Skip to content
SkillModel-led15,940 tokens in use

Academic Paper

A 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, and helps you answer reviewer comments, in eleven modes.

57,881 stars on the repository Custom / UnknownImbad0202/academic-research-skills · academic-paper
/plugin marketplace add Imbad0202/academic-research-skills /plugin install academic-research-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Academic Paper costs

383tokens idle
15,940tokens in use
75,669tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter4/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size2/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • File that was not read−15

    a file the skill ships that was not read, so what it does is unknown

    templates/latex_article_template.tex

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community60
  • Maturity32
  • Momentum40

Academic Paper covers the writing side of scholarship. A configuration interview sets paper type, discipline and citation format; agents then build the literature strategy, structure, argument, draft, bilingual abstract and a peer-review pass.

Eleven modes also handle revision after reviewer comments, rebuttal audits, citation checks, AI-use disclosure and format conversion. Output goes to Markdown, LaTeX, DOCX through Pandoc, or PDF, in APA, Chicago, MLA, IEEE or Vancouver style.

What You Get

  • A paper outline, argument chains and a section-by-section draft in your citation style
  • A bilingual abstract and a five-perspective peer-review assessment of the draft
  • A revision roadmap and rebuttal audit when you bring reviewer comments
  • Formatted output as Markdown, LaTeX, DOCX through Pandoc or PDF

Common Use Cases

  • Writing a journal article or thesis chapter from a topic
  • Parsing reviewer comments and deciding what to accept or push back on
  • Auditing a conference rebuttal or grant panel response before sending it
  • Checking references and drafting an AI-use disclosure for submission

What Makes It Unique

It covers the revision stage as well as drafting: a revision coach turns reviewer comments into a roadmap, and a rebuttal audit checks your reply draft before you send it. Iron-rule markers hold the pipeline to fixed steps, and Style Calibration adapts drafts to your own writing. It works with the sibling skills for research, review and full pipelines, and it keeps pasted reviewer text and fetched pages separate from instructions.

Under The Hood

The skill loads a long SKILL.md that routes a request to one of eleven modes and hands work to agent files, each with a narrow role. Agents search for literature and check citations, which means reaching external bibliographic sources, and they write drafts, abstracts, reports and converted files into your project. Format conversion calls local tools such as Pandoc, and optionally a LaTeX engine, through the shell. Pasted reviewer comments and fetched pages are treated as data, so instructions inside them are reported and not followed.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers