Meta-skill that extracts reusable skill patterns from research papers (arxiv), scientific workflows, and knowledge graph analysis. Activates when analyzing papers for skill patterns, creating skills from research methodologies, or mining patterns from scientific literature. Keywords: extract skill from paper, research skill mining, 论文技能提炼, paper to skill, arxiv skill extractor.
Extracts reusable skill patterns from research papers and scientific workflows.
Research papers contain valuable methodologies that can be extracted into reusable skills. This skill:
read: Read paper abstracts, SKILL.md templateswrite: Create new skill filesexec: Run kg_tool, arxiv search scriptsfeishu_fetch_doc: Fetch paper details if availableUse knowledge graph to identify valuable papers:
kg_tool pagerank kg.db # Find important papers
kg_tool similar kg.db <entity_id> 5 # Find related papers
sqlite3 kg.db "SELECT name, properties FROM kg_entities WHERE entity_type='paper' ORDER BY id DESC LIMIT 10"
Selection Criteria:
For each candidate paper, extract:
| Element | Look For |
|---|---|
| Core Method | Algorithm, workflow, framework name |
| Novelty | What's new vs existing methods |
| Applicability | Domain-general vs domain-specific |
| Implementation | Can it be coded/scripted? |
| Dependencies | Tools, APIs, libraries used |
Pattern Detection Signals:
Generate skill template:
---