powerofjinbo

powerofjinbo / phdtaketaketake

Public

Connection-first PhD advisor matcher — find the right advisor by network strength, not h-index. Quantitative 4.0 scoring across Connection, Publication, Experience, GPA.

github.compowerofjinbophdtaketaketake academic-network advisor-matching ai-skill claude-code claude-skill
14
1
100% credibility
Found May 10, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A PhD application assistant that ranks potential advisors by academic connections, research fit, and strength using evidence from real sources like OpenAlex and PubMed.

How It Works

1
🔍 Discover Your PhD Guide

You stumble upon this helpful tool that finds the best PhD advisors by checking real connections and fit to your background.

2
🚀 Quick Setup

With one easy command, you add it to your favorite AI chat like Claude, making your assistant smarter instantly.

3
💬 Tell Your Story

Chat casually about your field, school grades, research interests, and current mentor – it asks for what it needs.

4
⭐ See Magic Rankings

It searches real academic sources, scores dozens of advisors, and hands you a ranked list with clear reasons why each fits.

5
📋 Get Smart Advice

Review connection strengths, risks to fix, and tailored next steps like who to contact first.

6
📄 Polish Your CV

Ask it to customize a ready-to-print resume highlighting your top matches.

🎓 Apply Confidently

You now have a clear plan with priority advisors, evidence-backed insights, and everything set for successful applications.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 14 to 14 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is phdtaketaketake?

phdtaketaketake is a Python CLI matcher that helps PhD applicants find the right advisor by prioritizing network strength over h-index. It scores candidates on a quantitative 4.0 scale across connection (ties to your current advisor), publication, experience, and GPA, using real-time data from sources like OpenAlex and PubMed. Users get ranked lists with evidence breakdowns, strategy buckets (priority/target/reach/drop), and LaTeX CV tailoring tools—all installable as skills for Claude Code or Cursor.

Why is it gaining traction?

Unlike CSrankings or h-index scrapers, it's connection-first and personalized: feed your profile and get auditable rankings tied to verified co-authorships, grants, and collaborations. No static caches—agents fetch fresh evidence, widening confidence bands honestly on gaps. Devs love the LLM integration for natural-language workflows like "rank top-30 physics PIs for ATLAS ML."

Who should use this?

STEM PhD applicants (physics/HEP, CS/ML, biology, materials) targeting US top-50 schools, especially undergrads with a research advisor and 1-2 papers. Perfect for those using AI coding tools to triage 20-50 candidates and optimize CVs per top matches.

Verdict

Promising alpha for applicants (14 stars, 1.0% credibility score) with strong docs, field-calibrated YAMLs, and MIT license—install via npx for quick trials. Maturity shows in evidence-first design, but recalibrate weights against real admits before betting your cycle.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.