AB devils-advocate-on-demand
Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber. Use when asked to play devil's advocate, argue against this, challenge my conclusion, or talk me out of it. Produces the strongest case against your position, the uncomfortable questions you're avoiding, the evidence that cuts the other way, and an honest read on whether your conclusion survives the challenge — deliberately countering the 'that's a great idea!' agreement bias.
Argue hard against whatever you just concluded — so your decision has to survive a real challenge instead of an echo chamber.
As a process B 70/100 · Nearly there — weak spots: when it triggers, 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 70/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When 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. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 753 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)
- +1No license
- +2Single-language instructions
- +3Description length 505: enough signal without eating the budget
- +4Structure: 9 headings
- +3Step-by-step instructions: 27 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.