Structured interview kit with behavioural questions and scoring guides
Builds an interview kit for one role and one interview stage: competencies tied to real outcomes, behavioural questions with follow-ups, a 1/3/5 scoring guide per competency and a timing plan, so every candidate gets a fair, comparable interview.
Prompt in Operations by AISkillHub Library
What it does
Unstructured interviews tend to reward candidates who are like the interviewer. A structured kit asks every candidate the same job-related questions and scores answers against the same written guide, which makes comparisons fairer and debriefs shorter. This prompt builds that kit for one interview stage from the outcomes the role is actually hired for.
**Use it when** you are opening a role, adding an interviewer to a loop, or your debriefs keep turning into "I liked them" versus "I didn't".
**What you get** - Three to five competencies, each linked to a role outcome you provided. - For each competency: one main behavioural question ("Tell me about a time..."), an optional situational question, and three follow-up probes. - A 1 / 3 / 5 scoring guide describing what a weak, solid and strong answer sounds like. - "Watch for" notes on common ways answers mislead. - A timing plan that fits the interview length, including time for the candidate's questions. - An interviewer scorecard template to fill in during or right after the interview.
**What it will not do** - It will not include questions about protected characteristics or personal life (age, family plans, religion, health, nationality and similar), or proxies for them. If your inputs ask for such topics, it removes them and says why. - It will not write trick questions or brainteasers unrelated to the work. - It is not legal or HR compliance advice. Check the kit against your organisation's hiring policies and local employment law.
**Example** For a mid-market Customer Success Manager, the kit pairs "difficult conversations" with the renewal outcome and includes a question about delivering unwelcome news, three probes and a scoring guide. See the example file.
How to use it
## How to use
1. Open `prompts/structured-interview-kit.md` and copy everything below the title line. 2. Replace each `{{variable}}` with your own content. Paste long material (notes, transcripts, tables) directly in place of the variable; keep the surrounding tags so the model can tell inputs apart. 3. Start a new chat in ChatGPT, Claude or Gemini and paste the filled prompt as your first message. 4. Read the output against the quality checks at the end of the prompt before you use or send it.
## Variables
- `{{role_title}}`: the job title and level. - `{{role_outcomes}}`: what this person must achieve in the first 6 to 12 months. - `{{competencies}}`: competencies to assess at this stage, or `suggest` to have them derived from the outcomes. - `{{interview_length}}`: e.g. `45 minutes`. - `{{stage}}`: which interview this is, e.g. `phone screen`, `hiring manager`, `peer panel`. Helps avoid repeating other stages.
If you do not have a value for an optional variable, write `none` rather than deleting it, so the prompt still reads correctly.
## Example
`prompts/structured-interview-kit.example.md` shows the prompt with every variable filled and a trimmed sample of the output, so you can see the expected shape before you run it on real material.
## Reusing it
To reuse it often, save the prompt (with the variables left in) as the instructions of a Claude Project, a custom GPT or a Gemini Gem, then paste only the inputs in each new chat.
Files
Save each file at the path shown, relative to your project root.