Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when writing learning objectives, learning outcomes, or "students will be able to" statements for a lesson, course, module, or training. Writes each objective as one measurable, observable action verb (analyze, calculate, classify, design) so a teacher can assess whether a learner met it, and refuses vague verbs like understand, know, learn, and appreciate. Do NOT use for grading finished work against a rubric, writing practice problems or quiz items, explaining a concept, or laying out a full syllabus schedule.
.claude/skills/learning-objective-write/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | — | — |
| case-13 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-09 | ✗→✓ | ▲ Improved | — | — |
| case-06 | ✗→✓ | ▲ Improved | — | — |
Write each learning objective as one measurable, observable action a learner performs — something a teacher could watch them do or check in their work. Use the stem "[Learners] will be able to ..." (or an equivalent) followed by a single action verb and its object.
Vague (rejected):
> Students will understand the causes of World War I and appreciate its impact.
Rewritten:
> - Students will be able to identify three long-term causes of World War I. > - Students will be able to explain how alliance systems escalated a local conflict into a wider war.
The rewrite swaps the mental-state verbs for observable actions and splits the bundled "understand ... and appreciate" into two single-action objectives.
Pick the verb at the cognitive level the lesson actually targets — recalling a fact and critiquing an argument are different verbs. references/bloom_verbs.md lists observable verbs by cognitive tier (remember → create) and the vague verbs to avoid, when you need a wider menu.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.5-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 14 cases were attempted. The headline lift of +64 percentage points is the difference between those two pass rates over the 14 comparable cases.
Other measured skills in the registry, with their headline benchmark lift.