AB legal-page-discovery
Discover and classify a live website's legal/compliance pages — privacy policies, HIPAA/Part 2 notices, terms of use, informed consents, and similar documents — by triangulating sitemap.xml, robots.txt, footer/nav links scraped from multiple pages, and common compliance path-pattern guesses. Retrieves each candidate page's verbatim text via curl (not a summarizing fetch), classifies its content and controlling entity, flags nav-label/content/entity mismatches, and records open-ended salient observations grounded in the page's own language. Produces a manifest for downstream routing (e.g. by skill-router) — does not itself recommend which assessment skill to run.
Discover and classify a live website's legal/compliance pages — privacy policies, HIPAA/Part 2 notices, terms of use, informed consents, and similar documents…
As a process B 66/100 · Nearly there — weak spots: failures and branches, running it twice, progress reporting
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
- 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: Bash WebFetch WebSearch Read Write Glob Grep
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 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
- 70Execution cost. Instruction body is 4103 tokens
- 85Steps. 47 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 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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 670: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 47 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.