deeptutor
CommunityRegion-aware advisor evaluation with HTML reports.
System Documentation
What problem does it solve?
DeepTutor automates comprehensive evaluation of graduate advisors by aggregating publications, student trajectories, funding, and lab culture signals. It applies region-aware strategies (CN mainland vs international) and outputs a standalone HTML report generated from structured JSON, while supporting multiple agent ecosystems (Claude Code, Codex CLI, Cursor, OpenCode, and OpenClaw). It adheres to rigorous quality rules, sources every claim, and offers a full 10-phase workflow or a lite 6-phase option with a sharp critique and deal-breaker mechanism.
Core Features & Use Cases
- 10-phase investigation workflow with optional Lite mode
- Region-aware search strategies for Chinese mainland vs international institutions
- Outputs standalone HTML report and structured JSON for downstream rendering
- Sharp Critique and deal-breaker annotations to guide decision-making
- Supports multi-platform agent ecosystems (Claude Code, Codex CLI, Cursor, etc.)
- References and scripts for web data collection and report rendering
- Comparative mode to evaluate multiple advisors side-by-side
Quick Start
Prompt: "Investigate Prof. Smith at MIT Biology department" to generate a full advisor report.
Dependency Matrix
Required Modules
None requiredComponents
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: deeptutor Download link: https://github.com/jiadizhunine/deeptutor/archive/main.zip#deeptutor Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.