galleonlabs/crypto-defi-skills / packages/hyperliquid/skills/hyperliquid-setup
hyperliquid-setup
VerifiedConnect an agent's available tools to Hyperliquid workflows and complete a first public market read. Use when installing this pack, asking how to get started, diagnosing missing data or tools, or checking whether analysis, account monitoring, planning, or execution is available. Setup does not authorize trading or configure private keys.
| File | Kind | Size |
|---|---|---|
| ATTRIBUTION.md | markdown | 948 B |
| LICENSE | other | 1.0 KB |
| SKILL.md | skill md | 3.0 KB |
| agents/openai.yaml | config | 249 B |
| references/connections.md | markdown | 3.4 KB |
| references/official-tools.md | markdown | 1.7 KB |
| scripts/market-snapshot.mjs | script | 5.7 KB |
SKILL.md
View on GitHub---
name: hyperliquid-setup
description: "Connect an agent's available tools to Hyperliquid workflows and complete a first public market read. Use when installing this pack, asking how to get started, diagnosing missing data or tools, or checking whether analysis, account monitoring, planning, or execution is available. Setup does not authorize trading or configure private keys."
license: MIT
compatibility: "Any Agent Skills harness. Public reads need HTTP access or Node.js 20+. Account work needs a user-provided public account address; execution needs a separately configured trusted signer."
metadata:
version: "0.4.7"
protocol: "hyperliquid"
---
# Hyperliquid setup
Take a new agent from installed instructions to a verified first read and a precise next step.
## Tools and resources
Read [the tool contract](references/official-tools.md) only when selecting or verifying a capability. Resolve scripts and references from this skill's directory. Related skills are optional handoffs; their absence is not permission to invent state or bypass a prerequisite.
## Task
Inventory real tool capabilities and complete one public market read without account credentials.
## Workflow
1. Inventory the tools actually exposed by the harness: browser/HTTP, shell/Node, account reads, unsigned ticket building, signer submission, and reconciliation. Do not assume a named MCP server or wallet exists because a skill mentions it.
2. Read [connections and first-run procedure](references/connections.md). Select mainnet or testnet explicitly. Public market analysis needs no wallet or secret. Reuse the user's environment choice; ask only if it changes the task.
3. Run one public read for the exact requested market. From this skill's own directory, run `node scripts/market-snapshot.mjs --coin ETH --network mainnet`, substituting the requested market. Without a shell, use the two documented HTTP requests. Do not use a fixture as current evidence.
4. Validate network, coin, metadata precision, book freshness, and response coverage. Report mark/oracle price, spread, reported funding, observation time, and limitations. Missing data is unavailable, not zero. A successful public read establishes analysis access only.
5. Check the exact tool schema and supported operations for the next task. For account reads, request the public user/subaccount address; never substitute an API wallet address. For execution, require an existing trusted signer with the documented capabilities. Never handle secrets or approve an API wallet during setup.
6. Produce a readiness record: network, exact tool names, operations each tool supports, evidence, missing capabilities, available workflows, and one next action. Route to the appropriate installed skill; if absent, return the completed readiness record and name the missing capability.
## Completion
The first read must have a dated result or an explicit diagnostic failure. Setup is complete when the agent can name what it can do now and what remains unavailable. It is not proof of a connected account, complete trading integration, or authority to act.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |