Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

research-paper-writing · master-cai — Claude Code skill: structure and clarity

A skill to rewrite research papers into reviewer-friendly drafts. Checks paragraph logic, claim-evidence alignment, and visual quality across Abstract, Introduction, Method, Experiments, and Conclusion.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Master-cai/Research-Paper-Writing-Skills --skill research-paper-writing -a claude-code
Open on GitHub

What research-paper-writing does

This skill guides you through section-by-section revision of academic papers in ML/CV/NLP style. For each paragraph, it ensures one explicit message in the first sentence, clear sentence-to-sentence flow (cause, contrast, consequence, or refinement), and self-contained terminology. Section guides are included for Abstract, Introduction, Related Work, Method, Experiments, and Conclusion.

A core feature is the reverse outlining check: map each paragraph's topic sentence back to the section thesis, and evidence back to the topic sentence. Weak or unmapped paragraphs signal a revision target. Critical enforcement: every major claim in Abstract and Introduction is checked against experimental results; unsupported claims are flagged for weakening or removal.

Installation requires npx and access to the Master-cai repository on GitHub. File location varies by platform: ~/.claude/skills/research-paper-writing/SKILL.md for Claude Code, .cursor/skills/research-paper-writing/SKILL.md for Cursor, and so on.

What it helps with

  • Rewrite Abstract so every claim aligns with experimental evidence
  • Strengthen paragraph flow: state one message upfront and link sentences logically
  • Ensure Introduction frames motivation without overselling what Method delivers
  • Polish tables and figures for clarity: minimal ink, maximum readability
  • Self-review draft before submission: surface risks across contribution, clarity, strength, completeness, and method design

Example prompts for the agent

  • Rewrite my Abstract so each claim is backed by experimental results
  • Check if my Introduction flows logically: state one message per paragraph
  • Run an adversarial review: identify high-risk weaknesses a skeptical reviewer would spot

How to install research-paper-writing

1Skills CLI (Vercel)

npx skills add Master-cai/Research-Paper-Writing-Skills --skill research-paper-writing -a claude-code

2Manually: put the files in place

~/.claude/skills/research-paper-writing/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/research-paper-writing/

Other versions of research-paper-writing

Similar

video-extend prime-skills Extends existing clips using Google Veo 3-1 via the runcomfy CLI. Use it to lengthen short scenes or build shot-by-shot story sequences. Claude Code CX Codex Cursor +1 376,500installs image-outpainting prime-skills Extends an existing image with runcomfy, changes its aspect ratio, and fills in the missing surroundings while keeping the original scene. Claude Code CX Codex Cursor +1 376,300installs video-outpainting prime-skills Extend a video's spatial canvas, swap aspect ratio (9:16 to 16:9 or vice versa), add environment beyond the original frame. Via Wan 2-7 edit-video or ComfyUI workflow with precision seam handling. Claude Code CX Codex Cursor +1 376,100installs manim-video SHL0MS, Hermes Agent Builds Manim CE projects for math, algorithm, and technical animations. Useful when an AI agent needs to turn an explanation into a rendered video. Claude Code CX Codex Cursor +1 455installs ace-step prime-skills Generates music from tags, edits sections of existing tracks, and extends audio through the RunComfy CLI. Use it for instrumentals, vocal songs, and track revisions. Claude Code CX Codex Cursor +1 368,000installs mastra Mastra This skill helps build with Mastra by checking current documentation. Use it to verify APIs, set up TypeScript projects, and investigate errors. Claude Code CX Codex Cursor +1 82,600installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs

Questions about research-paper-writing

How do I install research-paper-writing in Claude Code?

Run npx skills add Master-cai/Research-Paper-Writing-Skills --skill research-paper-writing -a claude-code, then open the skill file at ~/.claude/skills/research-paper-writing/SKILL.md.

What does research-paper-writing do?

It guides revision of academic papers to be reviewer-friendly. Each paragraph gets one explicit message in the first sentence; sentences link logically; major claims are verified against data. Includes section-specific guides and adversarial self-review.

Which platforms support this skill?

Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. The skill file path differs by platform: .claude/ for Claude Code, .cursor/ for Cursor, .github/ for GitHub Copilot, etc.

Source text

SKILL.md · MIT
---
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`.

© Master-cai · MIT · Master-cai/Research-Paper-Writing-Skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor