Summarise Document logo

Summarise Document

Community
junruxiong
summarise-document

Writes a structured summary of one Document, or of each Document in the Question's Search scope, covering its key claims (each with a Citation), its methods or approach, its limitations and the questions it leaves open. Use when the User asks to summarise, digest or give an overview of a paper, report or other Document.

Overview

Publisherjunruxiong
RepositoryIncarnaMind
Skill namesummarise-document
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 Summarise Document 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/summarise-document
  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/summarise-document .claude/skills/summarise-document
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Summarise Document 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 Summarise Document 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 Summarise Document 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.

Summarise a Document

Write a structured summary of a Document the User added, drawn only from what its Passages say.

Which Documents

  • If the Question names a Document, or its Search scope holds a single Document, summarise that one.
  • If the Search scope holds several Documents and the Question doesn't pick one, summarise each in turn, in the same structure but shorter, then add a short paragraph on how they relate.
  • If you can't tell which Document is meant, summarise the one the Passages point to and say which one you chose.

Gather the material first

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

  • Make several focused searches rather than one broad one: the Document's main subject, its aims or research question, its methods or data, its findings or results, its limitations, and its conclusions or future work. Run several at once where you can.
  • After the first results, search again with the Document's own terms, and with its name if several Documents are in scope.
  • If you were given Passages instead of a search Tool, work from those.

Write the summary

Write it in the language the Question is written in, even when the Document is in another language. Translate the headings below into that language too.

Start with a heading naming the Document, then one or two sentences on what it is (a paper, a report, a book chapter, …), its subject, and its main contribution. Then these sections:

  1. Key claims: three to seven bullet points, each one claim or finding of the Document, in your own words, each with a Citation. Keep the numbers, conditions and qualifications the Document gives.
  2. Methods or approach: how the Document reaches its claims: its data, experiments, sources, analysis or line of argument.
  3. Limitations: the limitations the Document states itself, with Citations. Limitations you notice yourself go after them, clearly labelled as your own assessment and without a Citation.
  4. Open questions: what the Document leaves open or names as future work, with Citations, then any questions you see, labelled as yours.

Keep it short: a summary, not a rewrite. Bullet points are fine; don't use tables.

Citations and honesty

  • Cite every statement you take from a Document, the way your instructions for citing say: markers that point to the Passages you found. Don't write a list of sources or a bibliography, and never cite a Passage for something it doesn't say.
  • If you were told not to write citation markers, name the Document in the sentence instead.
  • Don't add details the Passages don't give: no names, numbers, dates or sample sizes from memory.
  • When the Passages found don't cover a section, say so plainly in that section (for example: "The Passages found don't describe the methods.") instead of guessing. If the Documents don't support what the Question assumes, say that too.
  • Report the Document's views as the Document's. Keep your own views out, apart from the labelled assessments above.

Frequently asked questions

What does the Summarise Document AI skill do?

Writes a structured summary of one Document, or of each Document in the Question's Search scope, covering its key claims (each with a Citation), its methods or approach, its limitations and the questions it leaves open. Use when the User asks to summarise, digest or give an overview of a paper, report or other Document.

Why use Summarise Document on TypingMind?

Because you install it once and use it with any model. Summarise Document 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 Summarise Document in TypingMind?

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

Which AI models can use Summarise Document?

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 Summarise Document?

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

Is the Summarise Document 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 👇