Job Hunting Hub

Problem

A job search often scatters personal history across chats, old documents, and memory. After receiving a JD, candidates repeatedly edit resumes, while company research, application status, and interview progress lack a single source of truth. The result is duplicated cleanup, weak keyword coverage, and lost pipeline state.

How It Works

The skill breaks the workflow into executable modules. First, it stores experience as a structured knowledge base, including work history, project history, skill inventory, and job preferences, with tags for retrieval. When a JD is provided, it parses required skills, nice-to-have skills, experience requirements, and responsibilities, then selects the most relevant material to generate a company- and role-specific resume. It then checks ATS/AI screening concerns such as keyword coverage, parseable formatting, standardized skill wording, quantified outcomes, and timeline continuity, producing Markdown, docx, or pdf versions.

It can also collect public company information such as basic profile, funding, business, and reputation signals, then write the result into an application tracking sheet. Later states such as “applied,” “interviewing,” and “offer” can be updated to keep a clear pipeline. Cross-session context can be synced to MEMORY.md, reducing repeated self-introduction.

Boundaries and Notes

This skill suits candidates who need to build reusable resume material, match JDs, and manage application progress. Company data depends on public sources and query tools such as tianyancha-cn; results may be outdated, so verify before applying. Resume content should stay truthful and avoid keyword stuffing; avoid writing sensitive details like exact salary into shared documents.