# Paper2agent Paper

Read and answer questions about the final Paper2Agent manuscript, its supplementary...

- Repository: https://github.com/jmiao24/Paper2Agent (3928 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-09-17
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add jmiao24/Paper2Agent --skill paper2agent-paper -g -a claude-code -y`
Codex: `npx skills add jmiao24/Paper2Agent --skill paper2agent-paper -g -a codex -y`
Cursor: `npx skills add jmiao24/Paper2Agent --skill paper2agent-paper -g -a cursor -y`
Gemini CLI: `npx skills add jmiao24/Paper2Agent --skill paper2agent-paper -g -a gemini-cli -y`

## Description

Read and answer questions about the final Paper2Agent manuscript, its supplementary information, figures, and tables.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Paper2Agent final paper

Start with the short [navigation index](references/index.md), then read only the material needed for the question. The documents represent the final manuscript and attachments supplied by the user, rather than the earlier arXiv version.

Use the index to choose a document and section. Locate its exact heading with `rg -n -F -x`, or search topic terms within that document. For example, from this skill directory:

```bash
rg -n -F -x '## 5 Scanpy Agent’s Adaptive Parameter Selection' references/supplement.md
rg -n -i -m 8 --max-columns 240 --max-columns-preview 'mitochondrial|MT-' references/supplement.md
```

Use the returned line numbers with `sed -n` to read a bounded passage, initially around 30, 60 lines. Search previews only locate evidence; read the full relevant paragraphs before answering. Include the section heading and any definitions, table headers or caption needed to interpret the passage. For long sections, narrow to a subsection or prompt first; expand in adjacent batches as needed. Avoid loading both full documents by default. A broad review may require more sections, read progressively. Headings inside fenced prompts/code are quoted content, not document section boundaries.

Each document remains one continuous Markdown file. Figure captions include optional JPEG links; open a figure when the question depends on a plotted value, panel, or visual comparison. Cite the section, figure, or supplementary table supporting the answer. Manuscript paragraph anchors such as `p0046` remain available for precise links.

The supplementary tables appear in the supplementary Markdown and are also available as CSV:

The rest: https://github.com/jmiao24/Paper2Agent/blob/HEAD/skills/paper2agent/paper2agent-paper/SKILL.md