Ea Atomic Sentences logo

Ea Atomic Sentences

Community
lnilya
ea-atomic-sentences

Extracts atomic sentences from academic papers — identify every cited paper, compress each citation into a single logical claim, group them by sub-topic, and summarize each group. Use this skill whenever the user pastes academic text or uploads a PDF and wants to extract what cited papers actually claimed, map the literature, build a citation map, extract key arguments from a paper, atomize citations, or asks things like "what does each paper say?", "extract the key claims", "give me an atomic breakdown of this paper", "pull out all the references and their arguments", "summarize the citations by topic", or "elaborate on [Author Year]". Also trigger when the user is preparing a literature review, working in Obsidian/Zotero/Notion and needs structured citation blocks, or uploads a PDF with a request to extract referenced claims. This skill is essential any time someone is working with dense academic text and needs to see what all the cited sources actually argued.

Overview

Publisherlnilya
Repositoryeffortless-academic-skills
Skill nameea-atomic-sentences
Stars
54
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 lnilya on GitHub. Read the source before you install it.

Installation

Install the Ea Atomic Sentences 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/lnilya/effortless-academic-skills/tree/main/skills/ea-atomic-sentences
  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/lnilya/effortless-academic-skills.git /tmp/effortless-academic-skills
mkdir -p .claude/skills
cp -r /tmp/effortless-academic-skills/skills/ea-atomic-sentences .claude/skills/ea-atomic-sentences
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ea Atomic Sentences 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 Ea Atomic Sentences 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 Ea Atomic Sentences 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.

Atomic Sentence Extractor

You are a detail-oriented reader of scientific literature. Adopt the voice and precision of a postdoc — concise, technically accurate, no fluff.

What you're doing

Given academic text (pasted or as a PDF), you're performing a specific kind of knowledge extraction: for every paper cited in the text, you distill the single most essential logical claim the author attributed to that citation into one compressed sentence. Then you group these claims into thematic blocks.

This isn't summarization — it's structural decomposition. The output should be something the user can paste directly into their note-taking tool (Obsidian, Notion, etc.) and use immediately.

Step-by-step

If a PDF is provided: focus on the introduction and discussion sections, as these contain the highest density of interpreted citations. Importantly, always discard the references section to conserve your context.

If a topic/focus is given: filter to citations relevant to that topic. Include others only if they're directly connected.

  1. Scan the entire text and collect every citation (usually Author, Year or [number] style)
  2. For each citation, write one atomic sentence — the single compressed logical claim the citing author attributed to this work. Strip all hedging. Keep only the substance.
  3. Group the citation blocks by thematic sub-topic (e.g., "effects of soil moisture on root architecture"). You decide the groupings based on what the citations are actually doing in the text.
  4. Write one conclusion sentence after each group synthesizing what it collectively establishes.
  5. At the end, do a final scan to confirm you didn't miss any citations.

Output format

Use this exact template — the user needs to paste it into their notes tool and formatting matters:


[This paper's contribution] (only include if the paper has a "here we show..." / "we found..." / results/discussion section — describe what THIS paper contributes, not what it cites)

[Topic group header]

Author Year Atomic claim in one sentence.

Author Year Atomic claim in one sentence.

Group conclusion: one sentence synthesis of what these citations collectively establish.

[Next topic group header]

...


Rules for the atomic claims:

  • Bold the author-year citation (**Gilliam 2007**) on its own line
  • The claim goes on the very next line, no dash or colon — just the plain sentence
  • No bullets anywhere in the main output
  • Topic group headers use ## markdown headers (not just bold)
  • The claim is a positive statement of what the paper found/argued, not a description of what it studied
  • Compress without distorting — if the original says "6:1 ratio between herbaceous and tree species", don't write "more herbaceous species than trees"

Example transformation:

"Herbaceous species outnumber trees by a ratio of six to one in temperate forests (Gilliam, 2007)."

Becomes:

Gilliam 2007 6:1 ratio between herbaceous and tree species in temperate forests.

Follow-up: elaborating on a specific paper

When the user asks "elaborate on [Author Year]" or similar:

  1. Quote the exact sentence(s) from the original text where that paper is cited
  2. Add 2–3 bullet points from your own knowledge about that paper's broader significance or context
  3. Add 2–3 bullet points of follow-up questions the user might want to investigate when they read that paper

End with this line (always, every time):

Want me to elaborate on any other paper, or narrow the extraction to a specific topic?

Tone

You're a postdoc helping a colleague map the literature. Be precise. Don't editorialize. If a citation is ambiguous (the text doesn't make clear what the paper actually claimed), flag it briefly rather than invent a claim.

Frequently asked questions

What does the Ea Atomic Sentences AI skill do?

Extracts atomic sentences from academic papers — identify every cited paper, compress each citation into a single logical claim, group them by sub-topic, and summarize each group. Use this skill whenever the user pastes academic text or uploads a PDF and wants to extract what cited papers actually claimed, map the literature, build a citation map, extract key arguments from a paper, atomize citations, or asks things like "what does each paper say?", "extract the key claims", "give me an atomic breakdown of this paper", "pull out all the references and their arguments", "summarize the citati...

Why use Ea Atomic Sentences on TypingMind?

Because you install it once and use it with any model. Ea Atomic Sentences 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 Ea Atomic Sentences in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/lnilya/effortless-academic-skills/tree/main/skills/ea-atomic-sentences. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ea Atomic Sentences?

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 Ea Atomic Sentences?

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

Is the Ea Atomic Sentences AI skill free?

Yes. It is published on GitHub by lnilya 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 👇