← 返回 Skills 市场
rishabhdugar

Generate Image

作者 Rishabh Dugar · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
76
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install generate-image-from-html
功能描述
Generate a PNG image from HTML content or a public URL using headless Chromium. Supports custom dimensions, retina quality, full-page screenshots, cookie con...
使用说明 (SKILL.md)

Generate Image

What It Does

Renders a webpage or HTML content to a PNG image using headless Chromium. Supports URL screenshots and HTML-to-image rendering with full customization.

When to Use

  • Take a screenshot of a live webpage
  • Render HTML/CSS to a PNG image (social cards, banners, certificates)
  • Generate full-page scrollable screenshots
  • Create retina-quality images with custom dimensions

Required Inputs

You must provide one of:

  • html_content — raw HTML string to render
  • url — a public URL to screenshot

Authentication

Send your API key in the CLIENT-API-KEY header.

Get your free API key at https://pdfapihub.com. Full API documentation is available at https://pdfapihub.com/docs.

Use Cases

  • Social Media Cards — Generate OG images, Twitter cards, or Instagram story images from HTML templates
  • Email Banners — Create personalized email header images with dynamic content
  • Website Screenshots — Capture full-page or viewport screenshots of live websites for monitoring or previews
  • Certificate Images — Render certificates as PNG images for sharing on social media
  • Product Mockups — Generate product images with dynamic text overlays
  • Thumbnail Generation — Create consistent thumbnail images for blog posts or video previews
  • QR Code Cards — Render HTML with embedded QR codes as shareable images

Key Options

Parameter Description
output_format url (default), base64, both, image/png/binary/file
width / height Output image dimensions in pixels
deviceScaleFactor 1 (default), 2 for retina quality
full_page true for full scrollable screenshot (URL mode)
wait_until load, domcontentloaded, networkidle, commit
cookie_accept_text Auto-click cookie consent before screenshot
font Google Font names, pipe-separated
dynamic_params Key-value object for {{placeholder}} replacement

Rate Limits

Tier Requests/min
Free/Basic/Pro 10
Enterprise 30
Business 100

Example Usage

curl -X POST https://pdfapihub.com/api/v1/generateImage \
  -H "CLIENT-API-KEY: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "html_content": "\x3Cdiv style=\"padding:40px;background:#4F46E5;color:white;\">\x3Ch1>Hello {{name}}\x3C/h1>\x3C/div>",
    "dynamic_params": { "name": "World" },
    "width": 800,
    "height": 400,
    "output_format": "url"
  }'

Notes

  • Files are automatically deleted after 30 days
  • Maximum output file size depends on your plan tier
安全使用建议
This skill is a coherent wrapper around a third-party API (pdfapihub.com) and appears to do what it says: POST your HTML or a public URL to that service to receive an image. Before installing or using it, consider: (1) Any HTML, URLs, or dynamic data you send will be transmitted to and processed by pdfapihub.com — do not include passwords, private tokens, or other sensitive data. (2) Obtain and treat the CLIENT-API-KEY like any API secret; check where the agent will store it and revoke it if compromised. (3) Confirm the service’s privacy/retention policy (SKILL.md says files are deleted after 30 days) and any cost or rate-limit implications. (4) If you require full control over sensitive rendering, consider a self-hosted rendering solution (headless Chromium) instead of a third-party API. Otherwise, this skill’s scope and requirements are proportionate and expected.
功能分析
Type: OpenClaw Skill Name: generate-image-from-html Version: 1.0.0 The skill is a standard API wrapper for the pdfapihub.com service, designed to generate PNG images from HTML content or URLs. The implementation in skill.json and SKILL.md is consistent with its stated purpose and lacks any indicators of malicious intent, data exfiltration, or prompt injection.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
The name/description match an HTTP-based HTML->PNG screenshot service. The skill declares the API endpoint and an API-key header (CLIENT-API-KEY) which is appropriate for this purpose. No unrelated binaries, config paths, or credentials are requested.
Instruction Scope
SKILL.md instructs the agent to POST HTML or a URL to https://pdfapihub.com/api/v1/generateImage with the CLIENT-API-KEY header — this is consistent with the stated purpose. Note: user-supplied HTML, URLs, and dynamic parameters will be transmitted to a third party; the instructions do not attempt to read local files or other system state.
Install Mechanism
There is no install spec and no code files to execute locally (instruction-only). This minimizes local install risk.
Credentials
The skill does not request host environment variables, filesystem paths, or unrelated secrets. Authentication is handled via an API key header for the external service, which is proportional to the task.
Persistence & Privilege
always is false and the skill does not request persistent/privileged system modifications. It is an agent-invocable skill that makes outbound API requests — normal for this category.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install generate-image-from-html
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /generate-image-from-html 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
- Initial release: generate PNG images from HTML content or public URLs using headless Chromium. - Supports custom image dimensions, retina-quality rendering, and full-page screenshots. - Offers dynamic parameter replacement for HTML templates. - Handles cookie consent clicks before capturing screenshots. - Multiple output formats available: URL, base64, and direct image file. - API key authentication now required.
元数据
Slug generate-image-from-html
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Generate Image 是什么?

Generate a PNG image from HTML content or a public URL using headless Chromium. Supports custom dimensions, retina quality, full-page screenshots, cookie con... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 76 次。

如何安装 Generate Image?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install generate-image-from-html」即可一键安装,无需额外配置。

Generate Image 是免费的吗?

是的,Generate Image 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Generate Image 支持哪些平台?

Generate Image 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Generate Image?

由 Rishabh Dugar(@rishabhdugar)开发并维护,当前版本 v1.0.0。

💬 留言讨论