Rechercher

PythonReactSEOPDF
OpenClaw

fastplaywright

High-performance browser automation with Fast Playwright MCP. Features token-optimized batch execution, intelligent element selection with fallback, diff detection for change tracking, and comprehensive diagnostics. Use for web testing, form automation, screenshots, navigation flows, and any browser-based task requiring efficient token usage.

frankausberlin0 installations selon la source☆ 0 Étoiles du dépôt

Installation

Suivez les instructions du dépôt pour votre agent. Consultez les fichiers et dépendances avant l’installation.

SkillHub CLI

skillhub install frankausberlin/fastplaywright

Examinez la source et la compatibilité, puis suivez les étapes d’installation.

Donnez le lien à votre agent et demandez-lui d’examiner instructions et dépendances avant d’expliquer les étapes.

Voir la source ↗Guides

Instructions

Fast Playwright MCP

High-performance browser automation skill using the Fast Playwright MCP server (@tontoko/fast-playwright-mcp). This fork of the Microsoft Playwright MCP provides significant token optimization, batch execution, and enhanced element discovery.

Key Advantages Over Standard Playwright MCP

Feature Benefit
Token Optimization 70-80% reduction via expectation parameter
Batch Execution 90% token savings for multi-step workflows
Diff Detection Track only changes, not full snapshots
Enhanced Selectors Multiple selector types with automatic fallback
Diagnostic Tools Advanced debugging and element discovery
Image Compression JPEG format, quality control, resizing

MCP Configuration

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@tontoko/fast-playwright-mcp@latest"]
    }
  }
}

Critical Workflow

Follow these steps in order for optimal results:

1. Navigate First

Use browser_navigate to load the target page before any other operations.

2. Use Batch Execution for Multi-Step Tasks

For 2+ operations, ALWAYS use browser_batch_execute instead of individual tool calls.

3. Optimize Token Usage

Apply expectation parameters to reduce response size.

4. Use Diff Detection for State Changes

Enable diffOptions when tracking changes without navigation.

Token Optimization

The Expectation Parameter

All browser tools support an expectation parameter to control response content:

{
  "includeSnapshot": false,    // 70-80% token reduction
  "includeConsole": false,      // Exclude console messages
  "includeTabs": false,         // Hide tab information
  "includeCode": false,         // Suppress code generation
  "includeDownloads": false     // Exclude download info
}
Snapshot Options

Limit snapshot content for focused analysis:

{
  "snapshotOptions": {
    "sel...

Informations sur la source

Source
github
Repository
openclaw/skills
Path
skills/frankausberlin/fastplaywright
Version
—
Commit
d0dafd88c1f94b3bf268ebc714018c2660fb92a1
Source de classification
rules
Statut
active
Visibilité
public

Ces informations proviennent de l’analyse indexée et peuvent être anciennes. Vérifiez les fichiers actuels.

Contenu extrait

SKILL.md
# Fast Playwright MCP

High-performance browser automation skill using the Fast Playwright MCP server (`@tontoko/fast-playwright-mcp`). This fork of the Microsoft Playwright MCP provides significant token optimization, batch execution, and enhanced element discovery.

## Key Advantages Over Standard Playwright MCP

| Feature | Benefit |
|---------|---------|
| **Token Optimization** | 70-80% reduction via `expectation` parameter |
| **Batch Execution** | 90% token savings for multi-step workflows |
| **Diff Detection** | Track only changes, not full snapshots |
| **Enhanced Selectors** | Multiple selector types with automatic fallback |
| **Diagnostic Tools** | Advanced debugging and element discovery |
| **Image Compression** | JPEG format, quality control, resizing |

## MCP Configuration

```json
{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": ["@tontoko/fast-playwright-mcp@latest"]
    }
  }
}
```

## Critical Workflow

Follow these steps in order for optimal results:

### 1. Navigate First
Use `browser_navigate` to load the target page before any other operations.

### 2. Use Batch Execution for Multi-Step Tasks
For 2+ operations, ALWAYS use `browser_batch_execute` instead of individual tool calls.

### 3. Optimize Token Usage
Apply `expectation` parameters to reduce response size.

### 4. Use Diff Detection for State Changes
Enable `diffOptions` when tracking changes without navigation.

## Token Optimization

### The Expectation Parameter

All browser tools support an `expectation` parameter to control response content:

```json
{
  "includeSnapshot": false,    // 70-80% token reduction
  "includeConsole": false,      // Exclude console messages
  "includeTabs": false,         // Hide tab information
  "includeCode": false,         // Suppress code generation
  "includeDownloads": false     // Exclude download info
}
```

### Snapshot Options

Limit snapshot content for focused analysis:

```json
{
  "snapshotOptions": {
    "sel...

Skills associés

OpenClaw

openbotx

openbotx

An open-source platform for orchestrating AI agents — secure, simple, and built for everyone. Multi-agent, real-time task board, web control panel, skills system, browser automation, multi-provider, scheduler,...

OpenClaw

zsxq-digest

sealiu1997

OpenClaw skill for 知识星球 / ZSXQ digests with token-first auth and browser recovery.

OpenClaw

browser-use-skill

abczsl520

🌐 OpenClaw skill for Browser-Use — AI-powered browser automation for complex multi-step workflows (login, form filling, scraping, posting)