Index of every page on this site: llms.txt
All skills
base avatar

/build-on-base

@ef8bcd5 official
by basebase/skills120 stars
130
Run it yourself

Complete Base development playbook. Covers: (1) Network — Base RPC URLs, chain IDs (8453/84532), explorer config, testnet setup, connect to Base, Base Sepolia; (2) Contracts — Foundry deployment, forge create, BaseScan verification, CDP faucet, testnet ETH, deploy contract to Base; (3) Builder Codes — ERC-8021 attribution suffix, referral fees, dataSuffix for Wagmi/Viem/Privy/ ethers.js/window.ethereum, transaction attribution, earn referral fees, append builder code; (4) Agent registration — trading bots, AI agents, automated senders, ERC-8021 attribution wiring, base.dev API, register agent, builder code registration; (5) Node operation — run Base node, Reth setup, hardware requirements, self-hosted RPC, sync.

Use this Skill: https://skilld.dev/gh/base/skills/build-on-base

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈187 tokens for metadata: the name and description. ≈611 when used: this file. ≈7.9k more on demand in 10 files.

Description uses 9.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈737 characters, or 9.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Base Development

Complete playbook for building on Base L2 — network setup, smart contracts, developer tool attribution, agent registration, and node operation.

Default Stack

Layer Default
Network Base Mainnet (8453) / Base Sepolia testnet (84532)
Contracts Foundry (forge create + BaseScan verification)
Transactions wagmi + viem
Attribution Builder Codes — ERC-8021 via ox/erc8021
RPC (prod) Dedicated node provider or self-hosted Reth

Safety Guardrails

  • Never commit private keys — use cast wallet import for Foundry keystores
  • Never expose RPC API keys or CDP credentials client-side — proxy through backend
  • Never send transactions without Builder Code attribution — silent data loss, no errors, no warnings
  • Validate all user-provided shell inputs before constructing forge/cast commands (no spaces, semicolons, pipes)

Task Routing

Read the reference for your task:

Task When to Use Reference
Network config RPC URLs, chain IDs, explorer links, testnet setup references/network.md
Deploy contracts Foundry deployment, BaseScan verification, faucet references/deploy-contracts.md
Run a Base node Self-hosted RPC, Reth, hardware requirements references/run-node.md
Builder Codes Add ERC-8021 attribution to transactions references/builder-codes/overview.md
Register AI agent/bot Register wallet, get builder code, wire attribution references/agents/register.md

Operating Procedure

  1. Classify the task using the table above
  2. Read the relevant reference before implementing
  3. Confirm the framework with the user when multiple options exist (e.g., Privy vs wagmi for Builder Codes)
  4. Implement with explicit chain ID, security requirements, and all required validations
  5. Deliver diffs, install commands, and any manual steps (env vars, API key setup, wallet registration)

For Edge Cases and Latest API Changes

Installation

npx skills add base/skills --skill build-on-base

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No alerts1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill is a development playbook for the Base network that includes scripts for project analysis and wallet registration. It contains behavioral instructions that guide the agent through specific workflows and set mandatory rules for transaction attribution.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

Provenance

Signed by skilld at ef8bcd5. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Activeupdated last month

Topics

  • base
  • l2
  • ethereum
  • smart-contracts
  • foundry
  • wagmi
  • viem
  • wallet-auth
  • payments
  • usdc
  • erc-8021
  • basescan
  • node-operation

README badge

README badge for base/skills/build-on-base

What it does

Instructs Claude to deploy and build applications on Base L2, covering network setup (RPC/chain IDs), contract deployment with Foundry, wallet authentication via Base Account SDK, USDC payments, ERC-8021 builder code attribution, and migrations from OnchainKit or Farcaster MiniKit. Includes safety guardrails for private keys, payment verification, and transaction attribution.

Generated from the current SKILL.md.

Frequently asked

Does this skill cover both Base Mainnet and testnet setup?
Yes. It includes network configuration for Base Mainnet (chain ID 8453) and Base Sepolia testnet (84532), with RPC URLs, explorer config, and testnet ETH faucet setup.
What contract deployment tools does this skill use?
Foundry — specifically `forge create` for deployment and BaseScan verification. It does not cover Hardhat or other frameworks.
Does this skill include payment and wallet authentication?
Yes. It covers Base Account SDK for Sign in with Base (SIWB), Base Pay for USDC transactions, gasless payments, paymasters, and sub-accounts with spend permissions.
Can this skill help migrate from OnchainKit?
Yes. It includes step-by-step migration paths from OnchainKit to wagmi, and separate guides for migrating MiniKit to Farcaster SDK and converting Farcaster miniapps to regular Base apps.
Does this skill cover AI agent and trading bot registration?
Yes. It includes agent registration with ERC-8021 attribution wiring, builder code registration, and base.dev API integration for automated senders and trading bots.

Generated from the current SKILL.md. These answers refresh after source changes.