agentleFS
mikezamayiasmikezamayias/agent-skills/skills/academic-research-assistant/SKILL.md

academic-research-assistant

Skill1 starsChanged 28 days agoBSD-3-ClauseView on GitHub

Synthesizes a set of research papers into one literature review of core claims, themes, debates and consensus. Use when asked to analyze, summarize or map several academic papers, articles, PDFs or research documents together.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user asks to analyze, summarize, or map a collection of academic papers, articles, or research documents.

    line 16
  2. Distinctive:

    Instead of summarizing documents one by one, you will behave like a graduate researcher performing a structured literature review.

    line 18
  3. Distinctive:

    When asked to run an academic review on a set of provided documents (PDFs, text files, or URLs):

    line 22
  4. Very specific:

    Ingest the Material: Use the pdf or read tools to process the provided documents.

    line 24
  5. Distinctive:

    Extract & Map: Do not summarize them sequentially.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Academic Research Assistant

Use this skill when the user asks to analyze, summarize, or map a collection of academic papers, articles, or research documents.

Instead of summarizing documents one by one, you will behave like a graduate researcher performing a structured literature review. You will extract core claims, connect the dots, group studies by shared ideas, and identify where authors contradict each other.

Workflow

When asked to run an academic review on a set of provided documents (PDFs, text files, or URLs):

  1. Ingest the Material: Use the pdf or read tools to process the provided documents.
  2. Extract & Map: Do not summarize them sequentially. Analyze them collectively.
  3. Generate the Synthesis Report: Output a structured markdown report containing the following exact sections:

The Synthesis Report Structure

# 📚 Literature Review Synthesis

## 1. 🎯 Core Claims

Extract and clearly state the primary thesis or core claim of each study. Keep this extremely concise (1-2 sentences per paper).

## 2. 🧩 Thematic Grouping

Group the studies by shared ideas, methodologies, or theoretical frameworks. Which papers are building on the same foundation? (e.g., "Papers A and B argue for X, while Papers C and D focus on Y").

## 3. ⚡ Active Debates & Contradictions

Highlight exactly where the authors directly contradict each other. What are the conflicting findings or opposing viewpoints across the papers?

## 4. 🤝 The Consensus

Outline the main consensus in the field based on the provided texts. What do all (or most) of the researchers agree on?

## 5. ❓ The Unresolved Question

Identify the single question or gap in the research that remains most unresolved across the entire body of work provided. What needs to be studied next?

Best Practices

  • Focus on the synthesis step. The value is in looking across the full set of studies, not summarizing them individually.
  • Cite the source documents inline when making claims (e.g., "As demonstrated by Smith (2023)...").
  • Maintain a rigorous, objective academic tone.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.