AC data-privacy-law-explainer
Explain U.S. state-by-state consumer data-privacy law (CCPA/CPRA, TDPSA, VCDPA, CPA, and the other comprehensive state acts) — who a law covers, applicability thresholds, privacy-policy requirements, consumer rights and opt-outs, private rights of action, and who enforces. Reads a bundled, source-cited snapshot per state. Use when the user says "CCPA," "CPRA," "state privacy law," "privacy policy," "data subject request," "consumer rights request," "opt-out of sale," "data broker," "sensitive data," asks "do I need to comply with <state>'s privacy law," or names a U.S. state together with privacy.
Explain U.S. state-by-state consumer data-privacy law (CCPA/CPRA, TDPSA, VCDPA, CPA, and the other comprehensive state acts) — who a law covers, applicability…
As a process C 55/100 · 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 · 2
✓ No critical or high findings
Medium and low: 2
-
low Risky intent
intent-offensive-securitycontent/north-dakota.md:75Offensive-security / dual-use content (legitimate for authorised testing; review intended use)The chapter is built on the model of the federal GLBA Safeguards Rule, which likewise requires designating a qualified individual to oversee, implement, and enforce the information security program [^
-
low Risky intent
intent-offensive-securitycontent/north-dakota.md:145Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)[^stat…ing]: **N.D. Cent. Code § 13-01.2-03(6)** — "Information systems monitoring and testing must include continuous monitoring or periodic penetration testing, and vulnerability assessm
detector
Files scanned: 55. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "catalog_group" - note
frontmatter-keyunknown frontmatter key "catalog_order"
Process rating: all ten parameters 55/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 23 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1156 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)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 604: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 23 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.