Showcase · Amplifier Bundle

Write Better
Papers, Faster

Rigorous AI-assisted academic paper authoring for every research format — from sharpened question to venue-ready PDF.

v0.8.5 · MIT License
May 2026 · michaeljabbour/amplifier-bundle-research
The Problem

AI helps you
write — not think

🧪

Rigor Takes a Decade

Precise questions, locked methodology, honest reporting against yourself, proper citations — researchers learn these habits over years. Everyone else reinvents the mistakes.

🚨

Overclaiming Everywhere

LLMs default to confident prose. Without guardrails, exploratory findings get reported as confirmatory — and causal language replaces correlation.

📚

Format Fragmentation

NeurIPS, ACL, IEEE, USPTO, NSF — every venue has different templates, page limits, and compliance checklists. Each one is a manual burden.

Scientific rigor is a set of habits. This bundle encodes the habits — so a patent attorney, a policy analyst, or a junior researcher drafting their first workshop paper all get the same scaffolding and the same honest critic.

The Solution

Full research
lifecycle

Six disciplined modes walk you from raw intuition to venue-ready output — with pre-registration lockdown and honest-pivot enforcement baked in.

1

/question

Sharpen a rough claim into a falsifiable research question with explicit predictions, named mechanisms, and disconfirmation criteria.

2

/study-plan

Lock your methodology before seeing results. Hash-sealed pre-registration with power analysis, named tests, and alpha levels.

3

/execute

Run the analysis, gather prior art, or pull evidence — depending on what you're making. Execution log tracks every step.

4

/critique → /draft → /publish

Honest peer review names specific limitations. Draft produces venue-structured output. Publish blocks until critique has run and honest-pivots are acknowledged.

8 Paper Types

One bundle, every research format

Empirical Paper

Full IMRAD structure with CONSORT/STROBE compliance, pre-registration, and honest-pivot enforcement.

Benchmark Paper

Dataset releases, method comparisons, and performance evaluations with protocol definition and fairness checks.

Grant Proposal

Funding applications for NSF, NIH, DARPA. Feasibility scoring, well-powered research plans, preliminary data emphasis.

Patent Brief

USPTO-style invention disclosure with prior-art section and claim chart for filing attorneys.

Literature Review

Systematic review with PRISMA compliance, multi-database search logging, and evidence synthesis.

White Paper

Technical thesis defense for decision-makers with comparative analysis and practical case studies.

Policy Brief

Evidence-based briefs for policymakers with counter-argument coverage and implementation feasibility.

Replication Study

Reproducibility research measuring deviations against original claims. Honest-pivot measures drift, not fresh hypotheses.

Architecture

14 agents, 6 modes, 7 tool modules

🧑‍🔬

Researcher

You — any skill level, any venue, any document type

🎯

Coordinator

Routes intent to the right mode/agent, enforces honest-pivot

📄

Venue Output

NeurIPS, ICML, ACL, IEEE, ACM, arXiv, USPTO, NSF, policy memo

Thinking Agents

Hypothesis designer, methodologist, statistician, preregistration reviewer — sharpen the question and lock the method.

Writing Agents

Paper architect, technical writer, citation manager, figure designer, venue formatter — structure and produce the artifact.

Quality Agents

Honest critic, ML paper reviewer, literature scout, idea generator — review, challenge, and strengthen the work.

Key Features

Discipline by default

Pre-Registration Lockdown

Hash-sealed study plans before you see results. The preregistration-reviewer checks predictions are specific and directional, tests are named, alpha levels set, MDEs calculated. Issues pass/fail/warn per section.

Honest-Pivot Enforcement

If your data contradicts the pre-registration, exploratory findings are automatically labeled as such. /publish blocks until pivots are acknowledged. No silent overclaiming.

PaperBanana Figures

Multi-agent figure generation with 8 quality veto rules: vector format, readable text (≥8pt), colorblind-safe palette, error bars, white background, proper aspect ratio, no misleading axis truncation, unobstructed legends.

Cross-Vendor Judge

Mitigates reflexivity hazards by routing critique through a different LLM vendor than the one that drafted. No model grading its own homework.

The honest-critic issues BLOCK/WARN/NOTE findings with severity levels. BLOCK items must be resolved before /draft. It argues against the work: overclaiming, methodology gaps, alternative explanations, limitation specificity.

Quick Start

Natural language, full pipeline

# Install amplifier bundle add --app git+https://github.com/michaeljabbour/amplifier-bundle-research@main amplifier bundle use research # Run any paper type with natural language amplifier run "Run the empirical-paper recipe on: Reflection tokens improve long-horizon reasoning" amplifier run "Run the patent-brief recipe on: Novel rolling-ROI control for AI agent sessions" amplifier run "Run the literature-review recipe on: Systematic review of chain-of-thought methods" # Or use slash commands interactively /question # sharpen the claim /study-plan # lock the method /execute # run the analysis /critique # honest peer review /draft # produce the artifact /publish # format for venue
By the Numbers

Built in 8 active dev days

14
Specialized agents
9
Venue formats
279
Files in repo
51K
Lines of content

7 Tool Modules

Experiment audit, power analysis, provenance check, stage analyzer, block-hypothesis, resume/repair, PaperBanana — each with CLI and tests.

28 Test Files

~4,946 lines of tests across 7 Python tool modules. ~13,048 lines of Python source. Real assertions, real coverage.

11 Behaviors

Honest-pivot, exploratory-labeling, PaperBanana, figure-generation, LaTeX authoring, conference-styling, cross-vendor-judge, stop-slop, and more.

Sources & Methodology

How we built this deck

Repository: michaeljabbour/amplifier-bundle-research (v0.8.5, MIT License)

Data collection: git log, git shortlog -sne, directory listings, file line counts via wc -l, README.md, bundle.md frontmatter, and team-knowledge YAML capability manifests.

Lineage: Thin wrappers over K-Dense scientific-agent-skills, orchestrated with Superpowers-style mode workflow, informed by Denario multi-agent topology. Gene-transfers from AI-Scientist (idea-generator, ML-paper-reviewer, literature-scout) and amplifier-bundle-scientificpaper (paper-architect).

Deck generated: May 2026. All figures are repo-verifiable counts, not estimates.

Get Started

Your next paper
starts here

Install with one command. Every paper type. Every venue. Pre-registration, honest critique, and PaperBanana figures — built in.

amplifier bundle add --app git+https://github.com/michaeljabbour/amplifier-bundle-research@main amplifier bundle use research amplifier
github.com/michaeljabbour/amplifier-bundle-research
MIT License · 14 agents · 8 paper types · 9 venue formats
More Amplifier Stories