AC mercator-address-evidence
Before you send a transaction, check that the chain and contract address you are about to use is the one the entity actually publishes. Not a scam or rug assessment — provenance. You supply the entity, the chain and the candidate address; the answer is whether the entity's own source and an independent chain source support that exact claim, with the URL, the verbatim excerpt and a transact true/false. Disagreeing sources return no address at all. Paid per call over x402 on Base ($0.25 USDC), with a free preflight. You pay from your own wallet — see "Who pays" below. Triggers: "is this the official contract for X", "verify this address before I trade", "did X publish this address", "which chain is this contract on and who says it's theirs".
Before you send a transaction, check that the chain and contract address you are about to use is the one the entity actually publishes.
As a process C 51/100 · Has gaps — 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:90High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"address":"0x73…7bD",
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:99High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"address":"0x73…7bD",
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:127High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"address": "0x73…7bD",
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:186High-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:187High-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 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
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 10 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1657 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 3 example trigger phrases
- +3Description length 751: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 10 items
- +4Has examples (2 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.