ai-paper-reproduction

README-first orchestrator for minimal, auditable AI paper repository reproduction.

lllllllama ↓ 9.1k

Claude Code

View source ↗

What it does

The user wants the agent to reproduce an AI paper repository.
The target is a code repository with a README, scripts, configs, or documented commands.
The goal is a minimal trustworthy run, not unlimited experimentation.
The user needs standardized outputs that another human or model can audit quickly.
The task spans more than one stage, such as intake plus setup, or setup plus execution plus reporting.
The task is a general literature review or paper summary.
The task is to design a new model, benchmark suite, or training pipeline from scratch.

Requirements & configuration

The user needs standardized outputs that another human or model can audit quickly.
5. Call analyze-project only when repo structure, insertion points, or suspicious implementation patterns need a read-only pass before continuing.
11. Never auto-route into explore-code or explore-run; exploration requires explicit user authorization.

Configuration: SUMMARYCOMMANDSPATCHES

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

README-first orchestrator for minimal, auditable AI paper repository reproduction.

Source

Repository: https://github.com/lllllllama/ai-paper-reproduction-skill

ai-paper-reproduction FAQ

What does the ai-paper-reproduction skill do?

Main orchestrator for README-first AI repo reproduction. Use when the user wants an end-to-end, minimal-trustworthy reproduction flow that reads the repository first, selects the smallest documented inference or evaluation target, coordinates intake, setup, trusted execution, optional trusted training, optional repository analysis, and optional paper-gap resolution, enforces conservative patch rules, records evidence assumptions deviations and human decision points, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, silent protocol changes, or broad research assistance outside repository-grounded reproduction. The user wants the agent to reproduce an AI paper repository. The target is a code repository with a README, scripts, configs, or documented commands.

What does ai-paper-reproduction require?

The user needs standardized outputs that another human or model can audit quickly. 5. Call analyze-project only when repo structure, insertion points, or suspicious implementation patterns need a read-only pass before continuing. 11. Never auto-route into explore-code or explore-run; exploration requires explicit user authorization. Configuration keys: SUMMARY, COMMANDS, PATCHES.

How do I install ai-paper-reproduction?

Run: npx -y skills add https://github.com/lllllllama/ai-paper-reproduction-skill --skill ai-paper-reproduction --agent claude-code — the source lives at github.com/lllllllama/ai-paper-reproduction-skill.

Maintain ai-paper-reproduction?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![ai-paper-reproduction on getagentictools](https://getagentictools.com/badge/skills/lllllllama-ai-paper-reproduction-skill-ai-paper-reproduction.svg)](https://getagentictools.com/skills/lllllllama-ai-paper-reproduction-skill-ai-paper-reproduction?ref=badge)

npx agentictools info skills/lllllllama-ai-paper-reproduction-skill-ai-paper-reproduction

The second line is the CLI lookup for this page — handy in READMEs and docs.