cold-start-interview

Collect law-student study context and write a personalized CLAUDE.md profile.

9.1k|1.8k|Updated Apr 21, 2026
One-click install
npx skills add https://github.com/anthropics/claude-for-legal --skill cold-start-interview-anthropics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cold-start-interview
Source: https://github.com/anthropics/claude-for-legal/tree/main/law-student/skills/cold-start-interview
Command: npx skills add https://github.com/anthropics/claude-for-legal --skill cold-start-interview-anthropics

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the cold-start problem of personalizing the law-student workflow by capturing how you study, what you’re studying, your bar/class context, and which materials you already have.

Core Features & Use Cases

  • Profiles your learning preferences: determines whether you learn best with drill-me versus explain-to-me, then uses that default to drive downstream studying behaviors.
  • Captures bar/class context and weak areas: collects your year/program situation, semester classes and exam formats, jurisdictions and target dates (if applicable), and what’s strong, shaky, and avoided so schedules and practice focus correctly.
  • Ingests your materials for tailored outputs: prompts for outlines, graded essays, old exams, syllabi, MBE sets, and other study artifacts, then writes a practice profile that future skills read from (including a LIMITED DATA flag if you share fewer than 10 items).
  • Checks connector availability on demand: runs an integration availability probe (without claiming success for merely configured connectors) and updates the generated practice profile’s available integrations section.

Quick Start

Run /law-student:cold-start-interview to answer the short setup questions and produce your personalized CLAUDE.md study profile.

Frequently Asked Questions about cold-start-interview

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up a personalized law school study profile for bar prep and class scheduling?

You can build a personalized law student study profile by running a cold-start interview that captures your learning style, semester classes, target jurisdictions, and study materials. It writes this configuration directly into your user plugin config for future study workflows.

What is the best way to onboard study materials like outlines and MBE sets for tailored practice?

The best way to onboard study materials is to input your outlines, graded essays, old exams, and MBE sets during profile setup. The system ingests these artifacts to generate a tailored practice profile, flagging limited data if you share fewer than ten items.

Can I resume a paused study profile setup without redoing the entire interview?

Yes, you can resume a paused study profile setup without restarting the entire interview. The system uses a paused marker to save your progress, allowing you to continue onboarding and capture remaining bar prep or class scheduling inputs seamlessly.

Does the study profile setup check MCP connectivity before claiming connector availability?

Yes, the setup process runs an integration availability probe that verifies actual MCP connectivity before updating your generated practice profile. It avoids claiming success for merely configured connectors, ensuring accurate integration status reporting.

How does capturing my learning style improve downstream studying behaviors?

Capturing your learning style determines whether you prefer drill-me or explain-to-me approaches, setting a default that drives downstream studying behaviors. This ensures practice schedules and study outputs align with how you learn best.

What happens to my study profile configuration if I re-run the integration checks?

Re-running the integration checks updates the available integrations section in your generated practice profile without overwriting your entire setup. The system gates overwrites to protect your existing study materials and learning style data.