Agent skill

Article Rewriter

by digoal in digoal/blog

给定一篇文章的 URL 或全文内容,深度阅读消化后,以更高屋建瓴的视角创作一篇全新文章: 提取核心观点+基石假设,找逻辑漏洞或用第一性原理重构假设,续写新内容,最终输出图文并茂的 Markdown 文章。

GPL-2.0Auto-check passed

Install Article Rewriter

skills CLI
$ npx skills add digoal/blog --skill article-rewriter -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog article-rewriter --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/article-rewriter .claude/skills/article-rewriter && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
article-rewriter
GitHub stars
8.6k
Token cost
~675 tokens
SKILL.md length
145 words
Files
1
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

给定一篇文章的 URL 或全文内容,深度阅读消化后,以更高屋建瓴的视角创作一篇全新文章: 提取核心观点+基石假设,找逻辑漏洞或用第一性原理重构假设,续写新内容,最终输出图文并茂的 Markdown 文章。

  • Works in 7 steps: :获取并阅读文章 → :提炼核心观点与基石假设 → :寻找逻辑漏洞 / 重构基石假设 → …
  • SKILL.md covers 定位, 执行流程, 质量自检清单 and 输出示例结构
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Article Rewriter is an agent skill from digoal/blog. 给定一篇文章的 URL 或全文内容,深度阅读消化后,以更高屋建瓴的视角创作一篇全新文章: 提取核心观点+基石假设,找逻辑漏洞或用第一性原理重构假设,续写新内容,最终输出图文并茂的 Markdown 文章。 触发条件:用户提供文章链接或粘贴文章内容,并说"帮我改写"、"写一篇更高层次的文章"、"找逻辑漏洞"、 "重构观点"、"消化后重写"、"升华这篇文章"、"基于这篇文章写一篇新的",或用户说"这篇文章有什么问题/ 漏洞/不足"并希望输出新文章时,必须使用本 skill。即使用户只说"帮我把这篇文章写得更好"或"这篇文章太 浅了,帮我深化一下",也应使用本 skill。

Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

Example prompts

  • “写一篇更高层次的文章”
  • “升华这篇文章”
  • “基于这篇文章写一篇新的”
  • “/article-rewriter”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. :获取并阅读文章
  2. :提炼核心观点与基石假设
  3. :寻找逻辑漏洞 / 重构基石假设
  4. :构建新文章骨架
  5. :搜索支撑数据(必须执行)
  6. :写作规范
  7. :输出文件

What it can do on your machine

Read from SKILL.md and the folder at commit 69fb793. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash, yaml and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Article Rewriter loads about 675 tokens when it runs. Until then it costs about 76 tokens; SKILL.md has 145 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~675

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit 69fb793, republished under its GPL-2.0 licence (© digoal). 145 words, ~675 tokens.

Download SKILL.mdSave it as .claude/skills/article-rewriter/SKILL.md (or your agent's skills folder).
name
article-rewriter
description
给定一篇文章的 URL 或全文内容,深度阅读消化后,以更高屋建瓴的视角创作一篇全新文章: 提取核心观点+基石假设,找逻辑漏洞或用第一性原理重构假设,续写新内容,最终输出图文并茂的 Markdown 文章。 触发条件:用户提供文章链接或粘贴文章内容,并说"帮我改写"、"写一篇更高层次的文章"、"找逻辑漏洞"、 "重构观点"、"消化后重写"、"升华这篇文章"、"基于这篇文章写一篇新的",或用户说"这篇文章有什么问题/ 漏洞/不足"并希望输出新文章时,必须使用本 skill。即使用户只说"帮我把这篇文章写得更好"或"这篇文章太 浅了,帮我深化一下",也应使用本 skill。

Article Rewriter Skill

定位

给定一篇文章(URL 或全文),深度消化后创作一篇全新的、更高屋建瓴的文章。 输出文章必须:

  • 零 AI 痕迹:不出现"总的来说"、"值得注意的是"、"不难看出"等 AI 惯用套话
  • 零原文痕迹:不出现"原文提到"、"作者认为"、"文章指出"等引用式表述
  • 全新创作:观点、结构、语言完全重建,不是改写而是重新立论

执行流程

Step 1:获取并阅读文章
  • 若用户给的是 URL,使用 web_fetch 抓取全文
  • 若用户粘贴了全文,直接使用
  • 完整通读,不跳过任何段落
Step 2:提炼核心观点与基石假设

对每个核心观点,整理成如下结构(内部思考,不输出给用户):

观点:[一句话陈述]
基石假设:[该观点成立所依赖的前提条件]
支撑证据:[数据 / 案例 / 逻辑链]
脆弱点:[假设在何种条件下会崩塌]

提炼 3-5 个核心观点,找出最有"破局"价值的 1-2 个。

Step 3:寻找逻辑漏洞 / 重构基石假设

两条路径,择优选择(或融合):

路径 A:找漏洞

  • 检查归纳谬误(以偏概全)
  • 检查因果倒置(把相关当因果)
  • 检查隐含假设(作者未明说但依赖的前提)
  • 检查时效性(旧数据 / 旧环境下的结论放到今天是否仍成立)

路径 B:第一性原理重构

  • 把基石假设剥离,问:如果这个假设不成立,甚至反过来成立,结论会怎样变?
  • 从物理/数学/经济/人性等底层出发,重建假设
  • 得出与原文不同(甚至相反)的新结论
Step 4:构建新文章骨架

新文章结构(可灵活调整):

  1. 引子:用一个反直觉的现象 / 数据 / 故事开场,制造认知张力
  2. 旧叙事的边界:简明指出流行认知的适用边界(不是推翻,是"它在哪里对,在哪里错")
  3. 新基石假设:清晰陈述新的出发点
  4. 新论证:逻辑链 + 权威数据 + 真实案例,支撑新观点
  5. 逻辑三洽检验:
    • 自洽:内部逻辑不矛盾
    • 他洽:与已知事实 / 权威研究不冲突
    • 续洽:若无法用时间验证,用推导式描述 + 给出未来可观测的佐证信号(如:若新假设成立,我们应该在 X 领域看到 Y 现象)
  6. 收尾:不做鸡汤式总结,而是抛出一个开放性问题或行动导向
Step 5:搜索支撑数据(必须执行)

在写作前,使用 web_search 搜索:

  • 新观点所需的权威数据(机构报告、学术研究、政府统计)
  • 反例 / 正例的真实案例
  • 最新行业动态(确保数据不过时)

每个核心论点至少有 1 个可引用的外部来源。

Step 6:写作规范

语言风格:

  • 第一人称或无主语,不用"我们"泛指
  • 句子长短交替,避免连续长句
  • 动词优先,少用"是……的"结构
  • 专业术语后紧跟通俗解释(括号内)

禁用词清单(坚决不出现): 总的来说、值得注意的是、不难看出、显而易见、毋庸置疑、令人深思、与此同时、不仅如此、综上所述、可以看出、正如、诚然、然而不可否认、深度解读、深度分析、赋能、颠覆、破局、底层逻辑(单独使用时)、顶层设计、内卷、躺平(作为结论词)

图表要求:

  • 逻辑关系 / 流程 → Mermaid 图
  • 数据对比 / 趋势 → SVG 简图(用文字标注数据,不依赖外部渲染)
  • 概念层级 → Mermaid mindmap 或 flowchart
  • 每篇文章至少包含 2 个图表
Step 7:输出文件
bash
mkdir -p markdown

文件命名:markdown/[主题关键词]-重构-[YYYYMMDD].md

文件头部 YAML frontmatter:

yaml
---
title: [新文章标题]
date: [今日日期]
tags: [主题标签]
---

质量自检清单

写完后逐项检查:

  • 文章中是否出现了"原文"、"作者"、"文章指出"等词?→ 全部删除
  • 是否出现禁用词?→ 替换
  • 每个核心论点是否有数据或案例支撑?→ 补充
  • 逻辑三洽是否完备?→ 续洽部分是否给出了可观测信号?
  • 是否有至少 2 个图表?→ 补充
  • 标题是否有吸引力(制造好奇 / 反直觉 / 明确收益)?→ 优化

输出示例结构

markdown
---
title: XXX
date: YYYY-MM-DD
---

[引子:反直觉现象或数据]

[旧叙事的边界]

```mermaid
flowchart LR
    ...

[新基石假设]

[新论证 + 数据]

[SVG 数据图]

[续洽:未来可观测信号]

[收尾:开放性问题]


---

## 注意事项

1. **不要一开始就问用户太多问题**。拿到文章直接开始执行,遇到真正的歧义再问(最多 1 个问题)。
2. **新文章长度**:通常 1500-3000 字,视原文深度而定。不强求字数,以论点完整为准。
3. **原文语言 ≠ 输出语言**:默认与用户对话语言一致(通常中文);若用户明确指定,按指定语言输出。
4. 完成后用 `present_files` 提交文件。

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/skills_for_claude_web/article-rewriter of digoal/blog.

Open the folder on GitHubat commit 69fb793

Compare with similar skills

Article Rewriter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Article Rewriter compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Article Rewriter this skilldigoal/blog8.6k—~675Automated safety check: PassGPL-2.0
Articlethedaviddias/Front-End-Checklist74k—~421Automated safety check: PassMIT
Article Magazinenexu-io/open-design100k—~495Automated safety check: PassApache-2.0
Rewrite Plannexu-io/open-design100k—~511Automated safety check: PassApache-2.0
Article Linksthedaviddias/Front-End-Checklist74k—~425Automated safety check: PassMIT
Article Writingaffaan-m/ECC275k3 repos~295Automated safety check: PassMIT

Similar skills

  • Article

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Implement valid Article structured data.

    74k GitHub stars~421 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Article Magazine

    nexu-io/open-design

    Huashu / huashu-md-html-inspired magazine article layout for turning Markdown or notes into a polished long-form HTML essay.

    100k GitHub stars~495 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Rewrite Plan

    nexu-io/open-design

    Author a long-running multi-file rewrite plan that subsequent patch-edit + diff-review + build-test stages will execute, with explicit ownership boundaries and patch-safety guarantees.

    100k GitHub stars~511 tokensUpdated today
    Frontend & DesignAuto-check passed
  • Article Links

    thedaviddias/Front-End-Checklist

    A skill your agent uses when auditing metadata, crawlability, structured data, or indexability related to Optimize article link density.

    74k GitHub stars~425 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Article Writing

    affaan-m/ECC

    根据提供的示例或品牌指导,以独特的语气撰写文章、指南、博客帖子、教程、新闻简报等长篇内容。当用户需要超过一段的精致书面内容时使用,尤其是当语气一致性、结构和可信度至关重要时。

    275k GitHub starsUsed in 3 repos~295 tokens
    Writing & ContentAuto-check passed
  • Article Writing

    affaan-m/ECC

    記事、ガイド、ブログ投稿、チュートリアル、ニュースレター号、その他の長文コンテンツを、提供された例またはブランドガイダンスから派生した独特の声で作成します。ユーザーが段落より長いポーランド済みの書き込みコンテンツを望む場合、特に声の一貫性、構造、および信頼性が重要な場合に使用します。

    275k GitHub stars~385 tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated 10 days ago
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated 10 days ago
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated 10 days ago
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated 10 days ago
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated 10 days ago
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated 10 days ago
    Auto-check passed

Questions about Article Rewriter

What does Article Rewriter do?

给定一篇文章的 URL 或全文内容,深度阅读消化后,以更高屋建瓴的视角创作一篇全新文章: 提取核心观点+基石假设,找逻辑漏洞或用第一性原理重构假设,续写新内容,最终输出图文并茂的 Markdown 文章。. Article Rewriter is an agent skill from digoal/blog.

How do I install Article Rewriter in Claude Code?

Run `npx skills add digoal/blog --skill article-rewriter -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/article-rewriter in digoal/blog) into .claude/skills/article-rewriter in your project. Claude Code loads it when a task matches its description.

How do I install Article Rewriter in Codex?

Run `npx skills add digoal/blog --skill article-rewriter -a codex`. Or copy the skill folder (skills/skills_for_claude_web/article-rewriter in digoal/blog) into .agents/skills/article-rewriter in your project. Codex loads it when a task matches its description.

Can I use Article Rewriter in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill article-rewriter -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/article-rewriter, .gemini/skills/article-rewriter, .github/skills/article-rewriter and .opencode/skills/article-rewriter in your project.

What does Article Rewriter need to run?

SKILL.md names no scripts, command-line tools or credentials: Article Rewriter is instructions for the agent only.

Does Article Rewriter access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Article Rewriter safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Article Rewriter use?

Article Rewriter is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Article Rewriter use?

About 675 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Article Rewriter?

Skills that share tags, products or a category with Article Rewriter: Article (thedaviddias/Front-End-Checklist, 74k stars), Article Magazine (nexu-io/open-design, 100k stars), Rewrite Plan (nexu-io/open-design, 100k stars) and Article Links (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Article Rewriter?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,587 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on September 28, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.