R

read

by @tw93v
4.4(27)

将任意URL或本地PDF转换为清晰Markdown格式,支持飞书文档、代理链和自动降级,快速提取结构化内容

data-extractionmarkdownweb-scrapingpdf-processinginformation-retrievalGitHub
安装方式
npx skills add tw93/waza --skill read
compare_arrows

Before / After 效果对比

1
使用前

手动复制网页内容到编辑器,清理HTML标签和广告,调整格式混乱的标题和列表,处理PDF需要OCR或在线转换工具,一篇文档需要20分钟

使用后

输入URL或PDF路径自动输出干净Markdown,智能识别标题层级和代码块,保留原文结构的同时去除冗余元素,30秒完成转换

SKILL.md

read

Read: Fetch Any URL or PDF as Markdown

Convert any URL or local PDF to clean Markdown and save it.

Routing

Input Method

feishu.cn, larksuite.com Feishu API script

.pdf URL or local PDF path PDF extraction

Everything else Run scripts/fetch.sh {url} (proxy cascade with auto-fallback)

After routing, load references/read-methods.md to get the specific commands for the chosen method, then execute.

Output Format

Title:  {title}
Author: {author} (if available)
Source: {platform}
URL:    {original url}

Summary
{3-5 sentence summary}

Content
{full Markdown, truncated at 200 lines if long}

Saving

Save to ~/Downloads/{title}.md with YAML frontmatter by default. Skip only if user says "just preview" or "don't save". Tell the user the saved path.

After saving and reporting the path, stop. Do not analyze, comment on, or discuss the content unless asked. If content was truncated at 200 lines, say so and offer to continue.

Notes

  • r.jina.ai and defuddle.md require no API key

  • Network failures: prepend local proxy env vars if available

  • Long content: | head -n 200 to preview first

  • GitHub URLs: prefer gh CLI over fetching directly

Weekly Installs522Repositorytw93/wazaGitHub Stars1.6KFirst Seen4 days agoSecurity AuditsGen Agent Trust HubWarnSocketPassSnykWarnInstalled onclaude-code483codex418opencode413gemini-cli413warp412amp412

用户评价 (0)

发表评价

效果
易用性
文档
兼容性

暂无评价

统计数据

安装量5.1K
评分4.4 / 5.0
版本
更新日期2026年5月22日
对比案例1 组

用户评分

4.4(27)
5
15%
4
52%
3
30%
2
4%
1
0%

为此 Skill 评分

0.0

兼容平台

🔧Claude Code

时间线

创建2026年4月9日
最后更新2026年5月22日