article-writer
Skill969 starsChanged 6 months agoMITView on GitHub
Multi-style article creation skill. Supports 5 writing styles (deep analysis, practical guide, story-driven, opinion, news brief), including complete workflow: material collection → outline → content → formatting. Activated when users mention "write article", "write post", "create", or "draft".
8 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- FuDesign2008/open-skillstheir own version, first seen Nov 6, 2026
- awaik/direct-mcp-ai-projecttheir own version, first seen Nov 1, 2026
- LDJ-creat/media-skillstheir own version, first seen Oct 9, 2026
- EvovexAI/EvoFlowedited, first seen Oct 8, 2026
- netease-youdao/LobsterAIword for word, first seen Oct 8, 2026
- ckt520728/claude-skillstheir own version, first seen Jul 1, 2026
Other versions8 projects use a version of this.
Word for word · 1
- netease-youdao/LobsterAI★ 6.2k100% same
Edited · 1
- EvovexAI/EvoFlow★ 61297% same
Wrote their own version · 6
- LDJ-creat/media-skills★ 28same name
- awaik/direct-mcp-ai-project★ 17same name
- FuDesign2008/open-skills★ 6same name
- huangzw9527-stack/openclaw-skills-zh★ 4same name
- ckt520728/claude-skills★ 0same name
- wingeek/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.
In this repository28 other files it gives its agents.
- AGENTS.mdAGENTS.md
- canvas-designSkill
- content-plannerSkill
- create-planSkill
- daily-trendingSkill
- develop-web-gameSkill
- docxSkill
- films-searchSkill
- frontend-designSkill
- imap-smtp-emailSkill
- local-toolsSkill
- music-searchSkill
- pdfSkill
- playwrightSkill
- pptxSkill
- remotion-best-practicesSkill
- seedanceSkill
- seedreamSkill
- skill-creatorSkill
- skill-vetterSkill
- stock-analyzerSkill
- stock-announcementsSkill
- stock-explorerSkill
- technology-searchSkill
- weatherSkill
- web-searchSkill
- xlsxSkill
- youdaonoteSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 44
If user hasn't specified, recommend based on topic:
- Distinctive: line 58
Use content-planner's search script to collect reference materials:
- Distinctive: line 138
After approval, write content paragraph by paragraph following the outline.
- Very specific: line 161
If specific data is needed but uncertain, mark [数据待确认] and confirm with user
- Distinctive: line 162
Use search tools to verify key facts
- Distinctive: line 175
No first-line indentation, use blank lines to separate paragraphs
- Distinctive: line 178
Use quotes for data, golden sentences, or important viewpoints
- Distinctive: line 216
Use these psychological strategies:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Multi-Style Article Creation
Use Cases
- User says "写一篇关于XX的文章"
- User says "帮我写一篇公众号文章"
- User selects a topic from the content calendar to start writing
- User specifies a writing style (e.g., "深度分析风格", "写个教程")
5 Writing Styles
| Style ID | Name | Characteristics | Word Count | Use Cases |
deep-analysis | 深度分析 | Rigorous structure, data-backed | 2000-4000 words | Trend analysis, in-depth reporting |
practical-guide | 实用指南 | Clear steps, highly actionable | 1500-3000 words | Tool tutorials, how-to guides |
story-driven | 故事驱动 | Conversational, emotional resonance | 1500-2500 words | Personal stories, case reviews |
opinion | 观点评论 | Sharp opening, pros/cons argumentation | 1000-2000 words | Hot takes, controversial topics |
news-brief | 新闻简报 | Inverted pyramid, fact-focused | 500-1000 words | Breaking news, information roundups |
Workflow
Step 1: Read the Brief
Obtain topic information from:
- Entries with status
plannedincontent_calendar.json - Topic description directly provided by the user
Extract key information:
- Topic direction / title
- Target audience
- Writing style (if not specified, recommend based on topic content)
- Reference material URLs
Step 2: Determine Writing Style
If user hasn't specified, recommend based on topic:
| Topic Characteristics | Recommended Style |
| Involves data, trends, underlying causes | deep-analysis |
| "How to", "tutorial", "steps" | practical-guide |
| Involves people, experiences, insights | story-driven |
| Involves controversy, hot topic commentary | opinion |
| Breaking events, quick information | news-brief |
Confirm the style choice with the user.
Step 3: Material Collection
Use content-planner's search script to collect reference materials:
node "$SKILLS_ROOT/content-planner/scripts/wechat_search.js" "topic keywords" -n 10Also use web-search skill for additional materials.
Organize material list:
- Citable data/statistics
- Reference cases/stories
- Facts that need verification
Step 4: Generate Outline
Generate an outline based on the selected style using the corresponding structure template.
deep-analysis Template
## 引入 (200-300字) — 反直觉数据/现象开头
## 背景 (300-500字) — 事件/现象的来龙去脉
## 分析维度1 (400-600字) — 核心论点 + 数据支撑
## 分析维度2 (400-600字) — 对比/反面论证
## 分析维度3 (400-600字) — 深层原因 + 影响预测
## 总结与展望 (200-300字) — 核心观点 + CTApractical-guide Template
## 开头 (100-200字) — 痛点共鸣 + 承诺
## 前置准备 (200-300字)
## 步骤1 (300-500字) — 具体操作 + 常见坑
## 步骤2 (300-500字) — 具体操作 + 关键参数
## 步骤3 (300-500字) — 具体操作 + 验证方法
## 进阶技巧 (200-300字)
## 总结 (100-200字) — FAQ + CTAstory-driven Template
## 开头 (150-200字) — 场景切入 + 悬念
## 背景铺垫 (200-300字) — 人物/背景/冲突
## 转折1 (300-400字) — 关键事件 + 感受
## 转折2 (300-400字) — 新尝试 + 结果
## 高潮 (200-300字) — 核心洞察
## 结尾 (150-200字) — 启发 + CTAopinion Template
## 锐利开头 (100-150字) — 直接亮观点
## 现象描述 (200-300字) — 主流观点
## 正面论证 (300-400字) — 我的论点 + 数据
## 反面回应 (200-300字) — 预设反驳 + 反驳
## 深度思考 (200-300字) — 本质 + 影响
## 总结 (100-150字) — 重申观点 + CTAnews-brief Template
## 核心信息 (100-200字) — What/When/Where/Who
## 事件详情 (200-300字)
## 背景 (100-200字)
## 反应 (100-200字)
## 编者按 (50-100字)Step 5: User Approval of Outline
This is a mandatory approval gate and cannot be skipped.
Present the outline to the user and ask for confirmation or modification requests.
Step 6: Write the Content
After approval, write content paragraph by paragraph following the outline.
Universal Writing Rules:
- Use stories instead of preaching
- ❌ "风险管理很重要,应该做应急预案"
- ✅ "去年,我的创业团队差点因为一个核心员工离职而崩溃,因为我们没有任何备选方案。"
- Use analogies and metaphors
- ❌ "分布式系统很复杂"
- ✅ "分布式系统就像连锁餐厅——每个分店需要协作,同时又要独立运营。"
- Support with data but don't pile it on
- ❌ "据IDC报告,全球AI市场2023年增长45%,预计2025年达1000亿美元..."
- ✅ "AI市场疯狂增长——每年翻一番。但在增长背后,真正赚钱的公司不到5家。"
- State opinions directly, avoid ambiguity
- ❌ "有人认为...也有人认为...各有道理"
- ✅ "说实话,我认为XX的做法是错的,因为..."
- Use short sentences and line breaks
Data integrity rules:
- If specific data is needed but uncertain, mark
[数据待确认]and confirm with user - Use search tools to verify key facts
- Can tell fictional stories using "我见过..." or "一个朋友...", but don't fabricate data
Step 7: Formatting Optimization
WeChat Formatting Hard Rules:
- Paragraphs no more than 4 lines (mobile screen visible range)
- Insert a subheading or bold sentence every 3-4 paragraphs
- Must have a hook within the first 3 lines (question, data, story, counter-intuitive viewpoint)
- Must have a clear CTA at the end (follow/share/comment prompt)
Markdown Formatting Standards:
- No first-line indentation, use blank lines to separate paragraphs
- Maximum 2 heading levels (
##), no deep nesting - Bold only the 1-2 most important words per paragraph
- Use quotes for data, golden sentences, or important viewpoints
- Lists maximum 5 items
Step 8: Output Draft
Save the article as Markdown:
Filename format: drafts/YYYYMMDD_[topic-slug].md
---
title: Article Title
date: YYYY-MM-DD
style: deep-analysis
summary: Article summary (within 100 words)
---
## Opening
Content...Step 9: Quality Checklist
✅ Title — Sparks curiosity or resonance
✅ Opening — First 100 words are engaging
✅ Body — Has 2-3 clear viewpoints
✅ Cases — Uses stories not preaching
✅ Formatting — Easy to read (short paragraphs, bold, subheadings)
✅ Word Count — Within style-specified range
✅ CTA — Ending has action promptTitle Optimization Process
Step 1: Generate 10 Candidate Titles
Use these psychological strategies:
| Strategy | Description | Example |
| Suspense | Spark curiosity | "为什么我放弃了年薪50万的工作" |
| Benefit | Clarify reader gains | "掌握这3个技巧,效率提升200%" |
| Pain Point | Hit reader anxiety | "别让这个习惯毁了你的职业生涯" |
| Numbers | Specific and tangible | "50%的人都误解了这个真相" |
| Rhetorical | Stimulate thinking | "你真的了解AI吗?" |
| Contrast | Create contrast | "BAT vs 创业公司:差别在哪" |
Step 2: Score and Filter
Score on 3 dimensions (Attractiveness 40%, Shareability 30%, SEO 30%) and present top 3 to user.
Integration with Other Skills
- Upstream: content-planner's
content_calendar.jsonprovides topic input - Downstream: Markdown files in drafts/ can be further processed
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.

