web-screenshot
Capture screenshots of web pages running on local or remote servers using Puppeteer in headless Chromium. Use when user asks to screenshot web pages, capture web UI, take website screenshots, or document web application interfaces. Supports login-required SPAs (Vue/React/Angular) by performing form-based authentication before navigating. Generates screenshots and an optional result.json with per-page descriptions.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/aowind/sjht-web-screenshotWhat This Skill Does
The web-screenshot skill is a professional-grade automated tool designed for OpenClaw agents to capture visual documentation of web applications. Built on top of Puppeteer and headless Chromium, it enables agents to take high-resolution snapshots of local or remote web interfaces. Unlike simple scrapers, this tool includes robust support for Single Page Applications (SPAs) built with frameworks like Vue, React, or Angular. It features a specialized login handler that manages form-based authentication, ensuring the agent can bypass gated content and capture protected dashboards, project management portals, or administration panels. Every execution produces a standardized collection of PNG files coupled with a metadata-rich 'result.json' file, which includes page titles, URLs, and custom descriptions for systematic reporting.
Installation
To deploy this skill, ensure your environment has Node.js and Chromium installed. You can verify your dependencies by running 'which chromium-browser' and 'npm ls -g puppeteer-core'. Install the skill using the OpenClaw command: 'clawhub install openclaw/skills/skills/aowind/sjht-web-screenshot' Once installed, you can trigger the script directly via 'node <skill_dir>/scripts/screenshot.js <config.json>'. Ensure that your configuration file accurately maps the selectors for your target application's login form to prevent automation failure.
Use Cases
This skill is perfect for automated QA reporting, where a developer needs to visualize the current state of a build. It is also highly effective for creating technical documentation, allowing agents to capture interface changes during a deployment pipeline. Teams can use it to maintain 'live' visual records of project management dashboards for stakeholders who lack direct system access, or to document web application states for audit trails and compliance tracking.
Example Prompts
- 'Please run a screenshot capture for the staging environment using the login credentials stored in the project config file and output the results to my docs folder.'
- 'I need to generate a visual report of the current dashboard and the user settings page; can you trigger the web-screenshot agent for me?'
- 'Generate a documentation package including screenshots of the primary project list view and verify that the UI components render correctly.'
Tips & Limitations
For complex SPAs, always ensure your selectors are precise; use stable IDs or specific CSS attributes rather than dynamic classes. If you experience timing issues, increase the 'waitMs' property in the page config to account for slow API responses or hydration delays. Note that this skill requires direct network access to the target URL; ensure your network configuration allows the agent to reach the specified base URL. Always store credentials in a secure configuration environment, as this skill performs direct form interactions.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-aowind-sjht-web-screenshot": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read
Related Skills
wisdom-forum
世纪智慧论坛自动化技能。支持自动注册、浏览帖子、发布新帖、回复帖子。 论坛地址: http://8.134.249.230/wisdom/
doubao-image-gen
使用豆包 Seedream 模型文生图,支持并发批量生成,输出图库预览页
data-annotation
通用数据标注处理工具。当用户提到需要数据标注、有标注任务、数据处理、数据集生成、 标注查看/编辑时使用此 skill。支持图像、视频、文本等多种数据类型,调用模型进行内容理解 和标注,生成结构化标注数据,提供 Web 查看编辑界面。 触发短语:「标注」「annotation」「数据集」「label」「tag data」「数据处理」。
long-running-harness
长时程 Agent 项目工作流框架(基于 Anthropic "Effective Harnesses for Long-Running Agents")。 用于创建、管理和调度跨多个上下文窗口的长期项目任务。 Use when: 启动新项目、初始化项目工作流、管理项目任务列表、调度子Agent增量开发、 恢复项目状态、生成项目进度报告。触发短语包括: "启动项目"、"初始化项目"、"创建工作流"、"项目进度"、"继续开发"、 "管理任务列表"、"分配任务"、"next feature"、"project status"。
hair-cam-anno
安防摄像头视频 VL 模型微调数据集标注工具。用于从安防摄像头视频中提取关键帧、分析视频内容、生成结构化标注(含环境/人物/行为/风险描述),并输出符合 dataset.jsonl 格式的微调训练数据。Use when 用户需要对安防摄像头视频进行数据标注、生成 VL 模型训练数据集、处理 /root/hair-cam 目录下的视频数据,或提及 "hair-cam"、"数据标注"、"视频标注"、"VL模型微调"。