prompt GP ChatGPT

LLM Researcher — Claude prompt: read papers, explain terms

A prompt that puts the model in the role of a large language model researcher: hand it a paper or a term, then ask your questions.

Open on GitHub

What LLM Researcher does

The prompt sets an expert role in large language model research. You supply a paper, a chunk of text or a single term, ask questions, and get an answer that covers the details easy to skim past.

Beyond the direct answer, it asks for the reason, procedure and purpose behind the concept. Web searches are allowed when something is missing, and paper references or links go into the answer when available.

This is a prompt, not a plugin with code, so there are no dependencies or API keys to set up. It runs in Claude and Claude.ai. The repository also ships .claude/commands/prompts.csv.md for Claude — used that way, the prompt becomes a slash command, and citations depend on whether the agent can reach the web.

What it helps with

work through an LLM paper and pull out the core idea
explain an unfamiliar term from language model research
show why a concept exists and how it is built
collect references to the original sources
answer questions about a text someone else wrote

Example prompts for the agent

Read this paper on attention and tell me what the authors changed from the base architecture
Explain the term "mixture of experts": why it appeared, how it works, what it is for
Here is a passage on reinforcement learning — answer my questions about it and cite the sources

How to install LLM Researcher

How to use

Paste the text at the start of a chat or into project instructions

Manually: put the files in place

.claude/commands/prompts.csv.md

Questions about LLM Researcher

How do I install LLM Researcher in Claude?

There is no install command: paste the prompt into the chat as a regular message. For Claude the repository includes .claude/commands/prompts.csv.md.

What does LLM Researcher do?

It gives the model an expert role in large language model research. You bring a paper or a term, and the answer covers the reason, the procedure and the purpose behind the concept.

Does it need web access?

The prompt allows searching the web for extra information when that is possible. Without search, the answer stays within the text you provided.

Source text

prompts.csv · CC0-1.0

I want you to act as an expert in Large Language Model research. Please carefully read the paper, text, or conceptual term provided by the user, and then answer the questions they ask. While answering, ensure you do not miss any important details. Based on your understanding, you should also provide the reason, procedure, and purpose behind the concept. If possible, you may use web searches to find additional information about the concept or its reasoning process. When presenting the information, include paper references or links whenever available.

Similar prompts

All prompts for AI and ML →

llm-evaluation Seth Hobson A skill for evaluating LLM applications: automated metrics, human feedback, LLM-as-judge and benchmarking. Useful when comparing models or catching regressions before deploy. CX Codex 12,755installs cost-aware-llm-pipeline affaan-m A skill for apps that call LLM APIs: picks a model by task complexity, tracks spend, caches prompts. Useful when your API bill keeps climbing. CX Codex +1 4,600installs llm-architect VoltAgent Community Designs production LLM architectures: covers RAG, LoRA fine-tuning, inference serving with vLLM, and multi-model routing. Essential when managing token budgets and latency targets. 649installs llm-cost-optimizer Alireza Rezvani Audits token usage and cuts LLM API spend through model routing, caching, and prompt compression. Useful when API bills spike or before launching new AI endpoints. 73installs persona-researcher official googleworkspace Sets up an AI researcher persona for Google Workspace. It organizes references in Drive, tracks data in Sheets, and manages review requests. CX Codex +1 31,300installs

From the same set77

The whole set →