Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply Bloom's revised taxonomy to classify learning objectives and design assessments across six cognitive levels. Use this skill when the user needs to write learning objectives at specific cognitive levels, align assessment with instructional goals, or evaluate curriculum for cognitive complexity distribution — even if they say 'how to write learning objectives', 'what level of thinking does this require', or 'higher-order thinking skills'.
.claude/skills/asgard-ai-platform-grad-blooms/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-08 | ✗→✓ | ▲ Improved | 64% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -14% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 73% | 0% |
Bloom's revised taxonomy (Anderson & Krathwohl, 2001) classifies cognitive processes into six hierarchical levels: Remember, Understand, Apply, Analyze, Evaluate, and Create. Combined with the knowledge dimension (factual, conceptual, procedural, metacognitive), it provides a two-dimensional framework for designing and assessing learning.
Trigger conditions:
When NOT to use:
IRON LAW: Higher-Order Thinking REQUIRES a Foundation of Lower-Order Knowledge
You cannot analyze what you don't understand. You cannot evaluate
what you haven't analyzed. You cannot create without evaluation criteria.
The hierarchy is:
Remember → Understand → Apply → Analyze → Evaluate → Create
Skipping levels produces superficial "higher-order" work built on
a weak knowledge foundation.Classify the target knowledge: factual (terminology, details), conceptual (categories, principles), procedural (how-to, techniques), or metacognitive (self-awareness, strategies).
Choose the appropriate cognitive process level. Use action verbs that are observable and measurable for each level.
Combine: "Students will be able to action verb] knowledge content] context/condition]." Ensure the verb matches the intended cognitive level.
Match assessment methods to the cognitive level. Remember/Understand → objective tests. Apply/Analyze → case studies, problem sets. Evaluate/Create → projects, portfolios, essays.
markdown# Learning Objectives Analysis: {Course/Module} ## Taxonomy Mapping | Objective | Cognitive Level | Knowledge Type | Action Verb | Assessment Method | |-----------|----------------|---------------|-------------|-------------------| | ... | Remember/Understand/Apply/Analyze/Evaluate/Create | Factual/Conceptual/Procedural/Metacognitive | ... | ... | ## Cognitive Level Distribution - Lower-order (Remember, Understand, Apply): {count, %} - Higher-order (Analyze, Evaluate, Create): {count, %} - Balance assessment: {adequate or needs adjustment} ## Alignment Check - Objectives ↔ Instruction: {aligned / gaps} - Objectives ↔ Assessment: {aligned / gaps} ## Recommendations {Specific suggestions for improving cognitive level balance and alignment}
references/verb-taxonomy.mdreferences/alignment-matrix.md| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | fail→pass | 8,670 | 11,214 | +29% | 1 | 1 | 0% | 1,392 | 2,280 | +64% | 0 | 0 | — |
case-01 | fail→pass | 26,926 | 16,794 | -38% | 1 | 1 | 0% | 4,968 | 3,386 | -32% | 0 | 0 | — |
case-02 | fail→pass | 23,563 | 12,164 | -48% | 1 | 1 | 0% | 3,954 | 3,065 | -22% | 0 | 0 | — |
case-03 | fail→pass | 23,339 | 11,596 | -50% | 1 | 1 | 0% | 3,362 | 2,901 | -14% | 0 | 0 | — |
case-04 | pass→pass | 28,480 | 23,789 | -16% | 1 | 1 | 0% | 3,667 | 4,181 | +14% | 0 | 0 | — |
case-05 | pass→fail | 20,680 | 19,667 | -5% | 1 | 1 | 0% | 2,768 | 3,772 | +36% | 0 | 0 | — |
case-06 | pass→pass | 21,739 | 34,102 | +57% | 1 | 1 | 0% | 2,939 | 3,844 | +31% | 0 | 0 | — |
case-07 | pass→pass | 10,401 | 9,881 | -5% | 1 | 1 | 0% | 1,790 | 2,391 | +34% | 0 | 0 | — |
case-09 | fail→pass | 10,670 | 14,412 | +35% | 1 | 1 | 0% | 1,732 | 3,002 | +73% | 0 | 0 | — |
case-10 | pass→pass | 8,908 | 10,008 | +12% | 1 | 1 | 0% | 1,500 | 2,424 | +62% | 0 | 0 | — |
case-11 | pass→pass | 12,544 | 27,807 | +122% | 1 | 1 | 0% | 2,186 | 3,234 | +48% | 0 | 0 | — |
case-12 | pass→pass | 19,982 | 18,052 | -10% | 1 | 1 | 0% | 2,930 | 3,895 | +33% | 0 | 0 | — |
case-13 | pass→pass | 15,218 | 13,211 | -13% | 1 | 1 | 0% | 1,947 | 2,665 | +37% | 0 | 0 | — |
case-14 | pass→pass | 13,106 | 11,604 | -11% | 1 | 1 | 0% | 1,738 | 2,754 | +58% | 0 | 0 | — |
case-15 | pass→pass | 15,399 | 15,472 | +0% | 1 | 1 | 0% | 2,230 | 3,243 | +45% | 0 | 0 | — |
case-16 | pass→pass | 14,406 | 11,987 | -17% | 1 | 1 | 0% | 2,261 | 2,958 | +31% | 0 | 0 | — |
case-17 | fail→pass | 19,708 | 16,094 | -18% | 1 | 1 | 0% | 2,570 | 3,466 | +35% | 0 | 0 | — |
case-18 | pass→pass | 14,118 | 13,727 | -3% | 1 | 1 | 0% | 2,348 | 2,709 | +15% | 0 | 0 | — |
case-19 | fail→pass | 5,002 | 14,343 | +187% | 1 | 1 | 0% | 933 | 3,394 | +264% | 0 | 0 | — |
case-20 | pass→pass | 18,331 | 12,760 | -30% | 1 | 1 | 0% | 2,294 | 2,909 | +27% | 0 | 0 | — |
case-21 | pass→pass | 8,492 | 9,854 | +16% | 1 | 1 | 0% | 1,545 | 2,666 | +73% | 0 | 0 | — |
case-22 | pass→pass | 20,865 | 16,035 | -23% | 1 | 1 | 0% | 2,788 | 3,524 | +26% | 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. 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.