Open Paper Machine

Open Academic Paper Machine

> A Claude Code plugin that autonomously writes academic papers — from literature search to production-ready LaTeX/PDF.

[](LICENSE) []()

> v6.4.0 — Paper-vs-Code Audit. New /audit-paper command and audit-engine skill: static audit of a paper's empirical claims (datasets, models, hyperparameters, metrics) against the linked code repository. Classifies each claim as CONFIRMED / PARTIAL / MISSING / MISMATCH / NOT_AUDITABLE with file:line evidence. Complements /verify-citations (external sources) by checking own-work claims against own code. Inspired by Feynman's /audit. [](https://github.com/kourgeorge/arxiv-style)

> Scope note. This project is a technical contribution: it explores what is possible with current LLM technology for academic paper production, not what is desirable or ethically permissible. The ethical, epistemological, and policy questions raised by AI-generated academic writing — authorship attribution, academic integrity, epistemic status, potential misuse — are important but outside the scope of this tool. They are addressed in the companion position paper (Blask & Funk, 2026).

Quick Start

# 1. Install the plugin
/plugin marketplace add TobiasBlask/open-paper-machine
/plugin install open-academic-paper-machine@open-paper-machine

# 2. Install dependencies
pip install paperbanana[google] academic-search-mcp

# 3. Set up your API key (free — https://aistudio.google.com/apikey)
echo 'GOOGLE_API_KEY="your-key"' > ~/.paperbanana.env
# Or per-project: echo 'GOOGLE_API_KEY="your-key"' > .env

# 4. Go
/write-paper The impact of generative AI on organizational decision-making

That's it. The plugin ships the academic-search MCP server, the PaperBanana direct Python API for figure generation, all 16 skill engines, 4 agents, 24 curated scientific skills, 20 slash commands, and the autonomous pipeline agent. Everything starts automatically.

Technical paper: [The Open Academic Paper Machine: An Autonomous LLM Plugin for End-to-End Academic Paper Production](paper/paper.pdf) (Blask, 2026) — describes the system architecture, design principles, and evaluation. LaTeX source in [paper/](paper/).

Position paper: From Creator to Orchestrator? How an LLM Agent Wrote This Paper and What That Means for Science (Blask & Funk, 2026) — a position paper on AI-augmented knowledge production, orchestrated through human-AI interaction using this system. GitHub repo.

---

How It Works

The machine runs autonomously through 9 phases:

| Phase | What Happens | Your Job | |-------|-------------|----------| | 0. Idea Evaluation (v6.3.0) | Stress-test idea along 7 dimensions, conclusion-first test, PURSUE/REFINE/KILL verdict | Decide whether to proceed | | 1. Reconnaissance | 4-6 search queries across 4 academic APIs, snowballing, deduplication | Check scope, redirect if needed | | 2. Framing | Theory selection, gap formulation, research questions, contribution statement | Confirm direction | | 3. Structure | Concept matrix, paper structure, word budget | Approve structure | | 4. Production | Write every section as complete paragraphs + generate figures | Read along, adjust | | 5. Assembly | Compile all sections, quality self-assessment, status report | Start review | | 6. LaTeX & PDF | Convert to arxiv-style LaTeX, resolve citations, compile PDF | Download and submit | | 7. Verification (opt.) | Fetch source abstracts/PDFs, verify each citation claim | Review flagged mismatches | | 8. Revision (repeatable) | Extract reviewer/co-author feedback, classify, implement changes, recompile + latexdiff | Approve change plan |

Core principle: Before producing, evaluate. The machine gates the pipeline — not every topic deserves months of work. Then it makes decisions and presents results. You steer at checkpoints.

Phase 8 closes the loop: send an annotated PDF from your co-author or paste reviewer comments, and the review-engine extracts, classifies, and implements all changes — then recompiles and generates a visual diff. The cycle repeats (Round 1 → 2 → 3 → ...) until acceptance.

---

Requirements

| Requirement | Version | Notes | |---|---|---| | Claude Code | Latest | CLI or IDE extension (VS Code / JetBrains) | | Python | 3.10+ | For PaperBanana and academic-search MCP servers | | LaTeX | Any recent | Optional — only needed for PDF compilation (/export-latex) | | Google API key | Free | For AI figure generation — get one here |

> No Google API key? The plugin works fully without one — you just won't get AI-generated figures. The figure-engine falls back to matplotlib/seaborn. All other features (literature search, writing, LaTeX, revision, etc.) work independently.

---

Installation

What Gets Installed

The plugin bundles one MCP server that starts automatically, plus PaperBanana via direct Python API:

| Component | pip package | What it does | |---|---|---| | academic-search (MCP) | academic-search-mcp | Searches Semantic Scholar, OpenAlex, CrossRef, arXiv. Snowballing, BibTeX/CSV export. | | PaperBanana (direct API) | paperbanana | AI figure generation via Google Gemini. Multi-agent pipeline with iterative refinement. Based on Zhu et al. (2026). |

The academic-search MCP server is configured in plugin.json and starts when Claude Code loads the plugin. PaperBanana is called via direct Python API (scripts/paperbanana_direct.py) — the MCP transport layer was removed in v6.3.0 due to persistent reliability issues (timeouts, silent failures).

> Academic foundation: The figure generation pipeline implements the methodology from PaperBanana: Automating Academic Illustration for AI Scientists (Zhu et al., 2026). The MCP integration uses the community implementation at llmsresearch/paperbanana. See also the official research repo.

Step-by-Step

1. Add the marketplace and install the plugin:

/plugin marketplace add TobiasBlask/open-paper-machine
/plugin install open-academic-paper-machine@open-paper-machine

2. Install Python dependencies:

pip install paperbanana[google] academic-search-mcp

3. Configure your Google API key (needed for AI figure generation):

Get a free key at Google AI Studio, then set it up (choose one):

# Option A — Global (recommended, works across all projects):
echo 'GOOGLE_API_KEY="your-api-key-here"' > ~/.paperbanana.env

# Option B — Per-project:
echo 'GOOGLE_API_KEY="your-api-key-here"' > .env

Key loading priority: Environment variable → ~/.paperbanana.env → project .env. Never commit .env to version control. See .env.example for a template.

4. Install LaTeX (for PDF compilation):

# macOS
brew install --cask mactex-no-gui

# Ubuntu/Debian
sudo apt-get install texlive-full

5. Start writing:

/write-paper Your Paper Title Here

Cowork Setup

1. Download the latest release ZIP from GitHub Releases
2. In Cowork, open the Plugins panel and click "+" → upload the ZIP
3. Set GOOGLE_API_KEY in plugin settings (optional — only needed for AI figures)
4. /write-paper Your Paper Title

---

Idea Evaluation — Phase 0 (v6.3.0)

Most AI writing tools help you write papers. Phase 0 helps you decide which papers to write.

The previous pipeline took any topic and produced. Version 6.3.0 adds the missing gate: Is this paper the right use of my time? Based on Nicholas Carlini's research philosophy (How to Win a Best Paper Award) and the research-companion plugin by Andre Huang.

# Standalone idea evaluation
/evaluate-idea Can LLMs replace systematic literature reviews?

# Or just run /write-paper — Phase 0 runs automatically first
/write-paper The impact of generative AI on organizational decision-making

How It Works

Three specialist agents evaluate your idea before the pipeline commits to production:

| Agent | Role | Output | |-------|------|--------| | Idea Critic | Adversarial stress-test along 7 dimensions | PURSUE / REFINE / KILL verdict | | Research Strategist | Strategic viability: competition, timing, comparative advantage | Green / Yellow / Red flags | | Brainstormer | Cross-field connections, assumption challenges, reframings | Alternative angles and extensions |

The 7 Evaluation Dimensions

| Dimension | Key Question | Signal | |-----------|-------------|--------| | Novelty (RS1) | If you don't do this, how long until someone else does? | Weeks / Months / Years | | Impact (RS2) | Can you write a compelling conclusion right now? | Low / Medium / High | | Timing (RS8) | Is the field ready? Too early? Already crowded? | Too Early / Well-Timed / Too Late | | Feasibility (RS4) | What's the riskiest assumption? Can you test it in a week? | High / Medium / Low Risk | | Competition (RS7) | Who else is working on this? What's your advantage? | Crowded / Moderate / Open | | Nugget (RS3) | Can you state the key insight in one sentence? | Clear / Fuzzy / Missing | | Narrative | Can you tell a story that makes a skeptical reader care? | Compelling / Workable / Weak |

The Conclusion-First Test

The decisive gate. Before investing, the engine writes the best-case conclusion: if everything works perfectly, what can this paper say? If the answer is hollow or generic — if it only says "our method achieves X% improvement" — the idea doesn't have enough impact. Kill it and move on.

Research Strategy Principles (RS1-RS8)

Eight principles guide evaluation (see principles/research-strategy.md):

• RS1 (Novelty Test): Favor problems where your unique skills create a months-to-years gap.
• RS2 (Conclusion-First Test): Write the conclusion before doing the research.
• RS3 (Nugget Test): One sentence. One idea. Every figure connects to it.
• RS4 (Fail Fast): Start with what's most likely to kill the project.
• RS5 (Kill Early): A working project with low impact is worse than a killed project.
• RS6 (Unreasonable Effort): Go to unreasonable lengths — but only AFTER RS4 and RS5.
• RS7 (Comparative Advantage): Research space is high-dimensional; find your unique corner.
• RS8 (Timing Awareness): Impact = skill x domain importance at this moment.

Evaluations persist to research-evaluations/*.md for cross-session continuity. Previously killed ideas are checked for changed conditions rather than re-evaluated from scratch.

---

Commands

Idea Evaluation (v6.3.0)

| Command | Description | |---------|-------------| | /evaluate-idea [topic] | Full idea stress-test — 7 dimensions, 3 agents, conclusion-first test, PURSUE/PARK/KILL verdict | | /brainstorm [topic] | Creative brainstorming — cross-field connections, assumption challenges, alternative framings, wild cards | | /triage-project | Project triage — should you continue, pivot, or kill? 5-signal assessment | | /scooping-check [topic] | Scooping risk — who else is working on this? Watch list with researchers, venues, search terms |

Core Pipeline

| Command | Description | |---------|-------------| | /write-paper [title] | Full pipeline — Phase 0 (evaluation) + Phases 1-8, start to finish | | /search-papers [topic] | Phase 1: systematic literature search across 4 APIs | | /draft-section [section] | Phase 4: write one specific section as complete paragraphs | | /export-latex | Phase 6: convert finished draft to arxiv-style LaTeX + compiled PDF | | /verify-citations | Phase 7: verify all citations against actual source content | | /respond-reviewers [pdf or comments] | Phase 8: full revision loop — extract feedback, classify, implement, recompile, latexdiff | | /generate-figure [description] | AI-generated academic diagram from text | | /generate-plot [datafile] [intent] | Statistical plot from CSV/JSON data |

Qualitative Data Analysis (v6.2.0)

| Command | Description | |---------|-------------| | /analyze-interviews [topic] | Qualitative analysis pipeline — structured summaries, thematic coding, cross-case analysis, evidence tables. Context-window-safe: summary-first, never loads all transcripts at once. Supports Gioia, Mayring, Braun & Clarke. |

Extended Capabilities (v6.0.0)

| Command | Description | |---------|-------------| | /review-paper [venue] | Simulated peer review — 2 independent reviewer reports calibrated to top IS/CS venues | | /screen-papers [criteria] | PRISMA-compliant SLR screening with quality assessment and flow diagram | | /analyze-positioning | Differentiation matrix against closest related work + positioning statement | | /analyze-writing [section] | Writing style analysis — passive voice, hedging, readability, 8 quality metrics | | /prepare-submission [venue] | Venue-specific submission package: anonymization, cover letter, reviewer suggestions | | /monitor-literature | Re-run search queries, find papers published since last search | | /generate-slides [format] | Conference presentation slides with speaker notes (Marp-compatible) |

---

Architecture

Skill Engines

The plugin contains 16 specialized skill engines (~6,500 lines of domain knowledge) that the paper-machine agent orchestrates, plus 24 curated scientific skills that auto-activate by context:

Idea Evaluation Engine (v6.3.0)

| Engine | Responsibility | Key Capabilities | |--------|---------------|-----------------| | idea-engine | Research idea evaluation | 7-dimension scoring, conclusion-first test, RS1-RS8 principles, PURSUE/REFINE/KILL verdicts, cross-session persistence |

Core Pipeline Engines

| Engine | Responsibility | Key Capabilities | |--------|---------------|-----------------| | literature-engine | Systematic literature discovery | 4 academic APIs, snowballing, PRISMA screening, concept matrix, monitoring | | theory-engine | Theoretical framing | Theory matching, gap formulation, hypothesis/design principle derivation | | method-engine | Research design | 13 method templates (SLR, DSR, case study, Gioia, Mayring, grounded theory, PLS-SEM, mixed, experiment/RCT, action research, ethnography, Delphi, simulation) + research data management | | writing-engine | Paragraph-level text production | Section templates, sentence formulas, academic register for IS/WI/BWL, style analysis (8 metrics) | | qualitative-engine | Qualitative data analysis | Summary-first transcript processing, thematic coding (Gioia/Mayring/Braun & Clarke), cross-case analysis, evidence tables | | figure-engine | Visual production | PaperBanana AI diagrams (Gemini) via direct Python API, matplotlib/seaborn fallback | | latex-engine | Document compilation | arxiv-style conversion, \citep/\citet citation resolution, PDF build | | verification-engine | Citation verification | Source retrieval (abstract + full-text), claim-source comparison, verification report | | review-engine | Revision automation | PDF annotation extraction, comment classification, change planning, latexdiff generation |

Extended-Capability Engines (v6.0.0)

| Engine | Responsibility | Key Capabilities | |--------|---------------|--

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: TobiasBlask
• Source: TobiasBlask/open-paper-machine
• License: MIT

Install and usage instructions live in the source repository linked above.