Verified against ChatGPT · 2026-08-10
Turn a job posting's requirements gap into a specific, time-boxed plan instead of a vague skills list
Compares your actual skills against a target role's requirements and produces a concrete closing plan with real time estimates, rather than a generic list of things to learn someday.
The prompt
Ready to copy — highlighted parts are example details you can swap.
Compare my current skills against what a target role actually requires, and build me a specific plan to close the real gap — not a vague "learn Python" list. MY CURRENT SKILLS AND EXPERIENCE 5 years as a backend engineer in Python/Django, no real frontend experience beyond basic HTML/CSS, never worked with a design system. TARGET ROLE REQUIREMENTS Full-stack engineer role requiring React, TypeScript, and comfort working directly from Figma designs without a dedicated frontend dev. TIME I REALISTICALLY HAVE About 6 weeks, evenings and weekends only, alongside my current full-time job. MY LEARNING CONSTRAINTS I learn best by building something real, not by watching video courses passively — courses I've bought in the past I never finish. Work through this in phases: PHASE 1 — REAL GAP, NOT SURFACE GAP For each requirement in the target role, classify it as: already have it (say where it shows in my background), transferable (I have something adjacent that would close most of the gap with practice, not from-scratch learning), or genuine gap (I have nothing close to this). Be skeptical of your own "transferable" calls — if it's a stretch, say so rather than rounding up to make the gap look smaller than it is. PHASE 2 — PRIORITIZE BY WHAT ACTUALLY BLOCKS APPLYING Of the genuine gaps, tell me which ones would likely get my application filtered out before a human even reads it (hard requirement, keyword-matched, or asked directly in a screening question) versus which ones matter more once I'm already in front of a person, since those two categories need different urgency. PHASE 3 — TIME-BOXED CLOSING PLAN Given the time I actually have, build a plan only for the gaps that are worth closing before I start applying versus ones I should plan to close after landing an interview or even after starting the role. For each gap in the "close before applying" bucket, give a specific method (not "take a course" in the abstract — name the type of resource and a realistic time estimate) and be honest if the timeline I have isn't enough to genuinely close a given gap, rather than compressing a plan to fit a deadline that can't support it. WHAT NOT TO DO Do not recommend generic "learn X" advice without tying it to a specific proof point I could show or talk about in an interview — a skill only counts as closed if I could demonstrate it, not just claim it. OUTPUT FORMAT A three-column gap table (requirement / current status / priority), then the time-boxed plan only for the gaps worth closing now, then one paragraph on what to say honestly about any gap you're advising me to leave open.
Customize
Optional — swap in your own details for the highlighted parts above.
Why this works
A generic skill-gap output — "you should learn React and TypeScript" — is nearly useless on its own because it doesn't answer the question that actually determines what a candidate should do this week: is this gap severe enough to block getting past an ATS keyword filter or a screening question, or is it something that matters more once a human is already evaluating the whole candidate. Phase 2's split between application-blocking gaps and interview-stage gaps forces the model to reason about where in the funnel a given requirement actually gets checked, which changes the urgency and the kind of proof needed — a hard keyword-matched requirement needs something resume-visible fast, while a requirement that surfaces in a technical interview has more room for in-progress learning to be discussed honestly rather than fully mastered. The instruction to be skeptical of the model's own "transferable" classifications addresses a specific optimism bias: a model asked to assess how close someone's existing skills are to a requirement tends to round up, treating "I've touched HTML/CSS" as closer to "comfortable working from Figma designs" than it honestly is, because a smaller gap makes for a more encouraging-sounding answer — explicitly asking it to flag its own stretch calls counteracts that. Requiring every closing-plan item to tie to a demonstrable proof point, rather than accepting a course-completion certificate as sufficient, matters because what actually gets evaluated in an interview or portfolio review is whether the candidate can show or discuss the skill in action, not whether they can claim exposure to it — a plan built around proof points produces talking points for the interview itself, not just a private sense of having studied.
What you get back
Requirement: 'comfort working from Figma designs.' Status: genuine gap, not transferable — basic CSS knowledge doesn't cover component-based design system work. Priority: interview-stage, not application-blocking, since it's rarely a resume keyword filter. Plan: spend two weekends rebuilding one real Figma community file as working React components, so you have a specific link to show and discuss rather than a claimed familiarity.
Verified against
ChatGPT GPT-5.1 · 2026-08-10
Changelog
- 2026-08-10 — Initial publish, verified against ChatGPT GPT-5.1.
Need this built into your business?
If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.
EXPLORE WHAT SCULT BUILDS
