BC part-2-notice-assessment
Public-document assessment for substance use disorder (SUD) treatment programs subject to 42 CFR Part 2. Reads only a program's publicly posted "Notice to patients of Federal confidentiality requirements" (the Part 2 notice, which §2.22(c)(3)(i) requires a program with a website to post) and checks it against the enumerated required content of §2.22(b). Produces a coverage map keyed to each required element, each gap cited at both ends, framed as a public-documentation gap a patient or an auditor would find on the face of the posted notice. Self-contained: the regulatory text it checks against is included below.
Public-document assessment for substance use disorder (SUD) treatment programs subject to 42 CFR Part 2.
As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, execution cost
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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Bash
Files scanned: 0. 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 substance use disorder (SUD) treatm… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 8963 tokens (recommended < 5000); move details to references/
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
- 30Running it twice. 5 mutating operations with no state check
- 40Execution cost. Instruction body is 8963 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
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 44 steps
- 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 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
- +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 619: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.