Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create a minimal Alchemy Web3 example: get ETH balance, fetch NFTs, read token balances. Use when starting blockchain development, testing Alchemy setup, or learning basic blockchain query patterns. Trigger: "alchemy hello world", "alchemy example", "alchemy quick start", "get ETH balance", "fetch NFTs alchemy".
.claude/skills/jeremylongshore-alchemy-hello-world/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 23% | 0% |
| case-02 | ✓→✗ | ▼ Worse | 59% | 0% |
| case-03 | ✓→✓ | = Same ✓ | 68% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 210% | 0% |
| case-05 | ✓→✓ | = Same ✓ | 93% | 0% |
Build a minimal, reviewable Alchemy EVM read with viem and prove its network, authentication, and failure behavior. This workflow produces a reviewable artifact and negative-path evidence before any live side effect.
The current Ethereum quickstart uses viem. A successful eth_blockNumber proves endpoint connectivity only; it does not prove Enhanced API, NFT API, Portfolio, Wallet API, or Admin entitlement. Chain identity must be checked from the response context rather than assumed from an endpoint string.
Use a development application key through the repository's approved server-side secret boundary. Never print the URL when it contains a credential. A browser proof requires the allowlist or short-lived-JWT protections documented in the approved threat model.
viem release and preserve the lockfile review; do not add alchemy-sdk.Use Read, Glob, and Grep to inspect current documentation, configuration, code, fixtures, and evidence. Use Write and Edit only for approved repository artifacts. Skill invocation alone does not authorize network access, credentials, wallet addresses, customer data, plan changes, spend, key creation or rotation, webhook changes, deployment, replay, transaction construction, signing, broadcast, or deletion.
Read-only development proof needs the application owner's scoped key. Installing a dependency follows repository review. Any transaction, wallet connection, browser credential, or production call is outside this skill and requires separate approval.
401 or 403 as a credential or policy failure, not as a reason to broaden access.429 and provider 5xx with a bounded retry budget; never loop until success.Return the chosen chain, current source links, dependency decision, minimal viem client, chain-ID assertion, redacted positive and negative test receipts, and rollback command. Mark assumptions, observations, source dates, environment-specific behavior, owners, and unresolved gaps explicitly.
Exercise and record expected and observed results for:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 10,118 | 6,460 | -36% | 1 | 1 | 0% | 2,186 | 2,695 | +23% | 0 | 0 | — |
case-02 | pass→fail | 7,308 | 5,239 | -28% | 1 | 1 | 0% | 1,577 | 2,502 | +59% | 0 | 0 | — |
case-03 | pass→pass | 6,932 | 5,628 | -19% | 1 | 1 | 0% | 1,482 | 2,497 | +68% | 0 | 0 | — |
case-04 | pass→pass | 2,713 | 1,796 | -34% | 1 | 1 | 0% | 510 | 1,582 | +210% | 0 | 0 | — |
case-05 | pass→pass | 5,704 | 4,389 | -23% | 1 | 1 | 0% | 1,138 | 2,196 | +93% | 0 | 0 | — |
case-06 | pass→pass | 8,446 | 6,178 | -27% | 1 | 1 | 0% | 1,757 | 2,560 | +46% | 0 | 0 | — |
case-07 | pass→pass | 9,865 | 6,586 | -33% | 1 | 1 | 0% | 2,064 | 2,509 | +22% | 0 | 0 | — |
case-08 | fail→fail | 8,559 | 5,969 | -30% | 1 | 1 | 0% | 1,628 | 2,312 | +42% | 0 | 0 | — |
case-09 | pass→pass | 6,798 | 2,862 | -58% | 1 | 1 | 0% | 1,362 | 1,808 | +33% | 0 | 0 | — |
case-14 | pass→pass | 5,044 | 4,113 | -18% | 1 | 1 | 0% | 877 | 1,968 | +124% | 0 | 0 | — |
case-10 | pass→pass | 8,528 | 4,620 | -46% | 1 | 1 | 0% | 1,699 | 2,050 | +21% | 0 | 0 | — |
case-11 | pass→pass | 7,087 | 2,878 | -59% | 1 | 1 | 0% | 1,276 | 1,773 | +39% | 0 | 0 | — |
case-12 | pass→pass | 2,985 | 2,618 | -12% | 1 | 1 | 0% | 551 | 1,779 | +223% | 0 | 0 | — |
case-13 | pass→pass | 11,437 | 7,403 | -35% | 1 | 1 | 0% | 2,118 | 2,708 | +28% | 0 | 0 | — |
case-15 | pass→pass | 2,245 | 1,394 | -38% | 1 | 1 | 0% | 383 | 1,467 | +283% | 0 | 0 | — |
case-16 | pass→pass | 5,454 | 10,670 | +96% | 1 | 1 | 0% | 1,066 | 3,404 | +219% | 0 | 0 | — |
case-17 | pass→pass | 4,828 | 2,962 | -39% | 1 | 1 | 0% | 879 | 1,832 | +108% | 0 | 0 | — |
case-18 | pass→pass | 5,501 | 2,551 | -54% | 1 | 1 | 0% | 1,064 | 1,743 | +64% | 0 | 0 | — |
case-19 | pass→pass | 7,395 | 4,113 | -44% | 1 | 1 | 0% | 1,607 | 2,205 | +37% | 0 | 0 | — |
case-20 | fail→fail | 13,103 | 10,883 | -17% | 1 | 1 | 0% | 2,736 | 3,684 | +35% | 0 | 0 | — |
case-21 | pass→pass | 6,482 | 7,019 | +8% | 1 | 1 | 0% | 1,364 | 2,748 | +101% | 0 | 0 | — |
case-22 | pass→pass | 6,754 | 6,710 | -1% | 1 | 1 | 0% | 1,386 | 2,723 | +96% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of 0 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The publisher has shipped newer versions since this run, so these numbers describe v1, not the version currently listed.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.