research-pipeline

Orchestrate an end-to-end research pipeline from idea discovery to manuscript draft.

2|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/chenghaoYang/auto-coder-trainer --skill research-pipeline-chenghaoyang
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-pipeline
Source: https://github.com/chenghaoYang/auto-coder-trainer/tree/main/aris/skills/research-pipeline
Command: npx skills add https://github.com/chenghaoYang/auto-coder-trainer --skill research-pipeline-chenghaoyang

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the full research lifecycle from idea discovery to submission-ready paper, reducing time and manual coordination.

Core Features & Use Cases

  • Idea discovery and literature survey orchestration
  • Implementation and reproducible experiment deployment
  • Auto-review loop with iterative improvements and reporting
  • Generated artifacts: IDEA_REPORT.md, AUTO_REVIEW.md, final manuscript draft

Quick Start

Provide a research direction to start the end-to-end pipeline.

Frequently Asked Questions about research-pipeline

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

FAQPage Schema
How do I automate the research workflow from idea discovery to paper writing?

You can automate the research workflow by orchestrating an end-to-end pipeline that handles idea discovery, experiment planning, and iterative improvements to generate a submission-ready paper.

How does the auto-review loop work for iterative experiment improvements?

The auto-review loop evaluates experimental results and automatically applies iterative improvements, generating an AUTO_REVIEW.md artifact to track evaluation and reporting across multiple stages.

Can I integrate arxiv literature into an automated experiment pipeline?

Yes, the pipeline supports arxiv integration via configurable ARXIV_DOWNLOAD gates, enabling literature survey orchestration and idea discovery based on downloaded papers.

What is the best way to enforce staged execution in an autonomous research lifecycle?

Staged execution is enforced through configurable gates like AUTO_PROCEED and HUMAN_CHECKPOINT, ensuring controlled progression across idea discovery, implementation, and experiment evaluation.

Do I need manual checkpoints when running automated experiments and idea generation?

Manual checkpoints are optional; you can configure HUMAN_CHECKPOINT gates to pause the pipeline for review, or enable AUTO_PROCEED to run the autonomous research lifecycle continuously.

What artifacts are generated by an end-to-end autonomous research pipeline?

The pipeline generates stage-specific artifacts including IDEA_REPORT.md for idea discovery, AUTO_REVIEW.md for evaluation feedback, and a final manuscript draft for submission.