write-article
Skill17 starsChanged 7 months agoMITView on GitHub
把零散的笔记、想法、要点整理成一篇结构完整、逻辑清晰的中文文章。支持指定风格和目标读者。
5 other projects use a version of this.
Adopted by
Most recently taken up by
- simonwong/skillstheir own version, first seen Nov 8, 2026
- greglas75/zuvotheir own version, first seen Oct 16, 2026
- atretyak1985/swarmerytheir own version, first seen Oct 13, 2026
- UXMagicai/seosorted-skillstheir own version, first seen Oct 4, 2026
- vishalsachdev/claude-skillstheir own version, first seen Aug 12, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- simonwong/skills★ 9same name
- atretyak1985/swarmery★ 7same name
- greglas75/zuvo★ 7same name
- vishalsachdev/claude-skills★ 2same name
- UXMagicai/seosorted-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
Files
整理文章
将用户提供的零散内容整理成一篇结构完整的中文文章。
第零步:加载配置(必做)
开始任何素材处理前,用 Read 工具依次加载以下配置文件(路径相对项目根目录),把其中所有规则作为硬性约束:
.claude/skills/write-article/persona.md:作者人设.claude/skills/write-article/style.md:语言、段落、标题、数字、地域范围.claude/skills/write-article/structure.md:章节编号、案例、数据、理论联系现实、结论要求.claude/skills/write-article/writing-rules.md:写作规则(append-only 禁区清单).claude/skills/write-article/output-format.md:参考文献与原始草稿附录格式
配图相关(.claude/skills/write-article/references/images.md)只在用户主动询问配图时加载。
第一步:收集素材
- 若
$ARGUMENTS包含文件路径,读取所有指定文件 - 若直接描述主题和要点,从
$ARGUMENTS提取 - 两者可结合
- 提取所有关键观点、数据、案例、引用;识别核心主题
第二步:分析与规划
- 确定核心论点(一句话概括)
- 按逻辑关系分组归类素材
- 设计大纲:标题、引言、3-5 个核心主节、结尾
- 大纲遵循
structure.md的章节编号规范
第三步:事实核查
- 用 WebSearch 逐一核查时间、数据、人名、事件细节
- 必要时用 WebFetch 抓取权威来源(官方网站、Wikipedia、NASA 等)
- 记录所有引用的来源 URL
- 原始草稿里的数据可能有误,主动核查并修正,不要照抄
- 近 6-12 个月内的事件/政策/数据必须独立 WebSearch 验证:即使草稿给出了看似具体的说法("X 月批准""N 万片""某日禁止"),也要重新搜索确认。原始笔记里"narrative-convenient"(正好契合论点)的事实尤其要警惕。时事话题的事实会在草稿到发文的窗口里改变
- 参考文献抽查:写完文章后抽查 1-2 条关键参考链接,确认目标页面真的说了正文所说的话。URL 可用不代表内容对得上
第四步:撰写
按大纲扩写,同时遵守第零步加载的 persona / style / structure 三份规则。
去除重复,合并相似观点,补充必要过渡句。
第五步:自检
对照 writing-rules.md 逐条自检(现 16 条),特别注意:
- 用 Grep 搜索
——,确认正文(不含原始草稿附录)为零 - 油腻话术关键词搜索
- 段落长度扫描(2-4 句)
- 数字可读性通读
- 地域范围与主题一致
- 案例有名有姓有数据
- 科普文章:每个理论概念后有实验或现实连接
- AI 味扫描:Grep 否定平行句式
不是.*\(而是\|,是\)(目标 0 次,严格例外最多 1 次)+ AI 中英文高频词清单(至关重要/意义重大/标志着/见证/根植于/delve/tapestry 等)+ 模糊归属("通常被认为""研究表明" 等) - 结尾单独过一遍:对最后 3 段额外扫 "从.*到.*到" 三项递进、"序章/新篇章/新阶段"、"让我们/共同期待/拥抱"、"那个画面/那一刻/历史将记住"、"最重要的/最具里程碑"
每发现一条违规,立即修正。
第六步:输出
按 output-format.md 的规范:
- 写入 Markdown 文件(项目根目录)
- 末尾附参考文献(超链接格式)
- 末尾附原始草稿(引用格式,原样保留)
- 向用户返回:文件路径、主节标题清单、大致字数、参考文献条数
规则追加
用户反馈"别再 X"时,向 .claude/skills/write-article/writing-rules.md 追加一条新条目(append-only,不修改历史条目),不要动 SKILL.md 或其他配置文件。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

