Token导航 LogoToken导航

Agent Skill · 效率

opengraph-io-skill(opengraph io 技能)

opengraph-io-skill 用于处理浏览器自动化、网页检查和页面信息提取,适合在 OpenClaw 中需要让 Agent 打开页面、读取网页或验证前端流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

opengraph-io-skill 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在效率类的 21,003 个 Skill 里排第 653。

总安装 73,712周安装 3,134GitHub Stars 6下载 25,824核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.4.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:opengraph-io-skill(opengraph io 技能)
来源仓库:https://github.com/primeobsession/opengraph-io-skill
安装命令:
openclaw skills install opengraph-io-skill
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install opengraph-io-skill

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

通过 OpenGraph.io 提取 Web 数据、捕获屏幕截图、抓取内容并生成 AI 图像。在处理 URL(展开、预览、元数据)、捕获网页屏幕截图、抓取 HTML 内容、询问有关网页的问题或生成图像(图表、图标、社交卡、QR 代码)时使用。

触发器:“获取 OG 标签”、“截取此页面的屏幕截图”、“抓取此 URL”、“生成图表”、“创建社交卡”、“此页面讲述了什么内容”。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install opengraph-io-skill;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

opengraph-io-skill 怎么安装?

在终端执行 openclaw skills install opengraph-io-skill。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

opengraph-io-skill 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

opengraph-io-skill 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

opengraph-io-skill 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

opengraph-io-skill 用的人多吗?

公开数据是累计安装 73,712 次,近一周安装 3,134 次,下载 25,824 次,GitHub 6 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

opengraph-io-skill 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
opengraph-io-skill

opengraph io 技能 · 本页

73,7126接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
opengraph-io
version
1.4.0
description
Extract web data, capture screenshots, scrape content, and generate AI images via OpenGraph.io. Use when working with URLs (unfurling, previews, metadata), capturing webpage screenshots, scraping HTML content, asking questions about webpages, or generating images (diagrams, icons, social cards, QR codes). Triggers: 'get the OG tags', 'screenshot this page', 'scrape this URL', 'generate a diagram', 'create a social card', 'what does this page say about'.
homepage
https://www.opengraph.io
metadata
{"clawdbot":{"emoji":"🔗","requires":{"bins":["curl"],"env":["OPENGRAPH_APP_ID"]},"primaryEnv":"OPENGRAPH_APP_ID","install":[{"id":"mcp","kind":"npm","package":"opengraph-io-mcp","global":true,"bins":["opengraph-io-mcp"],"label":"Install MCP server (optional, for other AI clients)"}]}}

OpenGraph.io

OpenGraph.io - Extract, Screenshot, Scrape, Query, Generate

Extract web data, capture screenshots, and generate AI-powered images via OpenGraph.io APIs.

🤖 AI Agents: For complete parameter docs and patterns, also read references/for-ai-agents.md.

Quick Decision Guide

"I need data from a URL"

NeedEndpoint
Meta tags / link preview dataGET /site/{url}
Raw HTML contentGET /scrape/{url} (add use_proxy=true if geo-blocked)
Specific elements (h1, h2, p)GET /extract/{url}?html_elements=h1,h2,p
AI answer about the pagePOST /query/{url} ⚠️ paid
Visual screenshotGET /screenshot/{url}

"I need to generate an image"

NeedSettings
Technical diagramkind: "diagram" — use diagramCode + diagramFormat for control
App icon/logokind: "icon" — set transparent: true
Social card (OG/Twitter)kind: "social-card" — use aspectRatio: "og-image"
Basic QR codekind: "qr-code"
Premium QR marketing cardkind: "illustration" — describe full design in prompt
General illustrationkind: "illustration"

QR Code: Basic vs Premium

Basic (kind: "qr-code"): Just the functional QR code.

Premium (kind: "illustration"): Full marketing asset with QR embedded in designed composition (gradients, 3D elements, CTAs, device mockups). Example prompt:

"Premium marketing card with QR code for https://myapp.com, cosmic purple gradient 
with floating 3D spheres, glowing accents, 'SCAN TO DOWNLOAD' call-to-action"

Diagram Tips

  • Use diagramCode + diagramFormat for reliable syntax (bypasses AI generation)
  • Use outputStyle: "standard" for structure-critical diagrams (premium may alter layout)
  • ❌ Don't mix syntax with description: "graph LR A-->B make it pretty" will fail

Pricing & Requirements

FeatureFree TierPaid Plans
Site/Unfurl✅ 100/monthUnlimited
Screenshot✅ 100/monthUnlimited
Scrape✅ 100/monthUnlimited
Extract✅ 100/monthUnlimited
Query (AI)❌✅
Image Generation✅ 4/monthUnlimited
💡 Try image generation free! Get 4 premium image generations per month on the free plan — no credit card required.

Sign up at dashboard.opengraph.io

Quick Setup

  1. Sign up at dashboard.opengraph.io — free trial available
  2. Configure (choose one):

Option A: Clawdbot config (recommended)

// ~/.clawdbot/clawdbot.json
{
  skills: {
    entries: {
      "opengraph-io": {
        apiKey: "YOUR_APP_ID"
      }
    }
  }
}

Option B: Environment variable

export OPENGRAPH_APP_ID="YOUR_APP_ID"

Clawdbot Usage (REST API)

Use curl with the OPENGRAPH_APP_ID environment variable. Base URL: https://opengraph.io/api/1.1/

Extract OpenGraph Data (Site/Unfurl)

# Get OG tags from a URL
curl -s "https://opengraph.io/api/1.1/site/$(echo -n 'https://example.com' | jq -sRr @uri)?app_id=${OPENGRAPH_APP_ID}"

Response includes hybridGraph.title, hybridGraph.description, hybridGraph.image, etc.

Screenshot a Webpage

# Capture screenshot (dimensions: sm, md, lg, xl)
curl -s "https://opengraph.io/api/1.1/screenshot/$(echo -n 'https://example.com' | jq -sRr @uri)?app_id=${OPENGRAPH_APP_ID}&dimensions=lg"

Response: { "screenshotUrl": "https://..." }

Scrape HTML Content

# Fetch rendered HTML (with optional proxy)
curl -s "https://opengraph.io/api/1.1/scrape/$(echo -n 'https://example.com' | jq -sRr @uri)?app_id=${OPENGRAPH_APP_ID}&use_proxy=true"

Extract Specific Elements

# Pull h1, h2, p tags
curl -s "https://opengraph.io/api/1.1/extract/$(echo -n 'https://example.com' | jq -sRr @uri)?app_id=${OPENGRAPH_APP_ID}&html_elements=h1,h2,p"

Query (Ask AI About a Page)

curl -s -X POST "https://opengraph.io/api/1.1/query/$(echo -n 'https://example.com' | jq -sRr @uri)?app_id=${OPENGRAPH_APP_ID}" \
  -H "Content-Type: application/json" \
  -d '{"query": "What services does this company offer?"}'

Image Generation (REST API)

Base URL: https://opengraph.io/image-agent/

Step 1: Create a Session

SESSION=$(curl -s -X POST "https://opengraph.io/image-agent/sessions?app_id=${OPENGRAPH_APP_ID}" \
  -H "Content-Type: application/json" \
  -d '{"name": "my-session"}')
SESSION_ID=$(echo $SESSION | jq -r '.sessionId')

Step 2: Generate an Image

curl -s -X POST "https://opengraph.io/image-agent/sessions/${SESSION_ID}/generate?app_id=${OPENGRAPH_APP_ID}" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A beautiful QR code linking to https://example.com with modern gradient design",
    "kind": "qr-code",
    "aspectRatio": "square",
    "quality": "high"
  }'

Image kinds: illustration, diagram, icon, social-card, qr-code

Style presets: github-dark, vercel, stripe, neon-cyber, pastel, minimal-mono

Aspect ratios: square, og-image (1200×630), twitter-card, instagram-story, etc.

Step 3: Download the Asset

ASSET_ID="<from-generate-response>"
curl -s "https://opengraph.io/image-agent/assets/${ASSET_ID}/file?app_id=${OPENGRAPH_APP_ID}" -o output.png

Step 4: Iterate (Refine an Image)

curl -s -X POST "https://opengraph.io/image-agent/sessions/${SESSION_ID}/iterate?app_id=${OPENGRAPH_APP_ID}" \
  -H "Content-Type: application/json" \
  -d '{
    "assetId": "<previous-asset-id>",
    "prompt": "Change the background to blue"
  }'

Natural Language Examples

When users ask in natural language, translate to the appropriate API call:

User saysAPI to use
"Get the OG tags from URL"GET /site/{url}
"Screenshot this page"GET /screenshot/{url}
"Scrape the HTML from URL"GET /scrape/{url}
"What does this page say about X?"POST /query/{url}
"Generate a QR code for URL"POST /image-agent/sessions/{id}/generate with kind: "qr-code"
"Create a premium QR marketing card"POST /image-agent/sessions/{id}/generate with kind: "illustration" + design in prompt
"Create a social card for my blog"POST /image-agent/sessions/{id}/generate with kind: "social-card"
"Make an architecture diagram"POST /image-agent/sessions/{id}/generate with kind: "diagram"

QR Code Options

Basic QR Code (kind: "qr-code"): Generates just the functional QR code with minimal styling.

Premium QR Marketing Card (kind: "illustration"): Generates a complete marketing asset with the QR code embedded in a professionally designed composition - gradients, 3D elements, CTAs, device mockups, etc.

# Premium QR marketing card example
curl -s -X POST "https://opengraph.io/image-agent/sessions/${SESSION_ID}/generate?app_id=${OPENGRAPH_APP_ID}" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Premium marketing card with QR code for https://myapp.com, cosmic purple gradient background with floating 3D spheres, glowing accents, SCAN TO DOWNLOAD call-to-action",
    "kind": "illustration",
    "aspectRatio": "square",
    "outputStyle": "premium",
    "brandColors": ["#6B4CE6", "#9B6DFF"],
    "stylePreferences": "modern, cosmic, premium marketing, 3D elements"
  }'

MCP Integration (for Claude Desktop, Cursor, etc.)

For AI clients that support MCP, use the MCP server:

# Interactive installer
npx opengraph-io-mcp --client cursor --app-id YOUR_APP_ID

# Or configure manually:
{
  "mcpServers": {
    "opengraph": {
      "command": "npx",
      "args": ["-y", "opengraph-io-mcp"],
      "env": {
        "OPENGRAPH_APP_ID": "YOUR_APP_ID"
      }
    }
  }
}

See references/mcp-clients.md for client-specific setup.

More Details

平台分布

OpenClaw

85.46%
按下载量换算22,069

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills