AC scam-wallet-screener
Screens Ethereum and other EVM wallet addresses (Base, Polygon, BSC, Arbitrum, etc.) against the ScamSniffer community-maintained blocklist of known phishing, wallet drainer, and scam addresses, with no API key required. Use this when the user asks to check if a crypto address is a scam, verify a wallet before sending funds or signing a transaction, screen for wallet drainer addresses, check if an address is blacklisted or flagged for phishing, do a quick on-chain safety check before an airdrop claim or NFT mint, or wants a fast keyless scam address lookup tool. Pulls a public, actively updated JSON feed (~2,500+ known bad addresses) and caches it locally for 6 hours. Complements, but does not replace, deeper on-chain forensics or paid threat-intel services — a clean result means the address is not on this particular list, not that it is verified safe.
Screens Ethereum and other EVM wallet addresses (Base, Polygon, BSC, Arbitrum, etc.) against the ScamSniffer community-maintained blocklist of known phishing…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 · 0
✓ No critical or high findings
Files scanned: 4. 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 57/100
- 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. 1 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 9 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 547 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
- +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 864: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 4 headings
- +3Step-by-step instructions: 9 items
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.