SuperAPI AI Directory

research-writer

Writing & research

View repository

Updated 11-06 16:22

About this skill

Research Content Writing Assistant

This skill can serve as your writing partner, helping you complete source research, draft outlines, write first drafts, and polish and refine, while maintaining your unique writing style and tone.

Use Cases

  • Writing blog posts, columns, or newsletters
  • Creating instructional content or tutorials
  • Drafting in-depth opinion articles
  • Researching and writing case studies
  • Writing technical documentation that requires citations
  • Standardizing citation and reference formatting
  • Optimizing article openings and introductions
  • Getting section-by-section feedback while writing

Features

  1. Collaborative outline drafting: Help you organize your ideas into a clear, well-structured outline
  2. Source research assistance: Search for relevant information and add citations
  3. Opening optimization: Strengthen article openings to capture readers' attention
  4. Section-by-section feedback: Review section by section as you write
  5. Style preservation: Maintain your writing style and tone
  6. Citation management: Standardize the addition and formatting of references
  7. Iterative polishing: Help you continuously improve through multiple rounds of revision

How to Use

Set Up Your Writing Environment

Create a dedicated folder for your article, then work within that folder. For example:

mkdir my-article-title
cd my-article-title

Create a draft file:

touch article-draft.md

Open Claude Code from this directory to start writing.

Basic Workflow

  1. Start with an outline:
帮我为一篇关于 [主题] 的文章创建大纲
  1. Research and add citations:
调研 [具体主题] 并在大纲中补充引用
  1. Optimize the opening:
这是我的引言,请帮我让开头更有吸引力。
  1. Get section-by-section feedback:
我刚写完"为什么这很重要"这一节,请审阅并给出反馈。
  1. Polish and refine:
审阅完整草稿,检查行文流畅度、清晰度和一致性。

Usage Guide

When a user requests writing help:

  1. Understand the writing project

    Ask the following questions to clarify requirements:

    • What is the topic and core argument?
    • Who is the target audience?
    • What is the desired length and format?
    • What is the purpose of the writing? (inform, persuade, share, explain)
    • Is there existing material or source material?
    • What writing style is preferred? (formal, conversational, technical)
  2. Collaborative outline drafting

    Help organize the content structure:

    # 文章大纲:[标题]
    
    ## 开头
    - [引言故事/开场白/数据]
    - [读者为什么要关注]
    
    ## 引言
    - 背景和上下文
    - 问题陈述
    - 本文涵盖内容
    
    ## 正文部分
    
    ### 第一节:[标题]
    - 要点 A
    - 要点 B
    - 举例/论据
    - [待调研:具体主题]
    
    ### 第二节:[标题]
    - 要点 C
    - 要点 D
    - 数据/引用待补充
    
    ### 第三节:[标题]
    - 要点 E
    - 反面观点
    - 回应与总结
    
    ## 结论
    - 要点回顾
    - 行动号召
    - 收尾思考
    
    ## 调研待办
    - [ ] 查找 [主题] 相关数据
    - [ ] 搜集 [概念] 的实例
    - [ ] 为 [论断] 查找引用来源
    

    Iteratively refine the outline:

    • Adjust based on feedback
    • Ensure logical coherence
    • Identify gaps in source material
    • Mark sections that need further development
  3. Conduct source research

    When a user requests research on a topic:

    • Search for relevant information
    • Find reliable sources
    • Extract key facts, quotes, and data
    • Add citations in the requested format

    Example output:

    ## 调研:AI 对生产力的影响
    
    主要发现:
    
    1. **生产力提升**:研究显示内容创作任务可节省 40% 的时间 [1]
    
    2. **采用率**:67% 的知识工作者每周使用 AI 工具 [2]
    
    3. **专家观点**:"AI 是增强而非替代人类创造力"
       —— Jane Smith 博士,MIT [3]
    
    参考文献:
    [1] McKinsey Global Institute. (2024). "The Economic Potential 
        of Generative AI"
    [2] Stack Overflow Developer Survey (2024)
    [3] Smith, J. (2024). MIT Technology Review interview
    
    已添加到大纲第二节。
    
  4. Optimize the opening

    When a user shares an introduction, analyze and strengthen it:

    Opening analysis:

    • Strengths: [positive elements]
    • Could be better: [directions for improvement]
    • Emotional impact: [current state vs. potential]

    Optimization options:

    Option 1: [bold statement]

    [Example] Why it works: [explanation]

    Option 2: [personal story]

    [Example] Why it works: [explanation]

    Option 3: [surprising data]

    [Example] Why it works: [explanation]

    Self-check questions:

    • Does it spark curiosity?
    • Does it convey a value promise?
    • Is it specific enough?
    • Does it match the target reader?
  5. Provide section-by-section feedback

    After the user finishes writing each section, review it from the following aspects:

    # 反馈:[章节名称]
    
    ## 亮点 ✓
    - [优点 1]
    - [优点 2]
    - [优点 3]
    
    ## 改进建议
    
    ### 清晰度
    - [具体问题] → [修改建议]
    - [复杂句子] → [更简洁的表达]
    
    ### 连贯性
    - [过渡问题] → [更好的衔接]
    - [段落顺序] → [调整建议]
    
    ### 论据
    - [需要支撑的论断] → [补充引用或示例]
    - [笼统的表述] → [更具体的说法]
    
    ### 风格
    - [语气不一致] → [更贴合你风格的表达]
    - [用词选择] → [更有力的替代词]
    
    ## 具体修改建议
    
    原文:
    > [草稿原文]
    
    建议改为:
    > [改进版本]
    
    原因:[说明]
    
    ## 值得思考的问题
    - [启发性问题 1]
    - [启发性问题 2]
    
    可以开始下一节了!
    
  6. Preserve the author's style

    Important principles:

    • Learn the other person's style: read their existing writing samples
    • Suggest rather than replace: offer options instead of imposing instructions
    • Match the tone: formal, casual, technical, friendly
    • Respect their choices: if they prefer their own version, support it
    • Enhance rather than change: make the article better, not turn it into a different style

    Ask regularly:

    • "Does this sound like your style?"
    • "Is this tone appropriate?"
    • "Would you like it a bit more formal / more conversational / more technical?"
  7. Citation management

    Handle references according to the user's preference:

    In-text citations:

    研究显示生产力提升了 40%(McKinsey, 2024)。
    

    Numbered citations:

    研究显示生产力提升了 40% [1]。
    
    [1] McKinsey Global Institute. (2024)...
    

    Footnote-style citations:

    研究显示生产力提升了 40%^1
    
    ^1: McKinsey Global Institute. (2024)...
    

    Maintain a continuously updated citation list:

    ## 参考文献
    
    1. 作者. (年份). "标题". 出版物.
    2. 作者. (年份). "标题". 出版物.
    ...
    
  8. Final draft review and polishing

    Once the draft is complete, provide comprehensive feedback:

    # 全文审阅
    
    ## 总体评价
    
    **优势**:
    - [主要优点 1]
    - [主要优点 2]
    - [主要优点 3]
    
    **整体效果**:[总体评估]
    
    ## 结构与连贯性
    - [结构组织评价]
    - [过渡衔接质量]
    - [节奏把控评价]
    
    ## 内容质量
    - [论证力度]
    - [论据充分性]
    - [举例效果]
    
    ## 技术质量
    - 语法与行文:[评价]
    - 一致性:[评价]
    - 引用完整性:[检查结果]
    
    ## 可读性
    - 清晰度:[评价]
    - 句式多样性:[评价]
    - 段落长度:[评价]
    
    ## 最终润色建议
    
    1. **引言**:[具体改进建议]
    2. **正文**:[具体改进建议]
    3. **结论**:[具体改进建议]
    4. **标题**:[备选标题建议]
    
    ## 发布前自查清单
    - [ ] 所有论断已标注出处
    - [ ] 引用格式规范
    - [ ] 示例清晰明了
    - [ ] 过渡自然流畅
    - [ ] 包含行动号召
    - [ ] 已校对错别字
    
    可以发布了!🚀
    

Examples

Example 1: Teresa Torres's workflow

User: "I'm writing an article about continuous discovery. Help me create an outline."

Process:

  1. Collaboratively draft the outline structure
  2. Identify research needs
  3. The user starts writing the introduction
  4. Review and optimize the opening
  5. The user writes section by section
  6. Provide feedback after each section is completed
  7. Conduct research and add citations
  8. Final review of the full text
  9. Polish and prepare for publication

Outcome: a well-researched article with properly formatted citations that preserves Teresa's writing style, with a clear structure and smooth prose.

Example 2: A research-heavy article

User: "I'm writing an article about the impact of AI on product management. Help me find the latest data and case studies."

Output:

## 调研汇总

### 最新数据
- Gartner:到 2025 年 80% 的产品经理将使用 AI 工具 [1]
- 调查显示:45% 反馈功能交付速度加快 [2]
- 案例:Airbnb 的 AI 辅助优先级排序 [3]

### 专家观点
- "AI 放大了产品经理的判断力,而非取代它" —— Marty Cagan
- [更多专家引言及出处]

### 实际案例
1. **公司 A**:使用 AI 进行用户调研综合分析
   - 成效:节省 60% 时间
   - 来源:[引用]

2. **公司 B**:AI 驱动的路线图分析
   - 成效:利益相关方对齐度提升
   - 来源:[引用]

所有内容已添加到大纲并标注了引用。

Example 3: Opening optimization

User's original text:

"Product management is changing because of AI. In this article, I will discuss some of the ways AI affects product managers."

Optimization options:

Option One (Data-Driven):

"Last month, I had AI analyze 500 customer interview records. It was done in 30 minutes instead of 3 weeks. Product management can never go back."

Option Two (Question-Based):

"What if you could talk to every customer, read every review, and analyze every support ticket—and finish it all before you finish your morning coffee?"

Option Three (Story-Based):

"Sarah spent two weeks building the wrong feature. Not because she didn't understand users, but because she didn't have time to process the patterns hidden in hundreds of interviews."

Example Four: Section-by-Section Feedback

User: "I just finished writing the 'Common Mistakes' section. What do you think?"

Reply:

# 反馈:常见错误

## 亮点 ✓
- 示例有力(Slack 通知的故事)
- 结构清晰(3 个错误,排版整齐)
- 每个错误都给出了实用建议

## 改进建议

### 更加具体
第二点"优先级排序不当"可以更有力:

原文:
> "很多团队优先级排序不当,只关注功能而不关注成果。"

建议改为:
> "我见过团队一个季度发布了 14 个功能,却没有推动任何核心指标。他们把活跃度当成了进步。"

### 补充数据
第三个错误如果能加上数据会更有说服力:
> "[补充引用]:研究表明,不与用户保持定期沟通的团队,做出无用功能的概率高出 3 倍 [待补充来源]"

### 优化顺序
建议调整顺序:错误 3 → 错误 2 → 错误 1
这样可以从小到大递进,层层加强。

可以开始下一节了!

Writing Workflows

Blog Post Workflow

  1. Draft the outline together
  2. Research key points
  3. Write the introduction → get feedback
  4. Write each body section → section-by-section feedback
  5. Write the conclusion → final review
  6. Polish and finalize

Newsletter Workflow

  1. Discuss opening ideas
  2. Quickly draft an outline (shorter length)
  3. Complete the first draft in one go
  4. Review for clarity and links
  5. Quick polish

Technical Tutorial Workflow

  1. List the steps
  2. Write code examples
  3. Add explanatory text
  4. Test the procedure
  5. Add a FAQ troubleshooting section
  6. Final review for accuracy

Deep Opinion Article Workflow

  1. Brainstorm to find a unique angle
  2. Research existing viewpoints
  3. Distill the core argument
  4. Write with a strong stance
  5. Add supporting evidence
  6. Polish the ending

Practical Tips

  1. Write in VS Code: better suited for long-form writing than the web version
  2. Write one section at a time: get feedback incrementally
  3. Save research materials separately: maintain a research.md file
  4. Version your drafts: article-v1.md, article-v2.md, etc.
  5. Read aloud to check: use feedback to find awkward sentences
  6. Set a deadline: "I want to finish the first draft today"
  7. Take proper breaks: write a section, get feedback, pause, then revise

File Organization

The following directory structure is recommended for writing projects:

your-project/
├── outline.md          # 大纲
├── research.md         # 调研资料和引用
├── draft-v1.md         # 第一稿
├── draft-v2.md         # 修改稿
├── final.md            # 定稿
├── feedback.md         # 收集到的反馈
└── sources/            # 参考材料
    ├── study1.pdf
    └── article2.md

Best Practices

Regarding Research

  • Verify source reliability before citing
  • Use the most recent data where possible
  • Consider different perspectives
  • Provide links to original sources

Regarding Feedback

  • Be specific about what feedback you want: "Is this section too technical?"
  • State your concerns: "I'm worried this section reads slowly"
  • Ask proactively: "Does this logic flow well?"
  • Request alternatives: "Could you explain this a different way?"

Regarding Style

  • Provide samples of your existing writing
  • Specify your tone preferences
  • Mark suitable styles promptly: "This part really sounds like my style!"
  • Also point out what doesn't fit: "Too formal, that's not my style"

Related use cases

  • Generate social media content based on articles
  • Rewrite content for different audiences
  • Write email newsletters
  • Write technical documentation
  • Create presentation content
  • Write case studies
  • Develop course outlines