job-application-system

Research companies to build strategic intel before interviews and applications. Use this skill when the user says "research this company," "tell me about [Company]," "what should I know about [Company]," "company deep dive," "study sheet for [Company]," "I need to learn about [Company] before my interview," "company brief," "what do we know about [Company]?", or any request to learn about a company before an interview or application decision. Also trigger when the user says "prep me" and there is no company-brief.md in the application folder. This skill produces three documents: a deep company brief, a quick-reference study sheet, and a strategic interview plan. Do NOT trigger for post-interview reflection (interview-debrief), general industry research without a specific company, or offer evaluation (offer-evaluator).

Tailor resumes to specific job descriptions using scored application data from job-intake. Use this skill whenever the user wants to customize their resume for a specific role — after a job has been evaluated, when the user says "tailor my resume," "customize my resume for this job," "adjust my resume," "make my resume match this posting," or when the user says "yes" or "let's apply" after a job-intake summary. This skill reads the application folder created by job-intake (metadata.json with match scores, gaps, and keywords) and produces a tailored resume that emphasizes the candidate's strongest matches and addresses gaps through strategic positioning. Outputs .docx, .pdf, and .md versions. Do NOT trigger for writing resumes from scratch (that's a different workflow), general career advice, or cover letters (that's cover-letter-writer).

Draft negotiation scripts, counter-offer emails, and BATNA tables after an offer has been received and scored. Use when the user says "draft a counter", "help me negotiate this", "write the email to push back", "what should I ask for", "I want to counter $X", or after offer-evaluator has produced a baseline evaluation. This skill is tactical: it produces ready-to-send messages, not strategic analysis. For the strategic go or no-go decision, use offer-evaluator first. Do NOT trigger for cold outreach or interview scheduling.

Audit LinkedIn profile alignment, generate optimized alert configurations, and track recommendation quality over time. Use this skill when the user says "my LinkedIn suggestions suck," "optimize my LinkedIn," "fix my job alerts," "what should my headline say," "am I showing up for the right roles," "audit my LinkedIn profile," "LinkedIn keywords," or any question about improving LinkedIn visibility and job match quality. Also trigger when the user forwards a LinkedIn job email digest for quality scoring. Do NOT trigger for general job search strategy (search-optimizer) or individual application evaluation (job-intake).

Prepare for upcoming interviews with role-specific talking points. Use this skill when the user says "I have an interview", "prep me for my interview", "interview tomorrow", "interview on Friday", "help me prepare for [company]", "what should I expect?", "what questions will they ask?", "practice interview", or any request to get ready for a specific upcoming interview. Also trigger when the user mentions a scheduled interview and seems nervous or wants to review key points. This skill generates a custom prep document based on the specific role, the user's match score, past interview patterns, and known gaps. Do NOT trigger for post-interview reflection (interview-debrief) or general job search strategy (search-optimizer).

Capture learning from interviews. Use this skill whenever the user says "I just had an interview", "finished talking to them", "interview went well/badly", "debrief", "let me tell you what happened in the interview", "they asked about X", "the interviewer seemed interested in Y", or any post-interview reflection. Also trigger when the user provides a transcript file (.txt) from an interview, wants to log interview notes, capture what resonated, track what questions were asked, or understand what signals to watch for. This skill turns a conversation about an interview into structured learning that improves future applications and interview prep. Do NOT trigger for pre-interview preparation (interview-prep-builder) or status updates without interview details (job-tracker).

Parse job descriptions, score candidate fit, and set up application tracking folders. Use this skill whenever the user shares a job posting — pasted into chat, saved as a file, or referenced by URL — and wants to evaluate whether it's a good match. Also trigger when the user says "check this job," "is this a fit," "parse this posting," "new application," "evaluate this role," "score this job," or shares a block of text that looks like a job description (title, company, requirements, responsibilities). This skill feeds into resume-tailor and cover-letter-writer — run it first to create the application folder that downstream skills expect. Do NOT trigger for general career advice, salary research, or interview prep — those are different workflows.

Analyze job application outcomes and identify what's working. Use this skill whenever the user asks "how's my search going?", "what's working?", "show me patterns", "why am I not getting interviews?", "which sources are converting?", "give me analytics", "pipeline health", "conversion rates", or any question about the effectiveness of their job search strategy. Also trigger when the user asks to compare application outcomes, wants to understand which resume tailoring approach works best, or needs data to decide where to focus next. This is the intelligence layer — it turns raw application metadata into actionable insights. Do NOT trigger for individual status updates (job-tracker) or strategic recommendations (search-optimizer). This skill provides the data; search-optimizer interprets it.

Track rejections, closures, and outcomes with learning. Use this skill when the user says "got a rejection", "they passed", "didn't get it", "no response after follow-up", "application closed", "they went with someone else", "internal hire", or any indication that an application ended without an offer. Also trigger for "I'm withdrawing from X", "pulling my application", or "decided not to continue with Y". This skill doesn't just update status — it captures WHY the application ended and detects patterns across rejections that can improve future applications. Do NOT trigger for positive outcomes like interviews (interview-debrief) or offers (offer-evaluator). For simple status updates without rejection context, job-tracker may be sufficient, but this skill adds the learning layer.

Write targeted cover letters for job applications using scored match data and tailored resumes. Use this skill whenever the user wants a cover letter for a specific role — after resume tailoring, when the user says "write a cover letter," "draft a cover letter for this job," "I need a cover letter," "write the letter," or when proceeding through the application workflow after resume-tailor completes. Also trigger when the user says "next step" or "let's keep going" after a resume has been tailored. This skill reads the application folder (metadata.json, tailored resume, job description) and produces a concise, formal cover letter that addresses gaps and reinforces strengths. Outputs .docx, .pdf, and .md versions. Do NOT trigger for general writing help, thank-you notes, follow-up emails, or resignation letters — those are different workflows.

Run and monitor the email-to-job pipeline scripts. Use this skill when the user says "run the email pipeline," "fetch my emails," "check for new job emails," "process emails," "run the pipeline," "update the pipeline," or any request to execute the email-to-job automation scripts. Also trigger when the user asks "pipeline status," "how many emails are pending," or "what's stuck in the pipeline." This skill orchestrates the four Python scripts (email_fetch, email_parse, career_search, job_score) and reports results. Do NOT trigger for reviewing ranked leads (that's email-triage) or for evaluating a specific job (job-intake).

Review and rank job leads from the email pipeline. Use this skill when the user says "check my email pipeline," "review new leads," "what came in from email," "show me the ranked jobs," "triage the email queue," "any new leads?", "process my forwarded emails," or when the user wants to review pending_review jobs from the email-to-job pipeline. Also trigger when the user says "promote this lead" or "skip this one" while reviewing pipeline results. This skill presents scored leads in ranked order and lets the user decide which to promote to full job-intake evaluation. Do NOT trigger for evaluating a specific job description the user pastes (that's job-intake), for updating status on existing applications (that's job-tracker), or for running the pipeline scripts (that's email-pipeline-runner).

Update application status, log follow-ups, and maintain the job tracker spreadsheet. Use this skill whenever the user wants to update the status of a job application — "I applied," "I got a rejection," "they scheduled an interview," "mark it as withdrawn," "update the tracker," "log this application," "I submitted it," "any follow-ups due?" Also trigger when the user says "I'm done" or "submitted" after the resume and cover letter are ready, or asks to check on pending applications, review follow-up dates, or get a status overview of all active applications. This is the bookkeeping skill — it keeps metadata.json and tracker.xlsx in sync so nothing falls through the cracks. Do NOT trigger for evaluating new jobs (job-intake), tailoring resumes (resume-tailor), or writing cover letters (cover-letter-writer).

Evaluate job offers and support negotiation. Use this skill when the user says "I got an offer", "received an offer from X", "they made me an offer", "evaluate this offer", "should I accept?", "is this a good offer?", "help me negotiate", "counter-offer", "they offered $X", "comparing two offers", or any discussion about accepting, declining, or negotiating a specific job offer. Also trigger when the user asks about salary ranges, equity evaluation, or how to respond to an offer. This is the final skill in the chain — turning interviews into outcomes. Do NOT trigger for general compensation research without a specific offer, or for interview prep (interview-prep-builder).

Recommend job search strategy adjustments based on application data. Use this skill when the user asks "what should I apply to next?", "where should I focus?", "how should I adjust my search?", "what types of roles are working?", "should I keep doing stretch applications?", "am I wasting time on LinkedIn?", "what's my best approach?", or any strategic question about job search direction. Also trigger for weekly check-ins, after a batch of rejections, or when the user seems discouraged and needs data-driven guidance. This skill interprets analytics data and makes specific recommendations — it doesn't just show numbers (that's application-analytics). Do NOT trigger for individual application evaluation (job-intake) or status updates (job-tracker).