@wsl8297: The biggest fear when writing a paper with AI is not being unable to produce content, but that it looks complete while the research gap, literature support, and argument structure are actually unsound. Academic Paper Skills solves this problem. GitHub: https://github.com/lishix520/…

X AI KOLs Timeline Tools
academic-writing paper-writing claude-code ai-tools research-workflow github open-source

Summary

Academic Paper Skills is a paper writing skill framework for Claude Code, dividing the writing process into two phases: strategy and composition. It incorporates features like literature support, reviewer simulation, and quality checks to help users generate a first draft from a research idea.

Writing a paper with AI: the biggest fear is not being unable to write, but that it looks complete while the research gap, literature support, and argument structure are actually unsound. Academic Paper Skills solves this problem. GitHub: https://github.com/lishix520/academic-paper-skills… This is a paper writing Skill for Claude Code, breaking down the process from idea to first draft into steps that more closely resemble real academic writing, rather than directly asking the model to generate the body text. Key features: - Divided into two phases: Strategist and Composer — first plan the paper, then write according to the outline - The research gap requires support from 3–5 papers to avoid fabricating a gap - Analyzes 8–10 samples from target platforms to learn writing standards and style - Built-in reviewer simulation mechanism with 7 dimensions on a 35-point scale - Provides 3 quality check gates and a Python verification script - Supports preprint platforms such as arXiv, PhilArchive, PsyArXiv It functions more as a paper writing workflow constraining tool, suitable for those who already have a research direction but whose literature, structure, and arguments are still scattered.
Original Article
View Cached Full Text

Cached at: 05/25/26, 06:46 AM

The worst fear when using AI to write a paper isn’t that it can’t produce anything — it’s that the output looks complete, but the research gap, literature support, and argument structure don’t hold up. Academic Paper Skills is built to solve exactly that.

GitHub: https://github.com/lishix520/academic-paper-skills

This is a set of paper writing skills designed for Claude Code. It breaks down the process from “idea to first draft” into steps that mirror real academic writing, rather than asking the model to generate full text directly.

Key features:

  • Split into two phases: Strategist and Composer — plan the paper first, then write following the outline
  • Research gaps must be supported by 3–5 citations to avoid creating a gap out of thin air
  • Analyzes 8–10 sample papers from the target platform to learn writing standards and style
  • Built‑in reviewer simulation across 7 dimensions, totaling 35 points
  • Provides 3 quality check gates along with Python validation scripts
  • Supports preprint platforms such as arXiv, PhilArchive, and PsyArXiv

It acts more like a constraint system for the paper writing workflow, ideal for those who already have a research direction but whose literature, structure, and argumentation are still scattered.

lishix520/academic-paper-skills

Source: https://github.com/lishix520/academic-paper-skills

Academic Paper Skills for Claude Code

A systematic framework for planning and writing philosophy and interdisciplinary academic papers using Claude Code. These skills transform your research ideas into submission-ready manuscripts through structured workflows with quality checkpoints.

Features

  • End-to-End Pipeline: From initial idea to polished manuscript
  • Evidence-Based Gap Identification: Every research gap backed by 3-5 citations
  • Platform-Specific Style Learning: Analyze 8-10 sample papers to extract writing standards
  • Reviewer Simulation: 7-dimension, 35-point assessment system
  • Quality Assurance: 3 validation gates + 2 Python verification scripts
  • Preprint Platform Support: PhilArchive, arXiv, PhilSci-Archive, PsyArXiv, and more

Two-Skill Workflow

┌─────────────────────────────────────────────────────────────┐ │ ACADEMIC-PAPER-STRATEGIST │ │ Phase 1: Platform Analysis → Target venue + style guide │ │ Phase 2: Theoretical Framework → Literature + gap analysis │ │ Phase 3: Outline Optimization → Reviewer-assessed outline │ └─────────────────────────┬───────────────────────────────────┘ ↓ [Detailed Outline] ↓ ┌─────────────────────────┴───────────────────────────────────┐ │ ACADEMIC-PAPER-COMPOSER │ │ Phase 1: Foundation → Style guide + chapter planning │ │ Phase 2: Systematic Writing → Draft with quality checks │ │ Phase 3: Polish → Final evaluation + submission prep │ └─────────────────────────────────────────────────────────────┘

Installation

Prerequisites

  • Claude Code (https://claude.ai/code) installed and configured
  • Python 3.8+ (for verification scripts)

Setup

  1. Clone this repository: bash git clone https://github.com/yourusername/academic-paper-skills.git

  2. Copy skills to your Claude Code skills directory: bash cp -r strategist ~/.claude/skills/academic-paper-strategist cp -r composer ~/.claude/skills/academic-paper-composer

  3. Restart Claude Code to load the skills.

Quick Start

Planning a Paper (Strategist)

`` You: Plan a paper on how mortality generates consciousness

Claude: [Activates academic-paper-strategist] Let me guide you through the three phases… ``

Writing from Outline (Composer)

`` You: Write the paper from this outline: [your outline]

Claude: [Activates academic-paper-composer] Starting Phase 1: Foundation setup… ``

Directory Structure

academic-paper-skills/ ├── strategist/ │ ├── SKILL.md # Main skill definition │ ├── references/ │ │ ├── quality_standards.md # Evaluation criteria │ │ └── search_strategy.md # Literature search guide │ └── scripts/ │ ├── evaluate_samples.py # Sample paper analyzer │ └── gap_analysis.py # Research gap validator ├── composer/ │ ├── SKILL.md # Main skill definition │ ├── references/ │ │ ├── section_guides.md # Section-by-section guidance │ │ └── writing_standards.md # Academic writing principles │ └── scripts/ │ ├── chapter_quality_check.py # Per-chapter validation │ └── final_evaluation.py # Full manuscript assessment └── examples/ ├── consciousness-paper.md # Example: Philosophy of mind └── ai-ethics-paper.md # Example: AI ethics

Quality Standards

Reviewer Simulation (7 Dimensions)

DimensionWeightCriteria
Originality5 ptsNovel contribution to field
Argumentation5 ptsLogical coherence, evidence support
Literature5 ptsComprehensive, current coverage
Methodology5 ptsAppropriate, rigorous approach
Clarity5 ptsAccessible, well-structured writing
Impact5 ptsPotential influence on field
Technical5 ptsAccuracy, proper citations

Threshold: Outlines scoring ≥28/35 proceed to writing phase.

Use Cases

  • PhD students: Transform dissertation chapters into publishable papers
  • Independent researchers: Professional-grade paper planning without institutional support
  • Interdisciplinary work: Navigate multiple platform requirements
  • Preprint submission: Prepare manuscripts for PhilArchive, arXiv, etc.

Contributing

Contributions are welcome! Please see CONTRIBUTING.md for guidelines.

License

MIT License - see LICENSE for details.

Author

Li Shixiong Independent Researcher ORCID: 0009-0008-2001-2865 (https://orcid.org/0009-0008-2001-2865)

These skills were developed through the author’s experience publishing philosophy papers on consciousness and mortality.

Similar Articles

@gaoren7716: Writing a thesis? It might get rewritten by a systematic AI system. Not just polishing or rewriting a sentence – from topic selection onward, there are 13 agents collaborating. Feature list: Deep Research (13-agent research team), Systematic Review (P…

X AI KOLs Timeline

Introduces an open-source AI tool called Academic Research Skills that automates the entire academic research process from topic selection to writing and peer review through collaboration of 13 agents. It can be installed as a Claude Code plugin, turning academic research into a standardized production line.

@IndieDevHailey: A blessing for researchers! This open-source tool helps you break through the sea of literature and manage the entire academic workflow with one click. Still struggling with slow literature research, writer's block, improper citations, and harsh peer reviews? Check out this open-source repository: academic-research-skills. It's not an AI ghostwriting tool, but a reliable human-AI collaboration framework—…

X AI KOLs Timeline

Recommends the open-source repository academic-research-skills, which provides a set of human-AI collaborative tools for the entire academic research workflow, including in-depth literature research, paper writing, peer review simulation, and citation audit. It supports AI assistance while keeping the user in control, suitable for graduate students and researchers.

@zhanlin990410: https://x.com/zhanlin990410/status/2055666660925943834

X AI KOLs Timeline

This article introduces a 6-step workflow for academic research using Kimi (an AI tool with a 1 million token context window), including literature dumping, gap identification, literature review draft, methodology stress testing, argument stress testing, and full-text assembly, which can significantly shorten paper writing time.

@sheriyuo: Actually, I have been writing papers purely with AI from the very beginning. Previously I used DeepSeek R1, now I use V4. Since I don't have English academic writing ability, but I can tell by eye whether a sentence or passage is appropriate. As for Chinese writing, I am fairly confident. So almost 9...

X AI KOLs Timeline

The user shared their experience of writing academic papers entirely using AI (DeepSeek R1 and V4), emphasizing that the Chinese outline and fine prompt tuning are key, and noting that manually editing AI-generated writing is more tiring than writing it themselves.