← Back to Skills Marketplace
93
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install anylink-to-note
Description
将任意链接一键转化为结构化笔记。支持的链接类型:微信公众号文章、Get 笔记共享链接、RSS 播客订阅、任意公开网页。当用户分享或发送链接并希望"保存"、"解析"、"总结"、"收藏"时触发。输出包含标题、正文内容、摘要和标签。
README (SKILL.md)
AnyLink to Note
任意链接 → 结构化笔记,一键完成。
支持的链接类型
| 链接类型 | 示例 | 提取方式 |
|---|---|---|
| 微信公众号 | mp.weixin.qq.com/... |
Jina Reader |
| Get 笔记 | d.biji.com/... |
Playwright 渲染 |
| RSS / 播客 | xiaoyuzhoufm.com/... |
HTTP + XML 解析 |
| 公开网页 | 任意 URL | Jina Reader |
工作流程
1. 检测链接类型
const host = new URL(url).host.replace(/^www\./, '');
// Get 笔记: /d\.biji\.com|biji\.com/.test(host)
// 微信公众号: /mp\.weixin\.qq|weixin\.qq/.test(host)
// RSS: url.includes('/feed') || url.includes('.xml')
2. 提取正文
微信公众号 / 普通网页:
const res = await fetch(`https://r.jina.ai/${encodeURIComponent(url)}`, {
headers: { Accept: 'application/json' }
});
const data = await res.json();
// → data.title, data.content
Get 笔记:
node skills/anylink-to-note/scripts/getnote.js \x3Curl>
RSS 播客:
curl -sL "\x3Crss-url>" | python3 -c "import sys,xmltodict; d=xmltodict.parse(sys.stdin.read()); print(d['rss']['channel']['item'][0]['description'])"
3. 生成摘要 & 标签
用 LLM 根据正文内容生成:
- 摘要:1-2 句话,概括核心内容或关键见解
- 标签:3-5 个,以
#开头,涵盖主题、人物、领域等维度
4. 返回结构化结果
{
"title": "文章标题",
"content": "完整正文...",
"summary": "1-2句摘要",
"tags": ["#主题", "#领域", "#人物"],
"sourceName": "WeChat" | "Get笔记" | "RSS" | "Web",
"url": "\x3C原始链接>"
}
注意事项
- Playwright 环境:Get 笔记提取依赖 Chromium,需确保已安装
npx playwright install chromium。 - Jina Reader 限制:部分网站(需登录、JS 渲染站)可能失败,此时可降级到 Playwright 方案。
Usage Guidance
This skill appears to do what it says: fetch page content (via r.jina.ai or Playwright), then summarize with an LLM. Before installing/using, consider: (1) privacy — content and URLs will be sent to external service r.jina.ai for extraction (avoid private/authenticated links); (2) execution risk — the Playwright path renders arbitrary pages locally (ensure you run this in a trusted/sandboxed environment and have Playwright/Chromium installed from official sources); (3) dependencies — you may need Node, the playwright package, and python xmltodict for the RSS path; (4) no credentials are requested by the skill. If you need to process private content, do not use the Jina Reader path or ensure an approved extraction method that keeps data local.
Capability Analysis
Type: OpenClaw Skill
Name: anylink-to-note
Version: 1.0.1
The skill contains a significant shell injection vulnerability in the RSS extraction logic described in SKILL.md and references/url-types.md. The instructions direct the agent to execute a shell command (`curl -sL "<rss-url>" | python3 ...`) using a user-provided URL without sanitization, which could lead to arbitrary command execution. While the intent appears to be legitimate web scraping and note-taking, the implementation of the RSS and Playwright-based extraction methods poses a security risk.
Capability Assessment
Purpose & Capability
Name/description match the implementation: Jina Reader for generic pages/WeChat, Playwright for Get 笔记, and HTTP/XML parsing for RSS. The included getnote.js is exactly for the Get 笔记 case.
Instruction Scope
SKILL.md instructs the agent to fetch content from r.jina.ai, curl RSS feeds, and to run a Playwright script against arbitrary user-supplied URLs. These are expected for the stated goal, but they involve sending page URLs/content to a third party (r.jina.ai) and executing/rendering arbitrary pages locally (Playwright), which has privacy and dynamic-content execution implications.
Install Mechanism
No install spec (instruction-only) — lowest risk. However Playwright/Chromium are required for the included script; the skill notes 'npx playwright install chromium' but does not declare Node/playwright as dependencies. There are no downloads from untrusted/obscure URLs in the skill files.
Credentials
The skill requests no environment variables, credentials, or config paths. This is proportionate to the described functionality.
Persistence & Privilege
always is false and the skill does not request elevated or persistent platform privileges or try to modify other skills' configs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install anylink-to-note - After installation, invoke the skill by name or use
/anylink-to-note - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Remove misleading URL conversion warning
v1.0.0
Initial release: parse WeChat, Get笔记, RSS, and any public webpage into structured notes
Metadata
Frequently Asked Questions
What is AnyLink to Note?
将任意链接一键转化为结构化笔记。支持的链接类型:微信公众号文章、Get 笔记共享链接、RSS 播客订阅、任意公开网页。当用户分享或发送链接并希望"保存"、"解析"、"总结"、"收藏"时触发。输出包含标题、正文内容、摘要和标签。 It is an AI Agent Skill for Claude Code / OpenClaw, with 93 downloads so far.
How do I install AnyLink to Note?
Run "/install anylink-to-note" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is AnyLink to Note free?
Yes, AnyLink to Note is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does AnyLink to Note support?
AnyLink to Note is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created AnyLink to Note?
It is built and maintained by FanX (@fanxlab); the current version is v1.0.1.
More Skills