Skip to content

Research Paper Writing

Makes the agent review and rewrite ML/CV/NLP paper sections for clarity, flow, and claim-evidence alignment.

Stars
8,005
Licence
MIT
Files
15 files

What it does

Once installed, the agent follows a structured playbook for academic papers: it outlines the paper's story first, rewrites each paragraph around one message, checks that Abstract and Introduction claims are backed by experimental evidence, and runs a skeptical 'reviewer' self-check before submission. It returns a section outline, revised paragraphs, a self-review checklist, and a claim-evidence map. The skill is mainly a set of written guidelines and examples rather than software.

Great for

  • Researchers and students preparing ML, computer vision, or NLP papers for conference submission
  • Authors who want a reviewer-style critique of an Abstract or Introduction before sending it out
  • Anyone revising a draft to make its contributions and paragraph flow clearer

Skip it if

  • Fields outside ML/CV/NLP-style papers, since the guidance is written for that style (the description targets these fields)
  • Ghostwriting or generating claims without real experimental results; the skill tells the agent to weaken or remove unsupported claims, but it cannot verify your data
  • Replacing your own review of the science: it improves presentation and does not check whether the research is correct

Try asking

  • “Rewrite my Abstract so the contribution is clear to a skeptical reviewer. Here is my draft: ...”
  • “Check whether each paragraph in my Introduction has one message and flows into the next.”
  • “Give me a claim-evidence map for the claims in my Conclusion and mark which ones need more evidence.”
  • “Do a five-dimension self-review of my Method section before I submit.”
Step-by-step guide: how to use Research Paper WritingInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    research-paper-writing.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip research-paper-writing.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip research-paper-writing.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Paste your current section text and state the paper's main contribution so the agent can judge the story against it.
  • Ask for one section at a time; the skill is designed to load only the guide for the section being edited.
  • Treat the output as a reviewer simulation and verify every flagged or weakened claim against your own results.

What's inside

  • agents/openai.yaml
  • references/abstract.md
  • references/conclusion.md
  • references/does-my-writing-flow-source.md
  • references/examples/abstract-examples.md
  • references/examples/abstract/template-a.md
  • references/examples/abstract/template-b.md
  • references/examples/abstract/template-c.md
  • references/examples/index.md
  • references/examples/introduction-examples.md
  • references/examples/introduction/novel-task-challenge-decomposition.md
  • references/examples/introduction/pipeline-not-recommended-abstract-only.md
  • references/examples/introduction/pipeline-version-1-one-contribution-multi-advantages.md
  • references/examples/introduction/pipeline-version-2-two-contributions.md
  • SKILL.md

Redistributed unmodified from Master-cai/Research-Paper-Writing-Skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.