"read", "get page", "content of URL"?
read_page (JS-rendered) or fetch_light (static)
← Skill registry
Developer workflowsPublic skills
Browser Automation
Web operations for AI agents — read pages, extract data, take screenshots, interact with forms, and scrape structured content via headless Chromium.
What this skill teaches
A reusable playbook for a specific kind of work.
An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.
Orchestrate browser operations — fetch web pages, extract content, take screenshots, interact with elements, and scrape structured data. Use when reading web pages, extracting data from websites, taking screenshots, checking if URLs are up, or interacting with web forms.
Architecture
How Browser Automation guides an ADK-Rust agent.
The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.
01
User request
The agent receives a goal expressed in ordinary language.
02
Browser Automation skill
Matches intent, supplies the decision guide, and narrows the tool boundary.
03
ADK-Rust agent
Plans the workflow and streams each meaningful step through the runtime.
04
mcp-browser
Executes authenticated operations against the system that owns the capability.
05
Verified result
The skill's completion rules shape the evidence returned to the user.
Decision guide
How the agent turns a request into the right action.
These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.
"screenshot", "capture", "visual"?
screenshot / screenshot_element
"links", "extract links"?
extract_links
"click", "fill form", "interact"?
click / type_text / wait_for
"is it up", "status", "check URL"?
check_status
"PDF", "save page"?
save_pdf
"structured data", "scrape fields"?
extract_structured / query_selector
Proven workflows
Repeatable sequences for useful outcomes.
A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.
011-2 calls
Read Page
Clean text from any URL
022 calls
Extract Data
Structured fields from pages
031 calls
Screenshot
Visual capture (full page or element)
043-4 calls
Interact
Fill forms, click buttons
051 calls
Status Check
Verify URL is reachable
Tool boundary
The skill may use 17 documented tools.
This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-browser retains responsibility for authentication, validation, and the connected system.
read_page
get_html
extract_links
extract_metadata
query_selector
get_accessibility_tree
extract_structured
screenshot
screenshot_element
save_pdf
click
type_text
evaluate_js
wait_for
navigate
check_status
fetch_light
Working rules
What the agent should do.
- Use check_status before heavy operations (avoid wasting time on dead URLs)
- Use fetch_light for static pages (10x faster than full browser)
- Use get_accessibility_tree for token-efficient extraction (77% fewer tokens than HTML)
Operating boundaries
What the agent should avoid.
- Don't use read_page for simple static pages (use fetch_light)
- Don't scrape sites that explicitly block bots (respect robots.txt)
- Don't store credentials entered via type_text
Install and connect
Add the skill beside the capability it expects.
Install the repository where your ADK-Rust skill loader can discover it, connect mcp-browser, and confirm the declared tools are available before asking the agent to use the workflow.
Install the skill
git clone https://github.com/zavora-ai/skill-browser-automation.git ~/.skills/skills/browser-automationADK-Rust loading shape
let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("browser-automation").await?;
let agent = LlmAgentBuilder::new("agent")
.instruction(skill.instructions())
.tools(skill.allowed_tools(toolset)?)
.build()?;The repository's compatibility statement: Requires mcp-browser server connected (Chromium-based, headless).
Official documentation
Read the complete skill package.
The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.
Keep exploring
More in developer workflows.
CI/CD Pipeline ManagementPipeline operations for AI agents — monitor builds, debug failures from logs, trigger safe deployments, and manage release gates via mcp-cicd.8 allowed toolsCode Search & NavigationCode intelligence for AI agents — semantic search, symbol lookup, call graphs, dependency mapping, blast radius analysis, and ownership resolution via mcp-code-search.8 allowed toolsComputer UseDesktop automation for AI agents — screenshot, click, type, scroll, accessibility trees, form filling, menu navigation, scripts (AppleScript/JXA/PowerShell), app/window management. 49 tools.50 allowed tools
Source record
Repository metadata for this skill entry.
- License
- Apache-2.0
- Allowed tools
- 17
- References
- 3
- Revision
- 38297870a375
- Updated
- May 31, 2026