Skip to content
Agentmart
Submit a tool

browse

Real browser automation for testing, QA, and demo verification.

Skill by The13thNode

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying browse?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/the13thnode-browse

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.

We use your email only for this newsletter. Privacy

About

Real browser automation for testing, QA, and demo verification. Provides Playwright-based browser control for navigating the live app, clicking elements, filling forms, taking screenshots, and verifying visual state.

Use cases: testing

No 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. 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/browse

What's inside

Skill name
browse
Description
Real browser automation for testing, QA, and demo verification. Provides Playwright-based browser control for navigating the live app, clicking elements, filling forms, taking screenshots, and verifying visual state.
License
MIT
Instructions
102 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Browser Skill

When you need to verify something in a real browser (not just unit tests), use this skill.

## Prerequisites
- Playwright must be installed: `npx playwright install chromium` (run once)
- Target URLs: `[LIVE_URL]` (production) or `http://localhost:3000` (dev)

## Browser Commands (use via Node.js script execution)

Launch browser and navigate:
```js
const { chromium } = require('playwright');
const browser = await chromium.launch({ headless: true });
const page = await browser.newPage();
await page.goto('[LIVE_URL]');
```

Take screenshot:
```js
await page.screenshot({ path: 'docs/screenshots/[feature]-[timestamp].png', fullPage: true });
```

Click element:
```js
await page.click('[data-testid="login-button"]');
// or by text
await page.click('text=Sign In');
```

Fill form:
```js
await page.fill('[data-testid="email-input"]', 'test@example.com');
```

Wait for navigation/element:
```js
await page.waitForURL('**/dashboard');
await page.waitForSelector('[data-testid="item-card"]');
```

Check element exists:
```js
const exists = await page.isVisible('[data-testid="error-message"]');
```

Get text content:
```js
const text = await page.textContent('[data-testid="status-badge"]');
```

Close:
```js
await browser.close();
```

## Flow Testing Pattern

For every QA flow, follow this structure:
1. Launch browser
2. Navigate to start URL
3. Execute steps (click, fill, wait)
4. Screenshot at each key state
5. Assert expected state (element visible, text correct, URL correct)
6. Screenshot final state
7. Close browser
8. Report: PASS with screenshots or FAIL with screenshot of failure state

## Screenshots
Save all screenshots to: `docs/screenshots/`
Naming: `[agent]-[feature]-[step]-[timestamp].png`
Post screenshot paths in Slack messages so PD can review.

## Generic Application Flows

[DOMAIN_ACTOR_1] signup flow:
1. goto /
2. click "Get Started" or "Sign Up"
3. fill email, name
4. verify redirect to profile setup
5. screenshot profile page

[DOMAIN_ENTITY] browse flow:
1. goto /[DOMAIN_ENTITY_PLURAL]
2. verify [DOMAIN_ENTITY] cards render
3. click first [DOMAIN_ENTITY]
4. verify detail page loads
5. screenshot detail page

[DOMAIN_ACTOR_2] review flow:
1. goto /[DOMAIN_ACTOR_2]/dashboard (requires auth)
2. verify application cards render
3. click an application
4. verify review modal opens
5. screenshot review state

## Limitations
- Cannot solve CAPTCHAs — if hit, report to CEO
- Cannot handle MFA — report to CEO
- If Playwright not installed, fall back to curl + DOM parsing and note the limitation

From The13thNode/VibeCorp_PromptCEO, MIT.

More from The13thNode/VibeCorp_PromptCEO

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Apr 5, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from The13thNode

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get browse running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying browse?

CallGet help
Cite this page

browse skill. Agent Mart. https://agentmart.dev/skills/the13thnode-browse (last updated 2026-10-24)