Build a custom research assistant that automatically finds relevant academic papers and generates high-quality summaries. This system delivers a daily research digest to your to-do list, helping you stay on top of your field with minimal effort.
with Claire Vo
Write a Python script that runs daily as a cron job. This script should query academic databases like arXiv and Google Scholar using a predefined list of your keywords and topics of interest. The script should track which papers it has already shown you to avoid duplicates.
When the daily digest from your script presents new papers, quickly scan the list. If a paper seems relevant, download the PDF and save it into a specific topic folder (e.g., research/creativity/sources/). This manual step is a crucial filter to ensure quality and prevent information overload.
Write a second Python script that runs nightly, also as a cron job. This script scans your research folders for any new PDFs you saved that day. For each new file, it should trigger a Claude Code agent to generate a detailed summary.
The key to getting useful summaries is prompt engineering. Create a specific prompt (or 'skill') for Claude that instructs it to focus on the elements you care about, such as the paper's methodology, effect size, and other details that help you critically assess the research quality, rather than just generating a generic abstract.
Improve your AI's performance by moving from a single, massive context file to a modular library of small, focused markdown files. This system allows the AI to intelligently load only the most relevant information for each task, enabling you to use simple, 'lazy' prompts and get better results.
Escape the friction of traditional GUI-based tools by building a bespoke task management system that runs in your terminal. This workflow uses Claude Code and markdown files to create and manage your to-do list with simple slash commands and natural language.
Leverage OpenAI Codex for high-level software architecture by using the `Plans.md` technique. This workflow guides the AI to generate a comprehensive, multi-step implementation plan for large projects before writing any code.
We've made ChatPRD affordable so everyone from engineers to founders to Chief Product Officers can benefit from an AI PM.