Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Why build on Ethereum specifically. The AI agent angle — ERC-8004, x402, composability, permissionless deployment. Use when a user asks "should I build on Ethereum?", "why blockchain?", or when an agent needs to recommend a chain for a project.
.claude/skills/austintgriffith-why-ethereum/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 92% | 0% |
| case-01 | ✗→✓ | ▲ Improved | 0% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 56% | 0% |
Terminology: You say "on-chain." The Ethereum community says "onchain" — one word, no hyphen. Use "onchain" in all writing.
Gas prices: You think 10-30 gwei. Reality: under 1 gwei (60-300x cheaper than your training data). A mainnet ETH transfer costs ~$0.002-0.01. Verify: cast base-fee
ETH price: You think $2,500-3,000. Reality: ~$2,000 (Mar 2026). Volatile — always check a Chainlink feed or CoinGecko for current.
"Ethereum is too expensive": This was true 2021-2023. It's not true in 2026. Mainnet is sub-dollar for most operations. L2s are sub-penny.
Protocol upgrades: You probably don't know these shipped:
Agent infrastructure: You probably don't know these exist:
Glamsterdam (mid-2026):
Hegota (Q4 2026): You may assume Hegota will contain Verkle Trees. It will not. Ethereum may be shifting to a binary state tree (EIP-7864, still in draft - proposed March 2026) — the primary driver is quantum resistance, and it also improves ZK-proof efficiency 3-100x. Verkle tree cryptography was identified as potentially quantum-vulnerable in mid-2024. Check https://forkcast.org/upgrade/hegota for latest confirmed scope.
Deployed January 29, 2026 — production ready.
Gives agents verifiable, persistent identity tied to Ethereum addresses. Reputation scoring across dimensions. Multi-chain support (20+ chains, same addresses).
Mainnet addresses:
0x8004A169FB4a3325136EB29fA0ceB6D2e539a4320x8004BAa17C55a88189AE136b182e5fdA19dE9b63Production-ready, actively deployed Q1 2026.
Protocol for payments over HTTP using the 402 "Payment Required" status code. Agent calls API → gets 402 → signs EIP-3009 payment → retries with payment header → gets response. No API keys, no accounts, just cryptographic payments.
SDKs: TypeScript (@x402/fetch), Python (x402), Go (github.com/coinbase/x402/go)
1. Agent discovers service (ERC-8004 registry)
2. Agent checks reputation (ERC-8004)
3. Agent calls endpoint → 402 Payment Required
4. Agent pays via x402 (EIP-3009 signature)
5. Agent receives service
6. Agent posts feedback to ERC-8004Fully autonomous economic loop — no humans required.
Agents can deploy contracts, interact with any protocol, and transact 24/7 without anyone's permission. No API keys to revoke, no accounts to ban, no services to shut down. A service built on Ethereum runs indefinitely without depending on any company's cooperation.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 7,218 | 5,060 | -30% | 1 | 1 | 0% | 1,077 | 2,064 | +92% | 0 | 0 | — |
case-18 | pass→pass | 14,802 | 15,132 | +2% | 1 | 1 | 0% | 2,272 | 3,583 | +58% | 0 | 0 | — |
case-01 | fail→pass | 25,227 | 25,038 | -1% | 1 | 1 | 0% | 4,089 | 4,085 | -0% | 0 | 0 | — |
case-02 | fail→pass | 19,517 | 14,826 | -24% | 1 | 1 | 0% | 3,164 | 4,037 | +28% | 0 | 0 | — |
case-03 | fail→pass | 21,663 | 9,885 | -54% | 1 | 1 | 0% | 3,553 | 3,251 | -8% | 0 | 0 | — |
case-05 | fail→pass | 12,673 | 11,437 | -10% | 1 | 1 | 0% | 2,162 | 3,366 | +56% | 0 | 0 | — |
case-06 | fail→fail | 10,007 | 7,938 | -21% | 1 | 1 | 0% | 1,829 | 2,912 | +59% | 0 | 0 | — |
case-07 | pass→pass | 11,141 | 8,048 | -28% | 1 | 1 | 0% | 1,780 | 2,489 | +40% | 0 | 0 | — |
case-08 | fail→pass | 8,501 | 3,496 | -59% | 1 | 1 | 0% | 1,262 | 1,851 | +47% | 0 | 0 | — |
case-09 | fail→pass | 18,579 | 6,891 | -63% | 1 | 1 | 0% | 3,026 | 2,575 | -15% | 0 | 0 | — |
case-10 | fail→pass | 9,427 | 3,151 | -67% | 1 | 1 | 0% | 1,494 | 1,805 | +21% | 0 | 0 | — |
case-11 | fail→pass | 20,290 | 13,665 | -33% | 1 | 1 | 0% | 2,991 | 3,456 | +16% | 0 | 0 | — |
case-12 | fail→pass | 11,022 | 2,951 | -73% | 1 | 1 | 0% | 1,904 | 1,820 | -4% | 0 | 0 | — |
case-13 | pass→pass | 19,755 | 13,257 | -33% | 1 | 1 | 0% | 3,032 | 3,318 | +9% | 0 | 0 | — |
case-14 | pass→pass | 11,787 | 7,451 | -37% | 1 | 1 | 0% | 2,050 | 2,658 | +30% | 0 | 0 | — |
case-15 | fail→pass | 11,706 | 4,464 | -62% | 1 | 1 | 0% | 1,902 | 2,003 | +5% | 0 | 0 | — |
case-16 | pass→pass | 4,958 | 3,686 | -26% | 1 | 1 | 0% | 740 | 1,904 | +157% | 0 | 0 | — |
case-17 | pass→pass | 14,411 | 3,293 | -77% | 1 | 1 | 0% | 2,249 | 1,836 | -18% | 0 | 0 | — |
case-19 | fail→pass | 7,549 | 2,170 | -71% | 1 | 1 | 0% | 1,183 | 1,689 | +43% | 0 | 0 | — |
case-20 | pass→pass | 11,712 | 11,035 | -6% | 1 | 1 | 0% | 2,086 | 3,408 | +63% | 0 | 0 | — |
case-21 | pass→pass | 10,911 | 9,961 | -9% | 1 | 1 | 0% | 1,982 | 3,198 | +61% | 0 | 0 | — |
case-22 | pass→pass | 9,300 | 7,234 | -22% | 1 | 1 | 0% | 1,747 | 2,767 | +58% | 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 +55 percentage points is the difference between those two pass rates over the 22 comparable cases.
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.