Decompose Review Modules logo

Decompose Review Modules

Community
xingtaxueshu
decompose-review-modules

Decompose a refined research question for a literature review into 3-5 clear, mostly non-overlapping review modules. Use when the user has a core review question and needs to build a literature review structure, reading map, subsection outline, coding scheme, or module-based search plan instead of listing papers author by author. 触发词:综述结构、拆模块、综述提纲、检索计划。

Overview

Publisherxingtaxueshu
Repositoryliterature-review-skills
Skill namedecompose-review-modules
Stars
78
Forks
6
Bundled files
9
LicenseMIT
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.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Decompose Review Modules 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/xingtaxueshu/literature-review-skills/tree/main/skills/decompose-review-modules
  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/xingtaxueshu/literature-review-skills.git /tmp/literature-review-skills
mkdir -p .claude/skills
cp -r /tmp/literature-review-skills/skills/decompose-review-modules .claude/skills/decompose-review-modules
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Decompose Review Modules 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 Decompose Review Modules 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 Decompose Review Modules 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.

Decompose Review Modules

Discipline And Interview Setup

Read discipline-routing.md, then only the selected discipline profile. Reuse the user's existing brief; do not restart intake at each stage. For journalism/communication or information science, use that profile's concepts, extraction fields, and appraisal checks instead of a generic social-science template.

When the user requests "grill me", 追问, or 模拟答辩, read research-interview.md. Ask one decision-relevant question per turn and wait; do not generate the stage deliverable until enough decisions are settled or the user asks to proceed. In quick/no-question mode, record assumptions and continue without inventing answers.

For evidence extraction or drafting, read review-workflow.md. With no sources, give a plan or outline, not a purported synthesis. If reference files are unavailable, retain the source guardrails below and state that discipline guidance is missing.

Goal

Convert one core research question into a small set of review modules that cover the key dimensions of the problem without collapsing into a loose topic list.

Workflow

  1. Restate the core question in one sentence.
  2. Identify the main actors, mechanisms, outcomes, contexts, and constraints embedded in the question.
  3. Propose 3-5 modules that are independent enough to become review sections.
  4. Check whether sub-questions repeat. A paper may inform several modules; record separate evidence contributions rather than forcing each paper into one bucket.
  5. Check coverage: the modules together should explain the main question's key dimensions.
  6. Assess coverage only from the supplied or retrieved corpus. Without it, label module coverage "not assessed"; do not infer a gap or literature density from the outline.

Module Design Rules

Good modules should be:

  • Mutually distinguishable: each module asks a different sub-question.
  • Collectively useful: together they help answer the core question.
  • Literature-searchable: each can generate keywords, inclusion criteria, and section titles.
  • Analytical rather than decorative: use a distinct synthesis task for each section, including conceptual or historical tasks; a mechanism is not mandatory.

Common Module Axes

Choose axes that fit the question:

  • Drivers: economic incentives, capability thresholds, social networks, institutional environment.
  • Mechanisms: perception, decision process, resource allocation, coordination, feedback loops.
  • Actors: individuals, organizations, platforms, governments, communities.
  • Stages: adoption, use, persistence, exit, diffusion.
  • Contexts: region, industry, policy period, population type, technology maturity.
  • Outcomes: performance, equity, participation, sustainability, resilience.

Output Format

Provide:

markdown
## Core Question

[One sentence]

## Proposed Modules

| Module | Sub-question | Include | Exclude |
|---|---|---|---|
| ... | ... | ... | ... |

## Coverage Check

- What the modules cover well: ...
- Possible missing dimension: ...
- Possible overlap to revise: ...

## Suggested Review Outline

1. ...
2. ...
3. ...

## 待核实清单

[Unverified sources, "未查到" results, sentences marked [需补来源], and inferences that still need checking; write "无" if empty]

## 给作者的问题

[Judgment calls that belong to the author; write "无" if empty]

The output sections above, and the two closing sections, keep fixed names and order; see references/output-contract.md (a copy bundled in this skill folder).

Guardrails

  • Do not create more than five main modules unless the user explicitly asks for a large taxonomy.
  • Do not organize modules only by author, year, country, or method unless that is the analytical point.
  • When the user gives only a broad topic, first invoke question refinement logic before decomposing modules.
  • Source integrity: follow references/source-integrity.md. Search keywords and expected literature distribution are suggestions, not findings; do not name specific papers unless the user provided them. Use only sources the user provided or that are verified, tag each with a status (用户提供 / 已核验 / 未核验), write "未查到" instead of completing authors, year, journal, or pages, and put anything unverified in ## 待核实清单. If that file is not available, still apply these rules.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Decompose Review Modules AI skill do?

Decompose a refined research question for a literature review into 3-5 clear, mostly non-overlapping review modules. Use when the user has a core review question and needs to build a literature review structure, reading map, subsection outline, coding scheme, or module-based search plan instead of listing papers author by author. 触发词:综述结构、拆模块、综述提纲、检索计划。

Why use Decompose Review Modules on TypingMind?

Because you install it once and use it with any model. Decompose Review Modules 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 Decompose Review Modules in TypingMind?

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

Which AI models can use Decompose Review Modules?

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 Decompose Review Modules?

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

Is the Decompose Review Modules AI skill free?

Yes. It is published on GitHub by xingtaxueshu under the MIT 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 👇