AB deep-validator
Validate email addresses and URLs with real network checks (DNS MX, DNSBL, disposable domain detection, HTTP reachability, redirect chain tracing). Use whenever you need to confirm that an email or URL is genuinely real and reachable, not just syntactically correct. This API does what you cannot do natively as a language model: it reaches out to the actual internet. Free tier: 10 validations/day and 1 000 classify items/day per IP. Beyond quota: $0.0005/item (validate) or $0.00005/item (classify), settled via dual payment rail — x402 (USDC on Base) or MPP (Tempo stablecoin). Free cost quote on every endpoint before any charge is committed.
As a process B 77/100 · Nearly there — weak spots: inputs and preconditions, 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Exfiltration
read-dotenvREADME.md:170Reads a .env filecp .env.example .env
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9346 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 77/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 17 mutating operations with no state check
- 40Execution cost. Instruction body is 9346 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 50 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 12 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
- low The response is described with custom markup (6 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)
- +2Single-language instructions
- +3Description length 647: enough signal without eating the budget
- +4Structure: 49 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
- +4Has examples (15 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.