AC judgment-loop
Turn consequential choices, uncertain claims, recurring failures, serious learning, and evidence-bearing reviews into provisional judgments, discriminating tests, and user-owned action. Use explicitly or when meaningful consequence and unresolved uncertainty coexist. Do not use for simple facts, well-specified execution, low-cost reversible choices, freeform creation, or emotional support alone.
Turn consequential choices, uncertain claims, recurring failures, serious learning, and evidence-bearing reviews into provisional judgments, discriminating…
As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, running it twice
How to improve
- 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: 12. 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 63/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 786 tokens
- medium 20 test cases, all positive: not one "should refuse" or "should ask first"
- low No test case covers injection arriving through data
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
- +4No input/output examples
- -31 of 1 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 398: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 14 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (4 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.