ar-retrieval

Generate deduplicated SourceRecord entries and a corpus_manifest from workspace inputs.

Updated Mar 22, 2026

Search Tags:#policy #web-search #corpus #retrieve #scholarly #academia #source-records

Ready to run

npx skills add https://github.com/ShinyGua/AutoArtsResearch --skill ar-retrieval

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ar-retrieval
Source: https://github.com/ShinyGua/AutoArtsResearch/tree/main/.claude/skills/ar-retrieval
Command: npx skills add https://github.com/ShinyGua/AutoArtsResearch --skill ar-retrieval

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Corpus retrieval for arts and social sciences requires assembling a structured set of sources from multiple domains (academic, policy, media, and reports) to support scoping and audit trails. This skill automates that process by translating research questions and scope into targeted searches and curated source records.

Core Features & Use Cases

Automated parameter extraction from a scoping document and generation of SourceRecord entries for each retrieved source.
Category-aware search strategy that balances academic, policy, media, and think-tank materials, with deduplication and manifest generation.
Suitable for a Claude Code workflow that feeds downstream analysis, peer review scoring, and export pipelines.

Quick Start

Provide a workspace path to initiate corpus retrieval and automatically generate source records and a corpus manifest.

Frequently Asked Questions about ar-retrieval

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

FAQPage Schema

How do I assemble a structured scholarly corpus from diverse sources?▼

To assemble a scholarly corpus, you need to search and curate academic, policy, media, and report materials into structured source records. This requires translating research questions into targeted searches and deduplicating results into a manifest.

What is the best way to retrieve academic and policy sources for a literature review?▼

Retrieving sources for a literature review involves applying a category-aware search strategy that balances academic and policy materials. You can parse workspace scoping inputs to generate deduplicated source records and a corpus manifest for downstream analysis.

Can I automate corpus retrieval for arts and social sciences research?▼

Yes, you can automate corpus retrieval by extracting parameters from a scoping document to generate targeted searches. This process automatically translates research scope into curated source records across academic, policy, and media domains.

How do I generate source records and a corpus manifest from a scoping report?▼

You generate source records and a corpus manifest by providing a workspace path to initiate retrieval. The system parses the scoping report, applies category-aware searches, deduplicates results, and writes the structured manifest.

Does this corpus retrieval approach work for comparative case studies and policy analysis?▼

Yes, this corpus retrieval approach works for comparative case studies and policy analysis workflows. It curates balanced source records from academic, policy, media, and think-tank materials to support scoping and audit trails.

What are the limitations of automated source record retrieval for academic research?▼

Automated source record retrieval requires a pre-existing scoping report to extract search parameters. It is designed for Claude Code workflows feeding downstream analysis, meaning it relies on structured workspace inputs rather than open-ended queries.