lc-new

Scope a research question into a complete astra.yaml project specification.

18|2|Updated Feb 15, 2026
One-click install
npx skills add https://github.com/LightconeResearch/lightcone-cli --skill lc-new
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lc-new
Source: https://github.com/LightconeResearch/lightcone-cli/tree/main/claude/lightcone/skills/lc-new
Command: npx skills add https://github.com/LightconeResearch/lightcone-cli --skill lc-new

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you turn a raw research question into a complete, structured ASTRA specification without starting from scratch or guessing how to organize inputs, outputs, and decisions.

Core Features & Use Cases

  • Interactive scoping into astra.yaml: Collects and refines your research question, then writes the evolving specification into astra.yaml so you can see progress as the project takes shape.
  • Structured analysis design: Transforms “what are we trying to do?” into a concrete analysis structure with clearly separated single-purpose outputs.
  • Evidence-informed decision creation: Guides a literature deep dive, delegates PDF extraction to lc-extractor agents, and then identifies and reviews candidate decisions with evidence links.

Quick Start

Tell the AI to start a new analysis scope from your research question by saying: “/lc-new: Scope a new ASTRA analysis for my research question and build the astra.yaml spec.”

Frequently Asked Questions about lc-new

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

FAQPage Schema
How do I scope a new research analysis from a raw question into a structured YAML spec?

Scoping a new research analysis involves conversation-guided structuring that refines your raw research question and iteratively writes the evolving project specification into an astra.yaml file.

How does literature extraction work when identifying evidence-informed research decisions?

Literature extraction for evidence-informed decisions delegates PDF parsing to lc-extractor agents, which feeds validated outputs back into the main specification for candidate decision identification and review.

What is the best way to structure analysis outputs to separate single-purpose project decisions?

The best way to structure analysis outputs is through interactive scoping that transforms your research goals into a concrete analysis structure with clearly separated single-purpose outputs.

Can I use lc-new to set up a project spec without any prior dependencies installed?

Yes, you can set up a project spec without prior dependencies, as the tool requires no external components and relies entirely on YAML frontmatter-defined metadata to guide the initial analysis workflow.

How do I validate the generated astra.yaml specification after completing the initial scoping?

You validate the generated astra.yaml specification by running the astra validate command, which checks the project specification after delegated per-paper extraction and iterative writes are finalized.

When should I not use a guided YAML workflow for research scoping?

A guided YAML workflow for research scoping is not suited for projects lacking a defined research question, or when you need rapid, unstructured note-taking instead of an evidence-informed, iterative specification build.