#8484th of 455 in Skills, plugins and promptsFor science, health and research, research and papers
academic-research-skills-codex
Codex skill suite for academic research, paper drafting, peer review and screening
- Stars
- 14.5k
- License
- custom license
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
95 on 21 Apr 202614,471 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
ARS-Codex packages the Academic Research Skills workflow as a single Codex skill, `academic-research-suite`, installable as a Codex plugin or directly from the repo. A router sends requests to six workflows: deep-research, academic-paper, academic-paper-reviewer, academic-pipeline, sr-screener and experiment-agent. It also emulates the Claude Code `/ars-*` commands as plain aliases. It vendors upstream ARS v3.24.2.
Who it is for: Researchers using Codex for literature review, papers and peer review
Strengths
- Single skill entry routes to six workflows, including systematic-review screening with eight modes
- Installs via `codex plugin add` or a skill-installer script from the repo path
- Maps Claude-style `/ars-*` commands to plain aliases such as `ars-plan` and `ars-reviewer`
- Includes quality-gate script and smoke tests to verify routing and install
Weaknesses
- License is CC BY-NC 4.0, so commercial use is not permitted
- Claude hooks and slash commands are not registered in Codex; kept as reference only
- Reviewer confirmation stop is prompt-level; README says Codex adherence is unmeasured
- Screening accuracy and model settings are unmeasured; output-language pack supports only zh-tw-en
What it needs
- no GPU
- Needs Codex CLI or Codex Desktop, Python 3
- Models: gpt-6-astra (project default in .codex/config.toml)
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |