Skyvern Browser Automation -- CLI Judgment Procedure

Skyvern uses AI to navigate and interact with websites. Every command below is a runnable

skyvern <command>

When to Use This Skill

• Use when you need AI-assisted browser automation for navigation, extraction, form filling, login flows, or reusable website workflows.
• Use when deterministic selectors are unavailable and Skyvern's visual/a11y reasoning can identify page controls.
• Use when a one-off browser task should become a repeatable workflow with run history and verification.

Step 1: Classify Your Task (ALWAYS do this first)

skyvern browser validate

skyvern browser extract

skyvern browser click/type

skyvern browser act

skyvern browser act

act

skyvern browser run-task

skyvern workflow create

run

MCP note: if you are using the Skyvern MCP instead of the CLI, prefer

observe + execute

Step 2: Apply These Decision Rules

1. If the prompt includes a selector, id, XPath, or exact field target, use browser primitives -- not

   act

   .
2. If you only need a yes/no answer, use

   validate

   -- not

   extract

   or

   act

   .
3. If the work stays on one page and labels are clear, use

   act

   or a primitive chain.
4. If the user says

   try this once

   ,

   see if this works

   , or clearly wants a one-off exploratory trial, use

   run-task

   .
5. If the task spans multiple pages and is meant to be reusable, scheduled, repeatable, or explicitly

   set up

   as automation, use

   workflow create

   .
6. Never type passwords. Always use stored credentials with

   skyvern browser login

   .

Step 3: Create a Session

Every browser command needs a session. Create one first:

# Cloud session (default -- works for public URLs)
skyvern browser session create --timeout 30

# Local session (for localhost URLs or self-hosted mode)
skyvern browser session create --local --timeout 30

# Connect to existing browser via CDP
skyvern browser session connect --cdp "ws://localhost:9222"

Session state persists between commands. After

session create

--session pbs_...

skyvern browser session close

Step 4: Execute by Classification

Quick check (yes/no)

skyvern browser validate --prompt "Is the user logged in? Look for a dashboard or avatar."

Returns true/false. Cheapest AI option -- prefer over extract or act for boolean checks.

Quick inspection

skyvern browser extract \
  --prompt "Extract all product names and prices" \
  --schema '{"type":"object","properties":{"items":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string"},"price":{"type":"string"}}}}}}'

Uses screenshots + dedicated extraction LLM. Better than screenshot+read because Skyvern's LLM interprets the page.

Single action (known target)

skyvern browser click --selector "#submit-btn"
skyvern browser type --text "user@co.com" --selector "#email"
skyvern browser select --value "US" --intent "the country dropdown"

Deterministic. No AI. Three targeting modes:

1. Intent:

   --intent "the Submit button"

   (AI finds element)
2. Selector:

   --selector "#submit-btn"

   (CSS/XPath, deterministic)
3. Hybrid: both (selector narrows, AI confirms)

Single action (unknown target)

skyvern browser act --prompt "Click the Sign In button"
skyvern browser act --prompt "Close the cookie banner, then click Sign In"

Warning: act has NO screenshots in its LLM reasoning. It uses an economy accessibility tree. Fine for well-labeled elements. For visually complex targets, use MCP observe+click or hybrid mode.

Same-page multi-step

skyvern browser act --prompt "Fill the shipping form and click Continue"

Use

act

click

type

select

press-key

wait

Throwaway autonomous trial

skyvern browser run-task \
  --url "https://example.com" \
  --prompt "Check whether the checkout flow works end to end and extract the confirmation number"

Use

run-task

Multi-page or reusable automation — build a workflow with one block per step

skyvern workflow create --definition @checkout-workflow.yaml
skyvern workflow run --id wpid_123 --wait
skyvern workflow status --run-id wr_789

Each navigation block runs with visual reasoning + verification. Split complex flows into multiple blocks (one per page/step). First run uses AI; subsequent runs replay cached scripts.

Repeated/production

skyvern workflow create --definition @workflow.yaml
skyvern workflow run --id wpid_123 --params '{"email":"user@co.com"}'
skyvern workflow status --run-id wr_789

Split into one block per step. Use navigation blocks for actions, extraction for data. First run uses AI; subsequent runs replay a cached script (10-100x faster). Set

--run-with agent

Step 5: Verify

Always verify after page-changing actions:

skyvern browser screenshot                          # visual check
skyvern browser validate --prompt "Was the form submitted successfully?"  # boolean assertion
skyvern browser evaluate --expression "document.title"                    # JS state check

Step 6: Error Recovery

skyvern browser wait --selector "#el" --state visible

Credentials

NEVER type passwords through

skyvern browser type

act

skyvern credentials add --name "my-login" --type password --username "user@co.com"
skyvern credential list                          # find the credential ID
skyvern browser login --url "https://login.example.com" --credential-id cred_123

Types:

password

credit_card

secret

Workflow Quick Reference

skyvern workflow create --definition @workflow.yaml   # create
skyvern workflow run --id wpid_123 --wait             # run and wait
skyvern workflow status --run-id wr_789               # check status
skyvern workflow list --search "invoice"              # find workflows
skyvern block schema --type navigation                # discover block types
skyvern block validate --block-json @block.json       # validate before creating

Engine: known path = 1.0 (default). Dynamic planning = 2.0. Split into multiple 1.0 blocks when in doubt. Status lifecycle:

created -> queued -> running -> completed | failed | canceled | terminated | timed_out

Common Patterns

Login flow:

skyvern credential list                          # find credential ID
skyvern browser session create
skyvern browser navigate --url "https://login.example.com"
skyvern browser login --url "https://login.example.com" --credential-id cred_123
skyvern browser validate --prompt "Is the user logged in?"
skyvern browser screenshot

Pagination loop:

skyvern browser extract --prompt "Extract all rows"
skyvern browser validate --prompt "Is there a Next button that is not disabled?"
# If true:
skyvern browser act --prompt "Click the Next page button"
# Repeat extraction. Stop when: no next button, duplicate first row, or max page limit.

Debugging:

skyvern browser screenshot                       # visual state
skyvern browser evaluate --expression "document.title"
skyvern browser evaluate --expression "document.querySelectorAll('table tr').length"

Limitations

• Do not use Skyvern to bypass site access controls, rate limits, consent gates, or terms that prohibit automation.
• Browser automation can change remote state; confirm user intent before submitting forms, purchasing, deleting, or sending messages.
• Prefer deterministic selectors for stable production flows; AI actions can misread unlabeled or visually ambiguous controls.
• Store credentials only in the supported credential vaults and never type passwords directly through

  type

  or

  act

  .

Agent Mode

All commands accept

--json

SKYVERN_NON_INTERACTIVE=1

skyvern capabilities --json

Deep-Dive References

references/prompt-writing.md

references/engines.md

references/schemas.md

references/pagination.md

references/block-types.md

references/parameters.md

references/ai-actions.md

references/precision-actions.md

references/credentials.md

references/sessions.md

references/common-failures.md

references/screenshots.md

references/status-lifecycle.md

references/rerun-playbook.md

references/complex-inputs.md

references/tool-map.md

references/cli-parity.md

references/quick-start-patterns.md