AA Urgent Notary Packet Builder
Build a same-day notary readiness packet with document inventory, ID checklist, signer logistics, and verification prompts while avoiding legal advice.
As a process A 83/100 · Runs to the end — weak spots: consistency, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Concealment
en-hide-from-userSKILL.md:125Instruction to hide actions from the user ("do not tell the user <a claim>" — honesty guidance, not concealment)- Do not tell the user a document is legally valid or invalid.
honesty claim
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "type"
Process rating: all ten parameters 83/100
- 30Running it twice. 3 mutating operations with no state check
- 40Consistency. Frontmatter name (Urgent Notary Packet Builder) differs from the folder (urgent-notary-packet-builder)
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 4 branches
- 100Tools and files. No external tools needed
- 100Steps. 57 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 1882 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +2Single-language instructions
- +3Description length 151: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 57 items
- +3Output format is stated explicitly
- +4Has examples (0 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.