Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Superior Trade — Hyperliquid | DecimalAI

Financeby superior-trade

Superior Trade — Hyperliquid

Backtest and deploy trading strategies on Superior Trade's managed cloud.

Maintained

SkillScore

SkillScore87/100

Test results 87

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

39%87%of test cases passed +48 pts

Without skill9 of 23

With skill20 of 23

12 fixed8 passed either way2 still failing1 broke

Measured on gemini-3.6-flash9/3/2026v4 · latest is v521 comparable

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI called `POST /v3/account/0x111.../hyperliquid` to bootstrap my trading wallet account for Hyperliquid live trading. Which endpoint must I inspect to verify that onboarding is complete and what fields indicate readiness?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add superior-trade-hyperliquid
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install superior-trade-hyperliquid

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/superior-trade-hyperliquid/SKILL.md https://app.decimal.ai/s/superior-trade-hyperliquid/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/superior-trade-hyperliquid/SKILL.md

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add superior-trade-hyperliquid

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add superior-trade-hyperliquid

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add superior-trade-hyperliquid

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add superior-trade-hyperliquid

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add superior-trade-hyperliquid

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("superior-trade-hyperliquid")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/superior-trade-hyperliquid/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add superior-trade-hyperliquid

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/superior-trade-hyperliquid/SKILL.md https://app.decimal.ai/s/superior-trade-hyperliquid/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/superior-trade-hyperliquid/SKILL.md

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/superior-trade-hyperliquid/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/superior-trade-hyperliquid.json

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v5 (v4 tested 9/3/2026)
Source: superior-trade/superior-skills ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Superior Trade — Hyperliquid

Backtest and deploy Freqtrade strategies on Hyperliquid through Superior Trade's managed cloud.

Read ../../references/unified-runtime.md before any Superior Trade request. Use only current Unified API methods and payload fields.

Base URL: https://api.superior.trade Auth: x-api-key header on all protected endpoints Discovery: GET /openapi.json (OpenAPI), GET /install.txt, and GET /.well-known/mcp.json

Unified API only

Before venue setup, backtesting, deployment, or execution, read ../../references/unified-runtime.md. Use GET /context/venues and GET /runtime/frameworks to discover support, then use the Unified runtime endpoints. If a required Hyperliquid operation is absent from the contract, report it as unavailable.

Reference files

Load these on demand — each is the full detail behind a summary below.

Read	When
`references/api.md`	You need Unified route selection for account, context, backtesting, deployment, typed execution, or withdrawal (`POST /wallet/withdraw`).
`references/strategy-config.md`	You are writing or fixing config JSON or strategy Python — config fields, code template, TA-Lib usage, multi-entry (DCA/grid), funding-rate access, `minimal_roi` shapes.
`references/wallets-and-accounts.md`	Anything about wallets, balances, deposits, sub-accounts, multi-strategy capacity, pair formats, or HIP-3 tickers.
`references/troubleshooting.md`	A deployment or backtest is failing, trading zero times, hitting rate limits, or showing orphan positions.

Gotchas

Environment-specific facts that defy reasonable assumptions. Read these before acting.

HIP-3 pairs use a HYPHEN, not a colon. XYZ-AAPL/USDC:USDC is correct; XYZ:AAPL/USDC:USDC is the single most common format mistake. HIP-3 pairs are also absent from the default {"type":"meta"} call — you must pass the dex, e.g. {"type":"meta","dex":"xyz"}.
The agent wallet holding $0 is normal. It signs against the main wallet's balance and never needs funds. Always check the main trading wallet's balance; checking the agent wallet's will always look like an empty account.
A balance that covers stake_amount × max_open_trades exactly will still fail. The exchange reserves roughly 1% for fees, so cap stake_amount at ~95% of balance / max_open_trades or entries get rejected silently.
The account URL is https://account.superior.trade. Never send users to app.superior.trade, including when an API error message itself contains that older URL.
Multi-output TA-Lib functions return tuples. talib.BBANDS(...) and friends crash at runtime if unpacked as a single value — see references/strategy-config.md.
Sub-account funds are not available to the master. A master's true capacity is its own balance plus sub-account balances queried separately via subAccounts2; funds sitting in a sub-account cannot back a master deployment.
Hyperliquid margin modes differ — never assume. If perps shows $0 but spot shows funds, inspect whether the exchange account uses unified margin or standard margin before telling the user to move anything themselves.
One live strategy per trading account. To run several at once, omit wallet_address when storing credentials and the server assigns the next idle trading account.

Safety

Security & Permissions

This skill requires exactly one credential: an x-api-key header value. The only secret the agent uses is SUPERIOR_TRADE_API_KEY from the environment.

Security rules (non-negotiable):

NEVER ask users for private keys, seed phrases, or wallet credentials
NEVER include private keys in API requests (the API rejects them)
NEVER log, store, or display private keys or seed phrases
NEVER tell users to deposit funds to the agent wallet address
NEVER fabricate wallet balances, API responses, or trade results
NEVER start a live deployment without explicit user confirmation
Prefer user-friendly language over internal technical names when speaking conversationally. Say "strategy", "the bot", or "the trading engine" instead of referencing internal class names or infrastructure details. This is a UX preference — if the user asks about the underlying technology, answer honestly (the platform uses Freqtrade for strategy execution on Hyperliquid).
NEVER send users to app.superior.trade — the correct URL is https://account.superior.trade

Key scope notice: The API key can create and start live deployments that execute real trades using the user's managed wallet, submit contract-supported typed executions, and request a Unified wallet withdrawal after confirmation. It cannot export private keys or provide an undocumented venue-specific deposit/transfer action. Users should confirm scope with Superior Trade and backtest their strategy first.

Can do	Cannot do
Create, list, delete backtests	Access other users' data
Create, start, stop, delete deployments (including live trading with real funds)	Export or view private keys
Trigger server-side credential resolution (no user secrets collected)	Ask users for wallet secrets
View deployment logs, status, wallet metadata	Move unsupported assets or use unsupported chains
Deposit native Arbitrum USDC from the user's platform wallet into Hyperliquid via the API	Bridge from external wallets
Return Hyperliquid USDC to the server-resolved Superior wallet via the API	Withdraw to an arbitrary external address

Live Deployment Confirmation

Before any live deployment, the agent MUST present this summary and wait for explicit confirmation:

Deployment Summary:
• Strategy: [name]
• Exchange: hyperliquid
• Trading mode: [spot/futures]
• Pairs: [list]
• Stake amount: [amount] USDC per trade
• Max open trades: [n]
• Stoploss: [percentage]
• Margin mode: [cross/isolated] (futures only)

⚠️ This will trade with REAL funds. Proceed? (yes/no)

Do NOT start a live deployment without an explicit affirmative response.

Setup

Getting an API Key

IMPORTANT: The correct URL is https://account.superior.trade — NOT app.superior.trade. Never send users to app.superior.trade.

Use SUPERIOR_TRADE_API_KEY from the environment or credential manager.

When a user needs to get their API key:

Go to https://account.superior.trade
Sign up (email or wallet)
Read the managed wallet and deposit details from GET /wallet
Fund the platform trading wallet with native USDC on Arbitrum One using the user's own capital
Create an API key (st_live_...) from your account settings
Add it as SUPERIOR_TRADE_API_KEY in your agent's environment/credential settings
Check Hyperliquid and framework support with GET /context/venues and GET /runtime/frameworks
If a required venue bootstrap or bridge action is absent from GET /openapi.json, report it as unavailable

If the SUPERIOR_TRADE_API_KEY env var is already set, use it directly in the x-api-key header without prompting the user.

Public Endpoints (no auth)

Method	Path	Description
GET	`/health`	`{ "status": "ok", "timestamp": "..." }`
GET	`/openapi.json`	Unified OpenAPI contract
GET	`/install.txt`	Installation instructions
GET	`/.well-known/mcp.json`	MCP discovery manifest

Agent Operating Rules

Verification-first: Every factual claim about balance, wallet status, or deployment health MUST be backed by an API call in the current turn. NEVER assume → report → verify later.
Anti-hallucination: If you can't call the API, say "I haven't checked yet." Every number must come from a real response.
Conversational: Make API calls directly and present results conversationally. Show raw payloads only on request.
Backtesting: Build config + code from user intent → create → poll → present results — all automatically.
Deployment: Create → store credentials → run checklist → show summary → get confirmation → start.
Proactive: Ask for missing info conversationally, one concern at a time. Always ask user to run a backtest before first live deployment.

Check Hyperliquid balances with BOTH endpoints:

Perps: POST https://api.hyperliquid.xyz/info → {"type":"clearinghouseState","user":"0x..."}
Spot: POST https://api.hyperliquid.xyz/info → {"type":"spotClearinghouseState","user":"0x..."}

Repeated Failures

If the agent fails the same task 3+ times (e.g. strategy code keeps crashing, backtest keeps failing), stop and:

Summarize what was tried and what failed
Pivot in two stages before giving up:
- First — param space. If you have not yet run a parameter sweep on this strategy/pair, run one (see Backtest Workflow → Parameter Sweeps). Most "this idea doesn't work" verdicts are really "this single config didn't work" — sweeping the key parameter often surfaces a viable variant in one batch.
- Second — pair space. Only after a full sweep also fails, suggest a different pair, timeframe, or strategy family (e.g. mean-reversion instead of momentum).
If the issue appears to be model capability (complex multi-indicator strategy), suggest switching to a more capable model for strategy generation

Workflows

Backtest Workflow

Build config + strategy code from user requirements
POST /runtime/backtests — create with framework: "freqtrade", venue: "hyperliquid", strategy source/config, instruments, and timerange fields from GET /openapi.json.
Poll GET /runtime/backtests/{id} every 10s until completed or failed (1–10 min)
Read GET /runtime/backtests/{id}/logs for framework output and diagnostics
Present the result fields published by the current contract: total trades, win rate, profit, drawdown, Sharpe ratio, and duration when available
If failed, check GET /runtime/backtests/{id}/logs
To cancel or remove: DELETE /runtime/backtests/{id}

Backtest Wallet and Stake Sizing

Backtests are simulations. Do not size a backtest from the user's live wallet by default; use simulated capital to evaluate the strategy. Only mirror the user's current wallet if they explicitly ask for a live-wallet simulation.

dry_run_wallet is the total simulated wallet inventory by asset. It is an object/map, not a scalar. Examples: { "USDC": 1000 }, { "USDC": 100, "BTC": 0.1 }.
stake_amount is the amount the backtest/bot may allocate per trade slot. A numeric value is fixed stake per entry slot; "unlimited" divides the simulated wallet across max_open_trades slots.
If using fixed stake, set dry_run_wallet to the total simulated balances so PnL is measured against the correct capital base. Example: a $50 USDC simulation with $45 usable per trade uses stake_amount: 45 and dry_run_wallet: { "USDC": 50 }.
For standard perps, keep fixed stake_amount at or below ~90% of USDC / max_open_trades; for HIP-3 assets, use ~70% because fees and isolated-margin buffers are higher.
Never combine stake_amount: "unlimited" with max_open_trades: -1. When stake is unlimited, max_open_trades must be a finite positive integer so the wallet can be divided across slots.
For DCA/grid/scaling strategies that use position_adjustment_enable and adjust_trade_position, stake_amount may be fixed or "unlimited". If using "unlimited", you must control the initial entry size in custom_stake_amount; otherwise the first entry can consume all available capital. In either mode, dry_run_wallet must cover the maximum laddered exposure, not just the first entry.

Parameter Sweeps (recommended for first-pass backtests)

For the first backtest of any new idea on a given pair, do not submit a single config. Submit a 3-variant sweep that varies ONE parameter, run all 3 in parallel, then compare horizontally.

Why: building a config is the expensive cognitive step; running a backtest is cheap. A single result tells you whether one point worked; three neighboring points tell you whether the region works and which direction to iterate.

How to fan out:

Issue all 3 POST /runtime/backtests calls in parallel (different config for each variant; same code unless the variant is a code-level change).
Poll all 3 GET /runtime/backtests/{id} endpoints in parallel each cycle.
Fetch all 3 GET /runtime/backtests/{id} results in parallel once status is completed.

Each backtest runs in isolation, so parallel execution does not slow any single run.

What to vary (pick ONE axis per sweep):

Strategy family	Parameter to vary	Three variants
Momentum / EMA cross	EMA periods	5/10/20, 8/13/21, 12/26/50
Trend-following	ATR stop multiplier	2.0, 3.0, 4.0
Mean-reversion (RSI)	Oversold threshold	<25, <30, <35
Bollinger Bands	Std-dev width	1.5, 2.0, 2.5
Breakout	Lookback window	20, 50, 100 candles

When NOT to sweep:

The user pinned specific parameter values ("backtest with EMA 8/21 only").
Walk-forward validation on a second pair after a confirmed setup — that should be a single config (sweeping there is parameter overfitting).
The user is iterating on a known winner ("now try the same config on ETH").

Result Interpretation

After status = completed, read both GET /runtime/backtests/{id} and GET /runtime/backtests/{id}/logs. Present only metrics actually returned by the Unified API or its framework logs:

Total trades — completed round-trips
Win rate — percentage of profitable trades
Total profit % — net profit as percentage of starting balance
Max drawdown — worst peak-to-trough decline
Sharpe ratio — risk-adjusted return (>1.0 good, >2.0 excellent)
Average trade duration — how long positions are held

Before suggesting deployment, always run a backtest first. If the backtest produced zero trades over a timerange that should have generated signals (e.g. weeks on a 5m timeframe), do not offer deployment — the strategy or pair likely has an issue. If PnL is negative, note the timerange may be unsuitable but don't dismiss the strategy outright. If PnL is positive, present results without overpromising — strong backtest fit can indicate overfitting. Stay neutral and let the user decide.

Sweep Result Comparison

All 3 profitable → pick the best Sharpe (not best PnL — small-sample PnL rewards luck). The parameter region is robust; proceed to walk-forward or deployment.
1–2 profitable → pick the winner, but flag that the parameter is sensitive. Suggest either (a) walk-forward on a second pair as an independent check, or (b) one tighter sweep around the winner.
All 3 unprofitable / < 10 trades → the idea doesn't work on this pair. Move to pair-space (different pair, timeframe, or strategy family). Do not sweep again on the same pair.
Monotonic edge (e.g. PnL strictly improves 2.0 → 3.0 → 4.0) → the best variant sits at the edge of the grid. Run ONE more variant past it (e.g. 5.0) — don't run another full 3-grid; just extend by one.

Zero-trade rule for sweeps: zeros in 1–2 variants of a sweep are informative (the parameter was too tight), not a failure. Only treat the sweep as failed when ALL 3 variants return zero trades.

Deployment Workflow

POST /runtime/deployments with top-level framework, venue, mode, name, code, and config
Ask the user: live or dry-run?
- Live: use PUT /runtime/deployments/{id}/credentials with a credential form published by GET /openapi.json
- Dry-run: Skip the credentials step — the deployment runs in simulation mode (no real funds)
Run the pre-deployment checklist
Show the deployment confirmation summary and wait for explicit user confirmation
PUT /runtime/deployments/{id}/status → {"action": "start"}
Monitor: GET /runtime/deployments/{id}, GET /runtime/deployments/{id}/logs
Stop: PUT /runtime/deployments/{id}/status → {"action": "stop"}

Pre-Deployment Checklist (MANDATORY)

Before PUT /runtime/deployments/{id}/status → {"action":"start"}:

For live deployments (credentials stored):

Account ready — fetch GET /wallet and GET /context/venues. Proceed only when the returned wallet and Hyperliquid capability data show the required support; otherwise report the blocker.
Credentials stored — inspect the credential state returned by GET /runtime/deployments/{id}. If credentials are required, attach the exact contract-defined payload with PUT /runtime/deployments/{id}/credentials.
Identify wallets — GET /runtime/deployments/{id} → note wallet_address (agent wallet) and agent_wallet_address.
Funds available — Check the managed wallet and live Hyperliquid state. Verify stake_amount × max_open_trades fits within available collateral with a fee buffer. If funding is insufficient and Unified API does not publish a venue deposit action, stop and tell the user what funding step remains unavailable.
No existing positions/orders — Check clearinghouseState for open positions on the main wallet. If positions or orders exist, show the user details (pair, side, size, PnL) and ask them to close before deploying — leftover positions can block new entries or cause unexpected margin usage.

For dry-run deployments (no credentials): Skip steps 1–5, the deployment runs in simulation mode without real funds.

Pair is tradeable — POST https://api.hyperliquid.xyz/info → {"type":"meta"} for standard perps, or {"type":"meta", "dex":"xyz"} (or the relevant dex name) for HIP3 pairs. Verify the coin name exists in the universe array.

Do NOT skip any step or assume it passed without the API call.

Getting Funds Back Out

Use POST /wallet/withdraw only with the request shape and verified destination published by the Unified contract. A typed POST /runtime/executions request may place or cancel supported orders; it is not an undocumented exit-all or sub-account transfer primitive. If the required unwind action is absent from GET /openapi.json, report it as unavailable. Every money-moving action requires an exact summary and explicit confirmation first.

Related skills

Strategy templates and primitives are separate skills in this library. Load one when the user's idea matches it, rather than writing a strategy from scratch.

Strategy templates: dca-weekly, grid-trading, funding-rate-arbitrage, funding-squeeze, basis-arb, breakout, mean-reversion, bollinger-reverter-4h, donchian-strong-regime, scalping

Primitives: regime-overlay (trend gate), dsl-exit-engine (ROI ladder + ratcheting trail), trade-thesis (pre-trade bull/bear case), backtesting (windows, sweeps, walk-forward), fees-optimizations (maker vs taker, fee budgeting)

Market scanning: intelligence — live multi-bucket scoring across Hyperliquid alts and HIP-3, deployed as multi-pair buckets

Other venues: aerodrome (Base spot AMM), lighter, polymarket

Funding an account: deposit-qr (payment QR for a Superior-managed wallet), external-deposit (bridging in from an external wallet)

About this skill

Automatic

Finance & Accounting pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/1/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

superior-trade / superior-skills

skills/v2/exchanges/hyperliquid/SKILL.md

View on GitHub ↗

License MITImported 11/1/2026Version v5Bundled 4 files

Illustrative Want to see what superior-trade/hyperliquid would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Superior Trade — Hyperliquid

Unified API only

Reference files

Gotchas

Safety

Security & Permissions

Live Deployment Confirmation

Setup

Getting an API Key

Public Endpoints (no auth)

Agent Operating Rules

Repeated Failures

Workflows

Backtest Workflow

Backtest Wallet and Stake Sizing

Parameter Sweeps (recommended for first-pass backtests)

Result Interpretation

Sweep Result Comparison

Deployment Workflow

Pre-Deployment Checklist (MANDATORY)

Getting Funds Back Out

Related skills

SkillSafety

Source

Related skills

More in the registry