agent-browser

Automatización del navegador para agentes de IA a través de inference.sh. Navega por páginas web, interactúa con elementos usando referencias @e, toma capturas de pantalla, graba video. Capacidades: raspado web, llenado de formularios, clics, escritura, arrastrar y soltar, carga de archivos, ejecución de JavaScript. Usos: automatización web, extracción de datos, pruebas, navegación de agentes, investigación. Disparadores: navegador, automatización web, raspar, navegar, hacer clic, llenar formulario, captura de pantalla, navegar por la web, playwright, navegador sin cabeza, agente web, navegar por internet, grabar video

npx skills add https://github.com/halt-catch-fire/skills --skill agent-browser

Install the belt CLI skill: npx skills add belt-sh/cli

Agentic Browser

Browser automation for AI agents via inference.sh. Uses Playwright under the hood with a simple @e ref system for element interaction.

Agentic Browser

Quick Start

Requires inference.sh CLI (belt). Install instructions

belt login

# Open a page and get interactive elements
belt app run agent-browser --function open --input '{"url": "https://example.com"}' --session new

Core Workflow

Every browser automation follows this pattern:

  1. Open - Navigate to URL, get @e refs for elements
  2. Interact - Use refs to click, fill, drag, etc.
  3. Re-snapshot - After navigation/changes, get fresh refs
  4. Close - End session (returns video if recording)
# 1. Start session
RESULT=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com/login"
}')
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
# Elements: @e1 [input] "Email", @e2 [input] "Password", @e3 [button] "Sign In"

# 2. Fill and submit
belt app run agent-browser --function interact --session $SESSION_ID --input '{
  "action": "fill", "ref": "@e1", "text": "user@example.com"
}'
belt app run agent-browser --function interact --session $SESSION_ID --input '{
  "action": "fill", "ref": "@e2", "text": "password123"
}'
belt app run agent-browser --function interact --session $SESSION_ID --input '{
  "action": "click", "ref": "@e3"
}'

# 3. Re-snapshot after navigation
belt app run agent-browser --function snapshot --session $SESSION_ID --input '{}'

# 4. Close when done
belt app run agent-browser --function close --session $SESSION_ID --input '{}'

Functions

FunctionDescription
openNavigate to URL, configure browser (viewport, proxy, video recording)
snapshotRe-fetch page state with @e refs after DOM changes
interactPerform actions using @e refs (click, fill, drag, upload, etc.)
screenshotTake page screenshot (viewport or full page)
executeRun JavaScript code on the page
closeClose session, returns video if recording was enabled

Interact Actions

ActionDescriptionRequired Fields
clickClick elementref
dblclickDouble-click elementref
fillClear and type textref, text
typeType text (no clear)text
pressPress key (Enter, Tab, etc.)text
selectSelect dropdown optionref, text
hoverHover over elementref
checkCheck checkboxref
uncheckUncheck checkboxref
dragDrag and dropref, target_ref
uploadUpload file(s)ref, file_paths
scrollScroll pagedirection (up/down/left/right), scroll_amount
backGo back in history-
waitWait millisecondswait_ms
gotoNavigate to URLurl

Element Refs

Elements are returned with @e refs:

@e1 [a] "Home" href="/"
@e2 [input type="text"] placeholder="Search"
@e3 [button] "Submit"
@e4 [select] "Choose option"
@e5 [input type="checkbox"] name="agree"

Important: Refs are invalidated after navigation. Always re-snapshot after:

  • Clicking links/buttons that navigate
  • Form submissions
  • Dynamic content loading

Features

Video Recording

Record browser sessions for debugging or documentation:

# Start with recording enabled (optionally show cursor indicator)
SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "record_video": true,
  "show_cursor": true
}' | jq -r '.session_id')

# ... perform actions ...

# Close to get the video file
belt app run agent-browser --function close --session $SESSION --input '{}'
# Returns: {"success": true, "video": <File>}

Cursor Indicator

Show a visible cursor in screenshots and video (useful for demos):

belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "show_cursor": true,
  "record_video": true
}'

The cursor appears as a red dot that follows mouse movements and shows click feedback.

Proxy Support

Route traffic through a proxy server:

belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "proxy_url": "http://proxy.example.com:8080",
  "proxy_username": "user",
  "proxy_password": "pass"
}'

File Upload

Upload files to file inputs:

belt app run agent-browser --function interact --session $SESSION --input '{
  "action": "upload",
  "ref": "@e5",
  "file_paths": ["/path/to/file.pdf"]
}'

Drag and Drop

Drag elements to targets:

belt app run agent-browser --function interact --session $SESSION --input '{
  "action": "drag",
  "ref": "@e1",
  "target_ref": "@e2"
}'

JavaScript Execution

Run custom JavaScript:

belt app run agent-browser --function execute --session $SESSION --input '{
  "code": "document.querySelectorAll(\"h2\").length"
}'
# Returns: {"result": "5", "screenshot": <File>}

Deep-Dive Documentation

ReferenceDescription
references/commands.mdFull function reference with all options
references/snapshot-refs.mdRef lifecycle, invalidation rules, troubleshooting
references/session-management.mdSession persistence, parallel sessions
references/authentication.mdLogin flows, OAuth, 2FA handling
references/video-recording.mdRecording workflows for debugging
references/proxy-support.mdProxy configuration, geo-testing

Ready-to-Use Templates

TemplateDescription
templates/form-automation.shForm filling with validation
templates/authenticated-session.shLogin once, reuse session
templates/capture-workflow.shContent extraction with screenshots

Examples

Form Submission

SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com/contact"
}' | jq -r '.session_id')

# Get elements: @e1 [input] "Name", @e2 [input] "Email", @e3 [textarea], @e4 [button] "Send"

belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e1", "text": "John Doe"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e2", "text": "john@example.com"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e3", "text": "Hello!"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "click", "ref": "@e4"}'

belt app run agent-browser --function snapshot --session $SESSION --input '{}'
belt app run agent-browser --function close --session $SESSION --input '{}'

Search and Extract

SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://google.com"
}' | jq -r '.session_id')

belt app run agent-browser --function interact --session $SESSION --input '{"action": "fill", "ref": "@e1", "text": "weather today"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "press", "text": "Enter"}'
belt app run agent-browser --function interact --session $SESSION --input '{"action": "wait", "wait_ms": 2000}'

belt app run agent-browser --function snapshot --session $SESSION --input '{}'
belt app run agent-browser --function close --session $SESSION --input '{}'

Screenshot with Video

SESSION=$(belt app run agent-browser --function open --session new --input '{
  "url": "https://example.com",
  "record_video": true
}' | jq -r '.session_id')

# Take full page screenshot
belt app run agent-browser --function screenshot --session $SESSION --input '{
  "full_page": true
}'

# Close and get video
RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')
echo $RESULT | jq '.video'

Sessions

Browser state persists within a session. Always:

  1. Start with --session new on first call
  2. Use returned session_id for subsequent calls
  3. Close session when done

Related Skills

# Web search (for research + browse)
npx skills add inference-sh/skills@web-search

# LLM models (analyze extracted content)
npx skills add inference-sh/skills@llm-models

Documentation

Más skills de halt-catch-fire

agent-tools
halt-catch-fire
We need to translate the given text from English to Spanish. The text is a description of an agent skill called "agent-tools". The instruction says to preserve product names, protocol names, URLs, numbers, and technical terms. Also, do not include the name unless it appears in the source text. The name "agent-tools" is not in the source text, so we don't include it. We only translate the text inside <text>. We must not add any labels or extra commentary. The text: "Run 250+ AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude
developmentapicreative
ai-avatar-video
halt-catch-fire
Crea videos de avatar AI y videos de cabezas parlantes mediante la CLI de inference.sh. Recomendado: P-Video-Avatar (más rápido, más barato, TTS integrado). También: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (más de 100 idiomas, control de emociones para personajes), ElevenLabs, Kokoro. Capacidades: avatares impulsados por audio, texto a avatar, videos de sincronización de labios, generación de cabezas parlantes, presentadores virtuales, contenido UGC. Usar para: presentadores AI, videos explicativos, influencers virtuales, doblaje, videos de marketing, anuncios UGC, avatares para juegos,...
videocreativemedia
ai-image-generation
halt-catch-fire
Genera imágenes de IA con GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve y más de 50 modelos a través de la CLI de inference.sh. Modelos: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capacidades: texto a imagen, imagen a imagen, inpainting, LoRA, edición de imágenes, escalado, renderizado de texto. Usos: arte de IA, maquetas de productos, arte conceptual, gráficos para redes sociales, imágenes de marketing, ilustraciones. Disparadores: flux, generación de imágenes, imagen de IA, texto a...
creativemediaimage
ai-video-generation
halt-catch-fire
Genera videos de IA con Google Veo, Seedance 2.0, HappyHorse, Wan, Grok y más de 40 modelos a través de la CLI de inference.sh. Modelos: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capacidades: texto a video, imagen a video, referencia a video, edición de video, sincronización de labios, animación de avatares, mejora de resolución de video, sonido foley. Usos: videos para redes sociales, contenido de marketing, videos explicativos, demostraciones de productos, avatares de IA. Disparadores: generación de video, video de IA,...
creativevideomedia
app-store-screenshots
halt-catch-fire
Creación de capturas de pantalla para App Store y Google Play con especificaciones exactas de plataforma. Cubre dimensiones de iOS/Android, orden de galería, maquetas de dispositivos y videos de vista previa. Útil para: optimización en tiendas de aplicaciones, ASO, capturas de pantalla de apps, vista previa de apps, listado en Play Store. Disparadores: capturas de pantalla de App Store, ASO, optimización en App Store, capturas de pantalla de Play Store, vista previa de apps, listado de apps, capturas de pantalla de iOS, capturas de pantalla de Android, imágenes de App Store, maqueta de app, maqueta de dispositivo, galería de apps, listado en tienda.
designmarketingcreative
character-design-sheet
halt-catch-fire
We need to translate the given text from English to Spanish. The text is a description of an agent skill for character design. We must preserve the name "character-design-sheet" but it's not in the text, so we ignore. We translate the text inside <text> only. No extra labels. Keep technical terms like "LoRA", "turnaround views", "expression sheets", etc. Translate naturally. The text: "Character consistency across AI-generated images with reference sheets and LoRA techniques. Covers turnaround views, expression sheets, color palettes, and style consistency tricks. Use for: character design, game art, illustration, animation, comics, visual novels. Triggers: character design, character sheet, character consistency, character reference, turnaround sheet, expression sheet, character art, consistent character, character concept, reference sheet, character creation, oc design,..." Translation: "Consistencia de personajes en imágenes generadas por IA con hojas de referencia y técnicas LoRA. Cubre vistas de rotación, hojas de expresiones, paletas de colores
creativedesignmedia
competitor-teardown
halt-catch-fire
We need to translate the given text from English to Spanish. The text is a description of an agent skill called "competitor-teardown". The instruction says to preserve the name if it appears in the source text. The name "competitor-teardown" appears in the triggers list: "competitor teardown" (without hyphen). Also note "SWOT" is a term, preserve as is. "UX" is technical term, preserve. "SWOT analysis" appears, preserve "SWOT". Also "pricing comparison", "feature matrices", etc. Need to translate naturally. The text: "Structured competitive analysis with feature matrices, SWOT, positioning maps, and UX review. Covers research frameworks, pricing comparison, review mining, and visual deliverables. Use for: market research, competitive intelligence, investor decks, product strategy, sales enablement. Triggers: competitor analysis, competitive analysis, competitor teardown, market research, competitive intelligence, swot analysis, competitor comparison, market landscape, competitor review, competitive..." Translate to Spanish. Keep "competitor
researchdata-analysismarketing
image-to-video
halt-catch-fire
Guía de conversión de imagen fija a video: selección de modelos, indicaciones de movimiento y movimiento de cámara. Cubre Wan 2.5 i2v, Seedance, Fabric, Grok Video con cuándo usar cada uno. Útil para: animar imágenes, crear video a partir de imágenes fijas, agregar movimiento, animaciones de productos. Disparadores: imagen a video, i2v, animar imagen, imagen fija a video, agregar movimiento a imagen, animación de imagen, foto a video, animar imagen fija, wan i2v, image2video, dar vida a imagen, animar foto, movimiento desde imagen