |\n\n## Tips\n\n- All click\u002Ftype\u002Fhover\u002Ffill actions auto-wait for the element to be actionable\n- All selector arguments also accept `@ref` from `vibium map`\n- Use `vibium map` before interacting to discover interactive elements\n- Use `vibium map --selector` to reduce noise on large pages\n- Use `vibium fill` to replace a field's value, `vibium type` to append to it\n- Use `vibium find --text` \u002F `--label` \u002F `--testid` for semantic element lookup (more reliable than CSS selectors)\n- Use `vibium find --role` for ARIA-role-based lookup\n- Use `vibium a11y-tree` to understand page structure without visual rendering\n- Use `vibium text \"\u003Cselector>\"` to read specific sections\n- Use `vibium diff map` after interactions to see what changed\n- `vibium eval` is the escape hatch for complex DOM queries\n- `vibium check`\u002F`vibium uncheck` are idempotent — safe to call without checking state first\n- Screenshots save to the current directory by default (`-o` to change)\n- Use `vibium storage-state` \u002F `vibium restore-storage` to persist auth across sessions\n",{"name":5,"tags":24,"agents":32,"author":46,"domains":47,"license":15,"version":50,"languages":51,"frameworks":56,"description":7,"testingTypes":58},[25,26,27,28,29,30,31],"browser-automation","vibe-coding","ai-agent","chrome","cli","testing","web-scraping",[33,34,35,36,37,38,39,40,41,42,43,44,45],"claude-code","cursor","github-copilot","windsurf","codex","aider","continue","cline","zed","bolt","opencode","gemini-cli","amp","vibiumdev",[48,49],"web","mobile","1.0.0",[52,53,54,55],"typescript","javascript","python","go",[57],"playwright",[59,60,61],"e2e","visual","accessibility","main","eac438ea9216a7cb8a570cab803eb01eeafc6793","skills\u002Fqa\u002Fvibe-check","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m","https:\u002F\u002Fid-preview--d5bef06d-6c9e-4563-a3d4-a855b9d61610.lovable.app\u002F","Eu sou Antonio B. B. Ndombe \r\nEu sou um Pesquisador e desenvolvedor de sistema autonomia cognitivos, fundador de sistemas ODCs ( organismos digital conscientes)","2026-11-04 06:53:39",{"source":8,"skillName":5,"commands":71,"prompt":81,"zipAvailable":82},[72,75,78],{"tool":73,"command":74},"npx","npx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Vibe Check - Browser Automation\"",{"tool":76,"command":77},"bunx","bunx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Vibe Check - Browser Automation\"",{"tool":79,"command":80},"pnpm","pnpm dlx skills add GrupoANDevelopment-m\u002Falberto-ai --skill \"Vibe Check - Browser Automation\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fskills\u002Fqa\u002Fvibe-check\u002FSKILL.md",true,[],[85,93,100,107,114,121],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7DASC6FSCJP49JZBSK0NY1Z","nemoclaw-user-reference","Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture, agent integration, plugin structure, or blueprint design. Trigger keywords - nemoclaw architecture, nemoclaw agent architecture, nemoclaw plugin blueprint structure, nemoclaw vs openshell, which cli, nemoclaw cli, openshell cli, sandbox commands, nemoclaw cli commands, nemoclaw command reference, nemoclaw network policy, sandbox egress control operator approval, nemoclaw troubleshooting, nemoclaw debug sandbox issues.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-reference\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7DAS5S79VK33XFGVAM2TFWF","nemoclaw-user-overview","Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when to prefer NemoClaw versus integrating OpenShell and OpenClaw directly. Use when users ask about the relationship between OpenClaw, OpenShell, and NemoClaw, or when to use NemoClaw versus OpenShell. Trigger keywords - nemoclaw ecosystem, openclaw openshell, nemoclaw vs openshell, sandboxed openclaw, how nemoclaw works, nemoclaw sandbox lifecycle blueprint, nemoclaw overview, openclaw always-on assistants, nvidia openshell, nvidia nemotron, nemoclaw release notes, nemoclaw changelog.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-overview\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7DAS0PQEMET5MNGZ1ABSZVS","nemoclaw-user-monitor-sandbox","Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs. Trigger keywords - monitor nemoclaw sandbox, debug nemoclaw agent issues.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-monitor-sandbox\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":19},"01M7DARQYGF7E9A69VH6S3CGN9","nemoclaw-user-manage-sandboxes","Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential reset, rebuilds, network presets, upgrades, and uninstall. Trigger keywords - manage nemoclaw sandboxes, nemoclaw status, nemoclaw list, nemoclaw dashboard port, nemoclaw rebuild, nemoclaw upgrade sandboxes, nemoclaw uninstall, sandbox mutability, sandbox runtime configuration, sandbox rebuild, nemoclaw backup, nemoclaw restore, workspace backup, openshell sandbox download upload, nemoclaw messaging channels, nemoclaw telegram, nemoclaw discord, nemoclaw slack, nemoclaw wechat, nemoclaw whatsapp, openshell channel messaging, nemoclaw workspace files, soul.md, user.md, identity.md, agents.md, sandbox persistence.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-sandboxes\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M7DARH8BRTG51TRCAB7YWDJ4","nemoclaw-user-manage-policy","Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint access. Trigger keywords - customize nemoclaw network policy, sandbox egress policy configuration, nemoclaw integration policy examples, post-install policy setup, openshell approval workflow, policy preset, nemoclaw approve network requests, sandbox egress approval tui.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-manage-policy\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":89,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M7DARAT62M2VR37590VCZ5NS","nemoclaw-user-get-started","Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time. Trigger keywords - nemoclaw quickstart, install nemoclaw openclaw sandbox, nemohermes quickstart, hermes agent nemoclaw, run hermes openshell sandbox, nemoclaw prerequisites, nemoclaw supported platforms, nemoclaw hardware software, nemoclaw windows wsl2 setup, nemoclaw install windows docker desktop.","https:\u002F\u002Fgithub.com\u002FGrupoANDevelopment-m\u002Falberto-ai\u002Fblob\u002Fmain\u002Fupstream\u002Fnemoclaw\u002Fskills\u002Fnemoclaw-user-get-started\u002FSKILL.md",[],[]]