acquire-data

Read a download manifest and acquire dataset files into a target directory.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/DamarisDeng/paper-writing-system --skill acquire-data
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: acquire-data
Source: https://github.com/DamarisDeng/paper-writing-system/tree/main/workflow/skills/acquire-data
Command: npx skills add https://github.com/DamarisDeng/paper-writing-system --skill acquire-data

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Stateless data downloader that reads a download manifest and acquires datasets. Used twice in the pipeline: Stage 0 (documented datasets from Data_Description.md) and Stage 4 (supplementary data from research_questions.json).

Core Features & Use Cases

  • Stateless, manifest-driven dataset acquisition
  • Downloads to data/[target_dir]/ and generates README and download report
  • Supports stage-based progress tracking and resume

Quick Start

Run the acquire-data tool with your chosen output folder and manifest file.

Frequently Asked Questions about acquire-data

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

FAQPage Schema
What is the best way to ensure reproducible data acquisition across pipeline stages?

Reproducible data acquisition is achieved by using a stateless downloader that reads a manifest file to fetch datasets, automatically generating a README and download report to document the provenance of the acquired files.

How do I download datasets with extraction and file verification patterns?

Downloading datasets with extraction and file verification requires specifying per-entry download URLs and matching verification patterns within a JSON manifest, allowing the downloader to process and validate files automatically.

Does manifest-based dataset downloading work without external dependencies?

Manifest-based dataset downloading can work without external dependencies by using a stateless approach that reads a JSON manifest and orchestrates file acquisition directly into the data directory structure.

What output files are generated when downloading datasets from a manifest?

Downloading datasets from a manifest generates the acquired dataset files in a data target directory, along with a data/README.md and a download report that document the progress and status of the acquisition.