interview-prep

Detects interview invitations and generates company research and prep documents.

Updated May 19, 2026
One-click install
npx skills add https://github.com/Jessitoii/career-os --skill interview-prep-jessitoii
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: interview-prep
Source: https://github.com/Jessitoii/career-os/tree/main/.agents/skills/interview-prep
Command: npx skills add https://github.com/Jessitoii/career-os --skill interview-prep-jessitoii

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Job seekers often miss interview invitations buried in email or scramble to research companies and interviewers at the last minute. This Skill automates the detection of interview invitations and the generation of structured preparation documents. ## Core Features & Use Cases - Invitation Detection: Identifies interview invites via ICS calendar attachments, keyword matching in email bodies, and LLM classification for ambiguous messages, with human confirmation for low-confidence cases. - ResearchAgent Pipeline: Runs company news research, interviewer LinkedIn profile analysis, and technical question prediction based on the job description and detected tech stack. - Prep-Doc Delivery: Generates a prep document, stores it per application, and sends a Telegram summary with predicted questions while updating the application status. - Use Case: A recruiter emails "let's schedule a call next week." The Skill detects the invitation, researches the company's recent news and the interviewer's background, predicts five likely technical questions, and delivers a prep document via Telegram before the interview. ## Quick Start Detect interview invitations from my inbox and generate a prep document with company research and predicted questions for each confirmed interview.

Frequently Asked Questions about interview-prep

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

FAQPage Schema
How do I automatically detect interview invitations in email?

Interview invitation detection uses three signals: ICS calendar attachments, keyword matching against terms like "interview", "screening", and "next steps", and LLM classification for ambiguous emails. Low-confidence classifications are routed to a human for confirmation via Telegram.

How to generate interview preparation documents automatically?

A ResearchAgent pipeline researches recent company news, analyzes the interviewer's public LinkedIn profile, and predicts likely technical questions from the job description and tech stack. The results are compiled into a prep document and delivered via Telegram.

What happens when email classification confidence is low?

When the LLM classification confidence falls below 0.8, the email is sent to a human for manual confirmation via Telegram instead of being auto-classified. This prevents false negatives on ambiguous interview invitations.

Which model is used for interview research and question prediction?

The pipeline uses claude-sonnet-4-20250514 for research synthesis and question prediction, chosen for its long context window and synthesis quality. Classification calls go through a fallback wrapper for reliability.

When should I not use interview invitation detection?

Do not use it for general email processing, which should go through Gmail MCP directly, or for rejection email analysis, which is handled by a separate rejection analysis flow. It is scoped specifically to interview invitation signals.