AC shopify-batch-payouts
Pay Shopify affiliates, creators, suppliers, and vendors in USDC — N recipients in ONE transaction on Base, via the Spraay Protocol batch payment gateway. Use this skill whenever the user wants to pay multiple people from a Shopify store or any commerce context - affiliate payouts, creator payments, referral commissions, ambassador rewards, supplier invoices, revenue splits, or "mass payments" / "bulk payouts" in crypto or USDC. Also use when the user mentions Spraay, batch payments, batch payouts, paying a CSV of wallet addresses, or asks how to send crypto to many wallets at once. Even if the user doesn't say "Shopify" - any multi-recipient stablecoin payout task should use this skill.
Pay Shopify affiliates, creators, suppliers, and vendors in USDC — N recipients in ONE transaction on Base, via the Spraay Protocol batch payment gateway.
As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Secrets in code
secret-high-entropy-tokenSKILL.md:17High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Token | USDC on Base: `0x83…913` |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:18High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Batch contract (Base) | `0x16…eEC` (verified on BaseScan) |
table -
low Risky intent
intent-wallet-secretsSKILL.md:122Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)4. **Never handle private keys.** Spraay is non-custodial; if a workflow appears to require the user's private key or seed phrase, stop — that's wrong.
detector
Files scanned: 2. 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 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 16 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1661 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
- +1No license
- +2Single-language instructions
- +5Description quotes 3 example trigger phrases
- +3Description length 696: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 16 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.