Generate Questions From a GitHub Profile or Portfolio
When to use it
Turn a candidate's public projects into real screening questions instead of skimming and moving on.
The prompt
I'm reviewing a candidate's GitHub profile or portfolio for a {{Job Title}} role. I'm not an engineer, so help me ask informed questions about it. WHAT I'M LOOKING AT: {{paste repo names and descriptions, README excerpts, pinned projects, or a portfolio's project list}} WHAT THE ROLE NEEDS: {{the 2-3 skills that matter most}} Give me: 1. A plain-English read of what these projects suggest the person can do, and which ones are relevant to this role. 2. Signals that carry weight — a project with real users, a README that explains design decisions, contributions to someone else's project that were reviewed and merged — versus ones that don't, like streaks, star counts and forked tutorials. 3. 4-5 questions about their specific projects that a non-technical person can ask credibly: why they built it, what broke, what they'd change now. 4. What a strong answer to each sounds like, next to a vague or rehearsed one. 5. Signs a project may be a course assignment, a template, or largely AI-generated, framed as things to ask about rather than conclusions. 6. One thing to flag to a technical interviewer, since it's beyond what I can evaluate. Don't penalise a thin public profile. Many strong engineers do all their work in private repositories.
Tip
You're not trying to fake technical depth. A question specific enough to prove you opened their project earns more candour than any general one, and the answer to 'what would you change now?' tells you more than the code does.
How to use it
Paste the prompt into ChatGPT, Claude or whichever assistant you use, then replace every {{bracketed}} part with your own detail. The more specific and messier your input, the better the output — a model given raw notes has more to work with than one given a tidy summary you wrote first.
More Technical Translation prompts
Open the full tool for all 87 prompts, the glossary, and the JD decoder.