# Literature Review

> Structured academic literature sweep — cover a topic across sources with per-query caps for a reproducible survey. Use before writing a survey, thesis chapter, or research proposal.

- Skill: `samraddhashrivastavatech/literature-review` (Agent Skill)
- Install (CLI): `npx skillmds@latest add samraddhashrivastavatech/literature-review`
- Raw SKILL.md: https://api.skillmd.com/api/skills/samraddhashrivastavatech/literature-review/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: SAMRADDHASHRIVASTAVATECH (https://skillmd.com/u/samraddhashrivastavatech)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/samraddhashrivastavatech/literature-review

---


# Literature review

Run a structured sweep of the academic literature on a topic.

## When to use

- Surveying a research area before writing/SDL-type documents.
- Checking for gaps: what has been studied, what has not.
- Building the reference base of a `deep-research` objective.

## Tools used

- `literature_review` — from `topic`, sweep with `limit_per_source`
  (default 6).

## Workflow

1. Fix the topic and its scope/boundaries.
2. `literature_review` across the sources (arXiv/Crossref).
3. Cluster by theme/method/position; note gaps and contradictions.
4. Back the survey with the actual papers (`web-reader`/`pdf-research`) rather
   than titles alone.

## Input schema

```json
{ "topic": "str", "limit_per_source": "int" }
```

## Output schema

```json
{ "papers": "list[{title,authors,year,source,url}]", "themes": "object" }
```

## Security

A sweep is a map of the conversation, not a verdict. Surface representative
positions, including dissenting ones; do not cherry-pick to fit a narrative.

## Related skills

`academic-research`, `pdf-research`, `contradiction-search`,
`evidence-extraction`, `knowledge-graph`, `deep-research`