structured-literature-review

structured-literature-review is a skill for Claude Code from redhuntlabs/wizard. It costs 26 tokens per session (1,081 once invoked), scanned A, original, MIT.

A structured process for producing a literature review, which summarizes and evaluates research papers on a defined question. It covers planning, searching, screening, extracting evidence, combining findings, writing, and checking sources.

In plain words
What is it for?
Writing reviews for papers, theses, reports, stakeholder briefs, or new research projects, and updating an existing review with newer evidence.
Why use it?
It turns a broad research task into clear stages with handoff documents and quality checks, reducing missed evidence and unsupported conclusions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wizard plugin — 37 skills, 6 commands, 1 agent, 1 hook shipped together

Good fit Writing reviews for papers, theses, reports, stakeholder briefs, or new research projects, and updating an existing review with newer evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhuntlabs/wizard/structured-literature-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add redhuntlabs/wizard --skill structured-literature-review
Clone the repo
git clone --depth 1 https://github.com/redhuntlabs/wizard

Made for: Claude Code.

Or install wizard, the plugin that ships this one along with the rest of its 37 skills, 6 commands, 1 agent, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for structured-literature-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhuntlabs/wizard/structured-literature-review/github.svg)](https://agentmods.dev/skills/redhuntlabs/wizard/structured-literature-review)
Your own site
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/structured-literature-review"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/structured-literature-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for structured-literature-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/structured-literature-review"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/structured-literature-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,081 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.01081
Opus 5 $0.00013 $0.00541
Sonnet 5 $0.00005 $0.00216
Haiku 4.5 $0.00003 $0.00108

Measured 10d ago against content hash b17be609cbdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

structured-literature-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

spells/research/structured-literature-review/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Structured Literature Review

What this does

Produces a publishable or shareable literature review by running a structured pipeline: scope → search → screen → extract → synthesize → write → verify. Each stage has an explicit handoff artifact and a quality gate.

When to use

  • Writing a literature review for a paper, thesis, or report
  • Producing a "state of the field" memo for stakeholders
  • Building a foundation for a new research project
  • Updating an existing review with new evidence

What you bring (Inputs)

  • Research question (one sentence)
  • Audience (academic / practitioner / executive)
  • Time and depth budget
  • Inclusion criteria you can articulate (date range, source types, languages)

What you get (Output)

A written review (1-20 pages depending on scope) with: scope, methods, themes, evidence map, gaps, and a verified bibliography.

How it works (Steps)

This is a chained workflow with 6 stages and explicit handoffs.

Stages

Stage 1: Scope (handoff: a one-page scope document)

  • Research question
  • Inclusion criteria (date range, study types, geography, languages)
  • Exclusion criteria
  • Audience and depth target

Gate: scope fits on one page; inclusion criteria are specific enough that two people would categorize the same source the same way.

Stage 2: Search (handoff: a list of candidate sources, 30-100)

Run literature-scan to identify the canonical sources. Then expand:

  • Forward citations from those canonical sources
  • Backward citations from recent reviews
  • Database searches with explicit queries (record the queries)

Save: source list with metadata (title, author, year, venue, where you found it).

Gate: at least 30 candidates; search queries are recorded.

Stage 3: Screen (handoff: included sources list, 10-40)

Apply inclusion/exclusion criteria from Stage 1 to each candidate. Record reason for each exclusion.

Gate: included list is non-empty and the exclusion reasons are concrete.

Stage 4: Extract (handoff: a structured table)

Read the full file on GitHub · 131 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 131 lines · 26 tokens per session scan A b17be609cbdb

Subscribe to this mod's changes

structured-literature-review is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 1,081 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.