Focus logo

Focus

Community
stephenturner
focus

A rigorous, detail-preserving summarization method for academic papers, reports, and long-form documents. Based on the FOCUS workflow (Lin, 2025, Nature Biotechnology). Extracts every key point with specific details and embedded direct quotes, organized section by section, then produces a clean final output with an overview/takeaway. Trigger this skill whenever the user types "/focus", says "summarize with focus", "FOCUS summary", "use the focus method", or asks for a thorough/exhaustive/detailed summary of a paper or document that should capture every key insight. Also trigger when the user wants a summary that preserves direct quotes and specific details (e.g., numbers, effect sizes, comparisons) rather than a high-level gloss.

Overview

Publisherstephenturner
Repositoryskill-focus
Skill namefocus
Stars
74
Forks
6
Bundled files
Instructions only
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.

  • Self-contained

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

  • Open source

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

Installation

Install the Focus 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/stephenturner/skill-focus/tree/main
  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/stephenturner/skill-focus.git \
  .claude/skills/focus
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Focus 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 Focus 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 Focus 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.

FOCUS Summarization Skill

This skill implements a two-step summarization method adapted from the FOCUS workflow (Lin, 2025, Nature Biotechnology). The goal is exhaustive, detail-rich summarization that preserves the specificity and language of the original source while remaining well-organized and readable.

When to use

  • The user invokes /focus or asks for a "FOCUS summary"
  • The user wants every key point extracted from a paper or document, not just the highlights
  • The user wants direct quotes embedded naturally alongside summarized points
  • The user needs section-by-section coverage of an academic paper or structured document

Core principles

  1. Exhaustiveness over brevity. Do not skip key points to save space. If a document has 30 distinct insights, list all 30.
  2. Specificity is mandatory. Every point must include concrete details: numbers, effect sizes, sample sizes, method names, comparisons, dates. Vague paraphrases are failures.
  3. Quotes support, not duplicate. Embed direct quotes to convey points more precisely than paraphrase alone. Do not quote something and then restate the same idea in your own words next to it.
  4. No meta-discourse. Never write "In this section, the authors argue..." or "Below is a summary..." or "End of summary." Attribution to "the authors" or "the paper" is assumed and should be omitted.
  5. Section structure mirrors the source. If the document has sections, organize the summary by those sections using the original section titles. Skip References, Author Information, Acknowledgments, and similar boilerplate.

Two-step process

Step 1: Exhaustive extraction

Read the document carefully. For each section, extract every key point or insight as a numbered list item with the following structure:

Format for each item:

N. **Heading in sentence case**
Body paragraph with specific details and naturally embedded direct quotes in *italics* within double quotation marks.

Rules for Step 1:

  • Start each item with an Arabic numeral, period, space, then a bold heading.
  • The body paragraph follows on the next line (no indentation).
  • Use bold within the body to emphasize key terms, concepts, or phrases.
  • Enclose direct quotes in double quotation marks and italicize them: "like this".
  • Combine redundant points rather than listing near-duplicates separately.
  • Proceed section by section. Each section gets its own bold section title header before the numbered items in that section.
  • Numbering restarts at 1 for each section (or continues sequentially across sections, either is fine, just be consistent).

Example of correct style:

Table 1 compares six methods (no software, point-and-click, modify code chunks, Excel, teach coding and Copilot) and emphasizes that "Copilot... is the only approach that is favorable across all [the] characteristics"...

Example of incorrect style (do not do this):

In Table 1 the authors compare six methods and emphasize that the Copilot method is the only one that is favorable across all five characteristics. They note that "Copilot... is the only approach that is favorable across all [the] characteristics"...

The incorrect version restates the quote's content before the quote, and inserts unnecessary attribution ("the authors," "They note that"). The correct version lets the quote carry the point directly.

Step 2: Clean and organize

Take the Step 1 output and apply these transformations:

  1. Remove all citation markers and reference links. Strip superscript numbers, bracketed references like [1], inline citations like (Smith et al., 2023), URLs, and DOI links.
  2. Add an overview/takeaway at the top. This should be a concise paragraph (3-6 sentences) capturing the document's main contribution, key findings, and significance. No bullet points in the overview.
  3. Organize into logical sections for easier reading. If the source's own section structure works well, keep it. If the extracted points would benefit from regrouping (e.g., a document without clear sections), organize them thematically. Do not remove any items from the list during reorganization.

Only output the Step 2 result. Do not show the Step 1 intermediate output. Do not include any preamble or closing meta-commentary.

Handling edge cases

  • Documents without clear sections: Organize thematically and create your own section headings that reflect the content's structure.
  • Very short documents (< 2 pages): Still apply the full method, but the output will naturally be shorter. Do not pad.
  • Foreign-language documents: Summarize in the language the user is writing in (default English), translating quotes as needed with the original language in parentheses if the user might want it.
  • Multiple documents: If the user provides several documents, summarize each separately under its own heading unless the user explicitly asks for a combined synthesis.
  • Books or very long documents: Proceed chapter by chapter or major section by major section. Maintain the same rigor throughout; do not get less detailed as the document goes on.

Frequently asked questions

What does the Focus AI skill do?

A rigorous, detail-preserving summarization method for academic papers, reports, and long-form documents. Based on the FOCUS workflow (Lin, 2025, Nature Biotechnology). Extracts every key point with specific details and embedded direct quotes, organized section by section, then produces a clean final output with an overview/takeaway. Trigger this skill whenever the user types "/focus", says "summarize with focus", "FOCUS summary", "use the focus method", or asks for a thorough/exhaustive/detailed summary of a paper or document that should capture every key insight. Also trigger when the use...

Why use Focus on TypingMind?

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

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

Which AI models can use Focus?

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 Focus?

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

Is the Focus AI skill free?

Yes. It is published on GitHub by stephenturner 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 👇