interact-browser
Escalate to Zenrows MCP browser_* sessions only when scrape/extract cannot do the job.
Skill by ZenRows
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/zenrows-interact-browser
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/interact-browser
What's inside
- Skill name
interact-browser- Description
- Escalate to Zenrows MCP browser_* sessions only when scrape/extract cannot do the job.
- License
- MIT
- Instructions
- 43 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Interact / Browser Sessions (MCP `browser_*`) Operate protected browser workflows (logins, clicks, forms, multi-step flows, persistent cookies) on JS-heavy or interactive pages that `scrape` / `extract` cannot handle. **Escalation only.** > Browser Sessions bill by **bandwidth + session time** and auto-terminate > after ~15 minutes. Same backend as CLI Browser Sessions / hosted MCP. ## Core flow 1. `browser_navigate` → get `session_id` 2. Inspect with `browser_get_accessibility_tree` / `browser_get_text` / `browser_screenshot` 3. Act: `browser_click`, `browser_fill`, `browser_type`, `browser_select_option`, `browser_check` / `browser_uncheck`, `browser_press_key`, `browser_scroll`, `browser_drag`, … 4. Wait: `browser_wait_for_selector`, `browser_wait_for_navigation`, `browser_wait` 5. Multi-step known sequences: `browser_batch` (actions against an existing session — **not** URL Batch / `batch_create`) 6. Always `browser_close` when done Other useful tools: `browser_evaluate`, cookies (`browser_get_cookies` / `browser_set_cookies` / `browser_clear_cookies`), local storage (`browser_get_local_storage` / `browser_set_local_storage` / `browser_clear_local_storage`), tabs (`browser_new_tab` / `browser_switch_tab`), `browser_generate_pdf`. ## Rules - Try [[protected-fetch]] (`scrape`) / [[extract]] first; escalate only with evidence — they cost less. - Pass `session_id` on every call after navigate. - Prefer `browser_batch` when you already know the full action sequence (fewer round trips). - Always `browser_close` interactive sessions. - `browser_select_option` matches the option's `value` attribute (bare value or a CSS selector like `option[value="2"]`). Label text / index are not supported. - Do not use CLI `zenrows browser` as the primary path when MCP `browser_*` tools are available.
From ZenRows/cli, MIT.
More from ZenRows/cli
- 0.640score
crawl
ZenRows
Collect the URLs behind one start page with Crawl (new): create a crawl, wait for it, read the kept URLs and optionally each page's HTML, stop it.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
batch-jobs
ZenRows
Scale protected fetch/extract over many URLs via Batch.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
protected-fetch
ZenRows
Use Zenrows Protected Fetch in auto mode for anti-bot-protected page retrieval.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
protected-fetch
ZenRows
Use the Zenrows MCP scrape tool for anti-bot-protected page retrieval.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
zenrows
ZenRows
Master playbook for choosing the right Zenrows MCP primitive for any web-data task, with cost and escalation rules.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
compliance-policy
ZenRows
Respect domain allow/deny rules, credit limits, and secret handling.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
cost-control
ZenRows
Pick the cheapest reliable primitive and understand the Zenrows cost multipliers.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
cost-control
ZenRows
Pick the cheapest reliable Zenrows MCP configuration and understand cost multipliers.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
extract
ZenRows
Turn protected pages into structured data with Extract / CSS / Markdown (Autoparse is deprecated).
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
interact-browser
ZenRows
Escalate to browser sessions only when fetch/extract cannot do the job.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
batch-jobs
ZenRows
Scale protected fetch/extract over many URLs via Zenrows MCP batch_* tools.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
trace-debug
ZenRows
Read run traces and choose the next action when a fetch/extract fails.
SkillAFreshness: A★ 16Claude Code +9
Signals
- Stars
- 16
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Oct 21, 2026 (7 days ago)
- Last release
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ZenRows/cli
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ZenRows
- 0.652score
Zenrows MCP
ZenRows
Zenrows MCP server: Fetch, Extract, Batch, and Browser Sessions for AI agents
ConnectorAFreshness: ARemoteLocal★ 20Claude Code +5 - 0.640score
crawl
ZenRows
Collect the URLs behind one start page with Crawl (new): create a crawl, wait for it, read the kept URLs and optionally each page's HTML, stop it.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
batch-jobs
ZenRows
Scale protected fetch/extract over many URLs via Batch.
SkillAFreshness: A★ 16Claude Code +9 - 0.637score
protected-fetch
ZenRows
Use Zenrows Protected Fetch in auto mode for anti-bot-protected page retrieval.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
protected-fetch
ZenRows
Use the Zenrows MCP scrape tool for anti-bot-protected page retrieval.
SkillAFreshness: A★ 16Claude Code +9 - 0.634score
extract
ZenRows
Turn protected pages into structured data with the Zenrows MCP extract tool (and scrape extraction params).
SkillAFreshness: A★ 16Claude Code +9
Cite this page
interact-browser skill. Agent Mart. https://agentmart.dev/skills/zenrows-interact-browser (last updated 2026-10-24)