Smart Resume Optimizer

Problem

A resume that gets few responses often suffers from misalignment between the target JD and the candidate's experience: missing keywords, vague responsibilities, weak project outcomes, or the wrong emphasis for the target company type. Generic edits can feel arbitrary when there is no clear benchmark or diagnostic basis.

Workflow

The skill runs a fixed five-step flow:

• Intake: It asks for target role, industry, city, company type, experience level, and structured career data such as education, work history, projects, measurable results, skills, and certifications. Optimization does not start until required fields are clear.
• JD benchmarking: It searches Liepin and BOSS Zhipin job data for relevant roles, extracts responsibilities, hard requirements, project preferences, certifications, and outcome expectations, then separates them into must-have, differentiating, and competitive-advantage tiers.
• Fit diagnosis: It maps the candidate's background against JD requirements, identifying matches, gaps, missing items, and irrelevant items, with ratings such as high, medium, low, or missing.
• Resume rewrite: It rewrites work and project bullets using STAR style, prioritizes measurable outcomes, embeds role-specific keywords, and adjusts emphasis for large companies, mid-size teams, or startups.
• Delivery: It produces a JD requirement list, fit diagnosis report, polished resume, and highlight summary. The resume defaults to HTML via resume-template.html, with plain-text or Markdown alternatives.

Boundaries

It is best for candidates with real experience who need role-specific restructuring. It can reframe transferable skills for career changes but will not invent missing projects, skills, or metrics. Final output still needs human review for contact details, timeline consistency, and platform-specific formatting.