Literature Review logo

Literature Review

Community
junruxiong
literature-review

Writes a literature review across the User's Documents on the Question's topic, synthesised by theme rather than one Document after another, showing where the Documents agree and disagree and what they leave out, with every claim cited. Use when the User asks for a literature review, a review of related work, a state-of-the-art overview or a synthesis of several Documents.

Overview

Publisherjunruxiong
RepositoryIncarnaMind
Skill nameliterature-review
Stars
804
Forks
55
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by junruxiong on GitHub. Read the source before you install it.

Installation

Install the Literature Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/junruxiong/IncarnaMind/tree/main/resources/skills/literature-review
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/junruxiong/IncarnaMind.git /tmp/IncarnaMind
mkdir -p .claude/skills
cp -r /tmp/IncarnaMind/resources/skills/literature-review .claude/skills/literature-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Literature Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Literature Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Literature Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Literature review across Documents

Write a literature review of the User's Documents on the topic of the Question: a synthesis organised by theme, never a summary of one Document after another.

Gather the material first

Search across the Documents before writing anything (search_documents searches only the Documents in the Question's Search scope):

  • Search for the topic in several ways: its key terms and their synonyms, each part of the Question, and the methods, findings, definitions and points of debate you expect. After the first results, search again with the terms the Documents themselves use.
  • Make several searches at once, in parallel, rather than one after another: Tool rounds are limited, and you need one at the end to record Citations. Six to ten searches are usually enough.
  • Keep track of which Document each finding comes from, so that you can compare them.
  • If you were given Passages instead of a search Tool, work from those.

Organise by theme

  • Find three to six themes in what the Documents say about the topic: shared questions, methods, findings or debates. Each theme gets its own section.
  • Within a theme, write about the Documents together: what they agree on, where they disagree or report different results, and, where the Passages show it, why (different methods, data, settings or definitions). Name the Documents you compare, as they are named in the Passages.
  • A Document can appear under several themes. Leave out what has nothing to do with the Question.

Structure

Write in the language the Question is written in, even when the Documents are in another language, and translate the headings too.

  1. Introduction: the topic, which Documents the review covers (how many, and what kind), and how it is organised.
  2. One section per theme, as above.
  3. Agreements and disagreements: a short overview of where the Documents converge and where they conflict, if the theme sections haven't made it plain already.
  4. Gaps: what the Documents don't cover, methods or settings nobody tried, and questions none of them answers.
  5. Conclusion: what the Documents, taken together, establish, and how firmly.

Write connected paragraphs; use bullet points sparingly. Don't use tables.

Citations and honesty

  • Cite every claim you take from a Document, the way your instructions for citing say: markers that point to the Passages you found. A claim several Documents support gets a Citation from each of them. Don't write a list of sources or a bibliography.
  • If you were told not to write citation markers, name the Document in the sentence instead.
  • Never cite a Document for something its Passages don't say, and don't add authors, years or other studies from memory. Only the User's Documents are sources here.
  • A gap is a claim about what the Documents don't say: base it on what you searched for, and word it that way ("none of the Documents found discusses …"), not as a claim about all research.
  • If the Documents are too few, or don't address the topic, say so plainly and review only what they support.

Frequently asked questions

What does the Literature Review AI skill do?

Writes a literature review across the User's Documents on the Question's topic, synthesised by theme rather than one Document after another, showing where the Documents agree and disagree and what they leave out, with every claim cited. Use when the User asks for a literature review, a review of related work, a state-of-the-art overview or a synthesis of several Documents.

Why use Literature Review on TypingMind?

Because you install it once and use it with any model. Literature Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Literature Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/junruxiong/IncarnaMind/tree/main/resources/skills/literature-review. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Literature Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Literature Review?

As many as you like. As long as a model supports skills, you can use Literature Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Literature Review AI skill free?

Yes. It is published on GitHub by junruxiong under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇