Skip to content
Back to skills

Academic Research

ASecurity

Search academic papers, scholarly articles, and research publications through SandBase. Use when asked for literature review, academic citations, scholarly research, paper discovery, or scientific evidence gathering.

  • 200 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 5, 2026
ai-agentsapidatabase

Works with

  • api
  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned September 26, 2026

npx -y skills add sandbaseai/sandbase-skills --skill academic-research --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Academic Research?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Academic Research
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/sandbaseai-academic-research/badge)](https://www.skillsdirectory.com/skills/sandbaseai-academic-research)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: academic-research
description: Search academic papers, scholarly articles, and research publications through SandBase. Use when asked for literature review, academic citations, scholarly research, paper discovery, or scientific evidence gathering.
---

# Academic Research

Academic paper search and research synthesis through SandBase. Find scholarly articles, search across academic databases, and get AI-powered explanations of findings. Read [the API map](references/sandbase-api-map.md) before selecting a capability.

## Call SandBase capabilities

Use the capability identifiers below as discovery hints, not MCP tool names. Find the matching endpoint with `sandbase_discover(q: "<provider and capability>")`; use its returned `name` in `sandbase_inspect(name: "<returned name>")`. Read `inputSchema`, pricing, and `execute_as`, then call `sandbase_run` using `execute_as.arguments.name` and schema-defined `arguments`. If a `run_id` is returned, poll `sandbase_run_get(run_id: "<returned run_id>")` within the task budget until `completed` or `failed`; report pending or failed runs without resubmitting them automatically.

## Operating principles

- Distinguish peer-reviewed sources from preprints and working papers.
- Cite papers with title, authors, year, and source.
- Use academic search for evidence-based claims; use web search for current context.
- Note publication recency — older papers may not reflect current consensus.

## Workflow

### 1. Search academic literature

Use `scholar_search_scholar` for pure academic/scholarly results.
Use `scholar_search_web` for broader web-inclusive academic search.
Use `scholar_search_mixed` for combined academic + web results (best default).

### 2. Analyze and explain

Use `scholar_explain` to get AI-powered confidence-scored explanations of research findings.

## Output

Return: paper citations (title, authors, year, source), key findings, methodology notes, evidence strength, and research gaps.

## Example tasks

- "Find recent academic papers about [topic] published in the last 2 years."
- "What does the research say about [question]? Cite the key studies."
- "Find papers comparing [approach A] vs [approach B] in [field]."
- "Literature review on [topic] — give me the top 10 papers with summaries."
- "What's the current scientific consensus on [claim]?"

Files in this skill

  • SKILL.md1.9 KB
  • references/sandbase-api-map.md629 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.