Agent skill

Brainstorming Research

by Norman-bury in Norman-bury/research-writing-skill

Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue

MITAuto-check passedAgent Workflows

Install Brainstorming Research

skills CLI
$ npx skills add Norman-bury/research-writing-skill --skill brainstorming-research -a claude-code

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

GitHub CLI
$ gh skill install Norman-bury/research-writing-skill brainstorming-research --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/Norman-bury/research-writing-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/brainstorming-research .claude/skills/brainstorming-research && 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
brainstorming-research
GitHub stars
3.4k
Token cost
~1.3k tokens
SKILL.md length
262 words
Files
3
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue

  • Works in 11 steps: 探索项目上下文 — 检查是否已有 plan/、现有文件、用户提供的信息 → 确认论文类型 — 对话式提问,等待回答 → 确认学科领域 — 对话式提问,等待回答 → …
  • Tasks that involve Brainstorming
  • SKILL.md covers 交互方式约束, 语言默认规则, 已有论文信息提示 and 反模式:"这太简单了不需要讨论", plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Brainstorming Research is an agent skill from Norman-bury/research-writing-skill. Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `chapter-templates.md` and `templates.md`).

It sits in Agent Workflows, covering Brainstorming. The repository describes itself as: 科研写作助手 (Research Writing Assistant). The licence is MIT.

When your agent uses it

  • Tasks that involve Brainstorming

Example prompts

  • “/brainstorming-research”

Workflow steps

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

  1. 探索项目上下文 — 检查是否已有 plan/、现有文件、用户提供的信息
  2. 确认论文类型 — 对话式提问,等待回答
  3. 确认学科领域 — 对话式提问,等待回答
  4. 确认论文题目 — 对话式提问,等待回答
  5. 确认研究背景与目的 — 对话式提问,等待回答
  6. 确认研究方法 — 对话式提问,等待回答
  7. 检测 LaTeX 模板 — 如果存在,询问是否使用
  8. 确认章节结构 — 根据论文类型提供标准结构,让用户确认
  9. 汇总确认 — 展示所有信息,获得最终确认
  10. 创建项目结构 — 创建 plan/ 和 chapters/
  11. 转到章节写作 — 询问从哪章开始

What it can do on your machine

Read from SKILL.md and the folder at commit 6f79595. 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 dot 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

Brainstorming Research loads about 1.3k tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 262 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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 Norman-bury/research-writing-skill at commit 6f79595, republished under its MIT licence (© Norman-bury). 262 words, ~1,315 tokens.

Download SKILL.mdSave it as .claude/skills/brainstorming-research/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
brainstorming-research
description
Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue

科研写作头脑风暴

通过自然的协作对话,帮助用户将论文想法转化为完整的写作计划。

核心原则:一次只问一个问题,等待用户回答后再继续下一个。

交互原则:让用户少做选择,多做确认。提供推荐方案,让用户确认或微调。

<EXTREMELY-IMPORTANT>
## 交互方式约束

你必须以对话方式进行头脑风暴,而不是列出表单让用户填写:

正确做法:

  • 每次只问一个问题
  • 用自然语言提问,像同事间的讨论
  • 等待用户回答后,确认理解,再问下一个问题
  • 提供推荐方案,让用户确认,而不是让用户从零开始选择
  • 给出你的建议和理由,帮助用户做选择

错误做法:

  • 一次性列出所有问题
  • 把问题编号像表单一样展示
  • 不等用户回答就继续
  • 干巴巴地列选项不给建议
  • 让用户从空白开始填写

示例对比:

❌ 错误:"请选择:1.本科 2.硕士 3.博士 4.期刊 5.会议 6.课程"

✅ 正确:"你这次要写的是什么类型的论文?是毕业论文、期刊投稿,还是课程作业?如果是毕业论文,是本科、硕士还是博士阶段的?" </EXTREMELY-IMPORTANT>

<HARD-GATE>
在完成所有问答并获得用户最终确认之前,禁止:
- 写任何正文内容
- 创建 chapters/ 目录
- 调用 writing-chapters 技能
- 输出任何论文章节的实际内容

无论用户的任务看起来多么"简单",都必须经过此流程。 </HARD-GATE>

语言默认规则

论文类型默认语言说明
本科毕业论文中文除非用户明确要求英文
硕士毕业论文中文除非用户明确要求英文
博士毕业论文中文除非用户明确要求英文
中文核心期刊中文
SCI/SSCI期刊英文根据期刊要求
会议论文英文国际会议为主
课程论文中文除非课程要求英文

不需要主动询问语言,根据论文类型自动确定。只有当用户有特殊语言需求时才调整。

已有论文信息提示

在开始问答前,检查用户是否已有论文相关信息:

"在开始之前,如果你已经有论文的相关材料(比如题目、摘要、导师要求的结构),可以现在发给我,我会根据这些信息来规划。如果没有也没关系,我们从头开始讨论。"

等待用户回复,如果提供了材料,快速浏览并提取关键信息,然后在后续问答中确认。

反模式:"这太简单了不需要讨论"

每个论文项目都要经过这个流程。一篇课程论文、一个简单修改、一段摘要 — 都需要。"简单"的项目往往因为未经检验的假设导致最多的返工。讨论可以很简短,但必须呈现信息并获得确认。

Checklist

按顺序完成:

  1. 探索项目上下文 — 检查是否已有 plan/、现有文件、用户提供的信息
  2. 确认论文类型 — 对话式提问,等待回答
  3. 确认学科领域 — 对话式提问,等待回答
  4. 确认论文题目 — 对话式提问,等待回答
  5. 确认研究背景与目的 — 对话式提问,等待回答
  6. 确认研究方法 — 对话式提问,等待回答
  7. 检测 LaTeX 模板 — 如果存在,询问是否使用
  8. 确认章节结构 — 根据论文类型提供标准结构,让用户确认
  9. 汇总确认 — 展示所有信息,获得最终确认
  10. 创建项目结构 — 创建 plan/ 和 chapters/
  11. 转到章节写作 — 询问从哪章开始

流程图

dot
digraph brainstorming_research {
    "探索上下文" [shape=box];
    "问论文类型" [shape=box];
    "等待回答" [shape=diamond];
    "问学科领域" [shape=box];
    "问论文题目" [shape=box];
    "问研究背景" [shape=box];
    "问研究方法" [shape=box];
    "检测LaTeX模板" [shape=box];
    "确认章节结构" [shape=box];
    "汇总确认" [shape=box];
    "用户确认?" [shape=diamond];
    "创建项目" [shape=box];
    "开始写作" [shape=doublecircle];

    "探索上下文" -> "问论文类型";
    "问论文类型" -> "等待回答";
    "等待回答" -> "问学科领域" [label="收到回答"];
    "问学科领域" -> "等待回答";
    "等待回答" -> "问论文题目" [label="收到回答"];
    "问论文题目" -> "等待回答";
    "等待回答" -> "问研究背景" [label="收到回答"];
    "问研究背景" -> "等待回答";
    "等待回答" -> "问研究方法" [label="收到回答"];
    "问研究方法" -> "等待回答";
    "等待回答" -> "检测LaTeX模板" [label="收到回答"];
    "检测LaTeX模板" -> "确认章节结构";
    "确认章节结构" -> "汇总确认";
    "汇总确认" -> "用户确认?";
    "用户确认?" -> "问论文类型" [label="需要修改"];
    "用户确认?" -> "创建项目" [label="确认"];
    "创建项目" -> "开始写作";
}

对话指南

第一个问题:论文类型

用自然语言询问,给出你的观察和建议:

"你这次要写的是什么类型的论文?

比如:

  • 毕业论文(本科/硕士/博士)
  • 期刊投稿(中文核心 / SCI)
  • 会议论文
  • 课程论文或报告

不同类型的论文在篇幅、结构和语言风格上会有差异,我需要先了解这个来帮你规划。"

等待用户回答。 收到回答后,确认你的理解:

"好的,[论文类型]。这类论文通常使用 [引用格式],写作风格偏向 [风格特点]。"

然后进入下一个问题。

第二个问题:学科领域

"你的研究属于哪个学科领域?

这会影响我给你的写作建议和章节安排。比如工科论文侧重技术方案和实验验证,社科论文更强调理论框架和数据分析,医学论文有特殊的报告规范要求。"

等待用户回答。

第三个问题:论文题目

"论文题目定了吗?可以是暂定的,我们后面还可以调整。

如果还在犹豫,可以告诉我你想研究的大方向,我帮你一起想想怎么聚焦。"

等待用户回答。

第四个问题:研究背景与目的

根据用户的学科和题目,用更具体的方式提问:

"关于你的研究,我想了解一下:

你为什么选择这个题目?是发现了什么问题想解决,还是想验证某个想法?

简单说说背景就好,不用太正式。"

等待用户回答。 如果回答不够清晰,可以追问:

"明白了。那你希望通过这个研究达成什么目标?解决什么具体问题?"

第五个问题:研究方法

根据学科领域,问题侧重点不同:

工科:

"你打算用什么技术方案或方法?有没有要做的实验或系统?性能怎么评估?"

社科:

"你的研究方法是什么?问卷调查、访谈、案例分析,还是其他?数据怎么收集和分析?"

医学:

"这是临床研究还是基础研究?样本量大概多少?伦理审批这块有没有考虑?"

文科:

"你打算从什么理论视角切入?研究的文本或材料来源是什么?"

法学:

"你要分析的法律问题是什么?会用到案例分析还是比较法研究?"

等待用户回答。

LaTeX 模板检测

检查 latex-templates/ 目录:

如果存在模板文件:

"我注意到你放了 LaTeX 模板文件。你想用这个模板来输出论文吗?

用模板的话,我会直接生成 .tex 文件,可以用 LaTeX 编译成 PDF。 不用的话,我会输出 Markdown 文件,你可以后续复制到 Word。

你想怎么处理?"

如果不存在模板:默认使用 Markdown,不需要询问。

第六个问题:章节结构

根据用户确认的论文类型,自动推荐对应的章节结构:

"根据你的 [论文类型],我建议这样的章节结构:

[展示对应类型的结构,> [从 templates.md 读取]

这是 [论文类型] 的标准结构。你可以:

  1. 直接确认 — 使用这个结构
  2. 微调 — 告诉我需要增删或调整的章节

你想怎么处理?"

重要:优先让用户确认, 而不是让用户设计。如果用户没有特殊要求, 使用默认结构即可.

汇总确认

收集完所有信息后,呈现汇总:

"好,我整理一下我们讨论的内容:

  • 论文类型:[类型]
  • 学科领域:[领域]
  • 论文题目:[题目]
  • 研究背景:[简述]
  • 研究目的:[简述]
  • 研究方法:[简述]
  • 输出格式:[Markdown / LaTeX]
  • 章节结构:
    • [章节列表]

这些信息都对吗?确认后我会创建项目结构,然后我们就可以开始写了。"

<HARD-GATE>
必须等待用户明确确认(如"对"、"可以"、"确认"、"没问题")后才能继续。
不得假设用户同意。
</HARD-GATE>

创建项目结构

用户确认后,执行以下操作:

  1. 创建 plan/ 目录(如不存在)
  2. 填充 project-overview.md:
markdown
# 项目概览

## 基本信息

- **论文类型**:[类型]
- **学科领域**:[领域]
- **论文题目**:[题目]
- **创建时间**:[日期]
- **输出格式**:[Markdown / LaTeX]
- **当前阶段**:头脑风暴完成,待开始写作

## 研究信息

### 研究背景
[用户描述]

### 研究目的
[用户描述]

### 研究方法
[用户描述]

## 章节结构

[章节列表]

## 写作规范

- **语言**:[中文/英文]
- **引用格式**:[格式]
- **写作模块**:[对应模块]
  1. 填充 outline.md:详细章节大纲
  2. 更新 progress.md:记录头脑风暴完成
  3. 创建 chapters/ 目录:创建空的章节文件

转到写作

"项目结构已经创建好了。

你想从哪一章开始写?

我的建议是先写绪论,把研究问题和目标明确下来,这样后面的章节写起来会更顺。不过如果你对文献综述或方法部分更有把握,也可以先从那里开始。

你想先写哪部分?"

等待用户回答,然后调用 writing-chapters 技能。


关键原则

  • 一次只问一个问题 — 不要用多个问题压倒用户
  • 等待回答再继续 — 不要假设用户的选择
  • 对话式而非表单式 — 像同事讨论,不是填问卷
  • 给出建议和理由 — 帮助用户做选择,不是干巴巴列选项
  • 灵活调整 — 如果用户想跳过某些讨论,可以简化但不能跳过最终确认
  • 记录一切 — 所有决策都写入 plan/

© Norman-bury, MIT. 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 2 other files in skills/brainstorming-research of Norman-bury/research-writing-skill.

  • SKILL.md
  • chapter-templates.md
  • templates.md

Open the folder on GitHubat commit 6f79595

Compare with similar skills

Brainstorming Research 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.

Brainstorming Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Brainstorming Research this skillNorman-bury/research-writing-skill3.4k—~1.3kAutomated safety check: PassMIT
Brainstormingobra/superpowers297k1 repos~2.5kAutomated safety check: PassMIT
Brainstormingxpinjection/test-driven-spring-boot11253 repos~2.6kAutomated safety check: PassMIT
Yao Meta Skillyaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT
Typesafe AIOpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMIT
Trellis StartROYIANS/foliq-print-template-designer1366 repos~646Automated safety check: PassMIT

Similar skills

  • Brainstorming

    obra/superpowers

    Makes the agent clarify intent and agree on a design with you before writing any code, scaling the process from a quick spike to a written spec.

    297k GitHub starsUsed in 1 repo~2.5k tokens
    Agent WorkflowsAuto-check passed
  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 53 repos~2.6k tokens
    Agent WorkflowsAuto-check passed
  • Yao Meta Skill

    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

    2.7k GitHub stars~768 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Typesafe AI

    OpenAgentsInc/openagents

    Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

    455 GitHub starsUsed in 9 repos~2.5k tokens
    Agent WorkflowsAuto-check passed
  • Trellis Start

    ROYIANS/foliq-print-template-designer

    Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

    136 GitHub starsUsed in 6 repos~646 tokens
    Agent WorkflowsAuto-check passed
  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from Norman-bury/research-writing-skill

All 20 skills in this repo
  • Evidence Driven Writing

    Norman-bury/research-writing-skill

    A skill your agent uses when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims

    3.4k GitHub stars~952 tokensUpdated 4 mo ago
    Auto-check passed
  • Environment Setup

    Norman-bury/research-writing-skill

    A skill your agent uses when Python environment setup is needed for data visualization or conda installation is required

    3.4k GitHub stars~840 tokensUpdated 4 mo ago
    Auto-check passed
  • Experiment Results Planning

    Norman-bury/research-writing-skill

    A skill your agent uses when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final

    3.4k GitHub stars~990 tokensUpdated 4 mo ago
    Auto-check passed
  • Figures Diagram

    Norman-bury/research-writing-skill

    A skill your agent uses when creating flowcharts, architecture diagrams, or conceptual diagrams - generates prompts for image AI

    3.4k GitHub stars~548 tokensUpdated 4 mo ago
    Auto-check passed
  • Figures Python

    Norman-bury/research-writing-skill

    A skill your agent uses when creating data visualizations for papers - generates publication-quality plots with top-journal color schemes

    3.4k GitHub stars~1.2k tokensUpdated 4 mo ago
    Auto-check passed
  • Latex Output

    Norman-bury/research-writing-skill

    A skill your agent uses when user requests LaTeX format output or has provided school/journal LaTeX templates

    3.4k GitHub stars~977 tokensUpdated 4 mo ago
    Auto-check passed

Categories

Questions about Brainstorming Research

What does Brainstorming Research do?

Use before writing any paper - clarifies paper type, discipline, topic, methodology, and chapter structure through natural dialogue. Brainstorming Research is an agent skill from Norman-bury/research-writing-skill.

When should I use Brainstorming Research?

Brainstorming Research fits situations like: tasks that involve Brainstorming.

How do I install Brainstorming Research in Claude Code?

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

How do I install Brainstorming Research in Codex?

Run `npx skills add Norman-bury/research-writing-skill --skill brainstorming-research -a codex`. Or copy the skill folder (skills/brainstorming-research in Norman-bury/research-writing-skill) into .agents/skills/brainstorming-research in your project. Codex loads it when a task matches its description.

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

What does Brainstorming Research need to run?

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

Does Brainstorming Research 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 Brainstorming Research 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 Brainstorming Research use?

Brainstorming Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Brainstorming Research use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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 Brainstorming Research?

Skills that share tags, products or a category with Brainstorming Research: Brainstorming (obra/superpowers, 297k stars), Brainstorming (xpinjection/test-driven-spring-boot, 112 stars), Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars) and Typesafe AI (OpenAgentsInc/openagents, 455 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Brainstorming Research?

Norman-bury (a GitHub user) maintains it in Norman-bury/research-writing-skill, which has 3,384 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on June 10, 2026.

Source: Norman-bury/research-writing-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.