skills.rest
kamilseghrouchni
kamilseghrouchniCOMMUNITY
Explore all skills by this author →
GitHub

compile-extract

Extract structured intelligence fragments from paper.md into JSON.

Updated Mar 31, 2026
Search Tags:#provenance#json#extract#fragments#structured-data#paper
One-click install
npx skills add https://github.com/kamilseghrouchni/vcro-sourcing --skill compile-extract
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: compile-extract
Source: https://github.com/kamilseghrouchni/vcro-sourcing/tree/main/.claude/skills/compile/extract
Command: npx skills add https://github.com/kamilseghrouchni/vcro-sourcing --skill compile-extract

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill reads a single paper.md and outputs a structured JSON representation of intelligence fragments, enabling downstream analysis without modifying source documents or the wiki.

Core Features & Use Cases

  • Read one paper.md and produce a deterministic JSON fragment set for downstream ingestion.
  • No wiki writes: ensures the source graph remains unchanged; fragments are emitted only as JSON.
  • Reuse and auditing: outputs include provenance quotes and structured fields suitable for auditing and re-use in commissioning workflows.

Quick Start

Provide the path to a paper.md and run the extract phase to emit a structured JSON fragment bundle.

Frequently Asked Questions about compile-extract

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

FAQPage Schema
How do I extract structured JSON from a paper.md file?▼

Extracting structured JSON from a paper.md file involves reading the YAML frontmatter and full paper body to produce deterministic intelligence fragments, outputting a JSON bundle with source, entity_hints, fragments, and open_questions.

What is the vcro-compile extract schema for structured paper fragments?▼

The vcro-compile extract schema is a structured JSON format that organizes extracted paper intelligence into source, entity_hints, fragments, and open_questions fields for downstream analysis.

Does the paper extraction process write data back to the wiki?▼

The paper extraction process does not write to the wiki. It emits structured JSON fragments only, ensuring the source graph remains unchanged and preserving original document integrity.

How do I get provenance quotes from a markdown paper for auditing?▼

Provenance quotes are included in the JSON output when extracting from a paper.md file, providing structured fields suitable for auditing and reuse in commissioning workflows.

Can I extract intelligence fragments from multiple papers at once?▼

The extraction process handles one paper.md file at a time, producing a deterministic JSON fragment set for downstream ingestion without batch processing capabilities.

Related Skills

Explore More Data & Analytics Skills→
RenJW418RenJW418

paper-analyzer

Extract 12 research elements from academic PDFs and Word files into Excel.

Community
Intermediate
kamilseghrouchnikamilseghrouchni

compile-resolve

Analyze fragment files and wiki index to generate a resolution_plan.json.

Community
Intermediate
oakossoakoss
14

knowledge-graph-builder

Design ontologies and select graph databases for knowledge graph implementation.

Official
Advanced
walter-lawalter-la

dummy-02-extract

Extract structured data from unstructured text using a shared JSON schema.

Community
Basic