Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Prepare for an informational interview — the outreach, the questions, and the follow-up — so a 20-minute chat actually helps your career instead of wasting their time. Use when asked to prep for an informational interview, questions to ask someone in [field], how to reach out for a career chat, or coffee chat prep. Produces a low-friction outreach message, a focused question set tuned to your goal (exploring a field, breaking in, a specific company), how to run the conversation, what NOT to do (
.claude/skills/mohitagw15856-informational-interview-prep/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 15% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 49% | 0% |
| case-23 | ✗→✓ | ▲ Improved | 85% | 0% |
| case-11 | ✓→✗ | ▼ Worse | 61% | 0% |
| case-14 | ✓→✓ | = Same ✓ | 70% | 0% |
An informational interview is one of the best career tools — a short, low-pressure conversation to learn about a field, role, or company from someone doing it. But done wrong (vague questions, or angling for a job) it wastes their time and yours. This preps the whole thing: the ask, the right questions for your goal, how to run it, and a follow-up that turns a chat into a relationship.
Ask for these if not provided:
Outreach ask > Specific, brief request to learn + why them + easy to say yes — no job ask].
Questions (tuned to your goal): their path · day-to-day · how they broke in · what they wish they'd known · specific advice for you]. Run it: open warmly · their story first · go deeper on useful bits · watch the time]. Don't: ask for a job · dominate · show up unprepared. Follow up: specific thank-you · act on advice/intros · keep it warm]. Prep: what to research about them].
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-14 | pass→pass | 16,920 | 14,140 | -16% | 1 | 1 | 0% | 1,862 | 3,161 | +70% | 0 | 0 | — |
case-15 | pass→pass | 22,190 | 24,047 | +8% | 1 | 1 | 0% | 2,658 | 3,906 | +47% | 0 | 0 | — |
case-01 | pass→pass | 22,254 | 23,409 | +5% | 1 | 1 | 0% | 2,605 | 3,708 | +42% | 0 | 0 | — |
case-02 | pass→pass | 27,859 | 20,893 | -25% | 1 | 1 | 0% | 3,565 | 3,525 | -1% | 0 | 0 | — |
case-03 | fail→pass | 25,017 | 23,196 | -7% | 1 | 1 | 0% | 3,243 | 3,741 | +15% | 0 | 0 | — |
case-04 | pass→pass | 20,961 | 16,295 | -22% | 1 | 1 | 0% | 2,117 | 2,655 | +25% | 0 | 0 | — |
case-05 | pass→pass | 22,605 | 22,348 | -1% | 1 | 1 | 0% | 2,766 | 3,715 | +34% | 0 | 0 | — |
case-06 | pass→pass | 23,253 | 25,164 | +8% | 1 | 1 | 0% | 2,953 | 3,973 | +35% | 0 | 0 | — |
case-07 | pass→pass | 17,784 | 19,011 | +7% | 1 | 1 | 0% | 2,064 | 3,244 | +57% | 0 | 0 | — |
case-08 | pass→pass | 16,945 | 18,317 | +8% | 1 | 1 | 0% | 2,036 | 3,207 | +58% | 0 | 0 | — |
case-09 | fail→pass | 14,963 | 9,353 | -37% | 1 | 1 | 0% | 1,658 | 2,470 | +49% | 0 | 0 | — |
case-10 | pass→pass | 19,018 | 21,105 | +11% | 1 | 1 | 0% | 2,166 | 3,548 | +64% | 0 | 0 | — |
case-11 | pass→fail | 14,915 | 10,939 | -27% | 1 | 1 | 0% | 1,677 | 2,705 | +61% | 0 | 0 | — |
case-12 | pass→pass | 25,311 | 20,387 | -19% | 1 | 1 | 0% | 2,659 | 4,126 | +55% | 0 | 0 | — |
case-13 | pass→pass | 20,987 | 19,555 | -7% | 1 | 1 | 0% | 2,478 | 3,404 | +37% | 0 | 0 | — |
case-16 | fail→fail | 17,112 | 18,859 | +10% | 1 | 1 | 0% | 1,939 | 3,368 | +74% | 0 | 0 | — |
case-17 | pass→pass | 13,080 | 15,829 | +21% | 1 | 1 | 0% | 2,302 | 3,291 | +43% | 0 | 0 | — |
case-18 | pass→pass | 17,084 | 19,332 | +13% | 1 | 1 | 0% | 2,028 | 3,400 | +68% | 0 | 0 | — |
case-19 | pass→pass | 9,304 | 11,447 | +23% | 1 | 1 | 0% | 1,594 | 2,993 | +88% | 0 | 0 | — |
case-20 | pass→pass | 16,473 | 17,303 | +5% | 1 | 1 | 0% | 1,713 | 2,869 | +67% | 0 | 0 | — |
case-21 | pass→pass | 19,470 | 18,364 | -6% | 1 | 1 | 0% | 1,896 | 3,162 | +67% | 0 | 0 | — |
case-22 | pass→pass | 17,688 | 16,808 | -5% | 1 | 1 | 0% | 1,848 | 2,599 | +41% | 0 | 0 | — |
case-23 | fail→pass | 14,621 | 11,987 | -18% | 1 | 1 | 0% | 1,472 | 2,716 | +85% | 0 | 0 | — |
case-24 | pass→pass | 15,271 | 17,444 | +14% | 1 | 1 | 0% | 2,099 | 2,790 | +33% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted. The headline lift of +8 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.