Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HK-hub/AgentSkills --skill juejin-article-to-markdowngit clone --depth 1 https://github.com/HK-hub/AgentSkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hk-hub/agentskills/juejin-article-to-markdown)<a href="https://agentmods.dev/skills/hk-hub/agentskills/juejin-article-to-markdown"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/juejin-article-to-markdown/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hk-hub/agentskills/juejin-article-to-markdown"><img src="https://agentmods.dev/badge/skills/hk-hub/agentskills/juejin-article-to-markdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.04008 |
| Opus 5 | $0.00037 | $0.02004 |
| Sonnet 5 | $0.00015 | $0.00802 |
| Haiku 4.5 | $0.00007 | $0.00401 |
Grade A, and why
juejin-article-to-markdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
掘金文章转 Markdown
概述
掘金文章页面包含大量无关内容（导航栏、侧边栏、评论区、推荐文章、代码块按钮等），直接复制粘贴会产生格式问题。此 Skill 提供一套完整的处理流程，将掘金文章转换为干净、规范的 Markdown 文件。
触发条件
- 用户提供掘金文章链接（
juejin.cn/post/） - 用户说"保存掘金文章"、"另存掘金为 Markdown"
- 用户想要整理掘金文章到笔记库
完整处理流程
第一步：获取文章内容
同时获取 HTML 和 Markdown 两种格式（并行请求）：
# 请求 1：HTML 格式（用于提取元信息和图片位置）
mcp__ScraplingServer__stealthy_fetch
- url: 掘金文章链接
- extraction_type: html
- main_content_only: true
- wait: 2000
# 请求 2：Markdown 格式（用于提取正文内容）
mcp__ScraplingServer__stealthy_fetch
- url: 掘金文章链接
- extraction_type: markdown
- main_content_only: true
- wait: 2000
第二步：提取文章元信息
从 HTML 或 Markdown 开头提取：
| 字段 | 提取方式 | 说明 |
|---|---|---|
| 标题 | <h1> 或 # 标题 |
文章主标题 |
| 作者 | 作者名称字段 | 作者用户名 |
| 发布日期 | 日期字段 | 格式：YYYY-MM-DD |
| 阅读量 | 阅读数字段 | 可选 |
| 标签 | 标签列表 | 文章标签 |
| 专栏 | 专栏名称 | 可选 |
第三步：清理无关内容
必须移除的内容：
-
导航栏和页眉
- 首页、沸点、课程、数据标注、AI Coding 等导航
- 搜索框
- 创作者中心
- 登录/注册按钮
-
侧边栏和推荐
- 搜索建议
- 精选内容
- 为你推荐文章列表
- 目录（可选择性保留简化版）
-
评论区
- 评论列表
- 评论输入框
- 点赞、屏蔽、举报按钮
-
页脚和推广
- 下载APP提示
- 微信公众号二维码
- 新浪微博链接
- AI代码助手推广
-
代码块无关内容
- "体验AI代码助手"按钮文字
- "代码解读"按钮文字
- "复制代码"按钮文字
-
互动元素
- 点赞、收藏、分享按钮
- 关注按钮
- 专栏订阅按钮
第四步：处理代码块
掘金代码块会包含无关的按钮文字，需要清理：
清理模式：
# 原始（有问题）
```bash
体验AI代码助手
代码解读
复制代码
# 实际代码
git clone https://github.com/xxx
清理后
# 实际代码
git clone https://github.com/xxx
**处理规则：**
1. 识别代码块开始（```language）
2. 删除代码块开头的空白行
3. 删除"体验AI代码助手"、"代码解读"、"复制代码"等无关行
4. 保留实际代码内容
5. 确保代码块正确闭合
### 第五步：处理图片
**掘金图片特点：**
| 域名 | 处理方式 | 说明 |
|------|---------|------|
| `p*-xtjj-sign.byteimg.com` | **保留** | 文章正文图片 |
| `p*-juejin-sign.byteimg.com` | **保留** | 文章正文图片 |
| `p1-juejin.byteimg.com` | **保留** | 封面图等 |
| `lf-web-assets.juejin.cn` | **丢弃** | Logo、图标等装饰 |
| `p*-passport.byteacctimg.com` | **丢弃** | 用户头像 |
**图片链接格式：**
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 506 lines · 74 tokens per session scan A 1eb67e781beb
juejin-article-to-markdown is a skill published in the GitHub repository HK-hub/AgentSkills (6 stars, last pushed 25d ago), licensed MIT. It adds 74 tokens to every session and 4,008 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
bootstrap
Bootstrap a greenfield project with parent-owned interviews and bounded plan, revision, and apply actions.
deep-research
Autonomous deep research on codebases and technical topics with structured report output via map-reduce explorer architecture.
mermaid
Create, validate, and repair Mermaid.js diagrams. Use when generating flowcharts, sequence, class, ER, state, or Gantt diagrams, or any visualization.
teach-me
Turn a 'teach me X' request into a single interactive HTML lesson, rendered Arcade-first, by emitting a lesson data model and assembling it with rp1 tooling.
blueprint
Guided parent-owned project charter and PRD interviews with durable artifact-only resume.
build-fast
Quick-iteration development for small/medium scope changes with persistent artifacts and optional review.