MCPInstall

academic-research-skills-codex

AI-assisted academic research workflows for literature review, paper writing, peer review, and research pipelines

Installs
437
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/codex-skills --skill academic-research-skills-codex
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads academic-research-skills-codex automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Academic Research Skills for Codex

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.

What It Does

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

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

Installation

Install using the Codex skill installer with git method:

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

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.

Verify Installation

/skills

You should see one entry: academic-research-suite. You should NOT see separate entries for academic-paper, deep-research, etc.

Core Usage Patterns

Basic Invocation

Use $academic-research-suite followed by your research task:

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.

Workflow Selection

WorkflowWhen to UseExample Trigger
deep-researchNeed research question refinement, literature review, fact-checking"conduct a systematic review on..."
academic-paperNeed paper outline, drafting, citations, revision"write a research paper about..."
academic-paper-reviewerNeed manuscript review, peer review simulation"review this research manuscript..."
academic-pipelineNeed full research-to-publication workflow"run end-to-end pipeline from topic to paper"
experiment-agentNeed code experiment design, study protocols"plan a reproducible code experiment..."

Structured Request Pattern

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

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

Command Aliases

Codex emulates Claude Code /ars-* commands as aliases:

AliasWorkflowPurpose
ars-planacademic-paperCreate paper plan/structure
ars-outlineacademic-paperGenerate outline only
ars-abstractacademic-paperDraft abstract
ars-lit-reviewacademic-paperBuild literature review
ars-citation-checkacademic-paperVerify citations
ars-disclosureacademic-paperGenerate AI disclosure statement
ars-format-convertacademic-paperConvert between formats
ars-revision-coachacademic-paperGet revision guidance
ars-revisionacademic-paperExecute revisions
ars-fullacademic-pipelineRun full pipeline

Using Aliases

Either prefix style works:

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

Or if your client supports it:

/ars-plan my paper on AI governance

Workflow Examples

Deep Research: Socratic Question Refinement

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

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.

Academic Paper: From Notes to Draft

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

Paper Review: Simulated Peer Review

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]

Academic Pipeline: Staged Execution

For checkpoint-based workflow:

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.

Experiment Agent: Reproducible Study Design

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

Configuration

Environment Variables

For cross-model verification (optional):

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.

Material Passport

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

{
  "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.

Working with Citations

Citation Check

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

Literature Review Mode

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

Paper Formatting and Conversion

Format Conversion

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

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

AI Disclosure Statement

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

Revision Workflow

Revision Coach

For guidance without executing changes:

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.

Execute Revisions

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.

Troubleshooting

Skill Not Found

If /skills doesn't show academic-research-suite:

  1. Verify installation path: ls -la "$HOME/.codex/skills/academic-research-suite"
  2. Reinstall using update command above
  3. Open a new Codex conversation (old sessions cache skills)

Multiple ARS Skills Showing

If you see academic-paper, deep-research, etc. as separate skills:

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

# Reinstall single 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

Wrong Workflow Selected

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

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

[your request]

Or use specific alias:

Use $academic-research-suite: ars-outline

[your request]

Citation Verification Fails

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

Codex Warnings

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

Advanced Patterns

Staged Pipeline with Checkpoints

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]

Parallel Literature Search

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.

Multi-Pass Review

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]

Integration with Research Tools

With Reference Managers

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.

With Data Analysis Code

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

With Institutional Templates

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

CLI Smoke Test

Test routing without full execution:

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.

Key Differences from Claude Code Version

This Codex package differs from the original Claude Code ARS:

FeatureClaude CodeCodex Package
InstallationPlugin marketplaceGit-based skill installer
CommandsNative /ars-* slash commandsEmulated aliases via router
Agent teamsAutomatic background agentsInline unless explicitly delegated
HooksSessionStart, SubagentStopVendored for traceability only
Cross-model reviewGPT/Gemini secondary dispatchAnthropic Claude API (explicit config)
UpdatesMarketplace auto-updateManual reinstall

Version Information

Additional Resources

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.

FAQ

What does the academic-research-skills-codex skill do?

AI-assisted academic research workflows for literature review, paper writing, peer review, and research pipelines

How do I install academic-research-skills-codex?

Run npx skills add https://github.com/reason-machines/codex-skills --skill academic-research-skills-codex in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/academic-research-skills-codex/ (personal) or .claude/skills/academic-research-skills-codex/ (project).

Which AI agents can use academic-research-skills-codex?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is academic-research-skills-codex safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains academic-research-skills-codex?

It is published by reason-machines in reason-machines/codex-skills. It has 437 recorded installs.

More from reason-machines/codex-skills

View all →

codexplusplus-launcher

reason-machines/codex-skills

Enhanced launcher for Codex App that unlocks plugins, enables session deletion, exports conversations, and syncs provider sessions via CDP injection

Security286 installs

awesome-codex-subagents

reason-machines/codex-skills

A curated collection of 136+ specialized Codex subagents for development tasks across 10 categories

AI & Agents273 installs

codex-plugin-claude-code

reason-machines/codex-skills

Open the skill to read its SKILL.md instructions.

273 installs

oh-my-codex-workflow

reason-machines/codex-skills

Expert in Oh My Codex (OMX) - workflow layer for OpenAI Codex CLI with agents, skills, and team coordination

codexbar-menubar-ai-usage-tracker

reason-machines/codex-skills

Monitor AI coding assistant usage limits and token resets in the macOS menu bar with CodexBar

271 installs

awesome-codex-skills-curator

reason-machines/codex-skills

Open the skill to read its SKILL.md instructions.

270 installs

Popular productivity & automation skills

View category →

agent-browser

vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

OfficialProductivity & Automation1.3M installs

lark-doc

open.feishu.cn

飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由;/page/ 是妙搭应用,非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive;随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。

lark-base

open.feishu.cn

飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps;文件导入/导出转 lark-drive,认证/授权转 lark-shared。

lark-drive

open.feishu.cn

飞书云空间(云盘/云存储):管理 Drive 文件和文件夹,包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签(secure labels)和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题,或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用;doubao.com 云空间 URL/token 也按资源路径和 token 路由,不回退 WebFetch。不负责:文档内容编辑(走 lark-doc)、表格/Base 表内数据操作(走 lark-sheets/lark-base)、知识空间节点/成员管理(走 lark-wiki)、原生 Markdown 文件读写/patch/diff(走 lark-markdown)。

lark-shared

open.feishu.cn

Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.

lark-im

open.feishu.cn

飞书即时通讯:收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片(Interactive Card)、监听卡片按钮回调(card.action.trigger)。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶(添加/移除/查询置顶会话)、管理标签数据、处理卡片回调时使用。