Agent skill
use-algokit-utils
AlgoKit Utils library for interacting with the Algorand blockchain from TypeScript or Python applications. Use when connecting to Algorand networks (LocalNet, TestNet, MainNet), sending payments or transferring assets, creating and managing accounts, deploying or interacting with smart contracts from client code, or composing transaction groups. NOT for writing smart contract code (use build-smart-contracts skill). Strong triggers include "How do I connect to Algorand?", "send a payment transaction", "create an account", "deploy my contract", "get an AlgorandClient", "AlgorandClient.fromEnvironment".
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/use-algokit-utils
SKILL.md
AlgoKit Utils
Use AlgoKit Utils to interact with the Algorand blockchain from TypeScript or Python applications.
Overview / Core Workflow
- Create an
AlgorandClientinstance - Get or create accounts for signing
- Send transactions using
algorand.send.*methods - Or compose groups using
algorand.newGroup()
How to proceed
-
Initialize AlgorandClient:
TypeScript:
typescriptimport { AlgorandClient } from '@algorandfoundation/algokit-utils' const algorand = AlgorandClient.fromEnvironment() // Or: AlgorandClient.defaultLocalNet() // Or: AlgorandClient.testNet() // Or: AlgorandClient.mainNet()Python:
pythonfrom algokit_utils import AlgorandClient algorand = AlgorandClient.from_environment() # Or: AlgorandClient.default_localnet() # Or: AlgorandClient.testnet() # Or: AlgorandClient.mainnet() -
Get accounts:
TypeScript:
typescriptconst account = await algorand.account.fromEnvironment('DEPLOYER')Python:
pythonaccount = algorand.account.from_environment("DEPLOYER") -
Send transactions:
TypeScript:
typescriptawait algorand.send.payment({ sender: account.addr, receiver: 'RECEIVERADDRESS', amount: algo(1), })Python:
pythonalgorand.send.payment(PaymentParams( sender=account.address, receiver="RECEIVERADDRESS", amount=AlgoAmount(algo=1), ))
Important Rules / Guidelines
- Use AlgorandClient — It's the main entry point; avoid deprecated function-based APIs
- Default to fromEnvironment() — Works locally and in production via env vars
- Register signers — Use
algorand.accountto get accounts; signers are auto-registered - Use algo() helper — For TypeScript, use
algo(1)instead of raw microAlgos
Common Variations / Edge Cases
| Scenario | Approach |
|---|---|
| LocalNet development | AlgorandClient.defaultLocalNet() |
| TestNet/MainNet | AlgorandClient.testNet() or .mainNet() |
| Custom node | AlgorandClient.fromConfig({ algodConfig: {...} }) |
| Deploy contract | Use typed app client factory (see app-client docs) |
| Transaction groups | algorand.newGroup().addPayment(...).addAssetOptIn(...).send() |
References / Further Reading
Language-specific references are organized in subfolders:
- TypeScript (
references/typescript/): AlgorandClient - Python (
references/python/): AlgorandClient
External documentation:
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?