AC stormproof
Look up historical NOAA hurricane weather data — peak wind speed, wind gust, and storm surge — for a SPECIFIC U.S. street address on a specific date. Use this skill ONLY when the user wants weather data tied to a specific property address — e.g. "wind speed at my address during Milton", "verify the storm for my insurance claim at [address]", "NOAA data for my date of loss", "how strong were the gusts at [address]". The tell is an address (or the user's intent to provide one) plus a verification purpose: an insurance claim, a date of loss, an adjuster dispute, forensic weather verification, wind vs. flood damage evaluation, or historical storm research on a property. Do NOT activate for general weather conversation, forecasts, storm news, or named-storm questions that aren't about a specific property.
As a process C 64/100 · Has gaps — weak spots: result and completion, 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: 2. 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 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 11 branches
- 70Execution cost. Instruction body is 4863 tokens
- 100Tools and files. No external tools needed
- 100Steps. 72 steps
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
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)
- +3Description length 811: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 4 example trigger phrases
- +4Structure: 17 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.