skills.rest
no-session
no-sessionCOMMUNITY
Explore all skills by this author →
𝕏@pawan_kumar100GitHub

browse

Controls a persistent headless Chromium browser for QA testing, page inspection, and user-flow verification.

107|7|Updated Mar 29, 2026
Search Tags:#playwright#web automation#screenshot#dogfooding#chromium#headless browser#qa testing
One-click install
npx skills add https://github.com/no-session/pstack --skill browse-no-session
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: browse
Source: https://github.com/no-session/pstack/tree/main/browse
Command: npx skills add https://github.com/no-session/pstack --skill browse-no-session

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, playwright-core, diff, bun, and includes scripts (resource) components.

What problem does it solve? Manually verifying that a web app works after every change is slow and error-prone. This Skill gives an AI agent a fast, persistent headless browser (~100ms per command) so it can navigate pages, click elements, fill forms, capture screenshots, and assert page state as evidence during QA testing and dogfooding. ## Core Features & Use Cases - Interactive Page Control: Navigate URLs, click, fill, hover, select, upload files, and press keys using CSS selectors or @e refs from accessibility-tree snapshots. - State Verification & Evidence: Diff snapshots before/after actions, assert element states (visible, enabled, checked), capture annotated screenshots, and inspect console, network, and dialog logs. - Responsive & Cross-Environment Testing: Take mobile/tablet/desktop screenshots, set custom viewports, and diff two URLs (e.g., staging vs production). - User Handoff: When blocked by CAPTCHAs or MFA, open a visible Chrome window preserving cookies and session state, then resume AI control afterward. - Use Case: After deploying a login flow, run the Skill to load the page, fill credentials, submit, diff the snapshot to confirm the dashboard appeared, and attach an annotated screenshot to a bug report. ## Quick Start Ask the AI to open your app's URL in the browse tool, run a snapshot to list interactive elements, then click through the flow and screenshot the result.

Frequently Asked Questions about browse

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I test a web user flow with a headless browser?▼

Navigate with goto, run snapshot -i to list interactive elements as @e refs, then use fill and click on those refs to walk the flow. Finish with snapshot -D to diff what changed and is visible to assert the success state.

How to take annotated screenshots for bug reports?▼

Run snapshot -i -a -o /tmp/annotated.png to capture a screenshot with red overlay boxes labeling each interactive element, or use screenshot /tmp/bug.png for a plain capture. Combine with the console command to attach error logs as evidence.

Does the headless browser keep cookies and login sessions between commands?▼

Yes. The browser runs as a persistent server, so cookies, localStorage, tabs, and login sessions persist across commands. You can also save and reload full browser state with the state save and state load commands.

Can I test responsive layouts on mobile and tablet viewports?▼

Yes. The responsive command captures screenshots at mobile (375x812), tablet (768x1024), and desktop (1280x720) sizes in one step. You can also set a custom viewport with viewport WxH before taking a screenshot.

What happens when the browser hits a CAPTCHA or MFA prompt?▼

Use the handoff command to open a visible Chrome window at the current page with all state preserved, let the user solve the CAPTCHA or complete MFA, then run resume to return control to the AI with a fresh snapshot.

Why do element refs stop working after navigation?▼

Refs like @e3 point to live element locators that are invalidated whenever the page navigates. Run snapshot again after any goto or page change to get fresh refs before interacting with elements.

Related Skills

Explore More Software Engineering Skills→
clfigueiredoclfigueiredo
5

browser-qa

Automates visual testing and UI interaction verification on deployed web pages using browser automation.

Community
Intermediate
YehudaFrankelYehudaFrankel
16

run-verification

Automate structured verification of feature changes with pass/fail reporting.

Community
Intermediate
eygrabereygraber
1

check

Run formatting, detekt, lint, and unit tests on Android and Kotlin projects.

Community
Intermediate
bacocobacoco
7

sg-visual-run

Execute Playwright/agent-browser YAML visual tests and detect UI regressions.

Community
Advanced