FeijiangHan/PaperForge

An active paper-reading skill that reconstructs author reasoning, explains methods mechanistically, stress-tests assumptions, and generates follow-up research ideas.

What it solves

PaperForge provides a structured framework for reading and analyzing academic papers using LLMs. It moves beyond simple summarization by forcing the AI to reconstruct the author's reasoning process, identify fragile assumptions, and propose novel follow-up research ideas, helping researchers avoid superficial understanding.

How it works

The project consists of a set of system prompts and "Skills" (formatted for Claude/Codex) that guide an LLM through a 12-13 step analysis pipeline. When provided with a paper's link, title, or PDF, the LLM follows a specific sequence of tasks:

  1. Contextualization: Identifying the research problem and its importance.
  2. Reasoning Reconstruction: Simulating the author's intuition and inspiration based on existing knowledge rather than just stating the paper's claims.
  3. Mechanistic Explanation: Breaking down the method's intuition, pipeline (input/processing/output), and mathematical derivations.
  4. Critical Analysis: Stress-testing the paper's claims by identifying the most fragile assumptions and designing potential counter-examples.
  5. Future Work: Researching follow-up studies via search tools and proposing a novel, non-incremental research idea.

Who it’s for

Researchers, students, and academics (primarily in STEM fields) who want to deeply understand the methodology and theoretical foundations of academic papers rather than just reading a summary.

Highlights

  • Reasoning Reconstruction: Focuses on how the author arrived at the idea, not just what the result was.
  • Critical Stress-Testing: Specifically prompts the AI to find the weakest point of the paper and design a minimal reproduction experiment.
  • Idea Generation: Encourages the generation of novel research directions based on identified limitations.
  • Flexible Deployment: Available as a system prompt for ChatGPT/Claude or as a predefined Skill.

Related

  • Project
    RhythmicWave/NovelForge

    An AI-powered long-form novel writing engine that uses structured cards, knowledge graphs, and a custom context DSL to maintain consistency across millions of words.

  • Project
    Imbad0202/academic-research-skills-codex

    ARS‑Codex is a Codex‑compatible skill that bundles the Academic Research Skills workflow suite (originally built for Claude Code) into a single plug‑in. After installing the plugin, users can invoke `$academic‑research‑suite` and let Codex route the request to one of six research‑oriented workflows—deep research, paper drafting, reviewer simulation, full research‑to‑paper pipeline, systematic‑review screener, or experiment planning. The repo contains the skill manifest, prompt templates, optional runtime adapters, and installation scripts; it does not include a new model.

  • Project
    meta-prompting/meta-prompting

    A prompting framework that uses structural templates instead of concrete examples to improve LLM reasoning, providing a formal mathematical foundation for automated prompt engineering.

  • Project
    dreadnode/rigging

    A lightweight LLM framework that simplifies production code integration by providing unified model access, structured Pydantic outputs, and type-safe prompt definitions.

  • Project
    HKUSTDial/Supervisor-Skills

    A collection of structured AI skills and theoretical guides that distill senior academic experience into LLM prompts to assist researchers with idea evaluation, paper writing, and peer review.