research-pipeline

Automate ML research pipeline management from ideation through publication.

Updated Mar 16, 2026

Search Tags:#planning #writing #research #spec-driven #pipeline #experimentation

Ready to run

npx skills add https://github.com/WanLanglin/spec-driven-vibe-research-skills --skill research-pipeline-wanlanglin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-pipeline
Source: https://github.com/WanLanglin/spec-driven-vibe-research-skills/tree/main/skills/research-pipeline
Command: npx skills add https://github.com/WanLanglin/spec-driven-vibe-research-skills --skill research-pipeline-wanlanglin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manages and governs ML research projects with a structured, risk-aware pipeline that converts ideas into verifiable artifacts and controlled experiments, reducing wasted compute and misaligned effort.

Core Features & Use Cases

Phase-gated lifecycle with constitutional gates that must be satisfied before progressing.
Artifact-driven output (spec.md, plan.md, tasks.md) to enable clear communication and reproducibility.
Seamless integration of 17 specialized skills across ideation, literature, spec creation, compute planning, experimentation, and writing.

Quick Start

Start a new ML research project using the spec-driven pipeline to generate spec.md, plan.md, and tasks.md, then reproduce a baseline and proceed through incremental experiments.

Frequently Asked Questions about research-pipeline

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

FAQPage Schema

How do I manage an ML research pipeline from ideation to publication?▼

An ML research pipeline can be managed by enforcing a spec-driven approach that generates spec.md, plan.md, and tasks.md. This structure converts ideas into verifiable artifacts and controlled experiments, reducing wasted compute through governed phase gates.

What is a spec-driven approach for machine learning experimentation?▼

A spec-driven approach for machine learning experimentation requires generating spec.md, plan.md, and tasks.md before allocating any compute. It automates lifecycle management by enforcing constitutional phase gates and artifact-driven planning for disciplined experiments.

How can I prevent wasted compute in ML research projects?▼

Wasted compute in ML research projects is prevented by enforcing governance rules that require spec.md, plan.md, and tasks.md before any compute is allocated. This risk-aware pipeline ensures effort remains aligned through controlled experiments and phase gates.

Do I need specific artifacts before running compute for ML experiments?▼

Yes, running compute for ML experiments requires specific artifacts. The pipeline enforces governance by requiring a spec.md, plan.md, and tasks.md to be generated beforehand, ensuring disciplined experimentation and clear reproducibility.

What's the best way to structure reproducible ML research outputs?▼

The best way to structure reproducible ML research outputs is using an artifact-driven pipeline that generates spec.md, plan.md, and tasks.md. This approach enables clear communication and converts ideas into verifiable artifacts across the project lifecycle.