AB doubt-driven-development
Stress-test high-risk changes with fresh-context skepticism before implementation or release. Use when work involves production, permissions, security controls, public packages, data deletion or migration, billing, credentials handling, irreversible operations, CI failures that are hard to explain, or any task where a confident but wrong agent answer would be costly.
Stress-test high-risk changes with fresh-context skepticism before implementation or release.
As a process B 69/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, 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 69/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 3 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 23 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 739 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)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 369: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 23 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.