safe

Create, manage, and execute Safe multisig transactions using the Safe{Core} SDK on EVM chains.

1|1|Updated May 21, 2026
One-click install
npx skills add https://github.com/naruto11eth/cryptoskills --skill safe-naruto11eth
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: safe
Source: https://github.com/naruto11eth/cryptoskills/tree/main/skills/safe
Command: npx skills add https://github.com/naruto11eth/cryptoskills --skill safe-naruto11eth

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents and developers frequently use outdated Safe SDK patterns (deprecated @gnosis.pm packages, removed EthersAdapter classes) and hallucinate contract addresses, which can lead to failed transactions or lost funds when working with Safe multisig wallets. ## Core Features & Use Cases - Safe Deployment & Prediction: Deploy new multisig Safes with deterministic counterfactual addresses using Protocol Kit v4+, including owner and threshold configuration. - Full Transaction Lifecycle: Create, propose, confirm, and execute multisig transactions through the Safe Transaction Service, including batch transactions via MultiSend and rejection flows. - Modules, Guards & ERC-7579: Enable and audit Safe modules, set transaction guards, and integrate ERC-7579 modular smart account features via the Safe7579 adapter. - Use Case: A DAO treasury team needs a 3-of-5 multisig. Use this Skill to deploy the Safe, propose an ERC-20 transfer, collect confirmations from owners, and execute it once the threshold is met. ## Quick Start Ask the agent to deploy a 2-of-3 Safe multisig on Ethereum mainnet and propose a 0.5 ETH transfer to a recipient address using the Safe Protocol Kit.

Frequently Asked Questions about safe

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create and deploy a Safe multisig wallet programmatically?

Use Safe.init from @safe-global/protocol-kit with a predictedSafe config containing owners, threshold, saltNonce, and safeVersion. Call getAddress to predict the counterfactual address, then createSafeDeploymentTransaction to deploy it on-chain.

How do I propose and execute a Safe multisig transaction?

Create the transaction with protocolKit.createTransaction, sign it with signTransaction, then propose it via apiKit.proposeTransaction. Other owners confirm with apiKit.confirmTransaction, and anyone executes with executeTransaction once the threshold is met.

What is the difference between Safe modules and guards?

Modules can execute transactions on behalf of the Safe without owner signatures, bypassing the threshold. Guards are hooks that run pre- and post-execution checks on every transaction for policy enforcement but cannot initiate transactions.

Why does my Safe transaction fail with GS013?

GS013 means execTransaction reverted, usually due to invalid signatures. Verify signatures are sorted by signer address ascending, the signer count meets the threshold, the nonce matches the on-chain nonce, and all signers are current owners.

Does the Safe SDK still use EthersAdapter or @gnosis.pm packages?

No. Protocol Kit v4+ removed EthersAdapter and Web3Adapter entirely. Use @safe-global/protocol-kit, @safe-global/api-kit, and @safe-global/relay-kit, passing a provider RPC URL and signer directly to Safe.init.

Are Safe contract addresses the same on all EVM chains?

Yes. Safe v1.4.1 uses the ERC-2470 singleton factory for deterministic deployment, so the singleton, proxy factory, and MultiSend addresses are identical across Ethereum, Arbitrum, Base, Optimism, Polygon, and other supported networks.