AB dunning-kruger
Activate when: someone says 'how hard could it be' about an unfamiliar domain; a novice dismisses expert opinion or says 'I could do that'; someone's self-assessed confidence seems disconnected from their actual track record; a hiring or promotion decision is driven by self-presentation; feedback loops are absent and someone is operating on gut confidence alone. Do NOT activate when: the person is a known expert with an established external track record; the confidence claim is in a domain with tight, recent feedback loops that already calibrate performance. More: deciqai.com/c/dunning-kruger
Activate when: someone says 'how hard could it be' about an unfamiliar domain; a novice dismisses expert opinion or says 'I could do that'; someone's…
As a process B 73/100 · Nearly there — weak spots: failures and branches, 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: 1. 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 73/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1823 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
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 599: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 24 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: 95.