PluginBench
Skill
Pass
Audit score 90

research-paper-writing

master-cai/research-paper-writing-skills

Improve academic paper writing quality for ML/CV/NLP research with clear structure, flow, and reviewer-facing presentation.

What is research-paper-writing?

A skill for drafting and revising research papers in machine learning, computer vision, and NLP. Use it to strengthen section structure (Abstract, Introduction, Related Work, Method, Experiments, Conclusion), improve paragraph flow, align claims with evidence, and perform self-review before submission.

  • Rewrite sections with one-message-per-paragraph clarity and explicit paragraph roles
  • Check claim-evidence alignment in Abstract and Introduction against experimental results
  • Run reverse outlining to verify logical flow within and across sections
  • Provide section-specific guidance (Abstract, Introduction, Related Work, Method, Experiments, Conclusion)
  • Perform adversarial self-review using a five-dimension checklist (contribution, clarity, experimental strength, evaluation, method soundness)
  • Polish figures, tables, and visual presentation as core content

How to install research-paper-writing

npx skills add https://github.com/master-cai/research-paper-writing-skills --skill research-paper-writing
Claude Code
Cursor
Windsurf
Cline

How to use research-paper-writing

  1. 1.Load the section-specific reference guide (e.g., `references/introduction.md`) for your target section
  2. 2.Build a mini-outline before drafting prose, including motivation, design, and technical advantage
  3. 3.Rewrite paragraph-by-paragraph, stating the paragraph message in the first sentence
  4. 4.Run reverse outlining after each section: map topic sentences to thesis and evidence to topic sentences
  5. 5.Check every major claim in Abstract/Introduction against experimental evidence using the claim-evidence map
  6. 6.Run the full five-dimension self-review checklist from `references/paper-review.md` before finalizing

Use cases

Good for
  • Revising a draft Abstract to ensure all claims are supported by experiments
  • Restructuring an Introduction to improve logical flow and motivation
  • Checking whether a Method section clearly explains design and technical advantages
  • Performing final adversarial review before submission to catch rejection risks
  • Improving paragraph clarity and sentence-to-sentence flow in any section
Who it's for
  • ML/CV/NLP researchers drafting or revising papers
  • PhD students preparing manuscripts for conference or journal submission
  • Authors seeking to improve clarity and reviewer perception before resubmission
  • Teams performing collaborative paper editing and review

research-paper-writing FAQ

How do I know if my paragraph flows well?

Use the Paragraph Clarity Check: (1) Verify the first sentence states the paragraph's message and all key terms are defined; (2) Check that each sentence connects to the previous one with a clear relation (cause, contrast, consequence, refinement); (3) Run reverse outlining to map the paragraph's evidence back to its topic sentence and the section's thesis.

Should I load all section guides at once?

No. Load only the specific section guide you are currently editing (e.g., `references/method.md` for the Method section). Loading all guides at once is inefficient and violates the execution rules.

What is the claim-evidence map and when should I use it?

A claim-evidence map documents each major claim, the experimental evidence supporting it, and whether the support is sufficient. Use it for Abstract and Introduction claims, and include it in the output contract when revising those sections. Format: `Claim: ... | Evidence: ... | Status: supported/needs evidence`.

How do I handle a claim that cannot be supported by my results?

Weaken or remove the claim. Do not overstate findings. If a claim is central to your contribution, revise your experiments or analysis to generate the necessary evidence before finalizing the paper.

What should I do if my self-review checklist reveals unresolved issues?

Revise the paper to address each unresolved item before submission. Treat the five-dimension checklist (contribution, clarity, experimental strength, evaluation, method soundness) as a hard constraint, not optional feedback.

Full instructions (SKILL.md)

Source of truth, from master-cai/research-paper-writing-skills.


name: research-paper-writing description: Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation. Use when drafting or revising Abstract, Introduction, Related Work, Method, Experiments, or Conclusion; polishing figures/tables; checking claim-support alignment; or performing self-review before submission.

Research Paper Writing

Overview

Use this skill to rewrite a research paper into a reviewer-friendly, high-clarity draft. Prioritize first-impression quality (figures/tables/layout), logical flow, and evidence-backed claims.

Core Workflow

  1. Clarify the paper story before sentence-level edits.
  2. Use section-specific guidance in references/.
  3. Rewrite paragraph-by-paragraph with one message per paragraph.
  4. Run reverse outlining after writing each section.
  5. Check every major claim in Abstract/Introduction against experimental evidence.
  6. Run final-paper adversarial review with references/paper-review.md.

Global Principles

  1. Keep one paragraph for one message only.
  2. State the paragraph message in the first sentence.
  3. Make nouns self-contained; define new terms before reusing them.
  4. Maintain sentence-to-sentence flow (cause, contrast, consequence, or refinement).
  5. Iterate with adversarial self-review: read as a skeptical reviewer.
  6. Treat visual quality as core content, not decoration.
  7. Use a clean teaser and pipeline figure.
  8. Use readable, minimal-ink tables.
  9. Keep formatting consistent and tidy.

Paragraph Clarity Check (Important)

Use this quick test whenever the user asks whether a paragraph "flows" or is clear.

  1. Read as an external reader:
    • Does this paragraph have one explicit message?
    • Does the first sentence state what this paragraph will do?
    • Are all key nouns/terms readable without hidden context?
    • Does each sentence connect to the previous one with a clear relation (cause, contrast, consequence, refinement, example)?
  2. Run reverse outlining for the current section:
    • Write down thesis/main claim.
    • Write down each paragraph topic sentence.
    • Write down the evidence/explanation points under each paragraph.
    • Check mapping: topic sentence -> thesis, and evidence -> topic sentence.
    • Revise or remove any paragraph that cannot be mapped cleanly.
  3. If flow is still weak, add temporary section headers and explicit transition phrases during revision, then remove unnecessary headers before finalizing.

Source reference for this check:

  • references/does-my-writing-flow-source.md

Section Guides

Load only the needed section file:

  • Introduction: references/introduction.md
  • Abstract: references/abstract.md
  • Related Work: references/related-work.md
  • Method: references/method.md
  • Experiments: references/experiments.md
  • Conclusion: references/conclusion.md
  • Paper review (Paper Review): references/paper-review.md
  • Paragraph clarity source: references/does-my-writing-flow-source.md
  • Example bank index: references/examples/index.md

Paper Review Core Points

Use references/paper-review.md for the full checklist and workflow.

  1. Add an end-of-draft self-review question list in five dimensions:
    • contribution,
    • writing clarity,
    • experimental strength,
    • evaluation completeness,
    • method design soundness.
  2. Treat claim-evidence alignment as a hard constraint, especially for Abstract and Introduction.
  3. Perform adversarial writing: review as a skeptical reviewer and resolve every high-risk question.
  4. Revise until major rejection risks are explicitly addressed.

Execution Rules

  1. Build a mini-outline before drafting prose.
  2. For each subsection, explicitly include motivation, design, and technical advantage when applicable.
  3. Avoid writing style that looks like incremental patching of a naive baseline.
  4. Keep terminology stable across the full paper.
  5. If a claim cannot be supported by results, weaken or remove the claim.
  6. Before finalizing, append and answer a five-dimension self-review question list, then revise the paper based on unresolved items.
  7. Do not load all section references (Introduction/Abstract/Related Work/Method/Experiments/Conclusion) at once; load only the specific section guide needed for the current edit target.

Output Contract

When asked to rewrite or draft sections, return:

  1. A compact section outline (3-7 bullets).
  2. Revised paragraphs with explicit paragraph roles (opening/challenge/method/advantage/evidence/limitation).
  3. A short self-review checklist covering clarity, flow, terminology consistency, unsupported claims, and missing evidence.
  4. A claim-evidence map for each major claim in the revised text using Claim: ... | Evidence: ... | Status: supported/needs evidence.