Skip to main content

​
Overview

Goldsky Agent is a skill pack for AI coding assistants that helps you build, deploy, and debug Turbo pipelines that stream real-time blockchain data from 130+ chains into PostgreSQL, ClickHouse, Kafka, and more. Skills auto-trigger based on what you describe — no slash commands required. Interactive workflow skills walk you through multi-step tasks end-to-end. Reference skills provide YAML syntax, error patterns, and CLI commands on demand. Works with Claude Code, Cursor, Windsurf, OpenCode, Codex, and other AI coding assistants.

​
Quick Start

I want to…Use
Build a new pipeline/turbo-builder
Fix a broken pipeline/turbo-doctor
Find the right dataset name/datasets
Look up YAML syntax/turbo-pipelines
Check error patterns/turbo-monitor-debug
Just describe what you need in natural language — the right skill is selected automatically.

​
Installation

​
Available skills

​
Interactive skills

These guide you through multi-step tasks end-to-end:
SkillWhen to useWhat it does
turbo-builder”I want to build a pipeline for X”Guides you through chain → dataset → transforms → sink → validate → deploy
turbo-doctor”My pipeline is broken / not getting data / output looks wrong”Diagnoses the problem step-by-step and offers to run fixes
auth-setup”How do I install the CLI / log in?”Walks through CLI installation, login, and project switching
turbo-architecture”Should I use dataset or Kafka source? Fan-in or fan-out?”Helps make design decisions and choose architecture patterns
secrets”How do I create credentials for PostgreSQL / ClickHouse?”Guides you through creating and managing sink credentials

​
Reference skills

Look up syntax, rules, and examples without a guided workflow:
SkillWhen to useWhat’s inside
turbo-pipelines”What’s the YAML syntax for X?”Complete source/transform/sink field reference
turbo-transforms”How do I decode EVM logs / write a SQL transform?”SQL, TypeScript/WASM, dynamic tables, HTTP handlers
turbo-monitor-debug”How do I view logs? What does this error mean? TUI shortcuts?”CLI commands, log flags, TUI keys, error pattern lookup
turbo-lifecycle”How do I pause / restart / delete? Will delete lose my data?”Pause/resume/restart/delete rules, streaming vs job-mode differences
datasets”What’s the dataset name for Polygon NFTs?”Chain prefixes, dataset types, naming conventions

​
How it works

Skills are automatically discovered by your AI assistant and triggered based on what you describe. You don’t need to invoke them by name. 
User: "Build me a pipeline for USDC transfers on Base"
  ↓
turbo-builder  (auto-triggered)
  ↓ references
turbo-pipelines + datasets + secrets
  ↓
Generated pipeline.yaml + deployment
Interactive skills (turbo-builder, turbo-doctor) run as agents with access to CLI tools. Reference skills provide structured knowledge that the AI uses to answer questions or generate YAML.

​
Repository structure

goldsky-agent/
├── skills/              # All skills (auto-triggered by description matching)
│   ├── turbo-builder/         # Step-by-step pipeline creation wizard
│   ├── turbo-doctor/          # Diagnose and fix pipeline issues
│   ├── turbo-pipelines/       # YAML configuration reference
│   ├── turbo-transforms/      # SQL, TypeScript, dynamic tables
│   ├── turbo-monitor-debug/   # Error patterns, CLI commands
│   ├── turbo-lifecycle/       # List, pause, resume, delete
│   ├── turbo-architecture/    # Design patterns, sink selection
│   ├── datasets/              # Chain prefixes, dataset types
│   ├── secrets/               # Credential management
│   └── auth-setup/            # CLI installation, login
├── hooks/               # Pre/post deploy automation
│   └── scripts/               # Validation, secret checking
└── .claude-plugin/      # Plugin manifest

​
Pre-deploy hooks

When installed as a plugin, Goldsky Agent runs hooks automatically on goldsky turbo apply commands:
HookWhat it does
pre-deploy-validateRuns goldsky turbo validate, blocks on failure
secret-checkVerifies all secret_name references exist
post-deploy-inspectSuggests goldsky turbo inspect after deploy

​
Coverage

These skills cover the full Turbo pipeline surface:
  • Sources — 130+ chains (EVM, Solana, Bitcoin, Stellar, Sui, NEAR, Starknet), source filtering, bounded ranges
  • Transforms — SQL, TypeScript/WASM, dynamic tables, HTTP handlers
  • Sinks — PostgreSQL, ClickHouse, Kafka, S3, Webhook, S2
  • Modes — Streaming (continuous) and Job (batch with end_block)
  • Lifecycle — Deploy, pause, resume, restart, delete
  • Monitoring — Live inspect TUI, log analysis, error matching

​
Example prompts

Once installed, describe what you need in natural language:
  • “Build a Turbo pipeline to track USDC transfers on Base”
  • “My pipeline is stuck in error state — help me fix it”
  • “What’s the dataset name for Polygon ERC-20 transfers?”
  • “Show me the YAML syntax for a ClickHouse sink”
  • “Configure a PostgreSQL secret for my pipeline”
  • “Set up the Goldsky CLI and authenticate”