Research Paper Writing Skills for AI Agents

Research paper writing skills help an agent work on the structured argument a paper makes, from title through references. The sub-topics here map to the parts of that argument: framing why the paper exists in the first screen of reading, positioning related work as the conversation the paper joins, describing how evidence was produced in methods, separating what was observed from spin in results, working out what it means and what would change your mind in discussion, and handling submission, the social process of getting the paper in front of peers. Many fields use IMRaD as the default spine. Read the ranked list by sub-topic: if you are stuck on one section, start with the skill that names that section. Otherwise start at the top and work down until a skill's scope matches the draft you have.

8 to start with24 top options

Start with these.

A research paper is a structured argument: title to references, with IMRaD as the default spine in many fields.

These are the closest matches for this work. Start with the first one and open it to install.

Why this paper exists, in the first screen of reading.The conversation this paper is joining.How the evidence was produced.What was observed, cleanly separated from spin.What it means, and what would change your mind.The social process of getting the paper in front of peers.

24 top options

  1. Rank 04
    Direct

    nature-polishing

    Polishes, translates, or tightens existing academic prose while preserving facts and evidence boundaries, with Nature-style section and journal routing. Built for manuscript language work.

    • Framing
    • Methods
    • Results
    15,558 · popularity
    View Agent Skill
  2. Rank 05
    Direct

    academic-pipeline

    Orchestrates the full academic pipeline from research through writing, integrity checks, review, revision, and finalization across a 10-stage workflow. Built for end-to-end research paper production.

    • Results
    • Submission
    6,661 · popularity
    View Agent Skill
  3. Rank 06
    Direct

    latex-paper-en

    English LaTeX assistant for existing .tex journal or conference papers: compile repair, venue formatting, bibliography checks, section writing, related work, tables, pseudocode, and de-AI polish. Built for academic paper work.

    • Framing
    • Related work
    • Results
    5,649 · popularity
    View Agent Skill
  4. Rank 07
    Direct

    firecrawl-research-papers

    Finds and synthesizes research papers, whitepapers, and academic sources via Firecrawl's paper index with semantic search, related-paper expansion, and in-body verification. Built for literature reviews and sourced synthesis.

    • Framing
    • Related work
    • Results
    33,101 · popularity
    View Agent Skill
  5. Rank 08
    Direct

    academic-search

    Helps formulate academic search queries, recommends databases, analyzes abstracts, and structures literature reviews. Built for the related-work and literature-search facets of paper writing.

    • Framing
    • Related work
    5,583 · popularity
    View Agent Skill
Explore 16 more Agent Skills
  1. Rank 09
    Direct

    nature-academic-search

    Searches literature across sources, verifies and manages citations, builds MeSH strategies, and audits citation impact. Built for the related-work and citation facets of paper writing.

    • Related work
    • Results
    • Discussion
    13,446 · popularity
    View Agent Skill
  2. Rank 10
    Possible

    firecrawl

    Notable

    Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse. For papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.

    • Related work
    View Agent Skill
  3. Rank 11
    Possible

    notion-research-documentation

    Official

    Research across Notion and synthesize into structured documentation; use when gathering info from multiple Notion sources to produce briefs, comparisons, or reports with citations.

    • Results
    View Agent Skill
  4. Rank 12
    Possible

    academic-paper-reviewer

    Simulates a multi-perspective peer review panel with journal-fit, methodology, domain, and devil's-advocate roles plus an editorial decision. Adjacent to paper writing for pre-submission review.

    • Submission
    9,151 · popularity
    View Agent Skill
  5. Rank 13
    Possible

    paper-audit

    Reviewer-style audit and submission gate for .tex, .typ, or .pdf papers with issue bundles, revision roadmaps, and re-audits. Adjacent to paper writing for pre-submission review.

    • Framing
    • Related work
    • Submission

    Needs (stated): Python

    3,219 · popularity
    View Agent Skill
  6. Rank 14
    Possible

    academic-paper-review

    Produces structured peer-review-quality analyses of academic papers covering summary, strengths, weaknesses, methodology, and literature positioning. Adjacent to paper writing for review and self-assessment.

    • Framing
    • Related work
    • Results
    2,589 · popularity
    View Agent Skill
  7. Rank 15
    Possible

    scholar-evaluation

    Evaluates academic work against a reproducible rubric covering problem, literature, methodology, evidence, analysis, and citations. Adjacent to paper writing for self-assessment and revision.

    • Related work
    5,761 · popularity
    View Agent Skill
  8. Rank 16
    Possible

    latex-thesis-zh

    Chinese LaTeX thesis assistant for existing .tex theses: compile diagnosis, GB/T 7714, structure, formula layout, terminology consistency, and blind-review anonymization. Adjacent to paper writing for thesis work.

    4,033 · popularity
    View Agent Skill
  9. Rank 17
    Possible

    nature-reader

    Creates source-grounded Chinese-English paper readers with aligned text, figures, tables, and equations. Adjacent to paper writing for close reading of sources.

    • Results
    13,142 · popularity
    View Agent Skill
  10. Rank 18
    Possible

    deep-research

    Notable

    Courses whose content rests on current, external or real-world facts that must be verified against live sources before being taught — recent events, market or policy data, product and version specifics, scientific developments, named cases. Researches the topic first, keeps a claim-to-source ledger, and grounds the outline and every page in what was actually fetched. Use when the request depends on up-to-date or externally checkable facts; not for timeless textbook topics that stand on established knowledge alone.

    • Framing
    • Methods
    • Results
    View Agent Skill
  11. Rank 19
    Possible

    nature-paper2ppt

    Creates Chinese academic PPTX decks from a scientific paper with source figures and speaker notes. Adjacent to paper writing for conference or group-meeting presentations.

    • Methods
    • Results
    14,270 · popularity
    View Agent Skill
  12. Rank 20
    Possible

    ai-research-explore

    Notable

    Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow code-only or run-only exploration, passive repo analysis, verified novelty claims, or implicit experi

    • Related work
    • Methods
    311,248 · popularity
    View Agent Skill
  13. Rank 21
    Possible

    paper-context-resolver

    Resolves narrow reproduction-critical paper details such as dataset splits, preprocessing, or evaluation protocol from primary sources while recording conflicts. Adjacent to the methods facet of paper writing.

    • Methods
    451,036 · popularity
    View Agent Skill
  14. Rank 22
    Possible

    ai-research-reproduction

    Notable

    Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment se

    • Methods
    • Results
    310,973 · popularity
    View Agent Skill
  15. Rank 23
    Possible

    nature-paper-to-patent

    Turns research papers into evidence-grounded Chinese invention patent drafts and technical disclosures. Adjacent to paper writing but a different deliverable.

    • Framing
    • Results
    10,969 · popularity
    View Agent Skill
  16. Rank 24
    Possible

    doc-coauthoring

    Official

    Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.

    View Agent Skill
What this topic covers

What this topic covers

Each sub-topic groups Agent Skills for a specific situation.

Framing
Why this paper exists, in the first screen of reading.
Related work
The conversation this paper is joining.
Methods
How the evidence was produced.
Results
What was observed, cleanly separated from spin.
Discussion
What it means, and what would change your mind.
Submission
The social process of getting the paper in front of peers.
Frequently asked questions

Frequently asked questions

What counts as a research paper writing skill here?
Skills that operate on the paper as a structured argument, title to references. That includes work on framing, related work, methods, results, discussion, and submission, with IMRaD as the default spine in many fields.
How is the list ordered?
It is ranked by observed search demand, with direct matches to the topic first and a cap on any single publisher. Use the order as a starting point, then pick by which section of your paper needs work.
Should I pick one skill or several?
The sub-topics are distinct parts of the argument, so a skill scoped to results will not cover framing or submission. Match the skill to the section you are drafting, and use more than one when your draft spans several sections.
Where should I start if my draft is incomplete?
Start with framing, since it establishes why the paper exists in the first screen of reading. From there, move through related work, methods, results, and discussion in the order the argument is read.

How to install an Agent Skill

Start with the first skill on this page. Claude Code reads a SKILL.md once it is in the skills directory:

  • Claude Code — copy the SKILL.md for academic-paper into ~/.claude/skills/academic-paper/ for yourself, or .claude/skills/academic-paper/ to share it with a project.
  • From the registry — run npx skills add imbad0202/academic-research-skills@academic-paper.
  • Or download academic-paper from its source and place that SKILL.md in the directory above.

How to choose Check the source and the skill’s own instructions before you install. Official and Notable describe where a skill comes from.