Backtest, deploy, and monitor trading bots on Hyperliquid. An agent skill from LeoYeAI/openclaw-master-skills.

MITAuto-check passedBusiness, Finance & HR

Install Supurr

skills CLI
$ npx skills add LeoYeAI/openclaw-master-skills --skill supurr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install LeoYeAI/openclaw-master-skills supurr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/supurr-hyperliquid .claude/skills/supurr && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
supurr
GitHub stars
2.2k
Token cost
~6.5k tokens
SKILL.md length
1,616 words
Files
9 (incl. scripts)
Skills in repo
1,235
Repo updated
First seen
Licence
MIT

At a glance

Backtest, deploy, and monitor trading bots on Hyperliquid. An agent skill from LeoYeAI/openclaw-master-skills.

  • Works in 12 steps: supurr init — Credential Setup → supurr whoami — Show Identity → supurr new — Config Generator → …
  • Tasks that involve Trading and backtesting
  • SKILL.md covers Quick Reference, Global Options, 1. supurr init — Credential… and 2. supurr whoami — Show Identity, plus 11 more sections
  • Runs Shell scripts from its folder; reaches api.hyperliquid.xyz

What it does

Supurr is an agent skill from LeoYeAI/openclaw-master-skills. Backtest, deploy, and monitor trading bots on Hyperliquid. Supports Grid, DCA, and Spot-Perp Arbitrage strategies across Native Perps, Spot markets (USDC/USDH), and HIP-3 sub-DEXes.

Its SKILL.md is about 6.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts (for example `.claude-plugin/plugin.json`, `README.md` and `_meta.json`).

It sits in Business, Finance & HR, covering Trading and backtesting. It works with Hyperliquid and Circle USDC. The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.

When your agent uses it

  • Tasks that involve Trading and backtesting

Example prompts

  • “/supurr”

Requirements

  • A Bash shell

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. supurr init — Credential Setup
  2. supurr whoami — Show Identity
  3. supurr new — Config Generator
  4. supurr configs — List Saved Configs
  5. supurr config — View Config
  6. supurr backtest — Run Backtest
  7. supurr deploy — Deploy Bot
  8. supurr monitor — View Active Bots
  9. supurr history — View Bot History
  10. supurr stop — Stop Bot (Signature Auth)
  11. supurr prices — Debug Price Data
  12. supurr update — Self-Update

What it can do on your machine

Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • api.hyperliquid.xyz

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Supurr loads about 6.5k tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 1,616 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~6.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 1,616 words, ~6,518 tokens.

Download SKILL.mdSave it as .claude/skills/supurr/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
supurr
description
Backtest, deploy, and monitor trading bots on Hyperliquid. Supports Grid, DCA, and Spot-Perp Arbitrage strategies across Native Perps, Spot markets (USDC/USDH), and HIP-3 sub-DEXes.

Supurr CLI — Complete Command Reference

For LLMs: This is the authoritative reference. Use exact syntax. Config files are in ~/.supurr/configs/.


Quick Reference

CommandPurpose
supurr initSetup wallet credentials
supurr whoamiShow current wallet
supurr new gridGenerate grid strategy config
supurr new arbGenerate spot-perp arb config
supurr new dcaGenerate DCA strategy config
supurr configsList saved configs
supurr config <name>View config details
supurr backtestRun historical simulation
supurr deployDeploy bot to production
supurr monitorView active bots
supurr historyView historical bot sessions
supurr stopStop a running bot (signed)
supurr pricesDebug price data
supurr updateUpdate CLI to latest

Global Options

bash
supurr --help              # Show all commands
supurr --version, -V       # Show CLI version
supurr -d, --debug         # Enable debug logging (any command)

1. supurr init — Credential Setup

bash
# Interactive
supurr init

# Non-interactive
supurr init --address 0x... --api-wallet 0x...

# Overwrite existing
supurr init --force
OptionDescription
-f, --forceOverwrite existing credentials
--address <address>Wallet address (0x...)
--api-wallet <key>API wallet private key

2. supurr whoami — Show Identity

bash
supurr whoami    # Shows: Address + masked key

3. supurr new <strategy> — Config Generator

Supports three strategies: grid, arb, dca.

bash
supurr new grid [options]   # Grid trading
supurr new arb [options]    # Spot-perp arbitrage
supurr new dca [options]    # Dollar-cost averaging

3a. supurr new grid — Grid Strategy
Market Types
TypeQuoteRequiresExample
nativeUSDC—--asset BTC
spotVariable--quote--asset HYPE --type spot --quote USDC
hip3Per-DEX--dex--asset BTC --type hip3 --dex hyna
Grid Options
OptionDefaultDescription
-a, --asset <symbol>BTCBase asset (BTC, ETH, HYPE, etc.)
-o, --output <file>config.jsonOutput filename
--type <type>nativeMarket type: native, spot, hip3
--dex <dex>—Required for hip3: hyna, xyz, km, vntl
--quote <quote>—Required for spot: USDC, USDE, USDT0, USDH
--mode <mode>longGrid mode: long, short, neutral
--levels <n>20Number of grid levels
--start-price <price>—Grid start price
--end-price <price>—Grid end price
--investment <amount>1000Max investment in quote currency
--leverage <n>2Leverage (1 for spot)
--testnetfalseUse Hyperliquid testnet
Grid Examples
bash
# Native Perp (BTC-USDC)
supurr new grid --asset BTC --levels 4 --start-price 88000 --end-price 92000 --investment 100 --leverage 20

# USDC Spot (HYPE/USDC)
supurr new grid --asset HYPE --type spot --quote USDC --levels 3 --start-price 29 --end-price 32 --investment 100

# Non-USDC Spot (HYPE/USDH)
supurr new grid --asset HYPE --type spot --quote USDH --levels 3 --start-price 29 --end-price 32 --investment 100

# HIP-3 (hyna:BTC)
supurr new grid --asset BTC --type hip3 --dex hyna --levels 4 --start-price 88000 --end-price 92000 --investment 100 --leverage 20
HIP-3 DEXes
DEXQuoteAssets
hynaUSDECrypto perps (BTC, ETH, HYPE, etc.)
xyzUSDEStocks (AAPL, TSLA, etc.)
kmUSDTKinetiq Markets
vntlUSDEAI/tech tokens

3b. supurr new arb — Spot-Perp Arbitrage Strategy

Generates a config that simultaneously trades the spot and perp legs of the same asset, capturing spread differentials.

Market Constraint: Only assets that have both a spot token AND a perp market on Hyperliquid are eligible. The CLI auto-resolves the spot counterpart.

Spot Resolution Logic

Hyperliquid spot tokens for major assets use a U-prefix naming convention:

You pass --assetCLI resolves spot tokenSpot pairPerp pair
BTCUBTCUBTC/USDCBTC perp
ETHUETHUETH/USDCETH perp
SOLUSOLUSOL/USDCSOL perp
ENAUENAUENA/USDCENA perp
WLDUWLDUWLD/USDCWLD perp
MONUMONUMON/USDCMON perp
MEGAUMEGAUMEGA/USDCMEGA perp
ZECUZECUZEC/USDCZEC perp
XPLUXPLUXPL/USDCXPL perp
PUMPUPUMPUPUMP/USDCPUMP perp
HYPEHYPE (exact name)HYPE/USDCHYPE perp
TRUMPTRUMP (exact name)TRUMP/USDCTRUMP perp
PURRPURR (exact name)PURR/USDCPURR perp
BERABERA (exact name)BERA/USDCBERA perp

Resolution order: try U{ASSET} first → fallback to exact name → fail if neither exists.

⚠️ U-prefix Hazard: Do NOT pass asset names that already start with U (e.g., UNIT). The CLI will prepend another U and look for UUNIT, which doesn't exist. Always use the perp ticker name (e.g., BTC, not UBTC).

Arb Options
OptionDefaultDescription
-a, --asset <symbol>BTCPerp asset name (BTC, ETH, HYPE, etc.)
--amount <usdc>100Order amount in USDC per leg
--leverage <n>1Leverage for perp leg
--open-spread <pct>0.003Min opening spread (0.003 = 0.3%)
--close-spread <pct>-0.001Min closing spread (-0.001 = -0.1%)
--slippage <pct>0.001Slippage buffer for both legs (0.001 = 0.1%)
-o, --output <file>{asset}-arb.jsonOutput filename
--testnetfalseUse Hyperliquid testnet
Arb Examples
bash
# BTC spot-perp arb (default $100/leg)
supurr new arb --asset BTC

# HYPE arb with $50 per leg, 2x leverage on perp
supurr new arb --asset HYPE --amount 50 --leverage 2

# ETH arb with tighter spreads
supurr new arb --asset ETH --open-spread 0.002 --close-spread -0.0005 --slippage 0.0005

# SOL arb on testnet
supurr new arb --asset SOL --testnet

Balance Requirement: Arb bots require USDC balance in both Spot and Perps wallets on Hyperliquid, since the bot trades on both sides simultaneously.


3c. supurr new dca — DCA Strategy

Generates a Dollar-Cost Averaging config that opens positions in steps when price deviates, then takes profit on the averaged entry.

DCA Options
OptionDefaultDescription
-a, --asset <symbol>BTCBase asset
--mode <mode>longDirection: long or short
--type <type>nativeMarket type: native, spot, hip3
--trigger-price <price>100000Price to trigger base order
--base-order <size>0.001Base order size in base asset
--dca-order <size>0.001DCA order size in base asset
--max-orders <n>5Max number of DCA orders
--size-multiplier <x>2.0Size multiplier per DCA step
--deviation <pct>0.01Price deviation % to trigger first DCA (0.01 = 1%)
--deviation-multiplier <x>1.0Deviation multiplier for subsequent steps
--take-profit <pct>0.02Take profit % from avg entry (0.02 = 2%)
--stop-loss <pnl>—Optional stop loss as absolute PnL threshold
--leverage <n>2Leverage (1 for spot)
--restartfalseRestart cycle after take profit
--cooldown <secs>60Cooldown between cycles in seconds
-o, --output <file>config.jsonOutput filename
--testnetfalseUse Hyperliquid testnet
DCA Examples
bash
# BTC DCA long, trigger at $95k
supurr new dca --asset BTC --trigger-price 95000

# ETH DCA short with custom deviation
supurr new dca --asset ETH --mode short --deviation 0.02

# HYPE DCA with auto-restart
supurr new dca --asset HYPE --restart --cooldown 120 --take-profit 0.03

# DCA on spot market
supurr new dca --asset HYPE --type spot --quote USDC --trigger-price 25

4. supurr configs — List Saved Configs

bash
supurr configs    # Lists all configs in ~/.supurr/configs/

Output:

📁 Configs (/Users/you/.supurr/configs):
  btc-grid.json         grid     BTC-USDC
  hype-usdc-spot.json   grid     HYPE-USDC
  hyna-btc.json         grid     BTC-USDE

5. supurr config <name> — View Config

bash
supurr config btc-grid        # View btc-grid.json
supurr config btc-grid.json   # Same

6. supurr backtest — Run Backtest

Syntax
bash
supurr backtest -c <config> [options]
Options
OptionDescription
-c, --config <file>Required. Config file (name or path)
-s, --start <date>Start date (YYYY-MM-DD)
-e, --end <date>End date (YYYY-MM-DD)
-p, --prices <file>Use local prices file
-o, --output <file>Save results to JSON
--no-cacheDisable price caching
Examples
bash
# By config name (looks in ~/.supurr/configs/)
supurr backtest -c btc-grid.json -s 2026-01-28 -e 2026-02-01

# By full path
supurr backtest -c ~/.supurr/configs/btc-grid.json -s 2026-01-28 -e 2026-02-01

# Save results
supurr backtest -c btc-grid.json -s 2026-01-28 -e 2026-02-01 -o results.json
Archive Data Availability
DexAsset FormatExample
hyperliquidBTC, HYPENative perp + Spot
hynahyna:BTC, hyna:ETHHIP-3 DEX

Note: Archive data available from 2026-01-28 onwards.

Important: Backtests use Supurr's price archive (tick-level) or a user-provided prices file (-p). Do not use Hyperliquid Info API mids/candles for backtests; they don't provide tick-level historical data and will produce inaccurate results.


7. supurr deploy — Deploy Bot

bash
supurr deploy -c <config> [-s <address> | -v <address>]
OptionDescription
-c, --config <file>Required. Config file (name or path)
-s, --subaccount <address>Trade from a subaccount (validates master ownership)
-v, --vault <address>Trade from a vault (validates you are the vault leader)

Subaccount vs Vault:

  • Subaccount = personal trading account under your master wallet. Verified via subAccounts API (checks master field).
  • Vault = shared investment pool you manage. Verified via vaultDetails API (checks leader field).
  • Both set vault_address in the bot config on success.
  • Cannot use both --subaccount and --vault simultaneously.
Show full SKILL.md (644 more words)Show less
Examples
bash
# Deploy from main wallet
supurr deploy -c btc-grid.json

# Deploy from subaccount
supurr deploy -c btc-grid.json -s 0x804e57d7baeca937d4b30d3cbe017f8d73c21f1b

# Deploy from vault (you must be the vault leader)
supurr deploy -c config.json --vault 0xdc89f67e74098dd93a1476f7da79747f71ccb5d9

# HL: prefix is auto-stripped (copy-paste from Hyperliquid UI)
supurr deploy -c config.json -s HL:0x804e57d7baeca937d4b30d3cbe017f8d73c21f1b

Output:

✔ Loaded config for grid strategy
✔ Subaccount verified: 0x804e57d7...
✔ Bot deployed successfully!
📦 Deployment Details
  Bot ID:       217
  Pod Name:     bot-217
  Bot Type:     grid
  Market:       BTC-USDC
Gotchas
IssueSolution
HL: prefix in addressAuto-stripped — safe to paste from Hyperliquid explorer
"Subaccount not owned"Ensure the subaccount's master matches your supurr whoami address
"Vault not found"Check the vault address exists on the correct network (mainnet vs testnet)
"Vault leader mismatch"Only the vault leader can deploy — check vaultDetails API
subAccounts returns nullNormal — means no subaccounts exist for that address

8. supurr monitor — View Active Bots

Syntax
bash
supurr monitor [options]
Options
OptionDescription
-w, --wallet <address>Filter by wallet address
--watchLive mode (refreshes every 2s)
Examples
bash
supurr monitor                 # List all active bots
supurr monitor --watch         # Live monitoring (Ctrl+C to exit)
supurr monitor -w 0x1234...    # Filter by wallet

Output Columns:

  • ID — Bot identifier
  • Type — Strategy (grid, dca, mm, arb)
  • Market — Trading pair (BTC-USDC, HYPE-USDH)
  • Position — Size + direction (L=Long, S=Short)
  • PnL — Total profit/loss

9. supurr history — View Bot History

bash
supurr history             # Show last 20 bot sessions
supurr history -n 50       # Show last 50 bot sessions
OptionDefaultDescription
-n, --limit <count>20Number of bots to show

Output Columns:

  • ID — Bot identifier
  • Market — Trading pair (from config.markets[0])
  • Type — Strategy (grid, dca, mm, arb)
  • PnL — Total profit/loss (realized + unrealized)
  • Stop Reason — Why the bot stopped (shutdown:graceful → "User stopped the bot Successfully")

10. supurr stop — Stop Bot (Signature Auth)

Signs Stop <bot-id> with your API wallet private key (EIP-191 personal_sign) and sends the signature to the bot API.

bash
supurr stop              # Interactive - select from list
supurr stop --id 217     # Stop specific bot by ID
OptionDescription
--id <bot_id>Bot ID to stop (from supurr monitor)

Crypto: Uses @noble/curves/secp256k1 + @noble/hashes/sha3 (pure JS, no native deps). Signature format: 0x{r}{s}{v} (65 bytes).


11. supurr prices — Debug Price Data

bash
supurr prices -a BTC                     # Fetch BTC prices (7 days)
supurr prices -a hyna:BTC --dex hyna     # HIP-3 prices
supurr prices -a HYPE -s 2026-01-28      # From specific date
OptionDescription
-a, --asset <symbol>Required. Asset symbol
--dex <dex>DEX name (default: hyperliquid)
-s, --start <date>Start date
-e, --end <date>End date
--no-cacheDisable caching

12. supurr update — Self-Update

bash
supurr update    # Check and install latest version

Complete Workflows

Workflow 1: Grid — Backtest → Deploy → Monitor
bash
# 1. Initialize (first time only)
supurr init --address 0x... --api-wallet 0x...

# 2. Create config
supurr new grid --asset BTC --levels 4 --start-price 88000 --end-price 92000 --investment 100 --leverage 20 --output btc-grid.json

# 3. Backtest
supurr backtest -c btc-grid.json -s 2026-01-28 -e 2026-02-01

# 4. Deploy
supurr deploy -c btc-grid.json

# 5. Monitor
supurr monitor --watch

# 6. Stop when done
supurr stop --id <bot_id>
Workflow 2: Arb — Setup → Deploy → Monitor
bash
# 1. Initialize
supurr init --address 0x... --api-wallet 0x...

# 2. Generate arb config (auto-resolves spot counterpart)
supurr new arb --asset BTC --amount 200 --leverage 1 --output btc-arb.json

# 3. Review the generated config
supurr config btc-arb

# 4. Ensure USDC balance in BOTH Spot and Perps wallets on Hyperliquid

# 5. Deploy
supurr deploy -c btc-arb.json

# 6. Monitor
supurr monitor --watch
Workflow 3: DCA — Configure → Deploy
bash
# 1. Create DCA config
supurr new dca --asset BTC --trigger-price 95000 --base-order 0.001 --max-orders 5 --take-profit 0.02 --output btc-dca.json

# 2. Deploy
supurr deploy -c btc-dca.json

# 3. Monitor
supurr monitor --watch
Workflow 4: Test All Market Types
bash
# Native Perp
supurr new grid --asset BTC --output native-btc.json
supurr backtest -c native-btc.json -s 2026-01-28 -e 2026-02-01

# USDC Spot
supurr new grid --asset HYPE --type spot --quote USDC --output hype-usdc.json
supurr backtest -c hype-usdc.json -s 2026-01-30 -e 2026-01-31

# Non-USDC Spot
supurr new grid --asset HYPE --type spot --quote USDH --output hype-usdh.json
supurr backtest -c hype-usdh.json -s 2026-01-30 -e 2026-01-31

# HIP-3
supurr new grid --asset BTC --type hip3 --dex hyna --output hyna-btc.json
supurr backtest -c hyna-btc.json -s 2026-01-28 -e 2026-02-01

Config Storage

~/.supurr/
├── credentials.json      # { address, private_key }
├── configs/              # Saved bot configs
│   ├── btc-grid.json
│   ├── hype-usdc.json
│   └── ...
└── cache/                # Price data cache
    └── hyperliquid/
        ├── BTC/
        └── HYPE/

API Endpoints Used

PurposeEndpointAuth
Bot DeployPOST /bots/create/<wallet>—
Active BotsGET /dashboard/active_bots—
Bot HistoryGET /dashboard/user_bots/<address> (Python)—
Stop BotPOST /bots/<bot_id>/stop (Node)EIP-191 signature
Price DataGET /prices?dex=X&asset=Y&start_time=Z—
Price ArchiveGET /{dex}/{asset}/{date}.json—

Troubleshooting

IssueSolution
"Config not found"Use supurr configs to list available configs
"No credentials"Run supurr init first
"0 prices fetched"Check date range (data from 2026-01-28+)
"API wallet not valid"Register API wallet on Hyperliquid first
HIP-3 backtest failsUse format --dex hyna --asset BTC
"No spot market found"Asset has no spot counterpart — arb not available for this asset
Arb asset starts with UUse the perp name (e.g., BTC not UBTC) — CLI adds U prefix

Appendix: Hyperliquid Info API

Backtesting note: This appendix is for live metadata and user state lookups. It is not a source of tick-level historical data for supurr backtest.

Get address via: supurr whoami — returns the configured wallet address.

All endpoints use POST https://api.hyperliquid.xyz/info with Content-Type: application/json.

Market Data (No Address Required)

QueryRequest Body
All Mid Prices{"type": "allMids"}
Sub-DEX Prices{"type": "allMids", "dex": "hyna"}
Perp Metadata{"type": "metaAndAssetCtxs"}
Spot Metadata{"type": "spotMeta"}
L2 Order Book{"type": "l2Book", "coin": "BTC"}
List HIP-3 DEXes{"type": "perpDexs"}

User Data (Address Required)

QueryRequest Body
Perp Positions{"type": "clearinghouseState", "user": "0x..."}
Spot Balances{"type": "spotClearinghouseState", "user": "0x..."}
Open Orders{"type": "openOrders", "user": "0x..."}
Order History{"type": "historicalOrders", "user": "0x..."}
Trade Fills{"type": "userFills", "user": "0x...", "aggregateByTime": true}
Funding History{"type": "userFunding", "user": "0x...", "startTime": <ts>, "endTime": <ts>}
Sub-Accounts{"type": "subAccounts", "user": "0x..."}
Vault Details{"type": "vaultDetails", "vaultAddress": "0x..."}

HIP-3 Sub-DEXes

DEXQuoteAssets
hynaUSDECrypto perps (BTC, ETH, HYPE)
xyzUSDEStocks (AAPL, TSLA, NVDA)
vntlUSDEAI/tech tokens
kmUSDTKinetiq Markets
cashUSDCTech stocks

TypeScript Helper

typescript
const HL = "https://api.hyperliquid.xyz/info";

async function query<T>(body: object): Promise<T> {
  const res = await fetch(HL, {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify(body),
  });
  return res.json();
}

// Examples
const mids = await query({ type: "allMids" });
const positions = await query({ type: "clearinghouseState", user: "0x..." });
const spotBal = await query({ type: "spotClearinghouseState", user: "0x..." });
const dexes = await query({ type: "perpDexs" });

Common Hazards

IssueSolution
szDecimals truncationTruncate qty to szDecimals before submit
HIP-3 price prefixSub-DEX prices keyed as hyna:BTC, not BTC
Sub-DEX asset indexUse local index from DEX's universe, not global
Fill limitsuserFills max 2000 — paginate with time ranges

Tutorials

Step-by-step deployment guides with parameter selection advice and practical tips:

© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (scripts) in skills/supurr-hyperliquid of LeoYeAI/openclaw-master-skills.

  • SKILL.md
  • .claude-plugin/plugin.json
  • README.md
  • _meta.json
  • scripts/install.sh
  • scripts/skill-install.sh
  • tutorials/arb.md
  • tutorials/dca.md
  • tutorials/grid.md

Open the folder on GitHubat commit e5199b5

Compare with similar skills

Supurr next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Supurr compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Supurr this skillLeoYeAI/openclaw-master-skills2.2k—~6.5kAutomated safety check: PassMIT
Nansen Tradingnansen-ai/nansen-cli139—~3.3kAutomated safety check: NotesMIT
Funding Rate ArbitrageSuperior-Trade/superior-skills215—~1.9kAutomated safety check: PassMIT
Aomi Transactjeremylongshore/tons-of-skills-marketplace2.8k—~2.3kAutomated safety check: PassMIT
HyperliquidSuperior-Trade/superior-skills215—~5.5kAutomated safety check: WarnMIT
Minara Crypto Trading and WalletMinara-AI/minara-skills362—~5.7kAutomated safety check: PassNone

Similar skills

  • Nansen Trading

    nansen-ai/nansen-cli

    Execute DEX swaps on Solana or Base (including cross-chain bridges) and Hyperliquid perpetual trades.

    139 GitHub stars~3.3k tokensUpdated yesterday
    Business, Finance & HRAuto-check: notes
  • Funding Rate Arbitrage

    Superior-Trade/superior-skills

    A skill your agent uses when writing a funding-rate-driven perp strategy on Superior Trade — anything described as funding harvest, funding arbitrage, funding rate carry, negative funding, paid to…

    215 GitHub stars~1.9k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Aomi Transact

    jeremylongshore/tons-of-skills-marketplace

    Build natural-language crypto agents, web3 assistants, and trading bots that read and write EVM chain state.

    2.8k GitHub stars~2.3k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Hyperliquid

    Superior-Trade/superior-skills

    A skill your agent uses when backtesting, deploying, checking funding readiness, or debugging a Hyperliquid strategy through Superior Trade Unified API — writing Freqtrade configs and strategy code…

    215 GitHub stars~5.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check: warnings
  • Minara Crypto Trading and Wallet

    Minara-AI/minara-skills

    Drives the Minara CLI for crypto swaps, perps, limit orders, wallet transfers, deposits and withdrawals, plus AI market analysis.

    362 GitHub stars~5.7k tokensUpdated 23 days ago
    Business, Finance & HRAuto-check passed
  • Polymarket Trading

    BlockRunAI/ClawRouter

    A skill your agent uses when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools).

    6.6k GitHub stars~1.4k tokensUpdated 4 days ago
    Business, Finance & HRAuto-check passed

More from LeoYeAI/openclaw-master-skills

All 1,235 skills in this repo
  • DevOps Pipeline Management

    LeoYeAI/openclaw-master-skills

    Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.

    2.2k GitHub stars~4.2k tokensUpdated 2 mo ago
    Auto-check: notes
  • Feishu Document Collaboration

    LeoYeAI/openclaw-master-skills

    Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Auto-check passed
  • Files Memory System

    LeoYeAI/openclaw-master-skills

    Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.

    2.2k GitHub stars~3.8k tokensUpdated 2 mo ago
    Auto-check passed
  • GEO-Claw AI Visibility Agent

    LeoYeAI/openclaw-master-skills

    Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.

    2.2k GitHub stars~4.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Google Workspace CLI

    LeoYeAI/openclaw-master-skills

    Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.

    2.2k GitHub stars~2.6k tokensUpdated 2 mo ago
    Auto-check: notes
  • HealthFit Health Advisors

    LeoYeAI/openclaw-master-skills

    Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.

    2.2k GitHub stars~4.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Supurr

What does Supurr do?

Backtest, deploy, and monitor trading bots on Hyperliquid. An agent skill from LeoYeAI/openclaw-master-skills. Supurr is an agent skill from LeoYeAI/openclaw-master-skills. Backtest, deploy, and monitor trading bots on Hyperliquid.

When should I use Supurr?

Supurr fits situations like: tasks that involve Trading and backtesting.

How do I install Supurr in Claude Code?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill supurr -a claude-code`. Or copy the skill folder (skills/supurr-hyperliquid in LeoYeAI/openclaw-master-skills) into .claude/skills/supurr in your project. Claude Code loads it when a task matches its description.

How do I install Supurr in Codex?

Run `npx skills add LeoYeAI/openclaw-master-skills --skill supurr -a codex`. Or copy the skill folder (skills/supurr-hyperliquid in LeoYeAI/openclaw-master-skills) into .agents/skills/supurr in your project. Codex loads it when a task matches its description.

Can I use Supurr in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill supurr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/supurr, .gemini/skills/supurr, .github/skills/supurr and .opencode/skills/supurr in your project.

What does Supurr need to run?

Going by SKILL.md and its folder, Supurr needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Supurr access the network?

SKILL.md names 1 domain. In commands or code: api.hyperliquid.xyz; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Supurr safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Supurr use?

Supurr is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Supurr use?

About 6.5k tokens (SKILL.md is roughly 26k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Supurr?

Skills that share tags, products or a category with Supurr: Nansen Trading (nansen-ai/nansen-cli, 139 stars), Funding Rate Arbitrage (Superior-Trade/superior-skills, 215 stars), Aomi Transact (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Hyperliquid (Superior-Trade/superior-skills, 215 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Supurr?

LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.

Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.