| name | resume-interview-rehearsal |
| description | Generate a ranked interview prep sheet from the resume. Three interviewer personas (hiring-manager, bar-raiser, domain-sme-systems) each generate 5 questions they would ask based on specific resume bullets. The questions are then deduplicated and ranked by difficulty tier (softball, standard, hard, trap). Includes a coverage audit flagging bullets no persona asked about. Optionally accepts a job description as $ARGUMENTS to target the questions for a specific role. Use when the user has an interview coming up, asks for interview prep, or wants to rehearse what they'd be asked about their resume. |
| argument-hint | ["job-description"] |
| allowed-tools | Read, Grep, Glob, Agent |
Interview Rehearsal
Generate a ranked interview question set from the resume by having three interviewer personas each propose questions, then merge, deduplicate, rank, and audit coverage.
Process
-
Generate questions in parallel. Launch the 3 interviewer sub-agents in a single Agent tool message. Each generates exactly 5 questions grounded in specific lines of the resume. Use the prompt in REFERENCE.md ยง Question Generation Prompt. Pass $ARGUMENTS as target-role context if non-empty.
-
Deduplicate and merge. When two personas target the same bullet with essentially the same question, keep the more specific or harder version and attribute it to both personas.
-
Rank by difficulty. Apply the tiers in REFERENCE.md ยง Difficulty Tiers.
-
Coverage audit. Scan the resume for bullets with big numbers, big ownership claims, or strong impact verbs. Any such bullet that no persona asked about is a coverage gap โ flag it explicitly. See REFERENCE.md ยง Coverage Audit.
-
Emit the prep sheet. Use the format in REFERENCE.md ยง Prep Sheet Format.
Notes
- This is a prep tool, not a review tool. The output is questions for the candidate to rehearse answers to โ not feedback on the resume itself.
- Every question MUST be grounded in a specific line of the resume. Reject generic questions ("tell me about yourself", "what's your biggest weakness") โ those aren't what this skill is for.
- If
$ARGUMENTS contains a job description, the personas should generate questions weighted toward the JD's responsibilities and tech stack.
See REFERENCE.md for the generation prompt, difficulty tiers, coverage audit protocol, and output template.
