AB lobstercash
Use this skill when the user wants to spend money, make purchases, send crypto, pay for APIs, browse websites for shopping, complete checkout, or manage an AI agent's payment wallet. Covers buying products online with credit cards (with browser-automated checkout when available, or driven by the agent's own browser tooling otherwise), sending tokens, paying for x402 protocol APIs, checking balances, depositing funds, browsing available services, and signing on-chain transactions — all with secure guardrails, and appropriate human controls. Trigger on any spending, wallet, or shopping intent: "buy this", "pay for that", "send tokens", "how much do I have", "what can I buy", "top up my wallet", "get a card", "set up payments", "find me something to buy", "complete the checkout", or "browse that site" — even if the user doesn't mention "lobster", "crypto", or "Solana" directly.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions
How to improve
- 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: 16. 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 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 28 branches
- 85Steps. 51 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3787 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (8 tags): a typed call is more reliable
- medium 3 test cases, all positive: not one "should refuse" or "should ask first"
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)
- +3Description length 887: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 14 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 51 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (14 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.