publish-paper

Orchestrates validation and release of academic AI-agent publication bundles.

14|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/LionSR/AgenticPublicationProtocol --skill publish-paper
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: publish-paper
Source: https://github.com/LionSR/AgenticPublicationProtocol/tree/main/skills/publish-paper
Command: npx skills add https://github.com/LionSR/AgenticPublicationProtocol --skill publish-paper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces the effort readers face when trying to understand and reproduce scientific papers by packaging the paper with the instructions and artifacts needed to run an AI agent that can explain and help reproduce the work.

Core Features & Use Cases

  • Staging an APP publication bundle: Creates a clean, self-contained publication candidate in publication-staging/ that an external agent can treat as the repository root.
  • Multi-phase validation and paper-agent documentation: Runs structured validation, produces AGENTS.md/README.md/CLAUDE.md for the paper agent, and performs a staging-root smoke test.
  • Controlled publishing workflow: In real mode, promotes the validated staging tree to a tagged public release and generates APP_PUBLICATION.json; in developer sandbox mode, records an implementation-test outcome without creating public compliance records.
  • Use case: Turn an existing author working repo (paper + code/data/figures) into an APP release so readers can open the repo with an AI coding agent and ask questions grounded in the paper and reproducible artifacts.

Quick Start

Ask your AI assistant to run /publish-paper with your working repository as context, and follow the phase prompts until the validated publication-staging/ is ready for real publication or a developer sandbox test.

Frequently Asked Questions about publish-paper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I package my academic paper for reproducible AI agents?

You package your academic paper for reproducible AI agents by staging a self-contained publication bundle containing paper sources, code, and data, then generating AGENTS.md and README.md files to guide the agent.

What is the Agentic Publication Protocol for scientific workflows?

The Agentic Publication Protocol is a publishing standard that bundles academic papers with code, data, and agent instructions, allowing readers to use an AI agent to ask questions and reproduce the scientific workflows.

How do I validate a reproducible publication package before release?

You validate a reproducible publication package by running structured multi-phase validation checks at the structure and agents-md stages, followed by a staging-root smoke test to ensure the bundle is ready for release.

Can I test academic publishing workflows without creating a public GitHub release?

Yes, you can test academic publishing workflows in a developer sandbox mode that records an implementation-test outcome and validates the publication-staging tree without creating public compliance records or a tagged release.

What files are needed to make a scientific repository readable by AI coding agents?

To make a scientific repository readable by AI coding agents, you need AGENTS.md, README.md, and CLAUDE.md files containing paper-agent instructions, along with the bundled paper sources and reproducible artifacts.

How do I generate an APP_PUBLICATION.json manifest for a tagged release?

You generate an APP_PUBLICATION.json manifest by promoting a fully validated publication-staging tree to a real mode tagged public release, finalizing the academic paper as a reproducible bundle.