academic-research-skills-codex

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Academic Research Skills for Codex

面向Codex的学术研究技能（Academic Research Skills）

Skill by ara.so — Codex Skills collection.

This skill provides a comprehensive suite of AI-assisted academic research workflows including deep research, paper writing, peer review, and end-to-end research pipelines. Originally designed for Claude Code, this Codex-native package routes requests to specialized research agents based on user intent.

由ara.so开发的Skill — Codex Skills合集。

该Skill提供一套全面的AI辅助学术研究工作流，包括深度研究、论文撰写、同行评审以及端到端研究流程。它最初为Claude Code设计，这个Codex原生包会根据用户意图将请求路由到专门的研究Agent。

What It Does

功能介绍

Academic Research Skills (ARS) for Codex provides five core workflows:

Deep Research - Literature reviews, systematic reviews, research question refinement, fact-checking
Academic Paper - Outlining, drafting, citation formatting, revision, AI disclosure
Academic Paper Reviewer - Manuscript review, simulated peer review, editorial decisions
Academic Pipeline - End-to-end research-to-publication workflow with integrity gates
Experiment Agent - Code experiment planning, study protocols, reproducibility validation

面向Codex的学术研究技能（ARS）提供五大核心工作流：

深度研究 - 文献综述、系统性综述、研究问题细化、事实核查
学术论文 - 大纲制定、草稿撰写、引用格式规范、修订、AI使用声明
学术论文评审 - 稿件评审、模拟同行评审、编辑决策
学术流程管线 - 包含完整性校验的端到端研究至发表工作流
实验Agent - 代码实验规划、研究方案、可复现性验证

Installation

安装方法

Install using the Codex skill installer with git method:

bash

python "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
  --repo Imbad0202/academic-research-skills-codex \
  --ref main \
  --path skills/academic-research-suite \
  --method git

使用git方法通过Codex skill安装器进行安装：

bash

python "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
  --repo Imbad0202/academic-research-skills-codex \
  --ref main \
  --path skills/academic-research-suite \
  --method git

Update Existing Installation

已有安装更新

bash

rm -rf "$HOME/.codex/skills/academic-research-suite"
python "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
  --repo Imbad0202/academic-research-skills-codex \
  --ref main \
  --path skills/academic-research-suite \
  --method git

After installation, open a new Codex conversation to activate the skill.

bash

rm -rf "$HOME/.codex/skills/academic-research-suite"
python "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
  --repo Imbad0202/academic-research-skills-codex \
  --ref main \
  --path skills/academic-research-suite \
  --method git

安装完成后，开启新的Codex对话即可激活该Skill。

Verify Installation

验证安装

text

/skills

You should see one entry:

academic-research-suite

. You should NOT see separate entries for

academic-paper

deep-research

, etc.

text

/skills

你应该能看到一个条目：

academic-research-suite

。不应看到

academic-paper

、

deep-research

等单独条目。

Core Usage Patterns

核心使用模式

Basic Invocation

基础调用

Use

$academic-research-suite

followed by your research task:

text

Use $academic-research-suite to help me plan a systematic literature review on
AI adoption in higher education quality assurance.

The Codex adapter automatically routes to the appropriate workflow based on your request.

使用

$academic-research-suite

后跟你的研究任务：

text

使用$academic-research-suite帮我规划一份关于人工智能在高等教育质量保障中应用的系统性文献综述。

Codex适配器会根据你的请求自动路由到合适的工作流。

Workflow Selection

工作流选择

Workflow	When to Use	Example Trigger
`deep-research`	Need research question refinement, literature review, fact-checking	"conduct a systematic review on..."
`academic-paper`	Need paper outline, drafting, citations, revision	"write a research paper about..."
`academic-paper-reviewer`	Need manuscript review, peer review simulation	"review this research manuscript..."
`academic-pipeline`	Need full research-to-publication workflow	"run end-to-end pipeline from topic to paper"
`experiment-agent`	Need code experiment design, study protocols	"plan a reproducible code experiment..."

Workflow	适用场景	触发示例
`deep-research`	需要细化研究问题、开展文献综述、事实核查	"针对……进行系统性综述"
`academic-paper`	需要论文大纲、草稿撰写、引用规范、修订	"撰写一篇关于……的研究论文"
`academic-paper-reviewer`	需要稿件评审、模拟同行评审	"评审这份研究稿件……"
`academic-pipeline`	需要完整的研究至发表工作流	"运行从选题到论文的端到端流程管线"
`experiment-agent`	需要代码实验设计、研究方案	"规划一个可复现的代码实验……"

Structured Request Pattern

结构化请求模式

For best results, provide goal, current state, and constraints:

text

Use $academic-research-suite.

Goal: write a journal article on AI in higher education QA
Current materials: literature matrix and rough findings, no outline yet
Output needed: paper architecture and evidence checklist
Constraints: English, APA 7, policy audience

为获得最佳效果，请提供目标、当前状态和约束条件：

text

使用$academic-research-suite。

目标：撰写一篇关于人工智能在高等教育质量保障中的期刊文章
现有资料：文献矩阵和初步研究结果，尚未制定大纲
所需输出：论文架构和证据清单
约束条件：英文撰写、APA 7格式、面向政策受众

Command Aliases

命令别名

Codex emulates Claude Code

/ars-*

commands as aliases:

Alias	Workflow	Purpose
`ars-plan`	academic-paper	Create paper plan/structure
`ars-outline`	academic-paper	Generate outline only
`ars-abstract`	academic-paper	Draft abstract
`ars-lit-review`	academic-paper	Build literature review
`ars-citation-check`	academic-paper	Verify citations
`ars-disclosure`	academic-paper	Generate AI disclosure statement
`ars-format-convert`	academic-paper	Convert between formats
`ars-revision-coach`	academic-paper	Get revision guidance
`ars-revision`	academic-paper	Execute revisions
`ars-full`	academic-pipeline	Run full pipeline

Codex模拟Claude Code的

/ars-*

命令作为别名：

别名	对应工作流	用途
`ars-plan`	academic-paper	创建论文规划/结构
`ars-outline`	academic-paper	仅生成大纲
`ars-abstract`	academic-paper	撰写摘要
`ars-lit-review`	academic-paper	构建文献综述
`ars-citation-check`	academic-paper	验证引用格式
`ars-disclosure`	academic-paper	生成AI使用声明
`ars-format-convert`	academic-paper	格式转换
`ars-revision-coach`	academic-paper	获取修订指导
`ars-revision`	academic-paper	执行修订
`ars-full`	academic-pipeline	运行完整流程管线

Using Aliases

使用别名

Either prefix style works:

text

Use $academic-research-suite: ars-plan my paper on AI governance

Or if your client supports it:

text

/ars-plan my paper on AI governance

两种前缀方式均可：

text

使用$academic-research-suite: ars-plan 我的人工智能治理主题论文

或者如果你的客户端支持：

text

/ars-plan 我的人工智能治理主题论文

Workflow Examples

工作流示例

Deep Research: Socratic Question Refinement

深度研究：苏格拉底式问题细化

When you have a broad topic but no clear research question:

text

Use $academic-research-suite.

I want to write about AI adoption in higher education quality assurance.
I don't have a clear research question yet.
Use Socratic dialogue to help me narrow the question first.

Expected: ARS asks narrowing questions before producing an outline.

当你有宽泛主题但无明确研究问题时：

text

使用$academic-research-suite。

我想写关于人工智能在高等教育质量保障中的应用，但还没有明确的研究问题。请先用苏格拉底式对话帮我缩小问题范围。

预期结果：ARS会先提出细化问题，再生成大纲。

Academic Paper: From Notes to Draft

学术论文：从笔记到草稿

text

Use $academic-research-suite.

Task: Turn these research notes into an IMRaD paper.
Materials: [attach notes.md, data_summary.csv]
Target: 6000-8000 words, APA 7, submit to Higher Education Research
Output: Full outline with section word counts, then draft intro

text

使用$academic-research-suite。

任务：将这些研究笔记转换成IMRaD格式的论文。
资料：[附加notes.md, data_summary.csv]
目标：6000-8000字、APA 7格式、投稿至《高等教育研究》
输出：带章节字数的完整大纲，然后撰写引言草稿

Paper Review: Simulated Peer Review

论文评审：模拟同行评审

text

Use $academic-research-suite to review this manuscript.

Mode: full review
Focus: methodology, contribution, citation integrity, desk-reject risks
Output: reviewer reports + editorial decision letter

[attach manuscript.pdf or manuscript.md]

text

使用$academic-research-suite评审这份稿件。

模式：全面评审
重点：方法论、研究贡献、引用完整性、 desk-reject风险
输出：评审报告 + 编辑决策函

[附加manuscript.pdf或manuscript.md]

Academic Pipeline: Staged Execution

学术流程管线：分阶段执行

For checkpoint-based workflow:

text

Use $academic-research-suite to start an academic-pipeline run.

Begin with Stage 0 intake and stop after producing the pipeline dashboard.
Wait for my approval before Stage 1.

基于检查点的工作流：

text

使用$academic-research-suite启动academic-pipeline运行。

从Stage 0开始，生成流程管线仪表盘后停止。获得我的批准后再进入Stage 1。

Experiment Agent: Reproducible Study Design

实验Agent：可复现研究设计

text

Use $academic-research-suite experiment-agent.

Plan a code experiment comparing three ML models on education dataset.
Requirements: reproducible, statistical rigor, version control, artifact storage
Output: experiment protocol + reproducibility checklist

text

使用$academic-research-suite experiment-agent。

规划一个对比三种ML模型在教育数据集上表现的代码实验。
要求：可复现、统计严谨、版本控制、成果存储
输出：实验方案 + 可复现性检查清单

Configuration

配置

Environment Variables

环境变量

For cross-model verification (optional):

bash

export ARS_CROSS_MODEL=claude-opus-4.7
export ANTHROPIC_API_KEY=your_api_key_here

Without these, ARS runs entirely within Codex/OpenAI. Cross-model review uses Anthropic API when explicitly requested.

用于跨模型验证（可选）：

bash

export ARS_CROSS_MODEL=claude-opus-4.7
export ANTHROPIC_API_KEY=your_api_key_here

如果不设置这些变量，ARS将完全在Codex/OpenAI环境中运行。跨模型评审会在明确请求时调用Anthropic API。

Material Passport

资料护照

ARS tracks research artifacts through "Material Passports" - metadata files that follow:

json

{
  "artifact_id": "paper_v1_outline",
  "created": "2026-05-17T10:30:00Z",
  "workflow": "academic-paper",
  "stage": "outline",
  "integrity_checks": ["citation_format", "structure"],
  "sources": ["source1.pdf", "source2.pdf"],
  "status": "approved"
}

Reset Material Passport by starting a new Codex conversation.

ARS通过“资料护照（Material Passports）”跟踪研究成果，这是一种遵循以下格式的元数据文件：

json

{
  "artifact_id": "paper_v1_outline",
  "created": "2026-05-17T10:30:00Z",
  "workflow": "academic-paper",
  "stage": "outline",
  "integrity_checks": ["citation_format", "structure"],
  "sources": ["source1.pdf", "source2.pdf"],
  "status": "approved"
}

开启新的Codex对话即可重置资料护照。

Working with Citations

引用处理

Citation Check

引用检查

text

Use $academic-research-suite: ars-citation-check

[paste paper text with citations]

Verify all citations are formatted correctly in APA 7.
Flag any unverifiable sources.

Expected output:

Citation format compliance report
Unverifiable citations flagged
Suggested corrections

text

使用$academic-research-suite: ars-citation-check

[粘贴带引用的论文文本]

验证所有引用是否符合APA 7格式规范，标记无法验证的来源。

预期输出：

引用格式合规性报告
标记无法验证的引用
建议修正方案

Literature Review Mode

文献综述模式

text

Use $academic-research-suite: ars-lit-review

Topic: AI ethics in higher education
Scope: 2020-2026, peer-reviewed only
Output: thematic synthesis with citation matrix

text

使用$academic-research-suite: ars-lit-review

主题：高等教育中的人工智能伦理
范围：2020-2026年、仅同行评审文献
输出：主题性综述及引用矩阵

Paper Formatting and Conversion

论文格式与转换

Format Conversion

格式转换

text

Use $academic-research-suite: ars-format-convert

Input: [attach paper.md]
From: Markdown
To: LaTeX (IEEE conference template)
Preserve: citations, figures, tables

text

使用$academic-research-suite: ars-format-convert

输入：[附加paper.md]
源格式：Markdown
目标格式：LaTeX（IEEE会议模板）
保留内容：引用、图表、表格

AI Disclosure Statement

AI使用声明

text

Use $academic-research-suite: ars-disclosure

Paper stage: final draft before submission
AI tools used: Codex for literature search, outline generation, citation formatting
Human contribution: research design, analysis, interpretation, revision
Output: journal-ready disclosure statement

text

使用$academic-research-suite: ars-disclosure

论文阶段：提交前终稿
使用的AI工具：Codex（用于文献检索、大纲生成、引用格式规范）
人工贡献：研究设计、分析、解读、修订
输出：符合期刊要求的使用声明

Revision Workflow

修订工作流

Revision Coach

修订指导

For guidance without executing changes:

text

Use $academic-research-suite: ars-revision-coach

[attach draft.md and reviewer_comments.txt]

Analyze reviewer feedback and suggest revision strategy.
Prioritize major vs minor revisions.
Do not rewrite yet - provide plan only.

如需指导但不执行修改：

text

使用$academic-research-suite: ars-revision-coach

[附加draft.md和reviewer_comments.txt]

分析评审反馈并提出修订策略，区分主要修订与次要修订优先级。暂不重写，仅提供方案。

Execute Revisions

执行修订

text

Use $academic-research-suite: ars-revision

[attach draft.md and reviewer_comments.txt]

Execute revisions based on Reviewer 2 methodology concerns.
Track changes: show original -> revised for each section.
Update Material Passport with revision metadata.

text

使用$academic-research-suite: ars-revision

[附加draft.md和reviewer_comments.txt]

针对评审人2提出的方法论问题执行修订。跟踪变更：展示每个章节的原文→修订版。更新资料护照中的修订元数据。

Troubleshooting

故障排除

Skill Not Found

Skill未找到

/skills

doesn't show

academic-research-suite

Verify installation path:

ls -la "$HOME/.codex/skills/academic-research-suite"

Reinstall using update command above
Open a new Codex conversation (old sessions cache skills)

如果

/skills

未显示

academic-research-suite

：

验证安装路径：

ls -la "$HOME/.codex/skills/academic-research-suite"

使用上述更新命令重新安装
开启新的Codex对话（旧会话会缓存Skill）

Multiple ARS Skills Showing

显示多个ARS Skill

If you see

academic-paper

deep-research

, etc. as separate skills:

bash

undefined

如果看到

academic-paper

、

deep-research

等作为单独Skill：

bash

undefined

Remove all ARS skills

删除所有ARS Skill

rm -rf "$HOME/.codex/skills/academic-"* rm -rf "$HOME/.codex/skills/deep-research" rm -rf "$HOME/.codex/skills/experiment-agent"

Reinstall single suite

重新安装整合版

python "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py"
--repo Imbad0202/academic-research-skills-codex
--ref main
--path skills/academic-research-suite
--method git

undefined

python "$HOME/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py"
--repo Imbad0202/academic-research-skills-codex
--ref main
--path skills/academic-research-suite
--method git

undefined

Wrong Workflow Selected

路由到错误工作流

If ARS routes to the wrong workflow, be more explicit:

text

Use $academic-research-suite deep-research workflow in socratic mode.

[your request]

Or use specific alias:

text

Use $academic-research-suite: ars-outline

[your request]

如果ARS路由到错误工作流，请更明确地指定：

text

使用$academic-research-suite deep-research工作流的苏格拉底模式。

[你的请求]

或使用特定别名：

text

使用$academic-research-suite: ars-outline

[你的请求]

Citation Verification Fails

引用验证失败

When citations cannot be verified:

ARS should mark them as unverified rather than inventing support
If verification is critical, provide DOIs or URLs for sources
Use
```
ars-citation-check
```
mode with source files attached

当引用无法验证时：

ARS会将其标记为未验证，而非虚构支撑资料
如果验证至关重要，请提供来源的DOI或URL
使用
```
ars-citation-check
```
模式并附加源文件

Codex Warnings

Codex警告

These warnings are non-blocking:

```
[features].codex_hooks is deprecated
```
- update Codex config when convenient
```
hooks need review before they can run
```
- ARS Codex doesn't require hooks for normal use

以下警告不影响使用：

```
[features].codex_hooks is deprecated
```
- 方便时更新Codex配置即可
```
hooks need review before they can run
```
- ARS Codex正常使用无需hooks

Advanced Patterns

高级模式

Staged Pipeline with Checkpoints

带检查点的分阶段流程管线

text

Use $academic-research-suite academic-pipeline workflow.

Stage 0: Intake and dashboard
STOP and show dashboard for approval

[After approval]

Stage 1: Research question refinement via Socratic dialogue
STOP and show refined question

[Continue stage by stage]

text

使用$academic-research-suite academic-pipeline工作流。

Stage 0：接收任务并生成仪表盘
停止并展示仪表盘待批准

[批准后]

Stage 1：通过苏格拉底式对话细化研究问题
停止并展示细化后的问题

[逐阶段继续]

Parallel Literature Search

并行文献检索

text

Use $academic-research-suite deep-research workflow.

Search strategy: parallel tracks
Track 1: Scopus, Web of Science - quantitative studies
Track 2: Google Scholar - grey literature, policy docs
Track 3: Specialized databases - ERIC, ProQuest Education

Synthesize results into single literature matrix.

text

使用$academic-research-suite deep-research工作流。

检索策略：并行追踪
追踪1：Scopus、Web of Science - 定量研究
追踪2：Google Scholar - 灰色文献、政策文档
追踪3：专业数据库 - ERIC、ProQuest Education

将结果整合为单一文献矩阵。

Multi-Pass Review

多轮评审

text

Use $academic-research-suite academic-paper-reviewer workflow.

Pass 1: Structure and contribution (desk-reject check)
[Wait for my review]

Pass 2: Methodology rigor
[Wait for my review]

Pass 3: Citation integrity and ethics
[Final decision]

text

使用$academic-research-suite academic-paper-reviewer工作流。

第一轮：结构与研究贡献（desk-reject检查）
[等待我的评审]

第二轮：方法论严谨性
[等待我的评审]

第三轮：引用完整性与伦理
[最终决策]

Integration with Research Tools

与研究工具集成

With Reference Managers

与参考文献管理器集成

text

Use $academic-research-suite: ars-citation-check

Citation library: Zotero export attached (bibtex format)
Paper: [attach draft.md]

Cross-check all in-text citations against Zotero library.
Flag missing entries and formatting errors.

text

使用$academic-research-suite: ars-citation-check

引用库：附加Zotero导出文件（bibtex格式）
论文：[附加draft.md]

交叉检查所有文内引用与Zotero库是否匹配，标记缺失条目和格式错误。

With Data Analysis Code

与数据分析代码集成

text

Use $academic-research-suite experiment-agent workflow.

Existing analysis: [attach analysis.py, results.csv]
Task: Create reproducible experiment protocol around this analysis
Output: protocol.md, requirements.txt, reproduction checklist

text

使用$academic-research-suite experiment-agent工作流。

现有分析：[附加analysis.py, results.csv]
任务：围绕该分析创建可复现的实验方案
输出：protocol.md、requirements.txt、复现检查清单

With Institutional Templates

与机构模板集成

text

Use $academic-research-suite: ars-format-convert

Input: [attach paper.md]
Template: University PhD thesis LaTeX template [attach template.tex]
Preserve: custom environments for theorems, university citation style

text

使用$academic-research-suite: ars-format-convert

输入：[附加paper.md]
模板：大学博士论文LaTeX模板[附加template.tex]
保留内容：定理自定义环境、大学引用格式

CLI Smoke Test

CLI冒烟测试

Test routing without full execution:

bash

codex exec --ephemeral --sandbox read-only \
  -C /path/to/academic-research-skills-codex \
  'Use $academic-research-suite. Router smoke test only. Classify workflow and mode for: I want to write a paper on AI adoption but do not have a research question yet.'

Expected: Route to

deep-research

socratic

mode.

无需完整执行即可测试路由功能：

bash

codex exec --ephemeral --sandbox read-only \
  -C /path/to/academic-research-skills-codex \
  'Use $academic-research-suite. Router smoke test only. Classify workflow and mode for: I want to write a paper on AI adoption but do not have a research question yet.'

预期结果：路由到

deep-research

的

socratic

模式。

Key Differences from Claude Code Version

与Claude Code版本的主要差异

This Codex package differs from the original Claude Code ARS:

Feature	Claude Code	Codex Package
Installation	Plugin marketplace	Git-based skill installer
Commands	Native `/ars-*` slash commands	Emulated aliases via router
Agent teams	Automatic background agents	Inline unless explicitly delegated
Hooks	SessionStart, SubagentStop	Vendored for traceability only
Cross-model review	GPT/Gemini secondary dispatch	Anthropic Claude API (explicit config)
Updates	Marketplace auto-update	Manual reinstall

该Codex包与原版Claude Code ARS的差异：

功能	Claude Code	Codex Package
安装方式	插件市场	基于git的Skill安装器
命令	原生 `/ars-*` 斜杠命令	通过路由模拟别名
Agent团队	自动后台Agent	内置模式，除非明确委托
Hooks	SessionStart、SubagentStop	仅用于可追溯性的内置实现
跨模型评审	GPT/Gemini二次调度	Anthropic Claude API（需显式配置）
更新方式	市场自动更新	手动重新安装

Version Information

版本信息

Codex Package Version: v0.1.6

Vendored ARS Commit:

1d0c8625207c9cd8fc46132b1ef930f2cc012236

License: CC BY-NC 4.0 (non-commercial use)
Original Repository: https://github.com/Imbad0202/academic-research-skills

Codex包版本: v0.1.6

内置ARS提交哈希:

1d0c8625207c9cd8fc46132b1ef930f2cc012236

许可证: CC BY-NC 4.0（非商业用途）
原始仓库: https://github.com/Imbad0202/academic-research-skills

Additional Resources

额外资源

Codex Setup Guide:

skills/academic-research-suite/ars/docs/SETUP.md

Architecture Details:

skills/academic-research-suite/ars/docs/ARCHITECTURE.md

Claude Code Version: https://github.com/Imbad0202/academic-research-skills

For issues specific to the Codex packaging, open an issue at the Codex package repository. For ARS workflow issues, consult the original Claude Code repository.

Codex设置指南:

skills/academic-research-suite/ars/docs/SETUP.md

架构细节:

skills/academic-research-suite/ars/docs/ARCHITECTURE.md

Claude Code版本: https://github.com/Imbad0202/academic-research-skills

针对Codex打包相关问题，请在Codex包仓库提交issue。针对ARS工作流问题，请参考原版Claude Code仓库。