AB assumption-audit
Surface the hidden assumptions a plan or belief rests on, then test what happens when each one is wrong. Use when asked what am I assuming here, check my assumptions, what if I'm wrong about, or stress-test my thinking. Produces the unstated assumptions your conclusion depends on (ranked by how load-bearing they are), a flip of each to see which one breaking would change everything, and the cheapest way to check the riskiest ones — because the assumption you didn't know you were making is what sinks plans.
Surface the hidden assumptions a plan or belief rests on, then test what happens when each one is wrong.
As a process B 67/100 · Nearly there — weak spots: when it triggers, 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: 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 67/100
- 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
- 30Running it twice. 2 mutating operations with no state check
- 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 774 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 511: 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.