browser
- Repo stars 39
- Author updated Live
- Author repo awesome-omni-skill
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @diegosouzapw · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Required · Anthropic
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: browser
description: Control a Chrome session via Stagehand to browse, act, extract, and screenshot on demand inside…
category: data
runtime: no special runtime
---
# browser output preview
## PART A: Task fit
- Use case: Control a Chrome session via Stagehand to browse, act, extract, and screenshot on demand inside the Factory CLI. Use this skill when you need live browser automation during a Factory session—opening sites, clicking through flows, gathering structured data, or capturing screenshots. requires Anthropic API key. Works with Claude Code, Cursor, Cline and 23 m….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Inputs / Behavior / Verification” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Control a Chrome session via Stagehand to browse, act, extract, and screenshot on demand inside the Factory CLI. Use this skill when you need live browser automation during a Factory session—opening sites, clicking through flows, gathering structured data, or capturing screenshots. requires Anthropic API key. Works with Claude Code, Cursor, Cline and 23 m…”.
- **02** When the source has headings, the agent prioritizes “Inputs / Behavior / Verification” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; may access external network resources; requires Anthropic API keys.
## Running Rules
- read files, write/modify files, run shell commands; may access external network resources; requires Anthropic API keys.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Validate with a small run
Start with a small task and check whether the result follows “Inputs / Behavior / Verification”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: browser
description: Control a Chrome session via Stagehand to browse, act, extract, and screenshot on demand inside…
category: data
source: diegosouzapw/awesome-omni-skill
---
# browser
## When to use
- Control a Chrome session via Stagehand to browse, act, extract, and screenshot on demand inside the Factory CLI. Use t…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Inputs / Behavior / Verification” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; may access external network resources; requires Anthropic API keys.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "browser" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Inputs / Behavior / Verification
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files, run shell commands | may access external network resources
guardrails -> requires Anthropic API keys + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Skill: Browser
Use this skill when you need live browser automation during a Factory session—opening sites, clicking through flows, gathering structured data, or capturing screenshots.
Inputs
- Target URL or task description (natural language)
- Optional structured extraction schema (JSON field → type)
Behavior
- Ensure Chrome is running via Stagehand with the local profile stored in
.chrome-profile. - Support these commands:
navigate <url>: open a page and capture a screenshot.act "<instruction>": perform natural-language actions.extract "<instruction>" '{"field":"type"}': return structured data.observe "<goal>": list suggested steps the agent can take.screenshot: capture the current viewport.close: shut down the session when finished.
- Save screenshots to
agent/browser_screenshotsand report the file path in the response. - When tasks finish, summarize what happened plus any follow-up steps for the user.
Verification
- If a navigation/action fails, include the error message and prompt the user for next steps.
- Before ending the session, ensure
closehas been run so Chrome processes don’t linger.
Notes
- This skill expects
ANTHROPIC_API_KEY(for Stagehand) and, if used viadroid exec,FACTORY_API_KEYto already be configured. - The working directory should remain inside the cloned skill folder so relative paths resolve correctly.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review