Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Crypto wallet management across 7 blockchains via EmblemAI Agent Hustle API. Balance checks, token swaps, portfolio analysis, and transaction execution for Solana, Ethereum, Base, BSC, Polygon, Hedera, and Bitcoin.
.claude/skills/emblemai-crypto-wallet/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-15 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-16 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-17 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-18 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-20 | ✗→✓ | ▲ Improved | -22% | 0% |
You manage crypto wallets through the EmblemAI Agent Hustle API. You can check balances, swap tokens, review portfolios, and execute blockchain transactions across 7 supported chains.
Install the full skill with references and scripts:
bashnpx skills add EmblemCompany/Agent-skills --skill emblem-ai-agent-wallet
Or install the npm package directly:
bashnpm install @emblemvault/agentwallet
| Chain | Operations | |-------|-----------| | Solana | Balance, swap, transfer, token lookup | | Ethereum | Balance, swap, transfer, NFT | | Base | Balance, swap, transfer | | BSC | Balance, swap, transfer | | Polygon | Balance, swap, transfer | | Hedera | Balance, transfer | | Bitcoin | Balance, transfer |
Base URL: https://api.agenthustle.ai
Authentication requires an API key passed as x-api-key header.
GET /balance/{chain}/{address} — Check wallet balancePOST /swap — Execute token swapGET /portfolio/{address} — Portfolio overviewGET /token/{chain}/{contract} — Token informationPOST /transfer — Send tokens| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-15 | fail→pass | 7,340 | 1,654 | -77% | 1 | 1 | 0% | 1,293 | 809 | -37% | 0 | 0 | — |
case-16 | fail→pass | 6,114 | 1,652 | -73% | 1 | 1 | 0% | 1,184 | 769 | -35% | 0 | 0 | — |
case-17 | fail→pass | 9,079 | 1,221 | -87% | 1 | 1 | 0% | 1,644 | 785 | -52% | 0 | 0 | — |
case-18 | fail→pass | 8,460 | 1,998 | -76% | 1 | 1 | 0% | 1,224 | 864 | -29% | 0 | 0 | — |
case-19 | fail→fail | 11,420 | 2,171 | -81% | 1 | 1 | 0% | 1,858 | 877 | -53% | 0 | 0 | — |
case-20 | fail→pass | 6,511 | 1,911 | -71% | 1 | 1 | 0% | 1,091 | 847 | -22% | 0 | 0 | — |
case-21 | fail→pass | 8,696 | 1,746 | -80% | 1 | 1 | 0% | 1,359 | 850 | -37% | 0 | 0 | — |
case-22 | fail→fail | 16,832 | 21,512 | +28% | 1 | 1 | 0% | 4,331 | 5,223 | +21% | 0 | 0 | — |
case-23 | fail→fail | 12,269 | 7,475 | -39% | 1 | 1 | 0% | 2,473 | 2,149 | -13% | 0 | 0 | — |
case-24 | fail→fail | 14,486 | 8,434 | -42% | 1 | 1 | 0% | 2,949 | 2,362 | -20% | 0 | 0 | — |
case-01 | fail→pass | 9,704 | 8,985 | -7% | 1 | 1 | 0% | 1,825 | 2,345 | +28% | 0 | 0 | — |
case-02 | fail→pass | 16,214 | 8,556 | -47% | 1 | 1 | 0% | 2,150 | 2,451 | +14% | 0 | 0 | — |
case-03 | fail→pass | 10,206 | 7,863 | -23% | 1 | 1 | 0% | 1,965 | 2,281 | +16% | 0 | 0 | — |
case-04 | fail→pass | 6,055 | 1,676 | -72% | 1 | 1 | 0% | 935 | 863 | -8% | 0 | 0 | — |
case-05 | fail→pass | 7,379 | 4,363 | -41% | 1 | 1 | 0% | 1,554 | 1,432 | -8% | 0 | 0 | — |
case-06 | fail→pass | 7,066 | 3,985 | -44% | 1 | 1 | 0% | 1,532 | 1,320 | -14% | 0 | 0 | — |
case-07 | fail→fail | 8,936 | 2,536 | -72% | 1 | 1 | 0% | 1,567 | 994 | -37% | 0 | 0 | — |
case-08 | fail→pass | 11,698 | 2,305 | -80% | 1 | 1 | 0% | 1,787 | 958 | -46% | 0 | 0 | — |
case-09 | fail→pass | 6,518 | 1,689 | -74% | 1 | 1 | 0% | 1,027 | 793 | -23% | 0 | 0 | — |
case-10 | fail→fail | 12,881 | 3,511 | -73% | 1 | 1 | 0% | 2,564 | 1,184 | -54% | 0 | 0 | — |
case-11 | fail→pass | 6,547 | 2,666 | -59% | 1 | 1 | 0% | 1,294 | 1,155 | -11% | 0 | 0 | — |
case-12 | fail→fail | 9,830 | 2,530 | -74% | 1 | 1 | 0% | 1,630 | 1,058 | -35% | 0 | 0 | — |
case-13 | fail→pass | 9,036 | 4,282 | -53% | 1 | 1 | 0% | 1,975 | 1,232 | -38% | 0 | 0 | — |
case-14 | fail→pass | 7,220 | 1,468 | -80% | 1 | 1 | 0% | 1,237 | 776 | -37% | 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. 24 cases were attempted. The headline lift of +71 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is 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.