Agent Skills
› companion-inc/feynman
› pdf-explore
pdf-explore
GitHub用于跨页、多章节分析科学PDF，提取并交叉验证方法、图表、引用等关键信息，确保结论有据可依。
Trigger Scenarios
需要从多篇或单篇PDF的多处提取信息
需要交叉验证论文中的声明与方法、图表或补充材料
Install
npx skills add companion-inc/feynman --skill pdf-explore -g -y
SKILL.md
Frontmatter
{
"name": "pdf-explore",
"description": "Read, extract, and cross-check content across scientific PDFs. Use when a task needs methods, figures, tables, citations, accessions, or claims from multiple places in one or more papers."
}
PDF Explore
Use this skill when a PDF answer depends on more than one page or section.
Workflow:
- Parse or inspect the full PDF enough to map title, abstract, methods, figures, tables, supplement references, and citations.
- Extract the exact pages and regions that support the answer. Use Feynman's PDF preview annotations for page/line/rectangle anchors when available.
- Keep table values, figure labels, accession IDs, and quoted snippets tied to page numbers.
- Cross-check claims against methods, captions, supplement text, and cited papers when the conclusion depends on them.
- Save extracted notes, annotations, and provenance as artifacts.
Do not answer from a single visible page when the question spans methods, figures, or supplements.
Version History
- 54d08a3 Current 2026-07-25 07:16
