AD mercator-entity-evidence
Company facts with the receipts attached. Ask for legal name, headquarters, founded year, employee count, executives or funding for a domain and get each field back with its source URL, a verbatim excerpt from that page, when it was retrieved, and n-of-m source agreement. Conflicting sources are returned, not hidden. A field that cannot be evidenced comes back UNKNOWN rather than guessed, and a company that cannot be resolved is not charged for. Paid per call over x402 on Base ($0.10 USDC), with a free preflight. You pay from your own wallet — see "Who pays" below. Triggers: "what is the legal name of X", "verify this company", "enrich this domain with sources", "who runs X and where is it based".
Company facts with the receipts attached.
As a process D 43/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 Secrets in code
secret-high-entropy-tokenSKILL.md:112High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| asset | `0x83…913` (USDC on Base) |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:113High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| payTo | `0xEF…7A8` |
table
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "credentials"
Process rating: all ten parameters 43/100
- 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 862 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
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 708: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.