AF nudge-theory
Activate when: user says 'nudge,' 'default,' 'opt-in vs opt-out,' 'choice architecture,' or 'why do people know they should but don't?'; user has a behavior gap between intent and action; user is designing product onboarding, policy enrollment, or public health interventions and wants to change behavior without mandates or incentives. Do NOT activate when: the gap is informational (people genuinely don't know what to do — education precedes nudging); the designer's goal is to serve their own interests rather than the chooser's (that is a dark pattern, not a nudge). More: deciqai.com/c/nudge-theory
Activate when: user says 'nudge,' 'default,' 'opt-in vs opt-out,' 'choice architecture,' or 'why do people know they should but don't?'; user has a behavior…
As a process F 47/100 · Will not run — References files that are not bundled: examples/401k-automatic-enrollment-and-the-pension-protection-act-2006.md, examples/choice-architecture-in-ai-products-2023-2026.md, references/sources.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: examples/401k-automatic-enrollment-and-the-pension-protection-act-2006.md - warning
missing-refreference to a missing file: examples/choice-architecture-in-ai-products-2023-2026.md - warning
missing-refreference to a missing file: references/sources.md
Process rating: all ten parameters 47/100
- 0Tools and files. 3 referenced file(s) missing: examples/401k-automatic-enrollment-and-the-pension-protection-act-2006.md, examples/choice-architecture-in-ai-products-2023-2026.md, references/sources.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2155 tokens
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)
- +1No license
- +2Single-language instructions
- +3Description length 604: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 37 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.