AB voltage-effect
Diagnoses whether a result that worked at small scale will keep working when scaled — by testing an idea against John List's five reasons ideas lose 'voltage' (false positives, unrepresentative population, unrepresentative situation, spillovers, and the supply-side cost trap) BEFORE committing to scale. Activate when: user says 'the pilot worked, let's roll it out', 'this crushed it in the beta', 'we're ready to scale', 'the unit economics will improve with volume', 'it worked in one city/market/segment', 'should we franchise / expand nationally', or wants to predict whether a promising early result will survive scaling. Do NOT activate when: the question is purely how to build scale infrastructure with no doubt the result generalizes (use economies-of-scale); the idea has already scaled and held, and you are optimizing a mature operation; or the decision has no scale step at all (a one-off, non-repeatable choice). More: deciqai.com/c/voltage-effect
Diagnoses whether a result that worked at small scale will keep working when scaled — by testing an idea against John List's five reasons ideas lose 'voltage'…
As a process B 76/100 · Nearly there — weak spots: running it twice, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 76/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4605 tokens
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100Consistency. Name and required fields are in place
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 963: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 12 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.