Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build a standards-aligned K-12 lesson plan with clear objectives, a timed activity sequence, checks for understanding, and differentiation. Use when asked to plan a lesson, write a lesson plan, align a lesson to a standard, or turn a topic into a class period. Produces measurable objectives, a bell-to-bell timeline (hook → instruction → practice → close), formative checks, differentiation for varied learners, and the materials list.
.claude/skills/mohitagw15856-lesson-plan-builder/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -40% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 47% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -15% | 0% |
A good lesson plan is not a topic and a worksheet — it's a designed arc where every minute has a purpose and the teacher knows, before the bell, how they'll tell if it worked. This skill builds a plan backward from a measurable objective, with the checks for understanding and differentiation that make it survive a real classroom.
Given a topic, grade, and standard (or just a topic), write the full plan — infer the grade-appropriate objective and align to a plausible standard, labeling the assumption. Fit it to one class period unless told otherwise.
Ask for (if not provided, else infer and label):
Measurable and student-facing: _"Students will be able to verb] content] as measured by evidence]."_ Use observable verbs (identify, compare, model), not "understand."
The standard code + a one-line note on how the lesson meets it (labeled as inferred if you supplied it).
| Time | Phase | Teacher does | Students do | |---|---|---|---| | 0–5 | Hook / do-now | | | | 5–15 | Direct instruction | | | | 15–30 | Guided → independent practice | | | | 30–40 | Check + close | exit ticket | |
The formative moments — a question, a quick write, an exit ticket — and what answer tells you to move on vs. reteach.
Concrete moves for students who need support, who finish early, and for language learners (not "give more time").
Everything needed, ready to gather.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | pass→pass | 14,851 | 18,258 | +23% | 1 | 1 | 0% | 3,012 | 3,730 | +24% | 0 | 0 | — |
case-03 | fail→pass | 21,471 | 18,931 | -12% | 1 | 1 | 0% | 3,678 | 3,696 | +0% | 0 | 0 | — |
case-01 | fail→pass | 27,587 | 14,553 | -47% | 1 | 1 | 0% | 5,033 | 3,032 | -40% | 0 | 0 | — |
case-02 | pass→pass | 21,988 | 16,275 | -26% | 1 | 1 | 0% | 4,256 | 3,623 | -15% | 0 | 0 | — |
case-04 | pass→pass | 15,493 | 14,597 | -6% | 1 | 1 | 0% | 2,855 | 2,914 | +2% | 0 | 0 | — |
case-05 | fail→fail | 12,634 | 14,841 | +17% | 1 | 1 | 0% | 2,210 | 3,068 | +39% | 0 | 0 | — |
case-06 | fail→fail | 11,498 | 12,981 | +13% | 1 | 1 | 0% | 2,364 | 2,935 | +24% | 0 | 0 | — |
case-07 | fail→pass | 16,838 | 16,758 | -0% | 1 | 1 | 0% | 2,895 | 3,554 | +23% | 0 | 0 | — |
case-08 | fail→fail | 7,090 | 13,954 | +97% | 1 | 1 | 0% | 1,327 | 2,966 | +124% | 0 | 0 | — |
case-09 | fail→fail | 15,488 | 14,679 | -5% | 1 | 1 | 0% | 2,830 | 3,189 | +13% | 0 | 0 | — |
case-10 | fail→pass | 10,579 | 13,134 | +24% | 1 | 1 | 0% | 1,973 | 2,902 | +47% | 0 | 0 | — |
case-11 | pass→fail | 12,669 | 12,095 | -5% | 1 | 1 | 0% | 2,291 | 2,751 | +20% | 0 | 0 | — |
case-12 | pass→pass | 13,325 | 13,276 | -0% | 1 | 1 | 0% | 2,283 | 2,764 | +21% | 0 | 0 | — |
case-13 | fail→pass | 15,527 | 14,589 | -6% | 1 | 1 | 0% | 3,475 | 2,940 | -15% | 0 | 0 | — |
case-14 | pass→pass | 16,781 | 13,089 | -22% | 1 | 1 | 0% | 2,921 | 2,746 | -6% | 0 | 0 | — |
case-16 | fail→pass | 19,076 | 12,353 | -35% | 1 | 1 | 0% | 3,676 | 2,736 | -26% | 0 | 0 | — |
case-17 | fail→pass | 10,198 | 12,324 | +21% | 1 | 1 | 0% | 2,076 | 2,730 | +32% | 0 | 0 | — |
case-18 | pass→pass | 19,522 | 23,715 | +21% | 1 | 1 | 0% | 3,578 | 4,856 | +36% | 0 | 0 | — |
case-19 | fail→pass | 12,675 | 13,556 | +7% | 1 | 1 | 0% | 2,352 | 2,959 | +26% | 0 | 0 | — |
case-20 | pass→pass | 9,214 | 11,957 | +30% | 1 | 1 | 0% | 1,661 | 2,815 | +69% | 0 | 0 | — |
case-21 | pass→pass | 22,376 | 34,870 | +56% | 1 | 1 | 0% | 4,451 | 6,768 | +52% | 0 | 0 | — |
case-22 | pass→fail | 26,662 | 28,279 | +6% | 1 | 1 | 0% | 6,173 | 6,766 | +10% | 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 +27 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.