evidence-draft

Generate evidence packs with claim candidates and citation-backed snippets.

497|38|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill evidence-draft
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: evidence-draft
Source: https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/evidence-draft
Command: npx skills add https://github.com/WILLOSCAR/research-units-pipeline-skills --skill evidence-draft

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the creation of detailed evidence packs for research paper sections, ensuring every claim is backed by traceable citations and structured data, thereby streamlining the literature review and writing process.

Core Features & Use Cases

  • Evidence Pack Generation: Creates per-subsection evidence packs including claim candidates, comparisons, evaluation protocols, limitations, and citation-backed snippets with provenance.
  • Data Integration: Consolidates information from subsection briefs, paper notes, citations, and optional evidence banks/bindings.
  • Use Case: When drafting a literature survey, use this Skill to automatically compile all relevant evidence for a specific subsection, ensuring that claims made in the draft are directly supported by the source material and its metadata.

Quick Start

Use the evidence-draft skill to create evidence packs for the subsection briefs found in outline/subsection_briefs.jsonl.

Frequently Asked Questions about evidence-draft

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

FAQPage Schema
How do I generate evidence packs for research paper subsections from literature notes?

To generate evidence packs, process your subsection briefs, paper notes, and citations to automatically extract claim candidates, concrete comparisons, evaluation protocols, limitations, and citation-backed snippets with provenance for your research paper.

What is citation-backed evidence generation for academic writing?

Citation-backed evidence generation is the process of extracting claim candidates and evaluation protocols from subsection briefs and notes, ensuring every research draft claim is directly supported by traceable source material and metadata.

How do I ensure data provenance when drafting a literature review?

Ensure data provenance by processing subsection briefs and citations into structured evidence packs that pair extracted claim candidates and comparison snippets with their original traceable source material and metadata.

Can I compile evaluation protocols and limitations from paper notes automatically?

Yes, you can compile evaluation protocols and limitations automatically by processing your paper notes and citations into structured evidence packs designed to extract concrete comparisons and citation-backed snippets.

Do I need pre-formatted subsection briefs to use this evidence generation workflow?

Yes, you need pre-formatted subsection briefs, typically stored in JSONL format, along with your paper notes and citations, to consolidate information and generate structured evidence packs for your research writing.

What is the best way to structure literature review evidence for research writing?

The best way to structure literature review evidence is generating per-subsection evidence packs that organize claim candidates, comparisons, evaluation protocols, limitations, and citation-backed snippets with provenance for traceable drafting.