Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →austintgriffith/qa
Pre-ship audit checklist for Ethereum dApps built with Scaffold-ETH 2. Give this to a separate reviewer agent (or fresh context) AFTER the build is complete.
Passed 18 of 21 test cases with the skill, and 11 of 21 without it.
and 9 more in the full report
8 fixed11 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our staking portal shows user balances formatted strictly as `1.5 ETH` and `5000 USDC`. Does displaying token balances without secondary fiat estimates meet QA requirements?
| Checked | Without skill | With skill |
|---|---|---|
| flags token balance displays missing USD equivalent estimates as a failure | Missed | Passed |
The instructions your model reads when the skill loads.
"The app deployed, so we are done." For SE2 builds, shipping includes UX correctness, metadata, RPC reliability, contract verification, and branding cleanup.
"The flow is obvious." If Connect, Network, Approve, and Action are not strictly one-at-a-time with proper pending states, users will make duplicate or failing transactions.
"SE2 defaults are fine in production." Default README/footer/title/favicon and default RPC fallbacks are template scaffolding, not production decisions.
"Pass means no console errors." QA pass/fail here is behavioral and user-facing: real wallet flow, mobile deep-link behavior, readable errors, and trust signals must be validated.
Give this to a fresh agent after the dApp is built. The reviewer should:
app/, components/, contracts/)Fetch crops/SKILL.md first and include a CROPS Review in the report. Simple apps can get a concise baseline review; apps with funds, approvals, custody, wallet permissions, L2/bridge flows, private user data, identity, stablecoins, admin powers, or hosted RPC/indexer/relayer/paymaster/frontend infrastructure need the full four-pillar review.
Open the app with NO wallet connected.
This is the most common AI agent mistake. Every stock LLM writes a <p>Please connect your wallet</p> instead of rendering <RainbowKitCustomConnectButton />.
The app must show exactly ONE primary button at a time, progressing through:
1. Not connected → Connect Wallet button
2. Wrong network → Switch to [Chain] button
test cases passed, vs 11 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.