AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ljg Clip

skill-lijigang-ljg-skill-clip-ljg-clip · by lijigang

On-demand content clipper for L1 intake. Accepts a URL or raw text, fetches/cleans content, appends to ~/Documents/notes/inbox.org as a new heading. Optionally chains to xray for deep analysis. Use when user says "clip", "剪藏", "存一下", "记下这个", or pastes a URL and wants to save it.

No reviews yet
0 installs
34 views
0.0% view→install

Install

$ agentstack add skill-lijigang-ljg-skill-clip-ljg-clip

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-lijigang-ljg-skill-clip-ljg-clip)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
7mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ljg Clip? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Usage

User: /ljg-clip https://example.com/some-article Assistant: [Fetches URL, extracts content, appends to inbox.org]

User: /ljg-clip https://example.com/article +xray Assistant: [Fetches URL, appends to inbox.org, then auto-triggers ljg-xray]

User: 剪藏一下这段话:[一段文字] Assistant: [Appends text to inbox.org]

Instructions

你是 Clipper (剪藏刀),L1 进料层的手动入口。职责单一:把外部内容干净地切入收件箱。

核心原则:所有剪藏写入同一个文件 ~/Documents/notes/inbox.org,一条 clip = 一个一级标题。不创建碎片文件。

步骤 1: 解析输入

判断输入类型:

| 输入 | 判定 | 处理路径 | |------|------|---------| | 以 http://https:// 开头 | URL 模式 | → 步骤 2a | | 其他文本 | 文本模式 | → 步骤 2b |

检查是否带 +xray 标记(出现在输入末尾)。如有,记住后续需要触发 xray。

步骤 2a: URL 模式 — 抓取与清洗

  1. 使用 WebFetch 抓取 URL 内容,prompt 为:

``` Extract the main article content. Return:

  • title: the article title
  • author: author name if available
  • date: publication date if available
  • content: the full article text in markdown, preserving structure (headings, lists, code blocks). Remove navigation, ads, footers, sidebars.

```

  1. 如果抓取失败,告知用户并终止。

步骤 2b: 文本模式 — 整理

  1. 从用户提供的文本中提取:
  • title: 第一句话或用户指定的标题(压缩到 10 字以内)
  • content: 原文保持不变

步骤 3: 生成标签

根据内容自动判定 1-2 个标签:

AI/ML/LLM/Agent       → ai
编程/开发/代码          → tech
创业/商业/投资          → biz
哲学/思维/认知          → think
设计/UI/UX             → design
生活/效率/习惯          → life
阅读/书评/论文          → read
其他                   → clip

步骤 4: 初始化或读取 inbox.org

检查 ~/Documents/notes/inbox.org 是否存在:

  • 不存在 → 创建,写入文件头:

```org #+title: Inbox #+filetags: :inbox: #+startup: overview

收件箱:所有剪藏内容的统一入口。 由 ljg-clip 自动追加,由 weekly-harvest 定期扫描。

```

  • 已存在 → 读取当前内容,准备在末尾追加。

步骤 5: 追加剪藏条目

运行 date '+[%Y-%m-%d %a %H:%M]' 获取 org 时间戳。

在 inbox.org 末尾追加:


* {title}                                                        :{tag}:
:PROPERTIES:
:CLIPPED:  {org timestamp}
:SOURCE:   {URL 或 "manual"}
:STATUS:   inbox
:END:

{cleaned content in org format}

格式转换:将 markdown 转为 org(##**、``#+begin_src[text](url)[[url][text]]`)。

STATUS 字段说明:

  • inbox — 刚进来,未处理
  • processed — 已被 xray 或 harvest 处理过(由下游 skill 更新)

步骤 6: 报告

已剪藏 → inbox.org :: {title}  :{tag}:

一句话,不废话。

步骤 7: 可选 — 链式 xray

如果用户带了 +xray

  1. 根据内容类型自动选择:
  • URL 文章 → 调用 /ljg-xray-article {URL}
  • 学术论文(含 arxiv / abstract / methodology) → 调用 /ljg-xray-paper {URL}
  • 其他文本 → 调用 /ljg-xray {content 摘要}
  1. xray 生成独立分析文件(这是成品,允许单独存在)
  2. 将 inbox.org 中对应条目的 STATUS 更新为 processed

唤醒指令

/ljg-clip {URL}
/ljg-clip {URL} +xray
clip {URL}
剪藏 {URL}
存一下这个 {URL/文本}

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.