Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Apply Tesler's Law — every process has irreducible complexity that someone must absorb. Use when deciding whether the product or the user carries it. For reducing apparent choice, use `hicks-law`.
.claude/skills/owl-listener-teslers-law/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-17 | ✗→✓ | ▲ Improved | 27% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 39% | 0% |
| case-09 | ✓→✓ | = Same ✓ | 27% | 0% |
| case-06 | ✓→✓ | = Same ✓ | -10% | 0% |
| case-07 | ✓→✓ | = Same ✓ | 29% | 0% |
You are an expert in complexity management and the boundary between product responsibility and user responsibility.
You apply Tesler's Law to identify where complexity is being shifted onto users unnecessarily, locate where the product should absorb it instead, and resist the reflex to over-simplify in ways that create invisible downstream burden.
Larry Tesler proposed that every application has an inherent amount of irreducible complexity. This complexity cannot be eliminated — it can only be moved. The design decision is: does the user absorb the complexity, or does the product?
Simplifying the interface does not remove complexity. It relocates it.
Inherent complexity comes from the nature of the task itself. Booking a flight with multiple passengers, specific seats, and a connection is genuinely complex. Removing that complexity means removing capability.
Extraneous complexity comes from the design, not the task. A confusing form sequence, inconsistent terminology, redundant steps, or poorly structured decisions add burden the product has no reason to impose.
The job is to eliminate extraneous complexity and make a deliberate decision about who absorbs inherent complexity.
| User absorbs (move this to product) | Product absorbs (better) | |---|---| | User must type dates in the correct format | Product accepts multiple formats or provides a picker | | User selects country, then re-enters region | Product detects country, populates region options automatically | | User must follow a file naming convention | Product enforces or generates names | | User sets 12 options before starting | Product applies smart defaults; options available progressively | | User reads and interprets an error, then finds the fix | Product suggests the correction directly |
Tesler's Law warns against a common UX reflex: stripping all apparent complexity in pursuit of a "clean" interface. When you:
Simplifying the surface can create invisible complexity downstream — longer workflows, more error recovery, more support overhead. The complexity moved, it did not disappear.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 14,443 | 15,844 | +10% | 1 | 1 | 0% | 2,205 | 3,075 | +39% | 0 | 0 | — |
case-09 | pass→pass | 15,336 | 16,012 | +4% | 1 | 1 | 0% | 2,561 | 3,251 | +27% | 0 | 0 | — |
case-06 | pass→pass | 18,372 | 12,286 | -33% | 1 | 1 | 0% | 2,787 | 2,513 | -10% | 0 | 0 | — |
case-07 | pass→pass | 17,514 | 18,109 | +3% | 1 | 1 | 0% | 2,621 | 3,384 | +29% | 0 | 0 | — |
case-08 | pass→pass | 12,905 | 11,835 | -8% | 1 | 1 | 0% | 2,090 | 2,519 | +21% | 0 | 0 | — |
case-01 | pass→pass | 9,913 | 16,464 | +66% | 1 | 1 | 0% | 1,708 | 2,734 | +60% | 0 | 0 | — |
case-02 | pass→pass | 6,822 | 8,148 | +19% | 1 | 1 | 0% | 1,108 | 1,846 | +67% | 0 | 0 | — |
case-03 | pass→pass | 12,901 | 13,007 | +1% | 1 | 1 | 0% | 2,352 | 2,862 | +22% | 0 | 0 | — |
case-04 | fail→fail | 15,722 | 14,758 | -6% | 1 | 1 | 0% | 2,556 | 2,941 | +15% | 0 | 0 | — |
case-10 | pass→pass | 15,534 | 12,338 | -21% | 1 | 1 | 0% | 2,222 | 2,837 | +28% | 0 | 0 | — |
case-11 | pass→pass | 16,105 | 16,082 | -0% | 1 | 1 | 0% | 2,229 | 2,818 | +26% | 0 | 0 | — |
case-12 | pass→pass | 13,221 | 12,955 | -2% | 1 | 1 | 0% | 1,961 | 2,857 | +46% | 0 | 0 | — |
case-13 | pass→pass | 12,874 | 14,776 | +15% | 1 | 1 | 0% | 1,998 | 2,874 | +44% | 0 | 0 | — |
case-14 | pass→pass | 15,067 | 15,503 | +3% | 1 | 1 | 0% | 2,204 | 3,009 | +37% | 0 | 0 | — |
case-15 | pass→pass | 14,434 | 14,271 | -1% | 1 | 1 | 0% | 2,245 | 2,911 | +30% | 0 | 0 | — |
case-16 | pass→pass | 13,187 | 13,777 | +4% | 1 | 1 | 0% | 2,037 | 2,777 | +36% | 0 | 0 | — |
case-17 | fail→pass | 14,681 | 16,217 | +10% | 1 | 1 | 0% | 2,252 | 2,861 | +27% | 0 | 0 | — |
case-18 | pass→pass | 13,245 | 14,658 | +11% | 1 | 1 | 0% | 2,026 | 2,962 | +46% | 0 | 0 | — |
case-19 | pass→pass | 13,780 | 13,524 | -2% | 1 | 1 | 0% | 2,065 | 2,737 | +33% | 0 | 0 | — |
case-20 | pass→pass | 17,002 | 16,606 | -2% | 1 | 1 | 0% | 2,541 | 3,198 | +26% | 0 | 0 | — |
case-21 | pass→pass | 17,106 | 15,194 | -11% | 1 | 1 | 0% | 2,323 | 3,075 | +32% | 0 | 0 | — |
case-22 | pass→pass | 13,126 | 12,802 | -2% | 1 | 1 | 0% | 1,905 | 2,538 | +33% | 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.
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.