BC web-compliance-builder
Classify a web business, then identify, draft, and checklist the compliance pages, notices, disclosures, user flows, and launch gates it needs. Use when the user wants a Privacy Policy, Cookie Policy / banner, Terms of Service, Refund/Return Policy, Shipping Policy, Subscription Terms, Acceptable Use Policy, DPA outline, Accessibility Statement, AI disclosure, children/age notice, marketing-consent language, marketplace seller terms, GDPR/UK-GDPR/PECR/CCPA/CPRA/PIPEDA/CASL/Australian Privacy Act compliance, App Store / Google Play / Shopify / ad-platform requirements, a website compliance requirements matrix, a launch/go-live checklist, or a red-flag report. Also audits existing sites (审计/review/合规检查): existing pages or a URL → gap report + fixes. Covers ecommerce, dropshipping, digital products, subscriptions, SaaS, app landing pages, marketplaces, affiliate/lead-gen, AI products, newsletters, and cross-border stores. Classifies first; never drafts generic policies blind. Not legal advice.
Classify a web business, then identify, draft, and checklist the compliance pages, notices, disclosures, user flows, and launch gates it needs.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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 Write Edit AskUserQuestion Bash Glob Grep
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 1005 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 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. 3 mutating operations with no state check
- 60Consistency. The Hermes dialect needs category and tags
- 70When it triggers. States when to use, but not when not to
- 85Steps. 64 steps, 1 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Execution cost. Instruction body is 2352 tokens
- 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)
- +3Description length 1005: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 15 headings
- +3Step-by-step instructions: 64 items
- +4Reference files are cited in the instructions (7 of 7)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.