Apply Cognitive Load Theory to optimize instructional design by managing intrinsic, extraneous, and germane load within working memory limits.
SkillScore95Maintained
Automatic
◆Tutoring & Education pack
Last verified 8/27/2026
What it changes
Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill95%
Checks it passed that the model alone missed
classifies decorative marketing anecdotes in technical docs as seductive details
identifies lack of germane load processing as the cause of poor schema abstraction
evaluates intrinsic load as high due to element interactivity in calculus integration
and 2 more in the full report
5 fixed16 passed either way0 still failing1 broke
Pass-rate lift
+18 pp
Tokens
+18%
Agent turns
0%
Response time
-9%
Model gemini-3.6-flashMeasured 8/27/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 5
Prompt
High school calculus students struggle when transitioning from lecture explanations to complex integration-by-parts problem sets. Design an instructional strategy report evaluating current load and outlining a step-by-step problem-solving transition plan.
What was checked, without and with the skill
Checked
Without skill
With skill
evaluates intrinsic load as high due to element interactivity in calculus integration
Missed
Passed
recommends worked examples followed by faded scaffolding to build integration schemas
Passed
Passed
case-07 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md110 linessingle file
Cognitive Load Theory (CLT)
Overview
Cognitive Load Theory (Sweller, 1988) is grounded in the architecture of human cognition: working memory is severely limited in capacity (7 +/- 2 items) and duration, while long-term memory is essentially unlimited. Effective instructional design must manage three types of cognitive load — intrinsic (task complexity), extraneous (poor design), and germane (schema construction) — so that total load does not exceed working memory capacity.
When to Use
Diagnosing why learners fail to comprehend or retain instructional material
Redesigning documentation, tutorials, or training programs for reduced cognitive burden
Evaluating interface design, dashboards, or information displays for overload
Sequencing complex learning material to scaffold schema acquisition
When NOT to Use
When the problem is motivational rather than cognitive (learner can process but chooses not to)
For expert audiences where schemas already exist and the expertise reversal effect applies
When simplification would compromise essential task fidelity (some tasks are irreducibly complex)
Assumptions
IRON LAW: Working memory capacity is FIXED and limited —
instructional design must minimize extraneous load to maximize
germane processing. Total load (intrinsic + extraneous + germane)
must not exceed working memory capacity.
Key assumptions:
Working memory processes novel information; long-term memory stores schemas that bypass WM limits
Intrinsic load is determined by element interactivity — it cannot be reduced without changing the task
Extraneous load is under the designer's control and should always be minimized
Methodology
Step 1 — Analyze Element Interactivity (Intrinsic Load)
Assess how many information elements must be processed simultaneously:
Low interactivity: elements can be learned independently (vocabulary lists)
High interactivity: elements must be integrated to be understood (grammar rules, circuit design)