model:lit-review

Extracts structured notes from research papers and blogs for weekly quant literature reviews.

Updated Jun 27, 2026
One-click install
npx skills add https://github.com/HKUST-QUANT-SOCIETY/quantcode --skill model-lit-review-hkust-quant-society
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: model:lit-review
Source: https://github.com/HKUST-QUANT-SOCIETY/quantcode/tree/main/.opencode/groups/model/skills/model-lit-review
Command: npx skills add https://github.com/HKUST-QUANT-SOCIETY/quantcode --skill model-lit-review-hkust-quant-society

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Weekly literature sharing meetings produce scattered, unstructured meeting notes that are hard to search and reuse. This Skill converts papers, arXiv links, and blog posts into a consistent structured format so the model group can review and retain research knowledge. ## Core Features & Use Cases - Structured Extraction: Parses PDFs and web pages, then extracts problem, method, experiment, result, and takeaway fields for each source. - Unified Output Schema: Generates per-paper YAML records with relevance to quant, possible model features, and implementation risk ratings. - Group Knowledge Candidates: Submits summaries through a governed knowledge-candidate interface for review instead of directly editing protected group memory. - Use Case: Before the weekly model group meeting, feed three arXiv papers on alpha factors into the Skill and receive a ready-to-present markdown summary plus structured notes for the group knowledge base. ## Quick Start Ask the agent to structure these three paper links into literature review notes for this week's model group sharing session, covering alpha and portfolio topics.

Frequently Asked Questions about model:lit-review

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

FAQPage Schema
How do I turn research papers into structured literature review notes?

Provide the paper PDFs, arXiv links, or blog URLs along with optional topics of interest. The Skill fetches the content and extracts problem, method, experiment, result, and takeaway fields into a unified YAML schema for each source.

What input formats does this literature review workflow accept?

It accepts paper PDFs, arXiv links, and blog URLs, either as a single source or multiple sources at once. You can also specify topics of interest and related directions such as alpha, portfolio, execution, risk, or infra.

Can the structured notes be shared directly with a research group?

Yes, the Skill generates a markdown summary ready for weekly sharing meetings. It also submits knowledge candidates through a governed review interface rather than directly editing protected group memory files.

What fields are included in the output schema for each paper?

Each paper record includes title, authors, publication date, problem, method, experiment, result, takeaway, relevance to quant, possible model features, and an implementation risk rating of low, medium, or high.

What are the limitations of automated literature structuring?

Extraction quality depends on successful PDF parsing or web fetching, so paywalled or malformed sources may be incomplete. Shared knowledge promotion only completes with explicit approval and a confirmed success receipt from the review process.