Skip to content
Agentmart
Submit a tool

browser-test

Run and debug Playwright browser tests for this project (API, E2E, smoke).

Skill by bos-hieu

IndexedMIT
Write a review

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/bos-hieu-browser-test

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

Run and debug Playwright browser tests for this project (API, E2E, smoke). Wraps the existing tests/frontend Playwright setup with smart filtering, result parsing, and failure reporting.

Use cases: frontend, backend, 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/browser-test

Tools it pre-approves 9

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Bash(go
  • run
  • *),
  • Bash(npx
  • Bash(node
  • Bash(npm
  • Bash(cat
  • Bash(ls
  • *)

What's inside

Skill name
browser-test
Description
Run and debug Playwright browser tests for this project (API, E2E, smoke). Wraps the existing tests/frontend Playwright setup with smart filtering, result parsing, and failure reporting.
License
MIT
Allowed tools
Bash(go, run, *),, Bash(npx, *),, Bash(node, *),, Bash(npm, *),, Bash(cat, *),, Bash(ls, *)
Instructions
48 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (2)

  • SKILL.md
  • main.go

SKILL.md (first lines)

When the user wants to run browser tests, debug a failing test, or add a new Playwright test, use `${CLAUDE_SKILL_DIR}` to reference the Go file.

## Test Layout

```
tests/frontend/
├── playwright.config.js
└── tests/
    ├── api/    *.api.spec.js
    ├── e2e/    *.e2e.spec.js
    ├── smoke/  split-deployment.test.js
    ├── unit/   *.test.js (node --test)
    └── support/ helpers
```

## Usage

```bash
go run ${CLAUDE_SKILL_DIR}/main.go [flags]
```

| Flag | Description |
|---|---|
| `--project <name>` | Test project: `api`, `e2e`, `smoke` (default: all) |
| `--file <glob>` | Filter test files by pattern |
| `--test <name>` | Filter by test name substring |
| `--headed` | Run browser in headed mode |
| `--debug` | Run with PWDEBUG=1 |
| `--retries <n>` | Override retry count |
| `--base-url <url>` | Override BASE_URL (default: http://localhost:3030) |
| `--install` | Install Playwright + chromium |
| `--list-tests` | List discovered tests without running |
| `--report` | Open HTML report after run |

## Adding a New Test

Place in `tests/frontend/tests/api/<name>.api.spec.js` or `tests/frontend/tests/e2e/<name>.e2e.spec.js`:

```js
import { test, expect } from '@playwright/test';
test.describe('<Feature>', () => {
  test('<scenario>', async ({ page, request }) => {
    // API test: use `request`; E2E test: use `page`
  });
});
```

From bos-hieu/agent-skills, MIT.

More from bos-hieu/agent-skills

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Mar 31, 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 bos-hieu

Cite this page

browser-test skill. Agent Mart. https://agentmart.dev/skills/bos-hieu-browser-test (last updated 2026-10-24)