← 返回 Skills 市场
139
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install markdown-new-crawl
功能描述
Use `https://markdown.new/crawl/{target_url}` endpoints to recursively crawl a site section and return markdowns. Trigger this skill when the user asks for m...
安全使用建议
This skill appears to be a straightforward wrapper for a public crawl API and does not request credentials or install anything. Before installing: verify you trust the endpoint (markdown.new) and its owner; do not point the crawler at private/internal sites or URLs containing secrets (the service will fetch and store crawled content for 14 days by default); be aware of rate limits/costs documented in the SKILL.md; and be cautious about the ambiguous "fallback" behavior — confirm what fallback browsing methods the agent is allowed to use in your environment. If you need to crawl authenticated or sensitive sites, expect to need additional, explicit auth steps which are not described here.
功能分析
Type: OpenClaw Skill
Name: markdown-new-crawl
Version: 1.0.0
The skill bundle provides instructions for an AI agent to perform web crawling and Markdown conversion using the `markdown.new` API. It utilizes standard `curl` commands to interact with documented endpoints for job creation, status polling, and data retrieval. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the behavior is entirely consistent with the stated purpose of multi-page extraction.
能力评估
Purpose & Capability
Name/description match the instructions: all required actions (POST /crawl, poll status, GET per-URL) are appropriate for a site-crawling-to-markdown service and no unrelated credentials, binaries, or paths are requested.
Instruction Scope
SKILL.md stays within crawling behavior (construct requests, set limits, poll status). One minor vagueness: it says to "fall back to another method" if /crawl fails but doesn't define acceptable fallbacks — this could allow broader browsing methods unless the agent is constrained.
Install Mechanism
Instruction-only skill with no install spec or code files; nothing is written to disk and no external packages are fetched by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The SKILL.md explicitly assumes no authentication is needed (note below about potential risk if private sites are targeted).
Persistence & Privilege
always:false and normal autonomous invocation are set. The skill does not request elevated or persistent system presence and does not modify other skills or agent-wide config.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install markdown-new-crawl - 安装完成后，直接呼叫该 Skill 的名称或使用
/markdown-new-crawl触发 - 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 of markdown.new-crawl with local-first multi-page site crawling.
- Adds support for asynchronous website crawling and Markdown extraction via `markdown.new/crawl` API endpoints.
- Introduces local terminal access with `curl` for initiating, polling, and managing crawl jobs.
- Supports options for crawl scope (limits, depth, patterns, external links, subdomains).
- Uses Markdown as the default output, with per-page JSON as an option.
- Describes operational limits and fallback methods if the `/crawl` endpoint is inaccessible.
- Provides sample commands and explains default behaviors (same-domain, up to 500 pages, jobs retained 14 days).
元数据
常见问题
markdown.new/crawl 是什么？
Use `https://markdown.new/crawl/{target_url}` endpoints to recursively crawl a site section and return markdowns. Trigger this skill when the user asks for m... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 139 次。
如何安装 markdown.new/crawl？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install markdown-new-crawl」即可一键安装，无需额外配置。
markdown.new/crawl 是免费的吗？
是的，markdown.new/crawl 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
markdown.new/crawl 支持哪些平台？
markdown.new/crawl 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 markdown.new/crawl？
由 ctxinf（@ctxinf）开发并维护，当前版本 v1.0.0。
推荐 Skills