Goldsky Agent
AI-powered tools for the Goldsky data product surface. Build, deploy, and debug Turbo pipelines, Mirror pipelines, Subgraphs, Edge RPC, and Feeds — from natural-language prompts.
Compose skills, which send onchain transactions, are in a separate plugin: goldsky-io/goldsky-compose-agent.
Paste this to get started. The agent installs the CLI, then runs /get-started, which does the rest:
Set up Goldsky. Do this yourself. I only approve login in the browser and tell you what I am trying to do.
Install the Goldsky CLI by running auth-setup/scripts/install.sh with bash. It needs npm and does not download a shell script. If you cannot read that skill yet, install it first with npx skills add goldsky-io/goldsky-agent -y -g -a <agent> (claude-code, cursor, codex, or opencode, or -a '*' if you cannot tell which host you are). Do not curl an installer and do not ask for sudo.
Then run /get-started and follow it.
Installation
Recommended: Universal Skills Installer
npx skills add goldsky-io/goldsky-agent
The installer will prompt you to select your AI agent, or specify directly:
npx skills add goldsky-io/goldsky-agent -a claude-code # or cursor, opencode, etc.
Works with 30+ AI agents including Claude Code, Cursor, OpenCode, and Codex.
Claude Code (Plugin Marketplace)
/plugin marketplace add goldsky-io/goldsky-agent
/plugin install goldsky@goldsky-agent
Cursor (Local Plugin)
Clone and add to Cursor settings:
git clone https://github.com/goldsky-io/goldsky-agent.git
Then add the path to your Cursor settings (Settings > Cursor Settings > JSON):
{
"plugins.local": ["/absolute/path/to/goldsky-agent"]
}
Claude Code — load from local directory
git clone https://github.com/goldsky-io/goldsky-agent.git
claude --plugin-dir ./goldsky-agent
Copy skills directly (any tool)
git clone https://github.com/goldsky-io/goldsky-agent.git
cp -r goldsky-agent/skills/* .claude/skills/ # Claude Code
cp -r goldsky-agent/skills/* .cursor/skills/ # Cursor
Quick Start
| I want to... | Use |
|---|
| I just installed Goldsky | /get-started |
| Build a new Turbo pipeline | /turbo-builder |
| Fix a broken Turbo pipeline | /turbo-doctor |
| Fix a broken Mirror pipeline | /mirror-doctor |
| Build / deploy a subgraph | /subgraph-builder |
| Fix a broken / stalled subgraph | /subgraph-doctor |
| Migrate a subgraph from The Graph | /subgraph-migrate |
| Get a fast, reliable RPC endpoint | /edge |
| Cut the bill from your existing RPC provider | /boost |
| Query wallets, tokens, Polymarket, blocks (REST) | /feeds |
| Find the right dataset name | /datasets |
| Look up Turbo YAML syntax | /turbo-pipelines |
| Set up the CLI and log in | /auth-setup |
Just describe what you need in natural language — the right skill is selected automatically.
Use with autonomous or BYO agents
Claude Code and Cursor auto-discover these skills and trigger them from each skill's description. Autonomous or bring-your-own-model agents — Devin, Codex, custom LLM apps — don't implement that convention. Installing isn't enough: npx skills add copies the skills into a skills directory (.claude/skills/ for a single Claude Code target, or the shared .agents/skills/ when targeting several) but writes no entry-point file telling an agent to look there. Bridge that one of two ways:
- Connect the docs MCP (recommended) — any MCP-capable agent can search the docs and discover the skills (exposed as MCP resources) at query time. Devin: add it under
mcpServers in .devin/config.json (see Devin's MCP docs). Setup for other clients is under MCP Server below.
- Install the skills, then add an
AGENTS.md at your project root so agents that read it (Devin, Codex, Amp, …) know the skills exist — point it at your install path:
# AGENTS.md
This project uses Goldsky. AI-agent skills for building, deploying, and
debugging Goldsky pipelines are installed under `.agents/skills/` (or
`.claude/skills/`). Before a Goldsky task, read the matching
`<skills-dir>/<name>/SKILL.md` and the files it references. For reference
lookups, query the Goldsky docs MCP: https://docs.goldsky.com/mcp
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 Turbo pipeline issues
│ ├── turbo-pipelines/ # YAML config + architecture reference
│ ├── turbo-transforms/ # SQL, TypeScript, dynamic tables
│ ├── turbo-operations/ # Lifecycle commands, monitoring, errors
│ ├── mirror/ # Mirror pipeline deploy, operate, sources/sinks reference
│ ├── mirror-doctor/ # Diagnose and fix Mirror pipelines
│ ├── subgraph-builder/ # Author, build & deploy subgraphs; schema/mappings/manifest
│ ├── subgraph-doctor/ # Diagnose and fix failing/stalled subgraphs
│ ├── subgraph-migrate/ # Guided migration from The Graph
│ ├── edge/ # Managed RPC capabilities, error codes, pricing
│ ├── boost/ # Free CDN in front of your existing RPC provider
│ ├── feeds/ # Wallet balances and transfers, token prices and metadata
│ ├── datasets/ # Chain prefixes, dataset types
│ ├── secrets/ # Credential management
│ └── auth-setup/ # CLI installation, login
├── agents/ # `goldsky` subagent definition
├── hooks/ # Optional pre/post deploy automation
│ ├── optional/ # Opt-in Claude Code and Cursor configs
│ └── scripts/ # Validation, secret checking
├── .claude-plugin/ # Claude Code plugin manifest + self-hosted marketplace
└── .cursor-plugin/ # Cursor plugin manifest + logo
How It Works
Skills auto-trigger based on what you describe. Interactive skills guide you through processes, help make decisions, or walk you through multi-step tasks. Reference skills provide syntax lookups, command references, and documentation.
User: "Build me a pipeline for USDC transfers on Base"
↓
turbo-builder (skill — auto-triggered)
↓ references
turbo-pipelines + datasets + secrets
↓
Generated pipeline.yaml + deployment
Skills
Skills are grouped by product. Each group has interactive workflow skills (guided, multi-step) and/or reference skills (lookup-oriented).
Turbo pipelines
Streaming pipelines that index onchain data from 130+ chains into PostgreSQL, ClickHouse, Kafka, S3, and more.
| Skill | When to use | What it does |
|---|
turbo-builder | "I want to build a pipeline for X" | Guides you 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 |
turbo-pipelines | "What's the YAML syntax for X? Should I use dataset or Kafka?" | Config field reference + architecture decisions (source types, flow patterns, sizing) |
turbo-transforms | "How do I decode EVM logs / write a SQL transform?" | SQL, TypeScript/WASM, dynamic tables, HTTP handlers |
turbo-operations | "How do I pause / restart / delete? What does this error mean?" | Lifecycle commands, pipeline states, CLI monitoring, error patterns |
Mirror pipelines
Goldsky's original streaming pipeline product. Prefer Turbo for new pipelines — reach for Mirror only when you need a subgraph entity source, the one thing Turbo can't do.
| Skill | When to use | What it does |
|---|
mirror | "How do I sync my subgraph to PostgreSQL? Mirror vs Turbo?" | Sources, sinks, lifecycle commands, Mirror vs Turbo guidance |
mirror-doctor | "My Mirror pipeline is failing / stuck / terminated" | Runs status and log commands, identifies root cause, applies fixes |
Subgraphs
Hosted GraphQL APIs over indexed onchain data.
| Skill | When to use | What's inside |
|---|
subgraph-builder | "Build / write / deploy a subgraph; design a schema; write a mapping" | Interactive author→build→deploy; schema design, AssemblyScript mappings, manifest, instant subgraphs, performance, testing; endpoints, tags, webhooks |
subgraph-doctor | "My subgraph stopped syncing / won't deploy / is throwing errors" | Diagnostic workflow: status + log checks, the _meta query, error-pattern matching, preventive mapping-code root causes, fixes |
subgraph-migrate | "Move my subgraph off The Graph onto Goldsky" | Path selection, deploy, verify sync, migrate tags, swap endpoint |
Edge (managed RPC)
Globally distributed, low-latency JSON-RPC for EVM chains, built on eRPC — a drop-in replacement for Alchemy / Infura / QuickNode with hedged requests, automatic failover across node vendors, flashblocks, and pay-per-request (x402). Reach for Edge whenever you need a reliable RPC endpoint, not just indexing.
| Skill | When to use | What's inside |
|---|
edge | "RPC rate limits, hedged requests, flashblocks, x402, error code -32005" | Capabilities, supported chains, pricing, dashboard, error code reference |
boost | "cut my Alchemy bill", "why is my cache hit rate low", "x-cache MISS" | Free CDN over your own provider: setup, what the CDN serves, headers, metrics, troubleshooting |
Feeds
Ready-made onchain data over a REST API: one wallet's balances and transfers; metadata and current USD prices for up to 100 tokens per request; Prediction markets (Polymarket activity, positions and balances); and Network datasets (block headers by number, hash or timestamp, and each chain's head). Edge Data / Data APIs is now part of Feeds, with the same URLs and keys. One Feeds API key serves every feed: get it with goldsky feeds key reveal (or Feeds → API keys in the dashboard), then call the feeds over HTTP. Do not use the CLI login token. Callers without an account can pay per request with x402.
| Skill | When to use | What's inside |
|---|
feeds | "what does this wallet hold", "show its transfers", "what is this token worth", "this wallet's Polymarket positions", "which block was at this timestamp", "Feeds API key", "x402" | goldsky feeds key reveal, every feed's call and key parameters, pagination per family, pricing, and x402 pay-per-request |
Cross-cutting
Used across multiple products.
| Skill | When to use | What it does |
|---|
auth-setup | "Install the CLI / log in / switch projects / fix unauthorized errors" | Walks through CLI installation, login, and project switching |
secrets | "Create credentials for PostgreSQL / ClickHouse / Kafka / webhook sinks" | Guides credential creation and secret management |
datasets | "What's the dataset name for Polygon NFTs? What prefix does Solana use?" | Chain prefixes, dataset types, naming conventions |
Optional deployment hooks
Deployment hooks are off by default. The CLI already validates during
goldsky turbo apply, and the skills guide secret setup and post-deploy
verification. Enable these extra checks only if you want automatic reminders
and an additional pre-deploy check. The validation hook runs even when the
command contains --skip-validation.
When enabled, these hooks run on supported goldsky turbo apply commands:
| Hook | What it does |
|---|
pre-deploy-validate | Runs goldsky turbo validate, blocks on failure |
secret-check | Checks literal secret_name fields against project secrets |
post-deploy-inspect | Adds an inspect reminder to Claude context; emits a diagnostic reminder in Cursor |
Hooks require Bash, jq, and the Goldsky CLI. They inspect simple literal
goldsky turbo apply commands, including quoted YAML paths, in the host's
reported working directory. Compound commands, shell expansions, missing
prerequisites, and unrecognized secret-list output skip the checks. These hooks
are best-effort assistance, not an enforcement boundary. Cursor's post-shell
hook has no documented way to add agent context; its reminder may only appear
in hook diagnostics. See PRIVACY.md for network and data flows.
Enable for one Claude Code session
From a stable checkout of this repository:
claude --plugin-dir "$PWD" --settings "$(jq --arg root "$PWD" '
walk(if type == "string"
then split("${CLAUDE_PLUGIN_ROOT}") | join($root)
else . end)
' hooks/optional/claude.json)"
This supplies the hook settings for that session without editing your saved
settings. Start Claude without --settings to return to the default behavior.
The settings resolve script paths to this checkout, so keep it available.
Enable for a Cursor project
From a stable checkout, print the configuration with absolute script paths:
jq --arg root "$PWD" '
walk(if type == "string"
then split("${CURSOR_PLUGIN_ROOT}") | join($root)
else . end)
' hooks/optional/cursor.json
Add the resulting entries to the target project's .cursor/hooks.json, keeping
"version": 1 and preserving any existing hooks. Reload Cursor. Remove the
Goldsky entries and reload to disable them. These are project hook settings;
they do not depend on plugin-root environment variables at runtime.
See the Claude settings reference
and Cursor hooks reference for host settings.
After upgrading from a version with automatic hooks, restart your host and
remove any manually registered Goldsky hooks if you want the new default.
Local validation
With Node 22, npm 11.10 or newer, Python 3, Bash, and jq installed:
npm ci
npm run validate:skills
npm test
scripts/validate-skills.mjs checks skill metadata during development and CI;
it is not a runtime hook and remains mandatory in CI.
Tests use a stub CLI and temporary files; they do not deploy resources or use
Goldsky credentials. Real-host installation and authentication smoke tests are
still required before marketplace submission.
Coverage
The skills cover the Goldsky data products:
- Turbo pipelines — 130+ chain sources (EVM, Solana, Bitcoin, Stellar, Sui, NEAR, Starknet); SQL / TypeScript / dynamic table transforms; PostgreSQL, ClickHouse, Kafka, S3, Webhook, S2, SQS, MySQL, Pub/Sub sinks; streaming and job modes; full lifecycle and monitoring
- Mirror pipelines — Subgraph and direct-indexing sources, sinks, lifecycle, plus interactive diagnosis (legacy — prefer Turbo for new pipelines unless you need a subgraph entity source)
- Subgraphs — Author/build/deploy (
subgraph-builder: schema design, AssemblyScript mappings, manifest, instant subgraphs, performance, testing, endpoints/tags/webhooks); interactive diagnosis (subgraph-doctor); guided migration from The Graph (subgraph-migrate)
- Edge RPC — Capabilities, supported chains, hedged requests, flashblocks, x402, error code lookups
- Boost — Free CDN in front of the RPC provider you already pay for; cacheable reads served from Goldsky, everything else forwarded free
- Feeds — REST API for one wallet's balances and transfers, token metadata and prices, Polymarket activity, positions and balances, and block headers and chain head (formerly Edge Data / Data APIs); one key or x402 pay-per-request
- Cross-cutting — Authentication, secrets, dataset naming, full CLI reference
MCP Server
The plugin bundles the Goldsky docs MCP server, providing real-time search across Goldsky documentation.
When installed as a plugin, the MCP server starts automatically.
Claude Code
claude mcp add --transport http goldsky-docs https://docs.goldsky.com/mcp
Cursor / VS Code
Add to .cursor/mcp.json or .vscode/mcp.json:
{
"mcpServers": {
"goldsky-docs": {
"type": "http",
"url": "https://docs.goldsky.com/mcp"
}
}
}
Documentation
Policies
