Hyperliquid Reader logo

Hyperliquid Reader

CommunityPopular
himself65
hyperliquid-reader

Read Hyperliquid (app.hyperliquid.xyz) perp + spot market data via opencli (read-only, public info API). Use whenever the user wants Hyperliquid perpetual or spot markets, mark/oracle/mid prices, 24h change, funding rates (hourly or annualized APR), open interest, volume, the L2 order book, OHLCV candles, historical funding, or a cross-venue funding comparison (Hyperliquid vs Binance vs Bybit) for funding arbitrage. Triggers: "Hyperliquid funding for BTC", "HL perp markets", "funding on BTC perp", "Hyperliquid order book", "HL open interest", "funding arb Hyperliquid vs Binance", "Hyperliquid candles for SOL", "Hyperliquid spot markets", "PURR price on Hyperliquid", "hyperliquid", "hyperliquid.xyz", "HL DEX". READ-ONLY market data — no account, order, or trade operations.

Overview

Publisherhimself65
Repositoryfinance-skills
Skill namehyperliquid-reader
Stars
3.3K
Forks
378
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by himself65 on GitHub. Read the source before you install it.

Installation

Install the Hyperliquid Reader AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/himself65/finance-skills.git /tmp/finance-skills
mkdir -p .claude/skills
cp -r /tmp/finance-skills/plugins/data-providers/skills/hyperliquid-reader .claude/skills/hyperliquid-reader
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hyperliquid Reader in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hyperliquid Reader on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hyperliquid Reader is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Hyperliquid Reader (Read-Only)

Reads Hyperliquid — the on-chain perps/spot DEX — for market data via opencli and the hyperliquid plugin in this repo's opencli-plugins/hyperliquid tree (a separate plugin from opencli's built-in adapters, installed via opencli's monorepo subpath syntax).

This skill is read-only and market-data only. It reads Hyperliquid's fully public info API for analysis: market tables, funding, order book, and candles. It does NOT read individual accounts, place/modify/cancel orders, or move funds. There is no trading path in the plugin — order placement requires wallet-signed actions on a separate endpoint this adapter never calls.

How it works: every command issues a single POST https://api.hyperliquid.xyz/info with a { "type": "..." } body and normalizes the response. No API key, no wallet, no login, no running app — the info API is public.


Step 1: Ensure opencli + Plugin Are Installed and Ready

Current environment status:

!`(command -v opencli && opencli hyperliquid markets --coin BTC -f json 2>&1 | head -3 && echo "READY" || echo "SETUP_NEEDED") 2>/dev/null || echo "NOT_INSTALLED"`

If the status above shows READY, skip to Step 2. Otherwise:

NOT_INSTALLED — Install opencli

bash
npm install -g @jackwener/opencli

Requires Node.js >= 24 — the hyperliquid plugin declares engines.node >= 24.

SETUP_NEEDED — Install the Hyperliquid plugin

The Hyperliquid adapter is not built into opencli — it's a separate plugin:

bash
opencli plugin install github:himself65/finance-skills/hyperliquid

That's the entire setup — no auth, no launch step. Verify with opencli hyperliquid markets --coin BTC.

Common setup issues

SymptomFix
opencli: command not foundnpm install -g @jackwener/opencli (Node ≥ 24)
Unknown command: hyperliquidopencli plugin install github:himself65/finance-skills/hyperliquid
hyperliquid info 429Rate limited — wait a few seconds and retry

Step 2: Identify What the User Needs

User RequestCommandKey Flags
Perp markets overview / top by volumeopencli hyperliquid markets--sort, --limit, --coin
One perp's price + funding + OIopencli hyperliquid markets --coin BTC
Spot pairs overviewopencli hyperliquid spot-markets--sort, --limit, --pair, --canonical-only
All current mid pricesopencli hyperliquid mids--coin <substring>
Order book for a coinopencli hyperliquid book --coin ETH--depth, --n-sig-figs
OHLCV candlesopencli hyperliquid candles --coin BTC --interval 1h--limit
Historical funding for a coinopencli hyperliquid funding-history --coin BTC--hours, --limit
Funding arb: HL vs Binance vs Bybitopencli hyperliquid funding-compare--coin, --sort, --limit

Step 3: Execute the Command

General pattern

bash
# Use -f json or -f yaml for structured output
opencli hyperliquid markets --sort fundingAprPct --limit 15 -f json
opencli hyperliquid funding-compare --sort hlVsBinancePct --limit 20 -f md
opencli hyperliquid candles --coin BTC --interval 4h --limit 50 -f csv
opencli hyperliquid book --coin ETH --depth 5 -f json

Key rules

  1. Coin symbols are bare perp namesBTC, ETH, SOL, HYPE (no exchange prefix). Spot pairs are BASE/USDC (e.g. PURR/USDC); for book/candles you can pass either a perp coin or a spot pair.
  2. markets is the default lens for "how is X / the market doing" — it carries mark/oracle/mid price, 24h change, hourly funding + APR, open interest (coins and notional), and 24h volume in one row per perp. Filter with --coin for a single asset.
  3. Funding is reported two waysfundingHrPct is the raw hourly rate as a percent; fundingAprPct annualizes it (hourly × 24 × 365). Lead with APR when comparing carry across assets; use the hourly figure for "what will I pay next hour".
  4. funding-compare is the funding-arb screen — it annualizes each venue with its own interval (HL hourly, Binance/Bybit usually 4h) and reports hlVsBinancePct / hlVsBybitPct spreads. Default sort ranks by absolute HL-vs-Binance spread (widest dislocations first). A positive hlVsBinancePct means HL longs pay more than Binance longs.
  5. book defaults to 10 levels per side — raise --depth (max 20) for more, or --n-sig-figs 2..5 to aggregate price levels. Compute the spread/mid from the top bid and ask.
  6. candles pulls the most recent --limit candles of --interval (default 1h, 100 candles). Valid intervals: 1m 3m 5m 15m 30m 1h 2h 4h 8h 12h 1d 3d 1w 1M. Max 5000.
  7. -f json for programmatic processing / feeding other skills; -f md or -f table for human-readable output.
  8. NEVER call any write operation. This skill is read-only market data — no account reads, no order placement, modification, or cancellation, and no transfers. The plugin intentionally exposes no write endpoints.

Output format flag (-f)

FormatFlagBest for
Table-f table (default)Human-readable terminal output
JSON-f jsonProgrammatic processing, LLM context
YAML-f yamlStructured, readable
Markdown-f mdReports
CSV-f csvSpreadsheet export

Output columns

  • marketscoin, markPx, midPx, oraclePx, change24hPct, fundingHrPct, fundingAprPct, openInterest, oiNotional, dayNtlVlm, premiumPct, maxLeverage
  • spot-marketspair, base, markPx, midPx, change24hPct, dayNtlVlm, circulatingSupply, marketCap, canonical
  • midscoin, mid
  • bookside, level, px, sz, orders
  • candlestime, open, high, low, close, volume, trades
  • funding-historycoin, fundingRatePct, fundingAprPct, premiumPct, time
  • funding-comparecoin, hlAprPct, binanceAprPct, bybitAprPct, hlVsBinancePct, hlVsBybitPct, nextHlFunding

Step 4: Present the Results

  1. Lead with the headline number, then the table. For markets --coin BTC: state mark price, 24h change, funding APR, and open interest in prose first. For a full markets dump: lead with the count and the top movers / highest-funding names.
  2. Frame funding in carry terms — e.g. "BTC perp funding is +10.9% APR (longs pay shorts)". Positive funding ⇒ longs pay shorts; negative ⇒ shorts pay longs.
  3. For funding-compare, surface the widest dislocations first — name the coin, both venues' APRs, and the spread, and remember the spread is annualized; a real arb also pays exchange/withdrawal frictions, so present it as a screen, not a guaranteed edge.
  4. For book, report the spread — best bid, best ask, mid, and spread in bps before (or instead of) dumping every level. Don't paste 20 levels unless asked.
  5. For candles, describe the move — first/last close, high/low, and direction; only show the full OHLCV table when the user wants the series.
  6. Filter aggressively before showingmarkets has ~180 perps and mids ~700 markets; cap to top 15-20 by the relevant sort unless the user asks for the full list.
  7. Cross-reference for trade decisions — Hyperliquid is the on-chain venue; for equities/options context pair it with the tradingview-reader skill. For funding/basis trades, funding-compare plus markets (premium, OI) is the core view.

Step 5: Diagnostics

bash
opencli hyperliquid markets --coin BTC

A successful BTC row confirms opencli, the plugin, and the public API are all reachable. If it errors with Unknown command: hyperliquid, reinstall the plugin (Step 1). A hyperliquid info 4xx/5xx is an upstream API issue — retry after a short wait.


Error Reference

ErrorCauseFix
Unknown command: hyperliquidPlugin not installedopencli plugin install github:himself65/finance-skills/hyperliquid
hyperliquid info 429Rate limitedWait a few seconds, then retry
hyperliquid info 422/500Malformed body or upstream issueRe-check the coin/interval; retry after a wait
No perp market for coin "X"Wrong/unlisted symbolRun opencli hyperliquid markets (or mids) to find the exact symbol

Reference Files

  • references/commands.md — Every command with all flags, output schemas, and analyst workflows (funding carry, basis/arb, spot snapshot)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Hyperliquid Reader AI skill do?

Read Hyperliquid (app.hyperliquid.xyz) perp + spot market data via opencli (read-only, public info API). Use whenever the user wants Hyperliquid perpetual or spot markets, mark/oracle/mid prices, 24h change, funding rates (hourly or annualized APR), open interest, volume, the L2 order book, OHLCV candles, historical funding, or a cross-venue funding comparison (Hyperliquid vs Binance vs Bybit) for funding arbitrage. Triggers: "Hyperliquid funding for BTC", "HL perp markets", "funding on BTC perp", "Hyperliquid order book", "HL open interest", "funding arb Hyperliquid vs Binance", "Hyperliqu...

Why use Hyperliquid Reader on TypingMind?

Because you install it once and use it with any model. Hyperliquid Reader is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hyperliquid Reader in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/himself65/finance-skills/tree/main/plugins/data-providers/skills/hyperliquid-reader. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hyperliquid Reader?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hyperliquid Reader?

As many as you like. As long as a model supports skills, you can use Hyperliquid Reader with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hyperliquid Reader AI skill free?

Yes. It is published on GitHub by himself65 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇