playwriter
Controls Chrome browser via Playwright MCP for web automation, testing, screenshots, and scraping. Use when explicitly asked to "use playwriter".
Controls Chrome browser via Playwright MCP for web automation, testing, screenshots, and scraping. Use when explicitly asked to "use playwriter".
Playwriter
Browser automation via MCP. Requires Chrome extension installed and clicked on target tab.
Tools
execute
Run Playwright code with access to page, context, state (persistent), and utility functions.
// Single-line format with semicolons
await page.goto('https://example.com', { waitUntil: 'domcontentloaded' });
reset
Reset CDP connection when errors occur or pages show as about:blank.
Core Patterns
Check Page State (do this after actions)
console.log('url:', page.url()); console.log(await accessibilitySnapshot({ page }).then(x => x.split('\n').slice(0, 30).join('\n')));
Click Elements (use aria-ref from snapshot)
await page.locator('aria-ref=e13').click();
Fill Input
await page.locator('input[name="email"]').fill('test@example.com');
Screenshot
await page.screenshot({ path: 'shot.png', scale: 'css' });
Visual Screenshot with Labels
await screenshotWithAccessibilityLabels({ page });
Utility Functions
| Function | Purpose |
|---|---|
accessibilitySnapshot({ page, search? }) |
Get structured text of interactive elements |
screenshotWithAccessibilityLabels({ page }) |
Screenshot with Vimium-style element labels |
getCleanHTML({ locator }) |
Get cleaned semantic HTML |
getLatestLogs({ page?, count?, search? }) |
Retrieve browser console logs |
waitForPageLoad({ page }) |
Smart load detection |
getCDPSession({ page }) |
Send raw CDP commands |
Rules
- Multiple calls: Break complex logic into separate execute calls
- Never close: Don't call
browser.close()orcontext.close() - No bringToFront: Never call unless user asks
- Always verify: Check page state after clicks/navigation
- Persist data: Use
state.myVar = valueacross calls
You Might Also Like
Related Skills
mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
openclaw
model-usage
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
moltbot
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
affaan-m
skill-creation-guide
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
davila7
claude-code-guide
Claude Code 高级开发指南 - 全面的中文教程，涵盖工具使用、REPL 环境、开发工作流、MCP 集成、高级模式和最佳实践。适合学习 Claude Code 的高级功能和开发技巧。
2025Emma
filesystem-context
This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.
muratcankoylan