菜单
Crawl from one or more starting web pages, fetch readable content, search within pages, follow relevant links, and stop when the requested information is found or a bounded limit is reached.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/leon-ai/leon --skill tiny-web-crawler命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | tiny-web-crawler |
| description | Crawl from one or more starting web pages, fetch readable content, search within pages, follow relevant links, and stop when the requested information is found or a bounded limit is reached. |
| metadata | {"author":"Louis Grenard <louis@getleon.ai>","version":"1.0.0"} |
Use this skill to inspect web pages by fetching content, searching within it, and following relevant links from the starting page.
Use the bundled scripts for the actual web fetching and bounded crawling:
scripts/fetch-page.mjs: fetch one page, extract compact readable text, links, and query snippets.scripts/crawl-web.mjs: crawl from one or more start URLs, follow relevant links, and stop at limits or strong matches.Run scripts with node. Leon's shell tool injects runtime shims, so node
uses Leon's managed Node.js binary when available and falls back to PATH only
when the managed binary is missing.
Example:
node scripts/crawl-web.mjs --url "https://example.com" --query "target phrase" --max-pages 8 --max-depth 2
Do not build $LEON_HOME/bin/node/... or /bin/node/... paths manually.
scripts/crawl-web.mjs to fetch pages, search within content, and follow relevant links.scripts/fetch-page.mjs for one-off page inspection or deeper inspection of a promising page.Default limits unless the owner specifies otherwise:
Prefer stopping early over crawling broadly.
fetch-page.mjs returns compact output by default:
textPreview: short readable previewsnippets: query matches with nearby contextlinks: normalized URLs with short labels and contextchunk.hasMore and chunk.nextOffset: use these to fetch more text only when neededFor deeper inspection, use --include-text --offset <number> --max-text-chars <number>.
Prioritize links whose text, URL, title, surrounding text, or page structure mentions:
Avoid links that are likely unrelated, duplicated, navigational noise, ads, tracking links, login-only pages, or broad category pages unless they are the best available path.
Answer directly first.
Then include concise source notes:
If the target was not found, state that clearly and summarize the most relevant places checked.