BC ai-claims-assessment
Public-document assessment for healthcare-AI vendors. Reads only a company's public product pages, Terms of Service, and Privacy Policy, then finds where its stated use of AI on health data fails to reconcile across three sources — market claims, legal language, and HIPAA requirements. Produces a map of gaps, each cited at both ends, framed as a public-documentation gap a covered entity would hit during vendor review. Self-contained: the regulatory text it checks against is included below.
Public-document assessment for healthcare-AI vendors.
As a process C 64/100 · Has gaps — weak spots: failures and branches, execution cost, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: Public-document assessment for healthcare-AI vendors. Reads only a… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 8183 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 12 mutating operations with no state check
- 40Execution cost. Instruction body is 8183 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 32 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 494: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 32 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.