SKILLEMALL.ai
GitHub ↗ RU Sign in

AC evalanche

Multi-EVM agent wallet SDK with onchain identity (ERC-8004), payment rails (x402), cross-chain bridging (Li.Fi), and destination gas funding (Gas.zip). Supports 21+ 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), funding gas on destination chains (Gas.zip), cross-chain transfers (Avalanche C↔X↔P), delegating stake, querying validators, signing messages. Don't use when: trading on DEXes (use bankr), managing ENS (use moltbook scripts). Network: yes (EVM RPCs via Routescan + public fallbacks). Cost: gas fees per transaction.

modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 1 430 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Multi-EVM agent wallet SDK with onchain identity (ERC-8004), payment rails (x402), cross-chain bridging (Li.Fi), and destination gas funding (Gas.zip).…

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
97
Quality 40%
85
Run on models
none yet
Process rating
C
50/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • low Risky intent intent-wallet-secrets SKILL.md:32
      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:247
      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:248
      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

    Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 50/100

    • 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
    • 30Running it twice. 4 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web) that frontmatter does not declare
    • 85Steps. 19 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1430 tokens
    • 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 851: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +4Structure: 28 headings
    • +3Step-by-step instructions: 19 items
    • +4Has examples (6 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.