Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Operate Moralis EVM wallet and token reads through UXC with a curated OpenAPI schema, API-key auth, and wallet-intelligence guardrails.
.claude/skills/leoyeai-moralis-openapi-skill/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 8% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 15% | 0% |
Use this skill to run Moralis EVM data operations through uxc + OpenAPI.
Reuse the uxc skill for shared execution, auth, and error-handling guidance.
uxc is installed and available in PATH.https://deep-index.moralis.io/api/v2.2.https://raw.githubusercontent.com/holon-run/uxc/main/skills/moralis-openapi-skill/references/moralis-evm.openapi.jsonThis skill covers a read-first wallet intelligence surface:
This skill does not cover:
Moralis uses X-API-Key header auth.
Configure one API-key credential and bind it to deep-index.moralis.io/api/v2.2:
bashuxc auth credential set moralis \ --auth-type api_key \ --api-key-header X-API-Key \ --secret-env MORALIS_API_KEY uxc auth binding add \ --id moralis \ --host deep-index.moralis.io \ --path-prefix /api/v2.2 \ --scheme https \ --credential moralis \ --priority 100
Validate the active mapping when auth looks wrong:
bashuxc auth binding match https://deep-index.moralis.io/api/v2.2
command -v moralis-openapi-cliuxc link moralis-openapi-cli https://deep-index.moralis.io/api/v2.2 --schema-url https://raw.githubusercontent.com/holon-run/uxc/main/skills/moralis-openapi-skill/references/moralis-evm.openapi.json
moralis-openapi-cli -hmoralis-openapi-cli get:/{address}/balance -hmoralis-openapi-cli get:/wallets/{address}/tokens -hmoralis-openapi-cli get:/erc20/{address}/price -hmoralis-openapi-cli get:/{address}/balance address=0xd8da6bf26964af9d7eed9e03e53415d37aa96045 chain=ethmoralis-openapi-cli get:/erc20/{address}/price address=0xa0b86991c6218b36c1d19d4a2e9eb0ce3606eb48 chain=ethmoralis-openapi-cli get:/wallets/{address}/net-worth address=0xd8da6bf26964af9d7eed9e03e53415d37aa96045 chain=ethmoralis-openapi-cli get:/wallets/{address}/tokens address=0xd8da6bf26964af9d7eed9e03e53415d37aa96045 chain=ethmoralis-openapi-cli get:/wallets/{address}/history address=0xd8da6bf26964af9d7eed9e03e53415d37aa96045 chain=eth limit=20get:/{address}/balanceget:/wallets/{address}/tokensget:/wallets/{address}/historyget:/wallets/{address}/swapsget:/wallets/{address}/net-worthget:/erc20/metadataget:/erc20/{address}/price--text.ok, kind, protocol, data, error.chain explicitly instead of assuming Ethereum.moralis-openapi-cli <operation> ... is equivalent to uxc https://deep-index.moralis.io/api/v2.2 --schema-url <moralis_openapi_schema> <operation> ....references/usage-patterns.mdreferences/moralis-evm.openapi.json| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 10,725 | 6,247 | -42% | 1 | 1 | 0% | 741 | 1,783 | +141% | 0 | 0 | — |
case-02 | fail→fail | 14,222 | 8,010 | -44% | 1 | 1 | 0% | 2,745 | 1,742 | -37% | 0 | 0 | — |
case-03 | fail→fail | 15,109 | 6,152 | -59% | 1 | 1 | 0% | 3,156 | 1,530 | -52% | 0 | 0 | — |
case-04 | fail→pass | 14,414 | 2,580 | -82% | 1 | 1 | 0% | 2,339 | 1,815 | -22% | 0 | 0 | — |
case-05 | fail→pass | 14,763 | 4,137 | -72% | 1 | 1 | 0% | 2,650 | 2,068 | -22% | 0 | 0 | — |
case-06 | fail→pass | 8,907 | 2,620 | -71% | 1 | 1 | 0% | 1,515 | 1,631 | +8% | 0 | 0 | — |
case-07 | fail→pass | 7,046 | 2,724 | -61% | 1 | 1 | 0% | 1,336 | 1,771 | +33% | 0 | 0 | — |
case-08 | fail→pass | 9,836 | 5,453 | -45% | 1 | 1 | 0% | 2,050 | 2,349 | +15% | 0 | 0 | — |
case-09 | pass→pass | 12,138 | 4,051 | -67% | 1 | 1 | 0% | 1,697 | 1,897 | +12% | 0 | 0 | — |
case-10 | fail→pass | 7,554 | 2,388 | -68% | 1 | 1 | 0% | 1,424 | 1,709 | +20% | 0 | 0 | — |
case-11 | fail→pass | 14,630 | 5,382 | -63% | 1 | 1 | 0% | 2,537 | 2,466 | -3% | 0 | 0 | — |
case-12 | fail→pass | 11,238 | 4,886 | -57% | 1 | 1 | 0% | 2,360 | 2,145 | -9% | 0 | 0 | — |
case-13 | fail→pass | 14,992 | 5,004 | -67% | 1 | 1 | 0% | 2,777 | 2,377 | -14% | 0 | 0 | — |
case-14 | fail→pass | 10,909 | 3,529 | -68% | 1 | 1 | 0% | 2,151 | 2,098 | -2% | 0 | 0 | — |
case-15 | pass→fail | 10,754 | 6,308 | -41% | 1 | 1 | 0% | 2,367 | 1,708 | -28% | 0 | 0 | — |
case-16 | fail→pass | 13,034 | 3,308 | -75% | 1 | 1 | 0% | 2,072 | 1,875 | -10% | 0 | 0 | — |
case-17 | fail→pass | 10,038 | 2,086 | -79% | 1 | 1 | 0% | 1,603 | 1,626 | +1% | 0 | 0 | — |
case-18 | pass→pass | 11,572 | 5,255 | -55% | 1 | 1 | 0% | 1,784 | 2,360 | +32% | 0 | 0 | — |
case-19 | pass→pass | 11,150 | 3,018 | -73% | 1 | 1 | 0% | 1,774 | 1,770 | -0% | 0 | 0 | — |
case-20 | fail→pass | 11,210 | 3,593 | -68% | 1 | 1 | 0% | 1,757 | 1,988 | +13% | 0 | 0 | — |
case-21 | fail→pass | 11,319 | 6,619 | -42% | 1 | 1 | 0% | 2,558 | 2,662 | +4% | 0 | 0 | — |
case-22 | pass→pass | 9,040 | 4,055 | -55% | 1 | 1 | 0% | 1,841 | 1,973 | +7% | 0 | 0 | — |
case-23 | fail→pass | 14,271 | 8,831 | -38% | 1 | 1 | 0% | 2,811 | 2,834 | +1% | 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. 23 cases were attempted, and 19 counted toward the lift figure. The other 4 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +61 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.