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/dinglebear-ai/axon --skill scrape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。
Use Axon for RAG, web search, source indexing, extraction, memory, and grounded answers over indexed docs, repos, feeds, or web content.
Route web search, source indexing, extraction, RAG, jobs, and watch tasks through the local Axon CLI.
Use when extracting structured company lists from public or authorized directories into JSON, CSV, CRM-ready lists, or research tables.
基于 SOC 职业分类
正在显示 SKILL.md
| name | scrape |
| description | Use Axon scrape to turn one or more known URLs into markdown, HTML, JSON, or saved artifacts. |
Use axon scrape when the user gives a URL and wants that page's content.
scrape is the retained one-page projection of the unified source pipeline —
same adapter, ledger, embedding, and publication path as axon <url> --scope page.
Reach for it rather than a bare axon <url>: the web family's default scope is
site, so an unscoped URL indexes the whole domain.
mkdir -p .axon
axon scrape "https://example.com" --output .axon/example.md
axon scrape "https://example.com/pricing" --format json --output .axon/pricing.json
axon scrape "https://app.example.com" --render-mode chrome --output .axon/app.md
Multiple URLs:
axon scrape "https://example.com" "https://example.com/docs" --output-dir .axon/pages
.axon/ for anything larger than a short answer.extract when the desired output is structured fields rather than markdown.axon <url> --scope site when you need many linked pages — scrape is the one-page projection of the same source pipeline.