AC utilitarianism
Activate when: user asks 'what produces the most good,' 'who benefits and who gets hurt,' 'what's the net impact,' 'is this worth the trade-off,' 'what does the greatest good mean here'; user needs to evaluate a policy, product, or organizational decision that affects multiple parties differently; user is performing cost-benefit analysis or ethical trade-off evaluation. Do NOT activate when: the decision involves a single party with no stakeholder trade-offs (use expected-value-and-kelly instead); the question is purely about intrinsic rights or deontological constraints with no welfare aggregation needed. More: deciqai.com/c/utilitarianism
Activate when: user asks 'what produces the most good,' 'who benefits and who gets hurt,' 'what's the net impact,' 'is this worth the trade-off,' 'what does…
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
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: 4. 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 63/100
- 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
- 85Steps. 17 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1957 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 648: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 17 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: 91.