browse
Real browser automation for testing, QA, and demo verification.
Skill by The13thNode
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.
About
Use cases: testing
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. 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 limitationFrom The13thNode/VibeCorp_PromptCEO, MIT.
More from The13thNode/VibeCorp_PromptCEO
- 0.454score
jira
The13thNode
Manages JIRA issues, projects, and workflows using Atlassian MCP.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
content-trust
The13thNode
Diagnoses why content isn't converting and fixes it using the Trust Architecture framework.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
corporate-structure
The13thNode
Prepares founders for all corporate structure and governance questions from investors.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
ai-systems
The13thNode
Builds production-grade Claude Projects and CustomGPTs, improves AI output quality using meta-thinking prompts, and architects self-improving AI systems.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
database-design
The13thNode
Designs database schemas, migration strategies, indexing, query optimization, and ORM patterns.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
ceo-thinking-partner
The13thNode
The CEO's private brainstorming room and strategic sparring partner.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
change-management
The13thNode
Manages scope changes, strategic pivots, incident communication, and team alignment when direction changes.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
bootstrapped-saas
The13thNode
Playbook for bootstrapped and early-stage SaaS founders based on proven case studies ($0 to $5M ARR with 6 people, and creator-to-business flywheel models).
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
authentication-skill
The13thNode
Implements authentication and authorisation systems including JWT, OAuth2, sessions, MFA, social login, RBAC, and refresh token rotation.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
api-design
The13thNode
Designs REST APIs, GraphQL schemas, OpenAPI specs, webhook systems, and API versioning strategies.
SkillDFreshness: D★ 3Claude Code +9 - 0.446score
benchmark
The13thNode
Performance baseline measurement.
SkillDFreshness: D★ 3Claude Code +9 - 0.446score
autoplan
The13thNode
One-command review pipeline.
SkillDFreshness: D★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 5, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from The13thNode
- 0.454score
jira
The13thNode
Manages JIRA issues, projects, and workflows using Atlassian MCP.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
bootstrapped-saas
The13thNode
Playbook for bootstrapped and early-stage SaaS founders based on proven case studies ($0 to $5M ARR with 6 people, and creator-to-business flywheel models).
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
api-design
The13thNode
Designs REST APIs, GraphQL schemas, OpenAPI specs, webhook systems, and API versioning strategies.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
authentication-skill
The13thNode
Implements authentication and authorisation systems including JWT, OAuth2, sessions, MFA, social login, RBAC, and refresh token rotation.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
ai-systems
The13thNode
Builds production-grade Claude Projects and CustomGPTs, improves AI output quality using meta-thinking prompts, and architects self-improving AI systems.
SkillDFreshness: D★ 3Claude Code +9 - 0.449score
ceo-thinking-partner
The13thNode
The CEO's private brainstorming room and strategic sparring partner.
SkillDFreshness: D★ 3Claude Code +9
Cite this page
browse skill. Agent Mart. https://agentmart.dev/skills/the13thnode-browse (last updated 2026-10-24)