Agent skill

Research Writer

by rongxinzy in rongxinzy/RongxinAI

提供高质量的研究写作支持:从资料调研、补充引用,到优化开头、完善结构大纲,并实时提供逐节反馈与打磨建议。当用户提出写作协助请求,如“帮忙调研资料”、“优化开头”、“梳理大纲”,或需要逐节审阅、补充引用、润色文章时触发。

Apache-2.0Auto-check passed

Install Research Writer

skills CLI
$ npx skills add rongxinzy/RongxinAI --skill research-writer -a claude-code

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

GitHub CLI
$ gh skill install rongxinzy/RongxinAI research-writer --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/rongxinzy/RongxinAI.git skills-src && mkdir -p .claude/skills && cp -r skills-src/SKILLs/research-writer .claude/skills/research-writer && 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
research-writer
GitHub stars
154
Token cost
~1.8k tokens
SKILL.md length
280 words
Files
4
Skills in repo
94
Repo updated
First seen
Licence
Apache-2.0

At a glance

提供高质量的研究写作支持:从资料调研、补充引用,到优化开头、完善结构大纲,并实时提供逐节反馈与打磨建议。当用户提出写作协助请求,如“帮忙调研资料”、“优化开头”、“梳理大纲”,或需要逐节审阅、补充引用、润色文章时触发。

  • Works in 7 steps: 协作拟定大纲:帮你把想法梳理成条理清晰的大纲 → 资料调研辅助:搜索相关信息并补充引用 → 开头优化:加强文章开头,吸引读者注意力 → …
  • SKILL.md covers 适用场景, 功能介绍, 使用方法 and 使用指南, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Research Writer is an agent skill from rongxinzy/RongxinAI. 提供高质量的研究写作支持:从资料调研、补充引用,到优化开头、完善结构大纲,并实时提供逐节反馈与打磨建议。当用户提出写作协助请求,如“帮忙调研资料”、“优化开头”、“梳理大纲”,或需要逐节审阅、补充引用、润色文章时触发。

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `zhiyuan/metadata.yaml`).

The repository describes itself as: An all-in-one local AI Agent workspace with a fully self-developed stack. The licence is Apache-2.0.

Example prompts

  • “帮忙调研资料”
  • “/research-writer”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 协作拟定大纲:帮你把想法梳理成条理清晰的大纲
  2. 资料调研辅助:搜索相关信息并补充引用
  3. 开头优化:加强文章开头,吸引读者注意力
  4. 逐节反馈:在你写作过程中逐节审阅
  5. 风格保持:维持你的写作风格和语气
  6. 引用管理:规范添加和格式化参考文献
  7. 迭代打磨:通过多轮修改帮你不断提升

What it can do on your machine

Read from SKILL.md and the folder at commit 9c64865. 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 markdown).

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

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Research Writer loads about 1.8k tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 280 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 rongxinzy/RongxinAI at commit 9c64865, republished under its Apache-2.0 licence (© rongxinzy). 280 words, ~1,831 tokens.

Download SKILL.mdSave it as .claude/skills/research-writer/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
research-writer
description
提供高质量的研究写作支持:从资料调研、补充引用,到优化开头、完善结构大纲,并实时提供逐节反馈与打磨建议。当用户提出写作协助请求,如“帮忙调研资料”、“优化开头”、“梳理大纲”,或需要逐节审阅、补充引用、润色文章时触发。
license
Apache-2.0
<!-- Changes (zh): translated full body to Chinese, kept name slug unchanged. -->
<!-- Changes: added license field to frontmatter, replaced ~/writing/ example paths with relative paths. Original source: https://github.com/ComposioHQ/awesome-claude-skills/tree/master/content-research-writer (Apache-2.0) -->

研究内容写作助手

这个 skill 可以作为你的写作搭档,帮助你完成资料调研、拟定大纲、撰写初稿和打磨润色,同时保持你独有的写作风格和语气。

适用场景

  • 撰写博客文章、专栏或新闻简报
  • 创作教学内容或教程
  • 起草深度观点文章
  • 调研并撰写案例分析
  • 编写需要引用文献的技术文档
  • 规范引用和参考文献格式
  • 优化文章开头和引言
  • 边写边获取逐节反馈

功能介绍

  1. 协作拟定大纲:帮你把想法梳理成条理清晰的大纲
  2. 资料调研辅助:搜索相关信息并补充引用
  3. 开头优化:加强文章开头,吸引读者注意力
  4. 逐节反馈:在你写作过程中逐节审阅
  5. 风格保持:维持你的写作风格和语气
  6. 引用管理:规范添加和格式化参考文献
  7. 迭代打磨:通过多轮修改帮你不断提升

使用方法

搭建写作环境

为你的文章创建一个专用文件夹,然后在该文件夹下工作。例如:

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

创建草稿文件:

touch article-draft.md

从这个目录打开 Claude Code,即可开始写作。

基本工作流
  1. 从大纲开始:
帮我为一篇关于 [主题] 的文章创建大纲
  1. 调研并补充引用:
调研 [具体主题] 并在大纲中补充引用
  1. 优化开头:
这是我的引言,请帮我让开头更有吸引力。
  1. 获取逐节反馈:
我刚写完"为什么这很重要"这一节,请审阅并给出反馈。
  1. 打磨润色:
审阅完整草稿,检查行文流畅度、清晰度和一致性。

使用指南

当用户请求写作帮助时:

  1. 了解写作项目

    询问以下问题以明确需求:

    • 主题和核心论点是什么?
    • 目标读者是谁?
    • 期望的篇幅和格式?
    • 写作目的是什么?(科普、说服、分享、解释)
    • 是否有现成的资料或素材?
    • 偏好什么写作风格?(正式、口语化、技术性)
  2. 协作拟定大纲

    帮助梳理内容结构:

    markdown
    # 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

    反复打磨大纲:

    • 根据反馈调整
    • 确保逻辑连贯
    • 识别资料缺口
    • 标记需要深入展开的部分
  3. 进行资料调研

    当用户请求某一主题的调研时:

    • 搜索相关信息
    • 寻找可靠来源
    • 提取关键事实、引言和数据
    • 按要求的格式添加引用

    示例输出:

    markdown
    ## 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. 优化开头

    当用户分享引言时,分析并加强:

    当前开头分析:

    • 优点:[积极要素]
    • 可以更好:[改进方向]
    • 情感冲击力:[现状 vs. 潜力]

    优化方案:

    方案一:[大胆的陈述]

    [示例] 为什么有效:[说明]

    方案二:[个人故事]

    [示例] 为什么有效:[说明]

    方案三:[令人意外的数据]

    [示例] 为什么有效:[说明]

    自检问题:

    • 是否引发了好奇心?
    • 是否传递了价值承诺?
    • 是否足够具体?
    • 是否匹配目标读者?
  5. 提供逐节反馈

    用户每写完一节后,从以下方面审阅:

    markdown
    # 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. 保持作者风格

    重要原则:

    • 学习对方的风格:阅读其已有的写作样本
    • 建议而非替代:提供选项,而不是强加指令
    • 匹配语气:正式、随意、技术性、亲切
    • 尊重选择:如果对方更喜欢自己的版本,予以支持
    • 提升而非改变:让文章更好,而不是变成另一种风格

    定期询问:

    • "这听起来像你的风格吗?"
    • "这个语气合适吗?"
    • "需要更正式/更口语化/更技术性一些吗?"
  7. 引用管理

    根据用户偏好处理参考文献:

    行内引用:

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

    编号引用:

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

    脚注式引用:

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

    维护一个持续更新的引用列表:

    markdown
    ## 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. 终稿审阅与润色

    草稿完成后,提供全面反馈:

    markdown
    # 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!🚀
Show full SKILL.md (158 more words)Show less

示例

示例一:Teresa Torres 的工作流

用户:"我在写一篇关于持续发现的文章,帮我创建大纲。"

流程:

  1. 协作拟定大纲结构
  2. 识别调研需求
  3. 用户开始写引言
  4. 审阅并优化开头
  5. 用户逐节撰写
  6. 每节完成后提供反馈
  7. 进行调研并补充引用
  8. 全文终审
  9. 润色并准备发布

成果:一篇调研充分、引用规范的文章,保持了 Teresa 的写作风格,结构清晰、行文流畅。

示例二:重调研型文章

用户:"我在写一篇关于 AI 对产品管理影响的文章,帮我查找最新数据和案例。"

输出:

markdown
## 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。
示例三:开头优化

用户原文:

"产品管理正在因为 AI 而发生变化。在这篇文章中,我将讨论 AI 影响产品经理的一些方式。"

优化方案:

方案一(数据驱动):

"上个月,我让 AI 分析了 500 份客户访谈记录。30 分钟就完成了,而不是 3 周。产品管理,再也回不去了。"

方案二(提问式):

"如果你能和每一位客户对话、读完每一条评价、分析每一封工单——而且赶在早上喝完咖啡之前就做完呢?"

方案三(故事型):

"Sarah 花了两周时间做了一个错误的功能。不是因为她不了解用户,而是因为她来不及处理数百份访谈中隐藏的规律。"

示例四:逐节反馈

用户:"刚写完'常见错误'这一节,你觉得怎么样?"

回复:

markdown
# 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!

写作工作流

博客文章工作流
  1. 共同拟定大纲
  2. 调研关键要点
  3. 撰写引言 → 获取反馈
  4. 撰写正文各节 → 逐节反馈
  5. 撰写结论 → 终审
  6. 润色定稿
新闻简报工作流
  1. 讨论开头创意
  2. 快速拟定大纲(篇幅较短)
  3. 一次性完成初稿
  4. 审阅清晰度和链接
  5. 快速润色
技术教程工作流
  1. 列出操作步骤
  2. 编写代码示例
  3. 添加说明文字
  4. 测试操作流程
  5. 添加常见问题排查部分
  6. 终审准确性
深度观点文章工作流
  1. 头脑风暴,找到独特角度
  2. 调研现有观点
  3. 提炼核心论点
  4. 以鲜明立场撰写
  5. 补充支撑论据
  6. 打磨结尾

实用技巧

  1. 在 VS Code 中写作:比网页端更适合长文写作
  2. 一次写一节:逐步获取反馈
  3. 单独保存调研资料:维护一个 research.md 文件
  4. 为草稿做版本管理:article-v1.md、article-v2.md 等
  5. 朗读检查:借助反馈找出拗口的句子
  6. 设定截止时间:"我要在今天内完成初稿"
  7. 适当休息:写一段,拿反馈,暂停,再修改

文件组织

写作项目推荐使用以下目录结构:

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

最佳实践

调研方面
  • 引用前核实来源的可靠性
  • 尽量使用最新数据
  • 兼顾不同视角
  • 提供原始来源链接
反馈方面
  • 明确你想要什么反馈:"这段会不会太技术化了?"
  • 说出你的顾虑:"我担心这一节读起来拖沓"
  • 主动提问:"这个逻辑通顺吗?"
  • 请求替代方案:"换个方式解释这个,行吗?"
风格方面
  • 提供你已有的写作样本
  • 说明语气偏好
  • 遇到合适的风格及时标记:"这段很像我的风格!"
  • 遇到不合适的也要指出:"太正式了,不是我的风格"

相关应用场景

  • 基于文章生成社交媒体内容
  • 为不同受众改写内容
  • 撰写邮件简报
  • 编写技术文档
  • 制作演示文稿内容
  • 撰写案例分析
  • 开发课程大纲

© rongxinzy, Apache-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

SKILL.md and 3 other files in SKILLs/research-writer of rongxinzy/RongxinAI.

  • SKILL.md
  • LICENSE.txt
  • zhiyuan/icon.png
  • zhiyuan/metadata.yaml

Open the folder on GitHubat commit 9c64865

Compare with similar skills

Research Writer 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.

Research Writer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Writer this skillrongxinzy/RongxinAI154—~1.8kAutomated safety check: PassApache-2.0
Writerjeremylongshore/tons-of-skills-marketplace2.8k—~2.1kAutomated safety check: PassMIT
Writeraiskillstore/marketplace4333 repos~1.3kAutomated safety check: PassNone
Writerflaqai/backlink_skills756—~5.8kAutomated safety check: PassMIT
Writerwellwelwel/lagune173—~1.1kAutomated safety check: PassMIT
Writerrileyhilliard/claude-essentials130—~2kAutomated safety check: PassMIT

Similar skills

  • Writer

    jeremylongshore/tons-of-skills-marketplace

    Professional writing assistant for PM documents. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed
  • Writer

    aiskillstore/marketplace

    Document creation, format conversion (ODT/DOCX/PDF), mail merge, and automation with LibreOffice Writer.

    433 GitHub starsUsed in 3 repos~1.3k tokens
    Documents & OfficeAuto-check passed
  • Writer

    flaqai/backlink_skills

    SEO-friendly article writing, audit, and humanization workflow for Markdown content.

    756 GitHub stars~5.8k tokensUpdated 17 days ago
    Writing & ContentAuto-check passed
  • Writer

    wellwelwel/lagune

    Authoritative reference for writing the project's prose. An agent skill from wellwelwel/lagune.

    173 GitHub stars~1.1k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed
  • Writer

    rileyhilliard/claude-essentials

    Writing style and tone guide for human-sounding content. An agent skill from rileyhilliard/claude-essentials.

    130 GitHub stars~2k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed
  • Skill Writer

    sickn33/agentic-awesome-skills

    Create and improve agent skills following the Agent Skills specification.

    47k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed

More from rongxinzy/RongxinAI

All 94 skills in this repo
  • SaaS Metrics Coach

    rongxinzy/RongxinAI

    SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.

    154 GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed
  • Churn Prevention

    rongxinzy/RongxinAI

    Reduce voluntary and involuntary churn through cancel flow design, save offers, exit surveys, and dunning sequences.

    154 GitHub starsUsed in 3 repos~2.6k tokens
    Auto-check passed
  • Presentation Studio

    rongxinzy/RongxinAI

    The only skill for creating a new PowerPoint deck. An agent skill from rongxinzy/RongxinAI.

    154 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Zhiyuan Expert Manager

    rongxinzy/RongxinAI

    ZhiYuan Agent expert package lifecycle manager for the pi engine.

    154 GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Ziwei Doushu

    rongxinzy/RongxinAI

    Professional Ziwei Doushu consultation skill with an offline calculation engine.

    154 GitHub stars~746 tokensUpdated today
    Auto-check passed
  • Lark Mail

    rongxinzy/RongxinAI

    飞书邮箱:Use when user mentions 起草邮件、写邮件、草稿、发送/回复/转发邮件、查阅邮件、看邮件、搜索邮件、邮件文件夹、邮件标签、邮件联系人、监听新邮件、邮件收信规则等;use for mail/email intent only.

    154 GitHub starsUsed in 3 repos~4.1k tokens
    Auto-check: warnings

Questions about Research Writer

What does Research Writer do?

提供高质量的研究写作支持:从资料调研、补充引用,到优化开头、完善结构大纲,并实时提供逐节反馈与打磨建议。当用户提出写作协助请求,如“帮忙调研资料”、“优化开头”、“梳理大纲”,或需要逐节审阅、补充引用、润色文章时触发。. Research Writer is an agent skill from rongxinzy/RongxinAI.

How do I install Research Writer in Claude Code?

Run `npx skills add rongxinzy/RongxinAI --skill research-writer -a claude-code`. Or copy the skill folder (SKILLs/research-writer in rongxinzy/RongxinAI) into .claude/skills/research-writer in your project. Claude Code loads it when a task matches its description.

How do I install Research Writer in Codex?

Run `npx skills add rongxinzy/RongxinAI --skill research-writer -a codex`. Or copy the skill folder (SKILLs/research-writer in rongxinzy/RongxinAI) into .agents/skills/research-writer in your project. Codex loads it when a task matches its description.

Can I use Research Writer 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 rongxinzy/RongxinAI --skill research-writer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-writer, .gemini/skills/research-writer, .github/skills/research-writer and .opencode/skills/research-writer in your project.

What does Research Writer need to run?

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

Does Research Writer access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Research Writer 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 Research Writer use?

Research Writer is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Research Writer use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 Research Writer?

Skills that share tags, products or a category with Research Writer: Writer (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Writer (aiskillstore/marketplace, 433 stars), Writer (flaqai/backlink_skills, 756 stars) and Writer (wellwelwel/lagune, 173 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Writer?

rongxinzy (a GitHub organization) maintains it in rongxinzy/RongxinAI, which has 154 GitHub stars. The repository holds 94 skills in this directory. The repository was last updated on October 10, 2026.

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