agent-browser

por openai

CLI de automação de navegador para agentes de IA. Use quando o usuário precisar interagir com sites, verificar a saída do servidor de desenvolvimento, testar aplicativos web, navegar por páginas, preencher formulários,…

npx skills add https://github.com/openai/plugins --skill agent-browser

Browser Automation with agent-browser

When a dev server is running or the user asks to verify, test, or interact with a web page, use agent-browser to automate the browser.

Core Workflow

Every browser automation follows this pattern:

  1. Navigate: agent-browser open <url>
  2. Snapshot: agent-browser snapshot -i (get element refs like @e1, @e2)
  3. Interact: Use refs to click, fill, select
  4. Re-snapshot: After navigation or DOM changes, get fresh refs
agent-browser open http://localhost:3000
agent-browser wait --load networkidle
agent-browser snapshot -i

Dev Server Verification

When a dev server starts, use agent-browser to verify it's working:

# After starting a dev server (next dev, vite, etc.)
agent-browser open http://localhost:3000
agent-browser wait --load networkidle
agent-browser screenshot dev-check.png
agent-browser snapshot -i

Command Chaining

Commands can be chained with &&. The browser persists between commands via a background daemon.

agent-browser open http://localhost:3000 && agent-browser wait --load networkidle && agent-browser snapshot -i

Essential Commands

# Navigation
agent-browser open <url>              # Navigate (aliases: goto, navigate)
agent-browser close                   # Close browser

# Snapshot
agent-browser snapshot -i             # Interactive elements with refs
agent-browser snapshot -i -C          # Include cursor-interactive elements
agent-browser snapshot -s "#selector" # Scope to CSS selector

# Interaction (use @refs from snapshot)
agent-browser click @e1               # Click element
agent-browser fill @e2 "text"         # Clear and type text
agent-browser type @e2 "text"         # Type without clearing
agent-browser select @e1 "option"     # Select dropdown option
agent-browser check @e1               # Check checkbox
agent-browser press Enter             # Press key
agent-browser scroll down 500         # Scroll page

# Get information
agent-browser get text @e1            # Get element text
agent-browser get url                 # Get current URL
agent-browser get title               # Get page title

# Wait
agent-browser wait @e1                # Wait for element
agent-browser wait --load networkidle # Wait for network idle
agent-browser wait --url "**/page"    # Wait for URL pattern
agent-browser wait 2000               # Wait milliseconds

# Capture
agent-browser screenshot              # Screenshot to temp dir
agent-browser screenshot --full       # Full page screenshot
agent-browser screenshot --annotate   # Annotated screenshot with numbered labels
agent-browser pdf output.pdf          # Save as PDF

# Diff (compare page states)
agent-browser diff snapshot           # Compare current vs last snapshot
agent-browser diff screenshot --baseline before.png  # Visual pixel diff

Common Patterns

Form Submission

agent-browser open http://localhost:3000/signup
agent-browser snapshot -i
agent-browser fill @e1 "Jane Doe"
agent-browser fill @e2 "jane@example.com"
agent-browser click @e5
agent-browser wait --load networkidle

Authentication with State Persistence

# Login once and save state
agent-browser open http://localhost:3000/login
agent-browser snapshot -i
agent-browser fill @e1 "$USERNAME"
agent-browser fill @e2 "$PASSWORD"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# Reuse in future sessions
agent-browser state load auth.json
agent-browser open http://localhost:3000/dashboard

Data Extraction

agent-browser open http://localhost:3000/products
agent-browser snapshot -i
agent-browser get text @e5
agent-browser get text body > page.txt

Visual Debugging

agent-browser --headed open http://localhost:3000
agent-browser highlight @e1
agent-browser record start demo.webm

Ref Lifecycle (Important)

Refs (@e1, @e2, etc.) are invalidated when the page changes. Always re-snapshot after:

  • Clicking links or buttons that navigate
  • Form submissions
  • Dynamic content loading (dropdowns, modals)
agent-browser click @e5              # Navigates to new page
agent-browser snapshot -i            # MUST re-snapshot
agent-browser click @e1              # Use new refs

Annotated Screenshots (Vision Mode)

Use --annotate for screenshots with numbered labels on interactive elements:

agent-browser screenshot --annotate
# Output: [1] @e1 button "Submit", [2] @e2 link "Home", ...
agent-browser click @e2

Semantic Locators (Alternative to Refs)

agent-browser find text "Sign In" click
agent-browser find label "Email" fill "user@test.com"
agent-browser find role button click --name "Submit"

JavaScript Evaluation

# Simple expressions
agent-browser eval 'document.title'

# Complex JS: use --stdin with heredoc
agent-browser eval --stdin <<'EVALEOF'
JSON.stringify(
  Array.from(document.querySelectorAll("img"))
    .filter(i => !i.alt)
    .map(i => ({ src: i.src.split("/").pop(), width: i.width }))
)
EVALEOF

Session Management

agent-browser --session site1 open http://localhost:3000
agent-browser --session site2 open http://localhost:3001
agent-browser session list
agent-browser close  # Always close when done

Timeouts and Slow Pages

agent-browser wait --load networkidle  # Best for slow pages
agent-browser wait "#content"          # Wait for specific element
agent-browser wait --url "**/dashboard"  # Wait for URL pattern
agent-browser wait 5000                # Fixed wait (last resort)

Mais skills de openai

user-context
openai
Carregar ou gerenciar as preferências de roteamento de origem duráveis, a lógica de integração, o progresso de configuração e o registro da camada semântica do plugin Data Analytics.
official
notion-research-documentation
openai
Pesquise conteúdo do Notion e sintetize em briefs estruturados, relatórios ou comparações com citações. Pesquise e busque páginas do Notion usando consultas direcionadas, depois organize os achados por tema com citações inline das fontes e uma seção de referências. Escolha entre quatro formatos de saída (brief rápido, resumo de pesquisa, comparação, relatório abrangente) com base no escopo e no objetivo do usuário. Crie e atualize páginas do Notion usando modelos integrados; vincule fontes diretamente e acompanhe alterações à medida que novas informações chegam...
official
rcsb-pdb-skill
openai
Enviar solicitações compactas do RCSB PDB para metadados principais, consultas da API de busca e downloads FASTA. Use quando um usuário desejar resumos concisos do RCSB; salve JSON bruto ou…
official
pdf
openai
We need to translate the given text from English to Brazilian Portuguese. The text describes a skill related to PDF handling. The name "pdf" is to be preserved, but it appears in the text as "PDF" (uppercase). The instruction says "Do not include the name unless it appears in the source text." Since "PDF" appears multiple times, we should keep it as is. Also preserve technical terms like "Poppler", "pdftoppm", "reportlab", "pdfplumber", "pypdf", "ASCII". The translation should be natural in Brazilian Portuguese. Let's break down the text: "PDF reading, creation, and validation with visual rendering and programmatic generation. Render PDF pages to PNG for visual inspection of layout, spacing, and typography before delivery using Poppler ( pdftoppm ) Generate PDFs programmatically with reportlab for reliable formatting; extract text and metadata with pdfplumber or pypdf Enforce quality standards: no clipped text, overlapping elements, broken tables, or rendering artifacts; ASCII hyphens only, human
official
test-coverage-improver
openai
Improve test coverage in the OpenAI Agents JS monorepo: run `pnpm test:coverage`, inspect coverage artifacts, identify low-coverage files and branches, propose…
official
playwright
openai
Automação de navegador via terminal com snapshots de elementos e fluxos de UI interativos. Opera através do script wrapper playwright-cli (requer npx); suporta modos headless e headed para depuração visual. Fluxo principal: abrir página, capturar snapshot para referências estáveis de elementos, interagir usando referências, recapturar snapshot após navegação ou mudanças no DOM. Inclui preenchimento de formulários, cliques, digitação, gerenciamento de múltiplas abas, captura de screenshot/PDF e gravação de trace para depuração de fluxos. Referências de elementos (ex.: e3, e15)...
official
ukb-topmed-phewas-skill
openai
Busque resumos compactos de PheWAS UKB-TOPMed para variantes únicas, aceitando entrada rsID, GRCh37 ou GRCh38 e resolvendo para a consulta GRCh38 necessária. Use quando um…
official
code-review-context
openai
Contexto visível do modelo
official