resume-optimizer

Files (1)

• SKILL.md

SKILL.md (first lines)

# Resume Optimizer Skill

## Setup

```bash
pip install python-docx reportlab spacy scikit-learn python-dotenv
python -m spacy download en_core_web_sm
```

## Resume Data Structure

```python
from dataclasses import dataclass, field

@dataclass
class ResumeContact:
    name: str
    email: str
    phone: str
    location: str
    linkedin: str = ""
    github: str = ""
    website: str = ""

@dataclass
class ResumeExperience:
    company: str
    role: str
    start: str        # "Jan 2022"
    end: str          # "Present"
    location: str
    bullets: list[str] = field(default_factory=list)

@dataclass
class ResumeEducation:
    institution: str
    degree: str
    field: str
    start: str
    end: str
    gpa: str = ""
    achievements: list[str] = field(default_factory=list)

@dataclass
class ResumeSkills:
    technical: list[str] = field(default_factory=list)
    languages: list[str] = field(default_factory=list)
    tools: list[str] = field(default_factory=list)
    soft: list[str] = field(default_factory=list)

@dataclass
class Resume:
    contact: ResumeContact
    summary: str
    experience: list[ResumeExperience] = field(default_factory=list)
    education: list[ResumeEducation] = field(default_factory=list)
    skills: ResumeSkills = field(default_factory=ResumeSkills)
    certifications: list[str] = field(default_factory=list)
    projects: list[dict] = field(default_factory=list)
    languages_spoken: list[dict] = field(default_factory=list)  # [{"language": "Spanish", "level": "Native"}]
```

## ATS Keyword Analysis

```python
import re
from collections import Counter
import spacy

nlp = spacy.load("en_core_web_sm")

def extract_keywords(text: str, top_n: int = 30) -> list[str]:
    """Extract important keywords from a job description."""
    doc = nlp(text.lower())
    
    # Filter to nouns, proper nouns, adjectives — skip stopwords
    keywords = [
        token.lemma_ for token in doc
        if not token.is_stop and not token.is_punct and token.pos_ in {"NOUN", "PROPN", "ADJ"}
        and len(token.text) > 2
    ]
    
    counter = Counter(keywords)
    return [word for word, _ in counter.most_common(top_n)]

def ats_score(resume: Resume, job_description: str) -> dict:
    """Calculate ATS compatibility score against a job description."""
    jd_keywords = set(extract_keywords(job_description, top_n=50))
    
    # Build resume text blob
    resume_text = " ".join([
        resume.summary,
        " ".join(resume.skills.technical),
        " ".join(resume.skills.tools),
        " ".join([b for exp in resume.experience for b in exp.bullets]),
    ]).lower()
    
    resume_doc = nlp(resume_text)
    resume_words = {token.lemma_ for token in resume_doc if not token.is_stop}
    
    matched = jd_keywords & resume_words
    missing = jd_keywords - resume_words
    
    score = (len(matched) / len(jd_keywords)) * 100 if jd_keywords else 0
    
    return {
        "score": round(score, 1),
        "matched_keywords": sorted(matched),
        "missing_keywords": sorted(missing),
        "recommendation": "Good ATS match" if score >= 70 else "Add missing keywords to improve ATS score"
    }

def optimize_for_job(resume: Resume, job_description: str) -> dict:
    """Suggest bullet improvements to target a specific JD."""
    score = ats_score(resume, job_description)
    recommendations = []
    
    if score["score"] < 60:
        recommendations.append("⚠️  ATS score < 60%. You may be filtered automatically.")

From garri333/Skills, MIT.

More from garri333/Skills