Skip to content
Agentmart
Submit a tool

literature

Handle literature review tasks: searching arXiv papers, downloading PDFs, extracting key claims, identifying evidence quality, checking citations, and…

Skill by science-agent

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/suhyeong10-literature

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Handle literature review tasks: searching arXiv papers, downloading PDFs, extracting key claims, identifying evidence quality, checking citations, and summarizing scientific findings.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/literature

Tools it pre-approves 2

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • run_scitool,
  • read_file

What's inside

Skill name
literature
Description
Handle literature review tasks: searching arXiv papers, downloading PDFs, extracting key claims, identifying evidence quality, checking citations, and summarizing scientific findings.
License
MIT
Allowed tools
run_scitool,, read_file
Metadata
author: science-agent · version: 1.0
Instructions
33 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Literature Review Skill

Use this skill when the user asks about research papers, scientific evidence, or wants literature searched.

## Available Tools
- `DownloadPapers(keyword)` — Download papers from arXiv by keyword
- `DownloadPapersMuti(keywords_str)` — Multi-keyword paper download
- `PaperQA(question)` — Q&A over downloaded PDF papers

## Reading PDF files
Use `read_file` for PDFs already in the workspace.

## Extraction Framework
When reading a paper, always extract:
1. **Main claim** — What does the paper claim?
2. **Evidence** — What data/experiments support it?
3. **Methods** — How was it tested? Sample size, controls?
4. **Limitations** — What do the authors admit as limits?
5. **Conclusions** — Are conclusions supported by the evidence?

## Citation Quality Assessment
- Level 1: Peer-reviewed RCT or systematic review
- Level 2: Observational cohort study
- Level 3: Case study or expert opinion
- Level 4: Preprint (not yet peer-reviewed)

## Workflow
1. If user provides PDF path, use `read_file` to read it
2. If searching topic, use `DownloadPapers` then `PaperQA`
3. Extract claims using the framework above
4. Flag unsupported claims explicitly

From suhyeong10/Science-Agent, MIT.

More from suhyeong10/Science-Agent

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Apr 22, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Version
1.0
License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from science-agent

Cite this page

literature skill. Agent Mart. https://agentmart.dev/skills/suhyeong10-literature (last updated 2026-10-24)