AC task-boundary-auditor
Use when a user asks the AI to perform tasks that may exceed LLM capabilities, such as counterfactual reasoning, formal verification, real-time control, physical design, ethical judgment, zero-omission auditing, or extreme prediction. Also use when tasks mix safe and unsafe sub-tasks. Triggers: "verify all", "prove", "predict", "design a bridge/system", "what if X never happened", "ensure no omissions", "real-time monitor", "legal/medical judgment".
Use when a user asks the AI to perform tasks that may exceed LLM capabilities, such as counterfactual reasoning, formal verification, real-time control…
As a process C 59/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Use when a user asks the AI to perform tasks that may exceed LLM c… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 59/100
- 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
- 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
- 100Tools and files. No external tools needed
- 100Steps. 15 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2204 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +3Description length 453: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 15 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.