BF evalanche
Multi-EVM agent wallet SDK with onchain identity (ERC-8004), payment rails (x402), cross-chain liquidity (Li.Fi bridging + DEX aggregation + DeFi Composer), destination gas funding (Gas.zip), perpetual futures trading (dYdX v4), market intelligence (CoinGecko), prediction markets (Polymarket CLOB), and DeFi operations (liquid staking + EIP-4626 vaults). Supports 22+ EVM chains: Ethereum, Base, Arbitrum, Optimism, Polygon, BSC, Avalanche, and more. Agents generate and manage their own keys — no human input required. Use when: booting an autonomous agent wallet on any EVM chain, sending tokens, calling contracts, resolving agent identity, checking reputation, making x402 payment-gated API calls, bridging tokens cross-chain (Li.Fi), same-chain DEX swaps (31+ aggregators via Li.Fi), one-click DeFi operations (Composer: bridge + deposit into Morpho/Aave/Pendle/Lido/etc), tracking cross-chain transfer status, discovering tokens and prices across chains, querying gas prices, finding available bridges and DEX aggregators, funding gas on destination chains (Gas.zip), cross-chain transfers (Avalanche C↔X↔P), delegating stake, querying validators, signing messages, creating subnets, managing L1 validators, adding validators with BLS keys, querying node info, trading perpetual futures on dYdX v4 (100+ markets), searching for perp markets across venues, querying CoinGecko market data, searching Polymarket markets and order books, buying or selling Polymarket outcome shares on Polygon, staking/unstaking sAVAX via Benqi, depositing/withdrawing from EIP-4626 vaults (yoUSD, Morpho, Aave, etc), and resolving known Avalanche/Base DeFi contracts with canonical chain routing or interoperable-address inputs. Don't use when: managing ENS (use moltbook scripts). Network: yes (EVM RPCs via Routescan + public fallbacks, dYdX Cosmos chain). Cost: gas fees per transaction.
As a process F 44/100 · Will not run — References files that are not bundled: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md
How to improve
- Shorten the description to 1024 characters.
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 6
✓ No critical or high findings
Medium and low: 6
-
low Risky intent
intent-wallet-secretsSKILL.md:43Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)"description": "BIP-39 mnemonic phrase (required for Avalanche multi-VM X/P-Chain). Optional if using boot() or AGENT_PRIVATE_KEY.",
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:332High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)toToken: '0x83…913',
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:353High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)agent.getToken(8453, '0x83…913')
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:400High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Identity Registry | `0x80…432` | AVAX C-Chain (43114) |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:401High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Reputation Registry | `0x80…b63` | AVAX C-Chain (43114) |
table -
low Secrets in code
secret-high-entropy-tokenSKILL.md:402High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| sAVAX (Benqi) | `0x2b…4bE` | AVAX C-Chain (43114) |
table
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1878 chars, limit 1024 - warning
missing-refreference to a missing file: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md - note
description-budgetdescription takes 1878 of the ~15000-char shared budget for all skills
Process rating: all ten parameters 44/100
- 0Tools and files. 1 referenced file(s) missing: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3857 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1877: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 41 headings
- +3Step-by-step instructions: 35 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 47.