Borrowing it
Nothing to install: this file belongs to ZimoLiao/scholaraio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ZimoLiao/scholaraio/main/.claude/skills/webextract/SKILL.mdgit clone --depth 1 https://github.com/ZimoLiao/scholaraioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zimoliao/scholaraio/webextract)<a href="https://agentmods.dev/skills/zimoliao/scholaraio/webextract"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/webextract/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zimoliao/scholaraio/webextract"><img src="https://agentmods.dev/badge/skills/zimoliao/scholaraio/webextract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00911 |
| Opus 5 | $0.00023 | $0.00456 |
| Sonnet 5 | $0.00009 | $0.00182 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
webextract scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
WebExtract - 网页内容提取
当前 Agent 原生能力优先,但必须先做能力检查:按页面读取能力和输出契约路由,不按 Agent 品牌路由。若当前会话实际提供网页搜索和页面读取能力,就由当前使用的 Agent 原生能力完成普通检索、来源核验和阅读。只有该能力无法读取需要 JavaScript/PDF 渲染的页面,或任务明确需要可入库、可复现的渲染后 Markdown 时,才调用本 skill。
通过 qt-web-extractor 提取网页内容并转换为 Markdown。优先使用 MCP 方式连接
本机或远端 extractor;HTTP /extract 方式保留为兼容 fallback。
服务地址
默认 HTTP 服务运行在 http://127.0.0.1:8766。推荐 MCP endpoint 为
http://127.0.0.1:8766/mcp。
推荐通过 config.yaml 配置 MCP:
webextract:
transport: mcp
mcp_url: http://127.0.0.1:8766/mcp
api_key: your_key
mcp_tool: fetch_url
HTTP 兼容配置:
webextract:
transport: http
base_url: http://127.0.0.1:8766
api_key: your_key
功能特性
- 提取完全渲染的网页内容(支持 JavaScript 和 SPA)
- 自动转换为干净的 Markdown 格式
- 支持 PDF 文本提取
- 支持 JSON 格式输出
使用方法
基本用法
scholaraio webextract <URL>
PDF 提取模式
scholaraio webextract <PDF_URL> --pdf
全文与预览模式
# 默认只显示预览,避免长页面直接刷满终端
scholaraio webextract <URL>
# 查看全文
scholaraio webextract <URL> --full
# 自定义预览长度
scholaraio webextract <URL> --max-chars 1200
环境变量
WEBEXTRACT_URL- 自定义服务地址(默认: http://127.0.0.1:8766)WEBEXTRACT_API_KEY- API 认证密钥(如服务配置了认证)WEBEXTRACT_TRANSPORT-mcp或httpWEBEXTRACT_MCP_URL/QT_WEB_EXTRACTOR_MCP_URL- MCP endpointQT_WEB_EXTRACTOR_API_KEY- qt-web-extractor API 认证密钥别名
与 Agent 协作
当 agent 需要提取网页内容进行分析时:
- 普通网页发现、来源核验和阅读优先使用当前 Agent 原生网页能力
- 只有原生读取失败,或需要生成可入库的渲染后 Markdown 时,才确认
webextract.transport: mcp或远端 MCP endpoint 已配置 - 使用
scholaraio webextract <URL>提取网页内容 - 将提取的 Markdown 交给
ingest-link工作流或用于需要完整渲染正文的分析
注意事项
- MCP 模式下,确保 qt-web-extractor 的
/mcpendpoint 可访问;这样可以使用远端fetch_url,不需要每台机器都安装 Qt WebEngine 环境 - HTTP fallback 下,确保 qt-web-extractor 服务已在本地或远端 8766 端口运行
- 如果服务返回错误且没有正文,CLI 会直接报错退出,而不是显示“提取成功”
- 对于需要登录或特殊认证的页面,可能需要额外配置
- 大量提取时建议分批进行,避免过载
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 96 lines · 46 tokens per session scan A eed1ba4f6881
webextract is a skill published in the GitHub repository ZimoLiao/scholaraio (570 stars, last pushed 10d ago), licensed MIT. It adds 46 tokens to every session and 911 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
infrastructure-validation
Skill for the validation infrastructure module providing PDF validation, markdown validation, output integrity checks, link verification, documentation audits, issue categorization, and repository scanning. Use when validating research outputs, checking document quality, running audits, or verifying cross-references.
infrastructure-steganography
Skill for the steganography infrastructure module providing QR code generation with dynamic mailto links, hash manifests, metadata payloads, and document-wide overlay processing. Use this module to insert opt-in cryptographic and steganographic provenance data onto PDFs.
template-pitch-deck
Pitch-deck generation exemplar — short/medium/long PDF+PPTX decks from one token-resolved, diligence-cited content source.
template-validation-quality
Run validation CLI, prerender, markdown/PDF/integrity gates, and QA workflows for the Research Project Template. USE WHEN validate manuscript, check PDF for ?? refs, prerender gate, link checker, output integrity, or pre-commit validation — even without validationquality prompt.
template-storybook
Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.
template-textbook
Modular fillable textbook scaffold — parts/chapters/labs/question banks from config.yaml, auto-numbering, deterministic figures, structural contract enforcement.