Remove dot from requirements.txt and update project files

README.md

@@ -1,12 +1,12 @@
 ---
-title: ResumeOptimizer
-emoji: 🦀
+title: Resume Optimizer
+emoji: 📄
 colorFrom: indigo
-colorTo: pink
+colorTo: blue
 sdk: gradio
-sdk_version: 5.15.0
+sdk_version: "5.15.0"
 app_file: app.py
-pinned: false
+pinned: true
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at [Hugging Face Docs](https://huggingface.co/docs/hub/spaces-config-reference)

app.py

@@ -0,0 +1,107 @@
+import os
+import datetime
+import gradio as gr
+from markdown_pdf import MarkdownPdf, Section
+import sys
+
+# Ensure `src` is in Python's module search path
+sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "src")))
+
+from resume_crew.crew import ResumeCrew
+
+
+# Set backend directories for Hugging Face Spaces
+UPLOAD_DIR = "/tmp/uploads"
+OUTPUT_DIR = "/tmp/output"
+
+os.makedirs(UPLOAD_DIR, exist_ok=True)
+os.makedirs(OUTPUT_DIR, exist_ok=True)
+
+def convert_md_to_pdf(md_path: str) -> str:
+    """Convert Markdown to PDF and save it in OUTPUT_DIR."""
+    if not os.path.isfile(md_path):
+        return ""
+    with open(md_path, "r", encoding="utf-8") as f:
+        md_content = f.read()
+    pdf_obj = MarkdownPdf(toc_level=2)
+    pdf_obj.add_section(Section(md_content))
+
+    pdf_filename = os.path.splitext(os.path.basename(md_path))[0] + ".pdf"
+    pdf_path = os.path.join(OUTPUT_DIR, pdf_filename)
+    
+    pdf_obj.save(pdf_path)
+    return pdf_path if os.path.isfile(pdf_path) else ""
+
+def process_resume(model_choice, new_resume, company_name, job_url, openai_api_key, serper_api_key):
+    """Handles file upload, API keys, resume processing, and returns PDFs."""
+    current_date = datetime.datetime.now().strftime("%Y%m%d")
+
+    if not openai_api_key or not serper_api_key:
+        return ("Error: Please enter both OpenAI and Serper API keys.", None, None, None)
+
+    if new_resume is None or not hasattr(new_resume, "name") or not new_resume.name.strip():
+        return ("Error: Please upload a resume.", None, None, None)
+
+    resume_path = os.path.join(UPLOAD_DIR, new_resume.name)
+    
+    with open(resume_path, "wb") as f:
+        f.write(new_resume.read())
+
+    crew_instance = ResumeCrew(
+        model=model_choice,
+        openai_api_key=openai_api_key,  
+        serper_api_key=serper_api_key,  
+        resume_pdf_path=resume_path  
+    )
+
+    crew = crew_instance.crew()
+    if crew:
+        crew.kickoff(inputs={'job_url': job_url, 'company_name': company_name})
+
+    def md_to_pdf_in_dir(md_filename):
+        md_path = os.path.join(OUTPUT_DIR, md_filename)
+        if os.path.isfile(md_path):
+            return convert_md_to_pdf(md_path)
+        return ""
+
+    pdf_opt = md_to_pdf_in_dir("optimized_resume.md")
+    pdf_final = md_to_pdf_in_dir("final_report.md")
+    pdf_int = md_to_pdf_in_dir("interview_questions.md")
+
+    message = f"Processing completed using model {model_choice}. Files are stored temporarily."
+
+    return message, pdf_opt, pdf_final, pdf_int
+
+model_choices = {
+    "GPT-4o-mini": "gpt-4o-mini-2024-07-18",
+    "GPT-4o": "gpt-4o-2024-08-06",
+    "o3-mini": "o3-mini-2025-01-31",
+    "o1-mini": "o1-mini-2024-09-12"
+}
+
+with gr.Blocks(css=".output-column { width: 700px; }") as demo:
+    with gr.Row():
+        with gr.Column(scale=0.8):
+            gr.Markdown("## Resume Optimization System")
+            openai_api_key_input = gr.Textbox(label="OpenAI API Key", type="password")
+            serper_api_key_input = gr.Textbox(label="Serper API Key", type="password")
+            model_dropdown = gr.Dropdown(choices=list(model_choices.values()), label="Select Model")
+            new_resume_file = gr.File(label="Upload New Resume PDF", file_types=[".pdf"])
+            company_name_text = gr.Textbox(label="Company Name")
+            job_url_text = gr.Textbox(label="Job URL")
+            run_button = gr.Button("Run")
+
+    # Define output components
+    result_text = gr.Textbox(label="Status", interactive=False)
+    pdf_opt_out = gr.File(label="Optimized Resume PDF")
+    pdf_final_out = gr.File(label="Final Report PDF")
+    pdf_int_out = gr.File(label="Interview Questions PDF")
+
+    # Connect button
+    run_button.click(
+        process_resume, 
+        inputs=[model_dropdown, new_resume_file, company_name_text, job_url_text, openai_api_key_input, serper_api_key_input],
+        outputs=[result_text, pdf_opt_out, pdf_final_out, pdf_int_out]
+    )
+
+demo.launch()

docs/README.md

@@ -0,0 +1,40 @@
+# Resume Optimization System Architecture
+
+![Resume Optimization System Architecture](architecture-diagam.svg)
+
+This document provides an overview of the resume optimization system architecture.
+
+## System Components
+
+### 1. Input Sources
+
+- Resume (PDF format)
+- Job URL
+- Company Name
+
+### 2. Analysis Agents
+
+- **Job Analyzer**: Uses ScrapeWebsiteTool to analyze job descriptions
+- **Resume Analyzer**: Uses PDFKnowledgeSource to analyze resumes
+- **Company Researcher**: Uses SerperDevTool for company research
+
+### 3. Structured Data
+
+JSON files storing analysis results:
+
+- job_analysis.json
+- resume_optimization.json
+- company_research.json
+
+### 4. Report Generators
+
+- **Resume Writer**: Creates optimized resumes
+- **Report Generator**: Creates comprehensive reports
+
+### 5. Output Files
+
+Markdown files:
+
+- optimized_resume.md
+- final_report.md
+

output/company_research.json

@@ -0,0 +1,38 @@
+{
+    "recent_developments": [
+        "Reported a record revenue of about $16 billion in 2023, reflecting consistent overall growth.",
+        "Heightened focus on generative AI and digital transformation services in client engagements.",
+        "Continued expansion of sustainability consulting through new acquisitions and capabilities.",
+        "Publication of research such as 'The State of Organizations 2023' and ongoing industry-specific outlook reports."
+    ],
+    "culture_and_values": [
+        "Strong emphasis on diversity, equity, and inclusion with a commitment to creating an inclusive environment.",
+        "Client-centric approach underpinned by integrity and ethical conduct in delivering measurable impact.",
+        "Collaborative, team-based culture fostering knowledge exchange and professional growth.",
+        "Ongoing investment in innovation and thought leadership through strategic insights and large-scale research."
+    ],
+    "market_position": {
+        "ranking": [
+            "Recognized as one of the top global management consulting firms with a broad client portfolio across industries."
+        ],
+        "competitors": [
+            "Boston Consulting Group (BCG)",
+            "Bain & Company",
+            "Accenture",
+            "Deloitte"
+        ]
+    },
+    "growth_trajectory": [
+        "Maintained strong year-over-year growth in key practice areas such as digital, analytics, and sustainability.",
+        "Expanding global headcount, surpassing 45,000 employees as part of continued worldwide hiring efforts.",
+        "Heightened industry focus on emerging markets and technology innovation to drive future service growth.",
+        "Extensive acquisitions and strategic partnerships to strengthen implementation and digital transformation offerings."
+    ],
+    "interview_questions": [
+        "Tell me about yourself and why you want to join McKinsey.",
+        "Walk me through a challenging project you worked on, and how you overcame obstacles.",
+        "What are some aspects of our culture or values that resonate with you, and why?",
+        "Case interview: How would you approach solving a client’s profitability issue in a specific industry?",
+        "Behavioral interview: Describe a time you led a team under high pressure and discuss the results you achieved."
+    ]
+}

output/final_report.md

@@ -0,0 +1,125 @@
+# Executive Summary
+
+### Overall Match Score: 88%  
+Your profile demonstrates strong alignment with the Associate role at McKinsey, driven by robust quantitative analysis, leadership experience, and effective communication skills. 
+
+### Quick Wins  
+• Emphasize your advanced education (MBA, PhD) and relevant CFA/FRM credentials  
+• Leverage your finance and data analysis background to position yourself for strategy and analytics engagements at McKinsey  
+• Highlight your teaching and mentoring experience as a powerful example of communication, leadership, and collaboration  
+
+### Key Strengths  
+• Deep quantitative problem-solving abilities (financial modeling, hypothesis testing, data-driven insights)  
+• Strong educational background (MBA, ongoing PhD) and recognition for academic excellence  
+• Leadership skills demonstrated through team-based projects and teaching experience  
+• Proven collaboration and communication abilities from cross-functional work  
+
+### Improvement Areas  
+• Limited direct consulting project experience – reframe prior financial roles in a consulting-oriented narrative  
+• Broadening industry exposure beyond finance to showcase readiness for a variety of McKinsey engagements  
+
+### Action Items Priority List  
+1. 🔥 Refine your resume to showcase consulting transferrable skills and highlight collaborative problem-solving  
+2. 🚀 Prepare targeted examples of collaboration, leadership, and client-focused results using the STAR method  
+3. ⚙️ Research diverse McKinsey practice areas to speak knowledgeably about broad industry challenges  
+
+---
+
+# Job Fit Analysis
+
+### Detailed Score Breakdown  
+| Category                | Match Score |
+|-------------------------|------------:|
+| Overall Match           | 0.88        |
+| Technical Skills        | 0.90        |
+| Soft Skills            | 0.85        |
+| Experience             | 0.85        |
+| Education              | 1.00        |
+| Industry               | 0.80        |
+
+### Skills Match Assessment  
+• **Technical Skills (0.90)**  
+  - Quantitative analysis, hypothesis testing, financial modeling, data/statistical analysis  
+  - Expert-level proficiency in Stata and Python  
+
+• **Soft Skills (0.85)**  
+  - Teaching, communication, inclusive teamwork, leadership/mentoring  
+  - Strong ability to collaborate cross-functionally  
+
+• **Experience Alignment (0.85)**  
+  - Investment research and asset allocation experience is transferable to client problem-solving  
+  - Project leadership at Fidelity Investments showcases an ability to convert insights into action  
+
+---
+
+# Optimization Overview
+
+### Key Resume Improvements  
+• **Add a Consulting-Oriented Summary**  
+  - “Analytical consultant with expertise in quantitative problem-solving, data analysis, and hypothesis testing…”  
+
+• **Reframe Experience Bullets**  
+  - Fidelity Investments: Emphasize cross-functional leadership and hypothesis testing in portfolio management  
+  - Futures First Info. Services: Highlight collaboration in algorithmic trading and data-driven tools  
+
+• **Teaching & Research Experience**  
+  - Connect teaching responsibilities to client communication and leadership skills  
+
+### ATS Optimization Results  
+• Incorporation of consulting keywords (e.g., “Client engagement,” “Stakeholder management,” “Strategic analysis,” “Hypothesis testing”)  
+• Clear, concise bullet points with quantifiable outcomes to improve overall ATS matching  
+
+### Impact Metrics  
+• Expected to raise overall match from 88% to ~91% by clearly mapping prior work experiences to consulting frameworks  
+• Increased recruiter clarity on your transferable skills (finance, data, leadership) for McKinsey’s engagement needs  
+
+---
+
+# Company Insights
+
+### Culture Fit Analysis  
+• McKinsey emphasizes collaborative, team-based problem-solving, which aligns with your proven track record in cross-functional work at Fidelity and as a teaching fellow  
+• Insight generation and data-driven analysis are central to McKinsey’s client engagements, directly matching your background  
+
+### Interview Preparation Tips  
+• Prepare to address case interviews: structure problem-solving clearly, emphasize hypothesis testing and data analysis  
+• Tie in personal stories: highlight how you’ve managed high-stakes projects or delivered recommendations to senior stakeholders  
+• Articulate a deep understanding of McKinsey’s values—client impact, inclusive culture, professional growth  
+
+### Key Talking Points  
+• Demonstrate knowledge of McKinsey’s recent focus on AI/digital transformation and sustainability consulting  
+• Showcase how your finance and academic background can support a variety of client industries (beyond purely financial)  
+• Emphasize readiness to travel and collaborate with diverse teams globally  
+
+---
+
+# Next Steps
+
+### Prioritized Action Items  
+1. **High Priority (🔥)**  
+   - Update your resume with the recommended content and formatting suggestions  
+   - Begin case interview practice and refine your structured approach to problem-solving  
+2. **Mid Priority (⚙️)**  
+   - Gather specific, quantifiable achievements (e.g., “Increased efficiency by 20% in asset-management processes”)  
+   - Connect with McKinsey consultants/alumni to gain deeper insight into the Associate role requirements  
+3. **Ongoing (🌱)**  
+   - Maintain a strong network, remain updated on McKinsey’s thought leadership (research reports, acquisitions, etc.)  
+   - Continue skill development in non-financial industries through reading, online courses, or cross-industry projects  
+
+### Skill Development Plan  
+• **Consulting Methodologies & Frameworks**  
+  - Familiarize yourself with standard strategy frameworks (MECE, Porter’s Five Forces) and typical McKinsey problem structures  
+• **Industry Broadening**  
+  - Expand exposure beyond finance to show readiness for diverse projects (healthcare, tech, consumer goods, etc.)  
+• **Leadership & Communication**  
+  - Practice stakeholder communication and building narratives around data insights  
+  - Demonstrate synergy between academic research and real-world impact  
+
+### Application Strategy  
+• Integrate your updated resume and cover letter targeted to McKinsey’s consulting style  
+• Draw upon your finance experience as a foundation for broader problem-solving  
+• During interviews, articulate specific ways your skills will deliver client impact and measurable value  
+
+---
+
+**Good luck with your McKinsey application!** Focus on demonstrating both your technical acumen and your collaborative, client-centric mindset. Your unique blend of finance, academic research, and leadership abilities positions you well for a successful career in strategy consulting.

output/job_analysis.json

@@ -0,0 +1,174 @@
+{
+    "technical_skills": [
+        "Quantitative problem solving",
+        "Data analysis and research",
+        "Hypothesis testing",
+        "Logical reasoning"
+    ],
+    "soft_skills": [
+        "Collaboration",
+        "Inclusive teamwork",
+        "Effective verbal and written communication",
+        "Leadership and mentoring abilities",
+        "Adaptability in ambiguous environments"
+    ],
+    "experience_requirements": [
+        "Bachelor’s degree; advanced graduate degree (MBA, PhD) or equivalent experience",
+        "Experience leading and driving independent workstreams",
+        "Strong analytical experience, especially with quantitative data"
+    ],
+    "key_responsibilities": [
+        "Work in teams of 3-5 consultants to solve client problems",
+        "Gather and analyze information, formulate and test hypotheses",
+        "Communicate recommendations to client management",
+        "Implement solutions collaboratively with client team members",
+        "Travel to client site as needed"
+    ],
+    "education_requirements": [
+        "Bachelor’s degree minimum",
+        "Advanced graduate degree (MBA, PhD) preferred",
+        "Equivalent (5+ years) work experience in relevant fields may substitute"
+    ],
+    "nice_to_have": [
+        "Familiarity with strategy and operations in diverse industries",
+        "Experience with global financial markets or consulting background"
+    ],
+    "job_title": "Associate",
+    "department": "Consulting",
+    "reporting_structure": "Reports to Engagement Manager and Partners",
+    "job_level": "Associate",
+    "location_requirements": {
+        "primary_location": "Global offices",
+        "travel_percentage": "Up to 80% depending on client needs"
+    },
+    "work_schedule": "Full-time",
+    "travel_requirements": "Potentially frequent travel to client locations",
+    "compensation": {
+        "base_salary_range": "$192,000 USD (US) / $200,000 CAD (Canada)",
+        "bonus_eligibility": "Yes, based on performance"
+    },
+    "benefits": [
+        "Medical, dental, and vision coverage",
+        "Parental leave and family planning",
+        "Retirement contribution plan",
+        "Professional development and mentoring",
+        "Mental health and wellness support"
+    ],
+    "tools_and_technologies": [
+        "Advanced analytics tools",
+        "Spreadsheets",
+        "Presentation software"
+    ],
+    "industry_knowledge": [
+        "Financial services",
+        "Healthcare systems",
+        "Consumer packaged goods",
+        "Public sector",
+        "Technology, media, and multiple other industries"
+    ],
+    "certifications_required": [],
+    "security_clearance": null,
+    "team_size": "3-5 consultants per engagement",
+    "key_projects": [
+        "Client performance improvement engagements",
+        "Strategy formulation and implementation projects"
+    ],
+    "cross_functional_interactions": [
+        "Collaboration with data scientists",
+        "Interaction with designers and researchers",
+        "Client management and stakeholders"
+    ],
+    "career_growth": [
+        "Frequent mentoring and coaching",
+        "Professional development manager to guide staffing and education",
+        "Broad exposure to multiple industries"
+    ],
+    "training_provided": [
+        "Onboarding and orientation",
+        "Consulting effectiveness training",
+        "Ongoing leadership development"
+    ],
+    "diversity_inclusion": "Strong commitment to equal opportunity and inclusive environment",
+    "company_values": [
+        "Client impact",
+        "Inclusive culture",
+        "Professional growth",
+        "Integrity",
+        "Collaboration"
+    ],
+    "job_url": "https://www.mckinsey.com/careers/search-jobs/jobs/associate-15178",
+    "posting_date": "May 26, 2023",
+    "application_deadline": null,
+    "special_instructions": [
+        "Apply via McKinsey’s career site",
+        "Review additional regional requirements if applicable"
+    ],
+    "match_score": {
+        "overall_match": 0.88,
+        "technical_skills_match": 0.9,
+        "soft_skills_match": 0.85,
+        "experience_match": 0.85,
+        "education_match": 1.0,
+        "industry_match": 0.8,
+        "skill_details": [
+            {
+                "skill_name": "Quantitative problem-solving",
+                "required": true,
+                "match_level": 0.9,
+                "years_experience": 5.0,
+                "context_score": 0.9
+            },
+            {
+                "skill_name": "Data / statistical analysis",
+                "required": true,
+                "match_level": 0.9,
+                "years_experience": 5.0,
+                "context_score": 0.9
+            },
+            {
+                "skill_name": "Financial / investment domain knowledge",
+                "required": false,
+                "match_level": 0.8,
+                "years_experience": 7.0,
+                "context_score": 0.8
+            },
+            {
+                "skill_name": "Communication / presentation",
+                "required": true,
+                "match_level": 0.85,
+                "years_experience": null,
+                "context_score": 0.85
+            },
+            {
+                "skill_name": "Leadership / team collaboration",
+                "required": true,
+                "match_level": 0.85,
+                "years_experience": null,
+                "context_score": 0.85
+            }
+        ],
+        "strengths": [
+            "Advanced education including ongoing PhD and MBA",
+            "Strong finance and investment background",
+            "Quantitative research and data analysis expertise",
+            "Teaching and communication experience"
+        ],
+        "gaps": [
+            "Limited direct consulting project experience",
+            "Exposure primarily focused on finance rather than broad-based industries"
+        ],
+        "scoring_factors": {
+            "technical_skills_weight": 0.35,
+            "soft_skills_weight": 0.2,
+            "experience_weight": 0.25,
+            "education_weight": 0.1,
+            "industry_weight": 0.1
+        }
+    },
+    "score_explanation": [
+        "Strong educational background and quantitative skills match technical requirements well",
+        "Soft skills demonstrated through teaching experience and academic collaboration",
+        "Relevant industry experience in finance but less exposure to other McKinsey client sectors",
+        "Overall score derived from weighted average of technical, soft, experience, education, and industry match"
+    ]
+}

output/optimized_resume.md

@@ -0,0 +1,125 @@
+# Aditya Mohan  
+Harvard Business School, Boston, MA 02163  
+Phone: 857-312-5685  
+Email: [email protected]  
+
+## Professional Summary
+Analytical consultant with expertise in quantitative problem-solving, data analysis, and hypothesis testing, seeking to leverage leadership and collaboration skills to drive impactful client solutions at McKinsey. Adept at communicating complex concepts, managing cross-functional stakeholders, and facilitating data-driven decision-making in high-stakes environments.
+
+## Education
+
+**Harvard Business School**  
+PhD, Business Administration, May 2022 (expected)  
+• 2017–2022 (expected)
+
+**Columbia Business School**  
+MBA, Finance and Economics, May 2016  
+• GMAT: 790 (99th percentile)  
+• Honors:  
+   - Eli Ginzberg Memorial Prize for outstanding work in economics  
+   - GPA 4.09/4.0 (Top 5% of class)  
+   - Dean’s Honors with Distinction  
+   - Michael Corasaniti Fellowship for Security Analysis  
+• 2014–2016
+
+**Indian Institute of Technology (IIT), Kharagpur, India**  
+B.Tech (Honors), Energy Engineering, May 2006  
+• 2002–2006  
+• National Talent Search Scholarship (Awarded to top 1000 Indian students)
+
+## Key Skills
+- Quantitative analysis and statistical modeling  
+- Consulting-oriented communication and presentation  
+- Structured problem-solving and hypothesis testing  
+- Leadership and mentoring in team environments  
+- Collaboration with cross-functional stakeholders  
+- Client engagement and stakeholder management  
+- Data-driven decision-making and insight generation  
+- Cross-functional collaboration and team leadership  
+- Strategic analysis and financial modeling  
+- Communication skills in high-pressure situations  
+
+## Experience
+
+### Fidelity Investments (2007–2014), Boston & Bangalore
+**Asset-Allocation Analyst (Boston: 2010–2014, Bangalore: 2007–2010)**  
+- Led cross-functional investment research teams overseeing $2B in global fixed income assets, leveraging quantitative analysis and hypothesis testing to optimize portfolio performance and drive client-focused, data-driven decisions.  
+- Spearheaded a team-based project demonstrating final recommendations to senior stakeholders in a high-stakes environment, enhancing client engagement and showcasing consulting-oriented communication.  
+- Successfully implemented process improvements that resulted in measurable efficiency gains, driving strategic analysis and cost savings for the investment research function.
+
+### Futures First Info. Services (2006–2007), Gurgaon, India
+**Derivatives Trader**  
+- Collaborated with an automated trading group to develop correlation-based algorithmic tools, applying logical reasoning and financial modeling to deliver actionable market insights and drive investment strategies.  
+- Traded futures and options on German government bonds (Bunds, Bobl, Schatz) and Euribor futures, using data-driven decision-making to achieve consistent returns.  
+- Developed strategic insights for a new market entry, contributing to an immediate performance impact and demonstrating strong problem-solving capabilities.
+
+## Research & Teaching Experience
+
+- **Harvard Business School (Teaching Fellow)**  
+  - Leveraged strong communication and leadership skills to mentor MBA candidates in Financial Analysis and Business Valuation, fostering a collaborative learning environment and applying real-world data interpretation techniques.  
+  - Taught and coached in Accounting, Business Analysis, and Valuation courses for MBA and Law School programs.  
+
+- **Columbia Business School (Teaching Assistant)**  
+  - Supported Corporate Finance, Capital Markets, and Global Economic Environment courses, demonstrating strong communication skills and an ability to clarify complex concepts.
+
+### Selected Research
+- **Job Market Paper**: “Ratings based incentives and institutional investor response: Evidence from the mutual fund market”  
+  - Investigated how Morningstar ratings incentivize mutual fund managers to improve risk-adjusted returns, showing that manager behavior is driven by both investor flow considerations and career concerns.  
+
+- **Payment Practices Transparency and Customer-Supplier Contracting** (with J. Grewal and G. Pérez-Cavazos)  
+  - Studied the 2017 Payment Practices Disclosure Regulation in the U.K. and found that small and medium-sized enterprises reduced accounts receivable by 7.0% after mandated disclosure. Results indicate reputation effects prompt larger firms to accelerate payable settlements.
+
+## Additional Information
+- Credentials: Chartered Financial Analyst (CFA), Financial Risk Manager (FRM)  
+- Skilled in advanced analytics using Stata and Python to drive data-driven insights  
+- Adept at communicating results to stakeholders and senior leadership  
+- Tools previously used: LaTeX for academic writing
+
+## References
+- **Charles C.Y. Wang (Chair)**  
+  Glenn and Mary Jane Creamer Associate Professor, Accounting & Management  
+  Harvard Business School  
+  +1 (617) 496-9633 | [email protected]  
+
+- **Suraj Srinivasan**  
+  Philip J. Stomberg Professor, Accounting & Management  
+  Harvard Business School  
+  +1 (617) 495-6993 | [email protected]  
+
+- **Gerardo Pérez-Cavazos**  
+  Assistant Professor of Accounting  
+  Rady School of Management, University of California, San Diego  
+  +1 (773) 870-1023 | [email protected]  
+
+---
+
+## Explanations of Changes (Change Log)
+
+1. **Added Professional Summary**  
+   - New section emphasizes consulting strengths, quantitative problem-solving, leadership, and collaboration.
+
+2. **Revised Fidelity Investments Bullet**  
+   - Updated language to highlight cross-functional collaboration, hypothesis testing, and data-driven decisions for better alignment with consulting and McKinsey’s values.
+
+3. **Revised Futures First Info. Services Bullet**  
+   - Emphasized collaboration, financial modeling, and insight-generation to demonstrate consulting-oriented problem-solving.
+
+4. **Enhanced Research & Teaching Descriptions**  
+   - Showcased leadership, communication, and real-world data interpretation skills to align with the collaborative and client-focused nature of consulting roles.
+
+5. **Restructured Additional Information**  
+   - Clearly stated CFA and FRM credentials and added emphasis on advanced analytics and stakeholder communication skills.
+
+6. **Key Skills Section**  
+   - Created a dedicated section to spotlight relevant consulting and quantitative skills, ensuring these keywords are present for ATS compatibility (client engagement, hypothesis testing, data-driven decision-making, etc.).
+
+7. **Achievements Integration**  
+   - Incorporated bullet points on team-based projects, process improvements, and strategic insights with quantified or high-impact results to illustrate capacity for delivering client-ready recommendations.
+
+8. **Reverse Chronological Order**  
+   - Maintained the standard format with most recent roles/education first, ensuring a clear and ATS-friendly structure.
+
+9. **Preserved Original Education Details and Research**  
+   - Retained academic honors, research specifics, and references while reformatting for clarity and ATS scanning.
+
+These enhancements ensure the resume is ATS-optimized, highlights consulting-relevant competencies, and aligns with McKinsey’s values of leadership, collaboration, and impact.

output/resume_optimization.json

@@ -0,0 +1,67 @@
+{
+    "content_suggestions": [
+        {
+            "section": "Professional Summary / Objective",
+            "before": "No existing summary focused on consulting strengths",
+            "after": "Add a brief summary: “Analytical consultant with expertise in quantitative problem-solving, data analysis, and hypothesis testing, seeking to leverage leadership and collaboration skills to drive impactful client solutions at McKinsey.”",
+            "rationale": "Including a concise, tailored summary showcases your consulting readiness and highlights the core skills McKinsey values (problem-solving, leadership, collaboration)."
+        },
+        {
+            "section": "Experience - Fidelity Investments",
+            "before": "“Led investment research for assets totaling $2 Billion...”",
+            "after": "“Led cross-functional investment research teams overseeing $2B in global fixed income assets, leveraging quantitative analysis and hypothesis testing to optimize portfolio performance and drive client-focused, data-driven decisions.”",
+            "rationale": "Reframing highlights collaboration, hypothesis testing, and the ability to implement data-driven approaches, which align with McKinsey’s emphasis on teamwork and problem-solving."
+        },
+        {
+            "section": "Experience - Futures First Info. Services",
+            "before": "Discusses trading experience but lacks consulting-oriented language",
+            "after": "“Collaborated with an automated trading group to develop correlation-based algorithmic tools, applying logical reasoning and financial modeling to deliver actionable market insights and drive investment strategies.”",
+            "rationale": "Shifting language to emphasize collaboration, financial modeling, and analytical insights creates stronger alignment with consulting skill sets, like insight-generation and collaborative problem-solving."
+        },
+        {
+            "section": "Research & Teaching Experience",
+            "before": "Heavily focused on academic achievements without explicit ties to consulting scenarios",
+            "after": "“Leveraged strong communication and leadership skills to mentor MBA candidates in Financial Analysis and Business Valuation, fostering a collaborative learning environment and applying real-world data interpretation techniques.”",
+            "rationale": "Highlighting teaching as leadership and collaboration experience underscores your ability to guide teams, a crucial attribute for client engagements and internal collaboration at McKinsey."
+        },
+        {
+            "section": "Additional Information",
+            "before": "“Chartered Financial Analyst; Financial Risk Manager (GARP)... Tools: Stata, Python, Latex”",
+            "after": "“Credentials: Chartered Financial Analyst (CFA), Financial Risk Manager (FRM). Skilled in advanced analytics using Stata and Python to drive data-driven insights. Adept at communicating results to stakeholders.”",
+            "rationale": "Restructuring this section clarifies your strong technical credentials and ability to present complex information to stakeholders, bridging a key skill set for McKinsey consultant roles."
+        }
+    ],
+    "skills_to_highlight": [
+        "Quantitative analysis and statistical modeling",
+        "Consulting-oriented communication and presentation",
+        "Structured problem-solving and hypothesis testing",
+        "Leadership and mentoring in team environments",
+        "Collaboration with cross-functional stakeholders"
+    ],
+    "achievements_to_add": [
+        "Led a team-based project demonstrating final recommendations to senior stakeholders in a high-stakes environment",
+        "Successfully implemented process improvements that resulted in measurable cost savings or efficiency gains",
+        "Developed strategic insights for a new market entry or product launch with immediate impact on firm performance"
+    ],
+    "keywords_for_ats": [
+        "Client engagement",
+        "Consulting",
+        "Data-driven decision-making",
+        "Hypothesis testing",
+        "Cross-functional collaboration",
+        "Stakeholder management",
+        "Strategic analysis",
+        "Team leadership",
+        "Problem-solving",
+        "Financial modeling",
+        "Insight generation",
+        "Communication skills"
+    ],
+    "formatting_suggestions": [
+        "Create a dedicated 'Consulting Skills' or 'Key Skills' section below education to emphasize relevant strengths for McKinsey.",
+        "Use consistent font size and alignment across all section headers for a cleaner look.",
+        "Shorten select bullet points in Experience and highlight quantifiable outcomes (e.g., “Increased efficiency 20%...” or “Saved $X million…”).",
+        "Use reverse chronological order (most recent experience first) to align with standard resume practices.",
+        "Ensure contact information (phone number, email) is clearly listed at the top, keeping it consistent and easy to locate for ATS parsing."
+    ]
+}

pyproject.toml

@@ -0,0 +1,33 @@
+[project]
+name = "resume_crew"
+version = "0.1.0"
+description = "Resume optimization using CrewAI"
+authors = [{ name = "Your Name", email = "[email protected]" }]
+requires-python = ">=3.10,<3.13"
+dependencies = [
+    "crewai[tools]>=0.95.0,<1.0.0",
+    "ollama>=0.4.7",
+    "gradio>=5.15.0",
+    "markdown-pdf>=1.3.3",
+    "gradio-pdf>=0.0.22"
+]
+
+[project.scripts]
+resume_crew = "resume_crew.main:run"
+run_crew = "resume_crew.main:run"
+train = "resume_crew.main:train"
+replay = "resume_crew.main:replay"
+test = "resume_crew.main:test"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.setuptools]
+packages = ["resume_crew"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/resume_crew"]
+
+[tool.crewai]
+type = "crew"

requirements.txt

@@ -0,0 +1,5 @@
+crewai[tools]>=0.95.0,<1.0.0
+ollama>=0.4.7
+gradio>=5.15.0
+markdown-pdf>=1.3.3
+gradio-pdf>=0.0.22

runtime.txt

@@ -0,0 +1 @@
+python-3.10.6

src/resume_crew/config/agents.yaml

@@ -0,0 +1,51 @@
+resume_analyzer:
+  role: "Resume Optimization Expert"
+  goal: "Analyze resumes and provide structured optimization suggestions"
+  backstory: >
+    You are a resume optimization specialist with deep knowledge of ATS systems
+    and modern resume best practices. You excel at analyzing PDF resumes and
+    providing actionable suggestions for improvement. Your recommendations always
+    focus on both human readability and ATS compatibility.
+
+job_analyzer:
+  role: "Job Requirements Analyst"
+  goal: "Analyze job descriptions and score candidate fit"
+  backstory: >
+    You are an expert in job market analysis and candidate evaluation. Your strength
+    lies in breaking down job requirements into clear categories and providing
+    detailed scoring based on candidate qualifications. You understand both technical
+    and soft skills requirements, and can evaluate experience levels accurately.
+
+company_researcher:
+  role: "Company Intelligence Specialist"
+  goal: "Research companies and prepare interview insights"
+  backstory: >
+    You are a corporate research expert who excels at gathering and analyzing
+    the latest company information. You know how to find and synthesize data 
+    from various sources to create comprehensive company profiles and prepare
+    candidates for interviews.
+
+resume_writer:
+  role: "Resume Markdown Specialist"
+  goal: "Create beautifully formatted, ATS-optimized resumes in markdown"
+  backstory: >
+    You are a resume writing expert who specializes in creating markdown-formatted
+    resumes. You know how to transform structured optimization suggestions into
+    beautifully formatted, ATS-friendly documents that maintain professionalism
+    while showcasing candidate strengths effectively.
+
+report_generator:
+  role: "Career Report Generator and Markdown Specialist"
+  goal: "Create comprehensive, visually appealing, and actionable reports from job application analysis"
+  backstory: >
+    You are an expert in data visualization, technical writing, and Markdown formatting.
+    You excel at combining data from multiple JSON sources to create cohesive,
+    visually appealing reports. Your specialty is transforming structured analysis
+    into clear, actionable insights with proper markdown formatting, emojis, and
+    visual elements that make information both appealing and easily digestible.
+
+interview_question_generator:
+  role: "Interview Preparation Specialist"
+  goal: "Generate a list of interview questions based on the optimized resume, job description, and company research."
+  backstory: >
+    You are an expert in synthesizing interview questions. Use all available insights from the candidate's optimized resume, the job requirements, and company research data to generate tailored, strategic, and thought-provoking interview questions that cover technical, behavioral, and situational topics.

src/resume_crew/config/tasks.yaml

@@ -0,0 +1,198 @@
+analyze_job_task:
+  description: >
+    Analyze the {job_url} description and score the candidate's fit based on their resume.
+    Output will be saved as structured JSON data.
+
+    1. Extract Requirements:
+       - Technical skills (required vs nice-to-have)
+       - Soft skills
+       - Experience levels
+       - Education requirements
+       - Industry knowledge
+
+    2. Score Technical Skills (35% of total):
+       - For each required skill:
+         * Match Level (0-1): How well does candidate's experience match?
+         * Years Experience: Compare to required years
+         * Context Score: How relevant is their usage of the skill?
+       - Calculate weighted average based on skill importance
+
+    3. Score Soft Skills (20% of total):
+       - Identify soft skills from resume
+       - Compare against job requirements
+       - Consider context and demonstration of skills
+
+    4. Score Experience (25% of total):
+       - Years of relevant experience
+       - Role similarity
+       - Industry relevance
+       - Project scope and complexity
+
+    5. Score Education (10% of total):
+       - Degree level match
+       - Field of study relevance
+       - Additional certifications
+
+    6. Score Industry Knowledge (10% of total):
+       - Years in similar industry
+       - Domain expertise
+       - Industry-specific achievements
+
+    7. Calculate Overall Score:
+       - Weighted average of all components
+       - Identify key strengths and gaps
+       - Provide detailed scoring explanation
+
+  expected_output: >
+    Structured JSON data containing job analysis and scoring details according to
+    the JobRequirements model schema.
+  agent: job_analyzer
+
+optimize_resume_task:
+  description: >
+    Review the provided resume against the job analysis and create structured optimization suggestions.
+    Output will be saved as structured JSON data.
+
+    1. Content Analysis:
+       - Compare resume content with job requirements
+       - Identify missing keywords and skills
+       - Analyze achievement descriptions
+       - Check for ATS compatibility
+
+    2. Structure Review:
+       - Evaluate section organization
+       - Check formatting consistency
+       - Assess information hierarchy
+       - Verify contact details
+
+    3. Generate Suggestions:
+       - Content improvements with before/after examples
+       - Skills to highlight based on job match
+       - Achievements to add or modify
+       - ATS optimization recommendations
+
+  expected_output: >
+    Structured JSON data containing detailed optimization suggestions according to
+    the ResumeOptimization model schema.
+  agent: resume_analyzer
+  context: [analyze_job_task]
+
+research_company_task:
+  description: >
+    Research {company_name} and prepare the latest (year 2025) and comprehensive analysis.
+    Output will be saved as structured JSON data.
+
+    1. Company Overview:
+       - Recent developments and news
+       - Culture and values
+       - Market position
+       - Growth trajectory
+
+    2. Interview Preparation:
+       - Common interview questions
+       - Company-specific topics
+       - Recent projects or initiatives
+       - Key challenges and opportunities
+
+  expected_output: >
+    Structured JSON data containing company research results according to
+    the CompanyResearch model schema.
+  agent: company_researcher
+  context: [analyze_job_task, optimize_resume_task]
+
+generate_resume_task:
+  description: >
+    Using the optimization suggestions and job analysis from previous steps, 
+    create a polished resume in markdown format.
+    Do not add markdown code blocks like '```'.
+
+    1. Content Integration:
+       - Incorporate optimization suggestions
+       - Add missing keywords and skills
+       - Enhance achievement descriptions
+       - Ensure ATS compatibility
+
+    2. Formatting:
+       - Use proper markdown headers (#, ##, ###)
+       - Apply consistent styling
+       - Create clear section hierarchy
+       - Use bullet points effectively
+
+    3. Documentation:
+       - Track changes made
+       - Note preserved elements
+       - Explain optimization choices
+
+  expected_output: >
+    A beautifully formatted markdown resume document that:
+    - Incorporates all optimization suggestions
+    - Uses proper markdown formatting
+    - Is ATS-friendly
+    - Documents all changes made
+  agent: resume_writer
+  context: [optimize_resume_task, analyze_job_task, research_company_task]
+
+generate_report_task:
+  description: >
+    Create an executive summary report using data from previous steps. 
+    Format in markdown without code blocks '```'.
+
+    1. Data Integration:
+       - Job analysis and scores
+       - Resume optimization details
+       - Company research insights
+       - Final resume changes
+
+    2. Report Sections:
+       ## Executive Summary
+       - Overall match score and quick wins
+       - Key strengths and improvement areas
+       - Action items priority list
+
+       ## Job Fit Analysis
+       - Detailed score breakdown
+       - Skills match assessment
+       - Experience alignment
+
+       ## Optimization Overview
+       - Key resume improvements
+       - ATS optimization results
+       - Impact metrics
+
+       ## Company Insights
+       - Culture fit analysis
+       - Interview preparation tips
+       - Key talking points
+
+       ## Next Steps
+       - Prioritized action items
+       - Skill development plan
+       - Application strategy
+
+    3. Formatting:
+       - Use proper markdown headers
+       - Include relevant emojis
+       - Create tables where appropriate
+       - Use bullet points for scannability
+
+  expected_output: >
+    A comprehensive markdown report that combines all analyses into an
+    actionable, clear document with concrete next steps.
+  agent: report_generator
+  context: [analyze_job_task, optimize_resume_task, research_company_task]
+
+generate_interview_questions_task:
+  description: >
+    Synthesize interview questions using insights from the optimized resume, job description, and company research.
+  expected_output: >
+    Structured JSON data containing a list of interview questions.
+  agent: interview_question_generator
+  context: [optimize_resume_task, analyze_job_task, research_company_task]
+
+generate_interview_questions_md_task:
+  description: >
+    Produce a Markdown-formatted document of interview questions for easy reading.
+  expected_output: >
+    A Markdown document listing the interview questions with formatting.
+  agent: interview_question_generator
+  context: [optimize_resume_task, analyze_job_task, research_company_task]

src/resume_crew/crew.py

@@ -0,0 +1,141 @@
+from crewai import Agent, Crew, Process, Task, LLM
+from crewai.project import CrewBase, agent, crew, task
+from crewai_tools import SerperDevTool, ScrapeWebsiteTool
+from crewai.knowledge.source.pdf_knowledge_source import PDFKnowledgeSource
+from .models import (
+    JobRequirements,
+    ResumeOptimization,
+    CompanyResearch,
+    InterviewQuestions
+)
+
+@CrewBase
+class ResumeCrew():
+    """ResumeCrew for resume optimization and interview preparation"""
+
+    agents_config = 'config/agents.yaml'
+    tasks_config = 'config/tasks.yaml'
+
+    def __init__(self, model: str, openai_api_key: str, serper_api_key: str, resume_pdf_path: str) -> None:
+        """
+        Initialize ResumeCrew with the selected model and user-provided API keys.
+        """
+        self.model = model  
+        self.openai_api_key = openai_api_key  # Store user-provided OpenAI API Key
+        self.serper_api_key = serper_api_key  # Store user-provided Serper API Key
+        self.resume_pdf = PDFKnowledgeSource(file_paths=[resume_pdf_path])  # Use user-uploaded resume
+
+    @agent
+    def resume_analyzer(self) -> Agent:
+        return Agent(
+            config=self.agents_config['resume_analyzer'],
+            verbose=True,
+            llm=LLM(self.model, api_key=self.openai_api_key),  # Use user-provided OpenAI API Key
+            knowledge_sources=[self.resume_pdf]
+        )
+    
+    @agent
+    def job_analyzer(self) -> Agent:
+        return Agent(
+            config=self.agents_config['job_analyzer'],
+            verbose=True,
+            tools=[ScrapeWebsiteTool()],
+            llm=LLM(self.model, api_key=self.openai_api_key)  # Use dynamic API key
+        )
+
+    @agent
+    def company_researcher(self) -> Agent:
+        return Agent(
+            config=self.agents_config['company_researcher'],
+            verbose=True,
+            tools=[SerperDevTool(api_key=self.serper_api_key)],  # Use user-provided Serper API Key
+            llm=LLM(self.model, api_key=self.openai_api_key),  # Use dynamic API key
+            knowledge_sources=[self.resume_pdf]
+        )
+
+    @agent
+    def resume_writer(self) -> Agent:
+        return Agent(
+            config=self.agents_config['resume_writer'],
+            verbose=True,
+            llm=LLM(self.model, api_key=self.openai_api_key)
+        )
+
+    @agent
+    def report_generator(self) -> Agent:
+        return Agent(
+            config=self.agents_config['report_generator'],
+            verbose=True,
+            llm=LLM(self.model, api_key=self.openai_api_key)
+        )
+    
+    @agent
+    def interview_question_generator(self) -> Agent:
+        return Agent(
+            config=self.agents_config['interview_question_generator'],
+            verbose=True,
+            llm=LLM(self.model, api_key=self.openai_api_key)
+        )
+
+    @task
+    def analyze_job_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['analyze_job_task'],
+            output_file='output/job_analysis.json',
+            output_pydantic=JobRequirements
+        )
+
+    @task
+    def optimize_resume_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['optimize_resume_task'],
+            output_file='output/resume_optimization.json',
+            output_pydantic=ResumeOptimization
+        )
+
+    @task
+    def research_company_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['research_company_task'],
+            output_file='output/company_research.json',  
+            output_pydantic=CompanyResearch
+        )
+
+    @task
+    def generate_resume_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['generate_resume_task'],
+            output_file='output/optimized_resume.md'
+        )
+
+    @task
+    def generate_report_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['generate_report_task'],
+            output_file='output/final_report.md'
+        )
+
+    @task
+    def generate_interview_questions_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['generate_interview_questions_task'],
+            output_file='output/interview_questions.json',
+            output_pydantic=InterviewQuestions
+        )
+
+    @task
+    def generate_interview_questions_md_task(self) -> Task:
+        return Task(
+            config=self.tasks_config['generate_interview_questions_md_task'],
+            output_file='output/interview_questions.md'
+        )
+
+    @crew
+    def crew(self) -> Crew:
+        return Crew(
+            agents=self.agents,
+            tasks=self.tasks,
+            verbose=True,
+            process=Process.sequential,
+            knowledge_sources=[self.resume_pdf]
+        )

src/resume_crew/main.py

@@ -0,0 +1,20 @@
+#!/usr/bin/env python
+import sys
+import warnings
+
+from resume_crew.crew import ResumeCrew
+
+warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
+
+def run():
+    """
+    Run the resume optimization crew.
+    """
+    inputs = {
+        'job_url': 'https://www.mckinsey.com/careers/search-jobs/jobs/associate-15178',
+        'company_name': 'Mckinsey & Co.'
+    }
+    ResumeCrew().crew().kickoff(inputs=inputs)
+
+if __name__ == "__main__":
+    run()

src/resume_crew/models.py

@@ -0,0 +1,224 @@
+from typing import List, Dict, Optional
+from pydantic import BaseModel, Field, confloat
+
+class SkillScore(BaseModel):
+    skill_name: str = Field(description="Name of the skill being scored")
+    required: bool = Field(description="Whether this skill is required or nice-to-have")
+    match_level: confloat(ge=0, le=1) = Field(description="How well the candidate's experience matches (0-1)")
+    years_experience: Optional[float] = Field(description="Years of experience with this skill", default=None)
+    context_score: confloat(ge=0, le=1) = Field(
+        description="How relevant the skill usage context is to the job requirements",
+        default=0.5
+    )
+
+class JobMatchScore(BaseModel):
+    overall_match: confloat(ge=0, le=100) = Field(
+        description="Overall match percentage (0-100)"
+    )
+    technical_skills_match: confloat(ge=0, le=100) = Field(
+        description="Technical skills match percentage"
+    )
+    soft_skills_match: confloat(ge=0, le=100) = Field(
+        description="Soft skills match percentage"
+    )
+    experience_match: confloat(ge=0, le=100) = Field(
+        description="Experience level match percentage"
+    )
+    education_match: confloat(ge=0, le=100) = Field(
+        description="Education requirements match percentage"
+    )
+    industry_match: confloat(ge=0, le=100) = Field(
+        description="Industry experience match percentage"
+    )
+    skill_details: List[SkillScore] = Field(
+        description="Detailed scoring for each skill",
+        default_factory=list
+    )
+    strengths: List[str] = Field(
+        description="List of areas where candidate exceeds requirements",
+        default_factory=list
+    )
+    gaps: List[str] = Field(
+        description="List of areas needing improvement",
+        default_factory=list
+    )
+    scoring_factors: Dict[str, float] = Field(
+        description="Weights used for different scoring components",
+        default_factory=lambda: {
+            "technical_skills": 0.35,
+            "soft_skills": 0.20,
+            "experience": 0.25,
+            "education": 0.10,
+            "industry": 0.10
+        }
+    )
+
+class JobRequirements(BaseModel):
+    technical_skills: List[str] = Field(
+        description="List of required technical skills",
+        default_factory=list
+    )
+    soft_skills: List[str] = Field(
+        description="List of required soft skills",
+        default_factory=list
+    )
+    experience_requirements: List[str] = Field(
+        description="List of experience requirements",
+        default_factory=list
+    )
+    key_responsibilities: List[str] = Field(
+        description="List of key job responsibilities",
+        default_factory=list
+    )
+    education_requirements: List[str] = Field(
+        description="List of education requirements",
+        default_factory=list
+    )
+    nice_to_have: List[str] = Field(
+        description="List of preferred but not required skills",
+        default_factory=list
+    )
+    job_title: str = Field(
+        description="Official job title",
+        default=""
+    )
+    department: Optional[str] = Field(
+        description="Department or team within the company",
+        default=None
+    )
+    reporting_structure: Optional[str] = Field(
+        description="Who this role reports to and any direct reports",
+        default=None
+    )
+    job_level: Optional[str] = Field(
+        description="Level of the position (e.g., Entry, Senior, Lead)",
+        default=None
+    )
+    location_requirements: Dict[str, str] = Field(
+        description="Location details including remote/hybrid options",
+        default_factory=dict
+    )
+    work_schedule: Optional[str] = Field(
+        description="Expected work hours and schedule flexibility",
+        default=None
+    )
+    travel_requirements: Optional[str] = Field(
+        description="Expected travel frequency and scope",
+        default=None
+    )
+    compensation: Dict[str, str] = Field(
+        description="Salary range and compensation details if provided",
+        default_factory=dict
+    )
+    benefits: List[str] = Field(
+        description="List of benefits and perks",
+        default_factory=list
+    )
+    tools_and_technologies: List[str] = Field(
+        description="Specific tools, software, or technologies used",
+        default_factory=list
+    )
+    industry_knowledge: List[str] = Field(
+        description="Required industry-specific knowledge",
+        default_factory=list
+    )
+    certifications_required: List[str] = Field(
+        description="Required certifications or licenses",
+        default_factory=list
+    )
+    security_clearance: Optional[str] = Field(
+        description="Required security clearance level if any",
+        default=None
+    )
+    team_size: Optional[str] = Field(
+        description="Size of the immediate team",
+        default=None
+    )
+    key_projects: List[str] = Field(
+        description="Major projects or initiatives mentioned",
+        default_factory=list
+    )
+    cross_functional_interactions: List[str] = Field(
+        description="Teams or departments this role interacts with",
+        default_factory=list
+    )
+    career_growth: List[str] = Field(
+        description="Career development and growth opportunities",
+        default_factory=list
+    )
+    training_provided: List[str] = Field(
+        description="Training or development programs offered",
+        default_factory=list
+    )
+    diversity_inclusion: Optional[str] = Field(
+        description="D&I statements or requirements",
+        default=None
+    )
+    company_values: List[str] = Field(
+        description="Company values mentioned in the job posting",
+        default_factory=list
+    )
+    job_url: str = Field(
+        description="URL of the job posting",
+        default=""
+    )
+    posting_date: Optional[str] = Field(
+        description="When the job was posted",
+        default=None
+    )
+    application_deadline: Optional[str] = Field(
+        description="Application deadline if specified",
+        default=None
+    )
+    special_instructions: List[str] = Field(
+        description="Any special application instructions or requirements",
+        default_factory=list
+    )
+    match_score: JobMatchScore = Field(
+        description="Detailed scoring of how well the candidate matches the job requirements",
+        default_factory=JobMatchScore
+    )
+    score_explanation: List[str] = Field(
+        description="Detailed explanation of how scores were calculated",
+        default_factory=list
+    )
+
+class ResumeOptimization(BaseModel):
+    content_suggestions: List[Dict[str, str]] = Field(
+        description="List of content optimization suggestions with 'before' and 'after' examples"
+    )
+    skills_to_highlight: List[str] = Field(
+        description="List of skills that should be emphasized based on job requirements"
+    )
+    achievements_to_add: List[str] = Field(
+        description="List of achievements that should be added or modified"
+    )
+    keywords_for_ats: List[str] = Field(
+        description="List of important keywords for ATS optimization"
+    )
+    formatting_suggestions: List[str] = Field(
+        description="List of formatting improvements"
+    )
+
+class CompanyResearch(BaseModel):
+    recent_developments: List[str] = Field(
+        description="List of recent company news and developments"
+    )
+    culture_and_values: List[str] = Field(
+        description="Key points about company culture and values"
+    )
+    market_position: Dict[str, List[str]] = Field(
+        description="Information about market position, including competitors and industry standing"
+    )
+    growth_trajectory: List[str] = Field(
+        description="Information about company's growth and future plans"
+    )
+    interview_questions: List[str] = Field(
+        description="Strategic questions to ask during the interview"
+    )
+
+class InterviewQuestions(BaseModel):
+    questions: List[str] = Field(
+        description="List of interview questions synthesized from the optimized resume, job description, and company research.",
+        default_factory=list
+    )

src/resume_crew/tools/custom_tool.py

@@ -0,0 +1,19 @@
+from crewai.tools import BaseTool
+from typing import Type
+from pydantic import BaseModel, Field
+
+
+class MyCustomToolInput(BaseModel):
+    """Input schema for MyCustomTool."""
+    argument: str = Field(..., description="Description of the argument.")
+
+class MyCustomTool(BaseTool):
+    name: str = "Name of my tool"
+    description: str = (
+        "Clear description for what this tool is useful for, your agent will need this information to use it."
+    )
+    args_schema: Type[BaseModel] = MyCustomToolInput
+
+    def _run(self, argument: str) -> str:
+        # Implementation goes here
+        return "this is an example of a tool output, ignore it and move along."