proofread — proofread setup for AI-powered review proofread, community, proofread setup for AI-powered review, ide skills, academic paper review with AI, Nature-style review for researchers, proofread for reproducibility and validation, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Research Assist Agents needing advanced academic document review capabilities. Proofread is an AI-powered academic review skill that evaluates documents for weaknesses in Methods and Results sections, providing detailed feedback and improvement suggestions.

Features

Evaluates GitHub files and repositories for academic document review
Assesses Methods sections for weaknesses in 5 key areas: Reproducibility, Controls, Sample size/power, Statistical appropriateness, and Validation
Analyzes Results sections for Claim type, Evidence level, and Overclaiming risk
Provides actionable feedback and improvement suggestions for identified weaknesses
References detailed evaluation guides in reports/proofreading_guide.md

# Core Topics

proofread setup for AI-powered review academic paper review with AI Nature-style review for researchers proofread for reproducibility and validation
yinijooy yinijooy
[0]
[0]
Updated: 3/8/2026

Agent Capability Analysis

The proofread skill by yinijooy is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for proofread setup for AI-powered review, academic paper review with AI, Nature-style review for researchers.

Ideal Agent Persona

Perfect for Research Assist Agents needing advanced academic document review capabilities.

Core Value

Empowers agents to assess reproducibility, evaluate statistical appropriateness, and identify overclaiming risks in academic documents using methods like controls and validation, while referencing GitHub files and code.

↓ Capabilities Granted for proofread

Evaluating Methods sections for reproducibility and statistical appropriateness
Analyzing Results sections for claim types, evidence levels, and overclaiming risks
Generating detailed feedback reports for authors, including specific problems and improvement suggestions

! Prerequisites & Limits

  • Requires access to academic documents, potentially via GitHub links
  • Limited to assessing documents from a Nature reviewer's perspective
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

proofread

Unlock expert-level proofreading for your academic papers with this AI agent skill, evaluating Methods and Results sections for weaknesses and providing...

SKILL.md
Readonly

Proofreading Skill

학술 문서를 Nature 리뷰어 관점에서 검토하고 평가합니다.

모든 상세 내용은 reports/proofreading_guide.md 참조

동작 순서

  1. GitHub 파일 참조 (필요시)

    • 사용자가 제공한 GitHub 링크에서 원본 문서 확인
    • 관련 코드/데이터 파일 검토

  2. Methods 섹션 평가

    • 5가지 측면에서 약점 지적: Reproducibility, Controls, Sample size/power, Statistical appropriateness, Validation
    • 각 약점에 대해: 구체적 문제점, 리뷰어 예상 질문, 개선 방안 제시

  3. Results 섹션 평가

    • 각 문장별 Claim type, Evidence level, Overclaiming risk 분석
    • 가장 위험한 overclaim 3개 지적 및 수정 방법 제시

  4. 종합 프루프리딩

    • 평가 결과 통합
    • 수정 사항 도출
    • 최종 권고안 작성

Methods 평가 프롬프트

다음 Methods 섹션을 Nature 리뷰어 관점에서 평가해줘:

[Methods text]

다음 5가지 측면에서 약점을 지적:
1. Reproducibility (재현성)
2. Controls (통제)
3. Sample size/power (샘플/검정력)
4. Statistical appropriateness (통계 적절성)
5. Validation (타당성)

각 약점에 대해:
- 구체적 문제점
- 리뷰어가 제기할 질문
- 개선 방안

Results 평가 프롬프트

다음 Results 문장들을 분석해줘:

[Results text]

각 문장에 대해:
1. Claim type (causal/correlational/mechanistic/general)
2. Evidence level (direct/indirect/suggestive)
3. Overclaiming risk (1-10)
4. Conservative alternative phrasing

그리고:
- 가장 위험한 overclaim 3개 지적
- 각각을 데이터에 맞게 수정하는 방법

참고

평가 기준, 출력 템플릿, 참고 문서 목록은 모두 reports/proofreading_guide.md 참조

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is proofread?

Perfect for Research Assist Agents needing advanced academic document review capabilities. Proofread is an AI-powered academic review skill that evaluates documents for weaknesses in Methods and Results sections, providing detailed feedback and improvement suggestions.

How do I install proofread?

Run the command: npx killer-skills add yinijooy/safa/proofread. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for proofread?

Key use cases include: Evaluating Methods sections for reproducibility and statistical appropriateness, Analyzing Results sections for claim types, evidence levels, and overclaiming risks, Generating detailed feedback reports for authors, including specific problems and improvement suggestions.

Which IDEs are compatible with proofread?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for proofread?

Requires access to academic documents, potentially via GitHub links. Limited to assessing documents from a Nature reviewer's perspective.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add yinijooy/safa/proofread. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use proofread immediately in the current project.

Related Skills

Looking for an alternative to proofread or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI