SKILLEMALL.ai

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.

ClawHub Agent Skills author: Giacomo Barbieri v1.13.0 MIT-0 2 files body ≈ 3 857 tokens Open the sourceclawhub.ai analyzed 3 d ago

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

IntegrationAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
75/100
safety, quality, tests
Safety 60%
94
Quality 40%
47
Run on models
none yet
Process rating
F
44/100
Will not run
References files that are not bundled: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Shorten the description to 1024 characters.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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-secrets SKILL.md:43
    Handles 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-token SKILL.md:332
    High-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-token SKILL.md:353
    High-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-token SKILL.md:400
    High-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-token SKILL.md:401
    High-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-token SKILL.md:402
    High-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-long description is 1878 chars, limit 1024
  • warning missing-ref reference to a missing file: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md
  • note description-budget description takes 1878 of the ~15000-char shared budget for all skills

Process rating: all ten parameters 44/100

Will not run. References files that are not bundled: /Users/jaack/Desktop/Github/evalanche/docs/live-smoke-checklist.md
  • 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.

External checks

ClawHub: suspicious
This is a disclosed autonomous wallet skill, but it exposes high-impact financial signing and trading powers with weak scoping and risky installation/runtime trust boundaries.
LLM: suspicious (high) · 7 Sept 2026