Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Prepare for a K-12 parent-teacher conference — including the hard ones. Use when asked to prep for a parent conference, plan what to say to a parent, or handle a difficult conversation about a student's behavior or grades. Produces a structured agenda, strengths-first talking points backed by specific evidence, a plan for the tough message, anticipated parent reactions with responses, and agreed next steps.
.claude/skills/mohitagw15856-parent-conference-prep/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 69% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-18 | ✗→✓ | ▲ Improved | 107% | 0% |
| case-20 | ✓→✗ | ▼ Worse | 18% | 0% |
| case-21 | ✓→✗ | ▼ Worse | 49% | 0% |
Parents remember how a conference felt more than the data in it. The teachers who land hard messages lead with genuine strengths, bring specifics instead of labels, and leave the parent with a partnership, not a verdict. This skill preps the whole conversation — including the reaction you're bracing for.
Given the student and the reason for the conference, write the full prep — infer likely parent concerns from the situation. Keep it partnership-framed: the teacher and parent on the same side of the table, the challenge on the other.
Ask for (if not provided, else infer and label):
Open warm → strengths with evidence → the concern (specific, non-labeling) → what we'll each do → close on partnership. With rough timing for a ~15–20 min slot.
2–3 genuine strengths, each with a specific example (not "he's a good kid").
The hard message scripted: describe the behavior/pattern with evidence, not a character label ("I've seen him leave three assignments unfinished this week" — not "he's lazy"). Name the impact, then pivot to the plan.
The likely parent responses (defensiveness, blame, overwhelm, disengagement) and a calm, non-escalating reply for each.
2–3 concrete, shared actions — what the teacher will do, what the parent can do, and when you'll check back.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 15,814 | 12,653 | -20% | 1 | 1 | 0% | 2,649 | 2,816 | +6% | 0 | 0 | — |
case-02 | pass→pass | 13,450 | 14,274 | +6% | 1 | 1 | 0% | 2,399 | 3,045 | +27% | 0 | 0 | — |
case-03 | pass→pass | 11,426 | 12,907 | +13% | 1 | 1 | 0% | 1,925 | 2,727 | +42% | 0 | 0 | — |
case-04 | pass→pass | 17,188 | 15,395 | -10% | 1 | 1 | 0% | 3,174 | 3,226 | +2% | 0 | 0 | — |
case-05 | pass→pass | 17,587 | 16,447 | -6% | 1 | 1 | 0% | 3,003 | 3,434 | +14% | 0 | 0 | — |
case-06 | pass→pass | 17,765 | 15,634 | -12% | 1 | 1 | 0% | 2,650 | 3,146 | +19% | 0 | 0 | — |
case-07 | pass→pass | 9,731 | 16,629 | +71% | 1 | 1 | 0% | 1,626 | 3,055 | +88% | 0 | 0 | — |
case-08 | pass→pass | 13,237 | 16,283 | +23% | 1 | 1 | 0% | 2,446 | 3,067 | +25% | 0 | 0 | — |
case-13 | pass→pass | 13,247 | 17,287 | +30% | 1 | 1 | 0% | 2,464 | 3,296 | +34% | 0 | 0 | — |
case-09 | fail→pass | 10,825 | 13,667 | +26% | 1 | 1 | 0% | 1,717 | 2,909 | +69% | 0 | 0 | — |
case-10 | pass→pass | 13,155 | 13,222 | +1% | 1 | 1 | 0% | 2,154 | 2,677 | +24% | 0 | 0 | — |
case-11 | pass→pass | 10,349 | 8,803 | -15% | 1 | 1 | 0% | 1,722 | 1,835 | +7% | 0 | 0 | — |
case-12 | pass→pass | 17,078 | 11,217 | -34% | 1 | 1 | 0% | 2,803 | 2,405 | -14% | 0 | 0 | — |
case-14 | pass→pass | 16,410 | 17,101 | +4% | 1 | 1 | 0% | 2,570 | 3,155 | +23% | 0 | 0 | — |
case-15 | pass→pass | 9,740 | 6,828 | -30% | 1 | 1 | 0% | 1,617 | 1,622 | +0% | 0 | 0 | — |
case-16 | pass→pass | 10,716 | 12,481 | +16% | 1 | 1 | 0% | 1,762 | 2,328 | +32% | 0 | 0 | — |
case-17 | fail→pass | 18,582 | 13,380 | -28% | 1 | 1 | 0% | 2,673 | 2,516 | -6% | 0 | 0 | — |
case-18 | fail→pass | 9,546 | 14,999 | +57% | 1 | 1 | 0% | 1,421 | 2,935 | +107% | 0 | 0 | — |
case-19 | pass→pass | 11,201 | 14,322 | +28% | 1 | 1 | 0% | 1,744 | 2,749 | +58% | 0 | 0 | — |
case-20 | pass→fail | 15,770 | 17,305 | +10% | 1 | 1 | 0% | 2,764 | 3,270 | +18% | 0 | 0 | — |
case-21 | pass→fail | 15,146 | 19,837 | +31% | 1 | 1 | 0% | 2,447 | 3,648 | +49% | 0 | 0 | — |
case-22 | pass→pass | 12,914 | 11,882 | -8% | 1 | 1 | 0% | 2,267 | 2,393 | +6% | 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 +5 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 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.