Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Write the follow-up messages that keep a candidate on the radar without being annoying. Use when asked to write a post-interview thank-you, a follow-up after no reply, a nudge on a stalled application, or a check-in sequence during a job search. Produces a timed sequence — what to send, when, and the exact wording — that adds value or shows interest at each step rather than just 'checking in'.
.claude/skills/mohitagw15856-follow-up-sequence/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 92% | 26 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -43% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -12% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -7% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 11% | 0% |
Most candidates either ghost after an interview or pester with "just checking in" — both hurt. The right follow-up is timed and adds something each time: a genuine thank-you, a useful thought, a graceful nudge. This skill builds the sequence — what to send, when, and the wording — so you stay top-of-mind and look like someone people want to work with.
Ask for these only if they aren't already provided:
A timed sequence — each step says when, why, and the exact message:
| When | Step | Goal | |---|---|---| | Within 24h | Thank-you | reinforce interest + one specific takeaway | | ~1 week | Value-add nudge | stay visible by adding something, not just asking | | ~2 weeks | Graceful status check | one polite ask, with an easy out |
For each step, the full message (subject + body), kept short:
End with a stop rule — when to let it go (and how to leave the door open).
Post-interview and job-search follow-up practice — timed, value-adding touches with a stop rule.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,582 | 9,324 | -31% | 1 | 1 | 0% | 2,498 | 2,349 | -6% | 0 | 0 | — |
case-02 | pass→pass | 15,293 | 9,183 | -40% | 1 | 1 | 0% | 2,801 | 2,372 | -15% | 0 | 0 | — |
case-03 | pass→pass | 15,687 | 11,228 | -28% | 1 | 1 | 0% | 2,694 | 2,587 | -4% | 0 | 0 | — |
case-04 | fail→pass | 11,392 | 2,582 | -77% | 1 | 1 | 0% | 2,087 | 1,183 | -43% | 0 | 0 | — |
case-05 | fail→fail | 14,733 | 8,557 | -42% | 1 | 1 | 0% | 2,614 | 2,307 | -12% | 0 | 0 | — |
case-06 | fail→pass | 15,269 | 8,237 | -46% | 1 | 1 | 0% | 2,559 | 2,242 | -12% | 0 | 0 | — |
case-07 | fail→fail | 12,131 | 11,630 | -4% | 1 | 1 | 0% | 2,096 | 2,787 | +33% | 0 | 0 | — |
case-08 | pass→pass | 17,280 | 10,455 | -39% | 1 | 1 | 0% | 2,874 | 2,499 | -13% | 0 | 0 | — |
case-09 | fail→pass | 15,220 | 8,196 | -46% | 1 | 1 | 0% | 2,455 | 2,283 | -7% | 0 | 0 | — |
case-10 | pass→pass | 11,551 | 9,042 | -22% | 1 | 1 | 0% | 1,870 | 2,363 | +26% | 0 | 0 | — |
case-11 | pass→pass | 12,772 | 10,313 | -19% | 1 | 1 | 0% | 1,976 | 2,507 | +27% | 0 | 0 | — |
case-12 | pass→pass | 10,506 | 7,698 | -27% | 1 | 1 | 0% | 1,914 | 2,346 | +23% | 0 | 0 | — |
case-13 | fail→pass | 12,616 | 9,000 | -29% | 1 | 1 | 0% | 2,049 | 2,284 | +11% | 0 | 0 | — |
case-14 | pass→pass | 10,817 | 10,746 | -1% | 1 | 1 | 0% | 1,767 | 2,601 | +47% | 0 | 0 | — |
case-15 | pass→pass | 12,331 | 10,167 | -18% | 1 | 1 | 0% | 2,078 | 2,431 | +17% | 0 | 0 | — |
case-16 | pass→pass | 16,421 | 11,428 | -30% | 1 | 1 | 0% | 2,545 | 2,556 | +0% | 0 | 0 | — |
case-17 | pass→pass | 14,497 | 10,701 | -26% | 1 | 1 | 0% | 2,249 | 2,502 | +11% | 0 | 0 | — |
case-18 | pass→pass | 10,611 | 8,758 | -17% | 1 | 1 | 0% | 1,809 | 2,286 | +26% | 0 | 0 | — |
case-19 | pass→pass | 10,702 | 9,036 | -16% | 1 | 1 | 0% | 2,159 | 2,305 | +7% | 0 | 0 | — |
case-20 | pass→fail | 8,095 | 8,894 | +10% | 1 | 1 | 0% | 1,404 | 2,215 | +58% | 0 | 0 | — |
case-21 | pass→fail | 8,824 | 11,668 | +32% | 1 | 1 | 0% | 1,407 | 2,675 | +90% | 0 | 0 | — |
case-22 | pass→fail | 9,096 | 12,393 | +36% | 1 | 1 | 0% | 1,632 | 2,974 | +82% | 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. 22 cases were attempted. The headline lift of +9 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 cases got worse with the skill loaded, and they are 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.