Academic Paper Writer plugin
Eight skills draft a CS, AI or ML paper section by section and halt any section that lacks supporting evidence.
- 116 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- Literature queries go to external search services, and optional Python scripts read and convert your PDF files.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/academic-paper-writerDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- Literature queries go to external search services, and optional Python scripts read and convert your PDF files.
This is third-party code. Review the repository files before installing.
What it does
A skill collection that builds a computer science, AI or machine learning paper as a chain of verifiable steps rather than one prompt. The `academic-paper-writer` orchestrator splits the paper into sections and calls sub-skills for literature search and verification (`academic-citation`), experiment checks (`academic-experiments`), self-review (`academic-reviser`), prose polishing (`academic-polishing`), Python figures (`academic-figure`), venue requirement research (`academic-venue-research`) and LaTeX layout (`academic-latex-layout`). Every section passes hard gates: when evidence is missing the section is blocked or weakened instead of being padded with guesses. Documentation and skill descriptions are written in Chinese.
Who it is for. Graduate students and researchers writing a CS, AI or ML paper who want a submission-ready draft without invented citations or results.
Good fit when
- The experiments are done but a section draft refuses to come together.
- Citations in the text must be checked against real sources.
- A specific conference's submission requirements need to be summarized before submitting.
- Ablation figures should be generated from result tables.
- A reviewer flagged overly strong claims and the wording needs to be softened.
Not a fit when
- The paper is outside CS, AI and ML, which the skills are tuned for.
- No experiment results exist yet but the section is wanted in advance.
- The whole text is expected from a single request with no step-by-step checks.
Example request
Run the Related Work section through the check loop: find sources, verify each citation and flag claims without support.Limitations
Documentation and trigger phrases are written in Chinese and no English process description exists. The skills target CS, AI and ML and drive each section strictly by evidence, so steps stop when experiment data is missing. The author calls the project work in progress: figures, prose polishing, literature search and citation management are still being refined. Optional Python scripts, such as PDF conversion, are installed separately, and literature search and verification send requests to outside services. A human must verify the final text.
How to disable. Remove the plugin with `/plugin` in Claude Code, or delete `~/.agents/skills/academic-paper-writer` in Codex. Drafts and figures created in working directories stay with your files and are removed by hand.
FAQ
How do I install it in Claude Code?
Add the marketplace with `/plugin marketplace add joshua-zyy/academic-paper-writer` and run `/plugin install academic-paper-writer@academic-paper-writer`. The commands `/academic-paper-writer`, `/academic-citation` and the rest then appear.
Does it work with Codex?
Yes. Clone the repository into `~/.agents/skills/academic-paper-writer` and Codex picks up the skills from the `skills/` directory.
Can I call a single skill on its own?
Yes, sub-skills run independently: `/academic-citation` only finds and verifies citations and `/academic-latex-layout` repairs figure and table placement.
What happens without experiment data?
The skill blocks the section or weakens the wording instead of inventing conclusions. Prepare result tables and run logs first.
Are extra packages needed?
Not for core use: the project needs no separate Python or Node.js packages. Optional Python scripts such as `citation_audit.py` are installed from the dependency table in the README.
Discussion
No questions or reviews yet.
Related
PluginsA plugin of two skills for a research paper: planning, drafting and revising sections, plus a four-pass manuscript review
The paper-spine skill takes a topic, materials and data through a scientific paper: literature, text, figures, review and Word, LaTeX and PDF files
A skill for writing and revising ML, CV and NLP papers: section structure, paragraph flow and reviewer-style self-review
An orchestrator skill that takes empirical social science work from idea or data to a reproducible manuscript with quality gates.
42 skills for the whole research paper path: from discovery and drafting to citation checks, submission, rebuttal and publication
A skill set for academic work: paper review, pre-analysis plan check, grant proposal review, code audit and slide decks.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Academic Paper Writer (this card) | no | 116 | |
| paper-writing-skill | no | 249 | a single skill for writing a paper; this one has eight sub-skills with hard evidence gates |
| Academic Research Skills | no | 56,682 | a research toolkit; this one is a section-by-section chain checking citations and experiments |
README in short
The project follows a chain: evidence audit, literature search, experiment check, drafting, quality gate. When data is lacking a stage is blocked or downgraded.