AB ethical-thinking
Use this skill when the user asks for ethical thinking (including naming it or directing use/apply/run with obvious misspellings; decisive) or wants a structured pass on values and harms—mapping stakeholders, tradeoffs, power asymmetries, harms and benefits, consent, justice, and fair process for a plan or product. Use for moral review, fairness or AI-ethics style questions, stakeholder harm scans, or should-we questions beyond pure legality, including indirect asks. Skip when they want legal advice as such, only neutral facts with no normative review requested, or implementation-only work with no values lens asked for.
As a process B 66/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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: 2. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 5 branches
- 100Tools and files. No external tools needed
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 784 tokens
- 100Running it twice. No mutating operations
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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +3Description length 627: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 12 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.