Resume Tune-Up

The problem

Resumes often fail because they list duties instead of achievements. Job seekers struggle to quantify their impact and rarely align their experience with the specific keywords required by modern ATS filters.

What it does

• Reconstructs weak "duty" bullets into evidence-based STAR achievement lines.
• Calculates a match score based on length, bullet density, and keyword overlap.
• Identifies critical skill gaps between the current resume and a target job description.
• Forces quantification by injecting specific metrics or scope markers into every bullet.
• Generates a pre-flight quality checklist to ensure the resume is ready for submission.

Frameworks & tools

Python 3 for score analysis and Markdown for structured reporting.

Why this beats prompting it yourself

Generic LLM prompts often hallucinate accomplishments or use flowery, non-standard language. This skill enforces the STAR framework strictly, removes "responsible for" filler, and uses a dedicated script to objectively measure keyword density against your target role.

Use cases

• Transforming a generic CV into a targeted application for a specific job post.
• Converting a task-heavy list of responsibilities into a results-oriented resume.
• Performing a final audit on a resume to ensure high ATS keyword compatibility.

Known limitations

Cannot invent numbers or history; requires user input for specific metrics. Focused on text-based resumes rather than visual design templates.