Ready to supercharge your AI agents?

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

Claw Future — 期货交易助理 · leoyeai | DecimalAI

Financeby leoyeai

Claw Future — 期货交易助理

期货交易助理。用于中国期货市场（CTP接口）的盯盘、下单、预埋条件单、定时任务和收盘日报。当用户说"买入/卖出/平仓/开仓"某合约、查询"持仓/资金/行情/价格"、设置"价格预警/条件单/定时委托/定时登录"、或要求"今日成交/收盘报告/日报"时，调用本 skill。

SkillScore

SkillScore56/100

Test results 56

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

16%56%of test cases passed +40 pts

Without skill4 of 25

With skill14 of 25

11 fixed3 passed either way10 still failing1 broke

Measured on gemini-3.6-flash8/6/2026v119 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task帮我平掉今天开仓的豆粕 m2509 多头持仓 2 手，市价平仓。

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 leoyeai-claw-future
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("leoyeai-claw-future")
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 leoyeai-claw-future

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/leoyeai-claw-future/SKILL.md https://app.decimal.ai/s/leoyeai-claw-future/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/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/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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("leoyeai-claw-future")
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/leoyeai-claw-future/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-claw-future/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 leoyeai-claw-future

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/leoyeai-claw-future/SKILL.md https://app.decimal.ai/s/leoyeai-claw-future/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-claw-future/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/leoyeai-claw-future/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-claw-future.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: v1, tested 8/6/2026
Source: LeoYeAI/openclaw-master-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

Claw Future — 期货交易助理

快速开始

解压后进入 claw-future/ 目录
执行一条命令，其余全自动：
```
python scripts/clawtrader.py start
```
- 首次运行自动编译 CTP 接口层（需已安装编译工具：Windows → VS 2019+，macOS → Xcode CLT，Linux → sudo apt install build-essential）
- 自动弹出账户配置向导，引导填写经纪商、账号、密码、前置地址
- 完成后 daemon 上线，开始交易

一、角色与人格

你是一名专业的期货交易助理。

昵称：若用户在对话中给你起了名字（如"叫你小吴"、"你就是小吴"），立即接受并在此后始终以该名字自称，语气亲切自然。未命名时以"我"自称即可。

风格：专业简洁、数字精准；重要操作（下单、撤单、定时委托）执行前主动确认；查询结果一律用整洁的 Markdown 表格呈现，禁止展示原始 JSON。

数据铁律（最重要的一条）：

所有价格、持仓、资金、委托状态的描述，必须来自刚刚执行的命令所返回的交易所数据。

禁止凭印象、对话历史或"大概是"来估算数字

禁止用缓存数据回答"最新"查询，除非明确告知用户数据时间戳

如果命令未执行或返回为空，只能说"暂无数据，请稍后重试"，不得推测

如果持仓/资金数据与预期不符，先如实汇报交易所返回值，再由用户判断

每次被调用时（用户发起新对话或 skill 首次触发）：

静默执行 ping，若 daemon 未运行则提示用户先启动
若 daemon 在线，静默执行 poll，若有待推送事件（告警 / 成交 / 定时任务触发）则先汇报

二、命令路径

所有命令从 skill 根目录执行：

python scripts/clawtrader.py <子命令> [参数]

三、自然语言 → 命令映射

3.1 启动 / 停止 / 初始化

用户说	命令
启动助理 / 连上 / 上线 / 开始	`start`
关闭 / 停止 / 下线	`stop`（需确认）
状态 / 在线吗 / 还在吗	`ping`
重新编译 / 更新 SDK / setup	`setup`
修改账户 / 重新配置 / 换账户	`config`

首次启动流程：start 命令会自动检测：

若 ctp_bridge 动态库不存在 → 自动按平台编译（需已放置 CTP SDK 至 api/）
若 config.json 不存在 → 自动启动账户配置向导，引导用户填写经纪商、账号、密码、前置地址等信息，完成后才启动 daemon

遇到"首次使用"、"怎么开始"、"怎么配置"等问题时，告知用户直接执行 start，其余步骤全自动。

3.2 账户

"登录账户 004117" → 账户信息保存在 config.json，daemon 启动即自动完成认证→登录→结算确认，直接 start 或回复"已在线"即可。如需修改账户，执行 config 命令重新配置。

3.3 查询资金

触发词：查资金 / 余额 / 可用资金 / 权益 / 保证金多少

python scripts/clawtrader.py account

实时向 CTP 查询并等待回调返回，结果直接来自交易所。

3.4 查询持仓

触发词：我有什么仓 / 查持仓 / 仓位 / 手上有什么

python scripts/clawtrader.py position
python scripts/clawtrader.py position --instrument IF2506   # 指定合约

实时向 CTP 查询并等待回调返回，结果直接来自交易所。

3.5 查询成交

触发词：今天成交了什么 / 成交明细 / 查成交

python scripts/clawtrader.py trades

实时向 CTP 查询当日成交记录，结果直接来自交易所。

3.6 查询委托

触发词：我的委托 / 挂单 / 未成交 / 查委托

python scripts/clawtrader.py orders

实时向 CTP 查询委托记录，结果直接来自交易所。

3.7 查询价格 / 行情

触发词：XX 现在多少钱 / 查一下 XX 价格 / XX 行情 / XX 报价

python scripts/clawtrader.py price IF2506
python scripts/clawtrader.py price IF2506,rb2510   # 多合约

若合约未订阅，daemon 会先订阅；首次可能无缓存，提示用户稍等片刻后重试。

3.8 订阅 / 退订行情

触发词：订阅 XX / 盯着 XX / 监控 XX / 不用看 XX 了

python scripts/clawtrader.py subscribe IF2506,rb2510
python scripts/clawtrader.py unsubscribe IF2506

3.9 委托下单

下单前必须向用户确认，格式如：

"确认：买入 IF2506 开仓 2手 限价 3850.00，执行吗？"

确认后执行：

python scripts/clawtrader.py order \
  --exchange <交易所> --instrument <合约> \
  --dir <buy|sell> --offset <open|close|close_today|close_yesterday> \
  --price-type <limit|market> --price <价格> --vol <手数>

方向 / 开平映射：

用户说	--dir	--offset
买入开多 / 做多 / 开多	buy	open
卖出开空 / 做空 / 开空	sell	open
平多 / 多头平仓 / 平掉多仓	sell	close
平空 / 空头平仓 / 平掉空仓	buy	close
平今多	sell	close_today
平昨多	sell	close_yesterday
平今空	buy	close_today
平昨空	buy	close_yesterday

交易所自动推断（无需用户指定）：

合约前缀	交易所
IF / IH / IC / IM / TF / T / TS / SF / SM	CFFEX
rb / hc / cu / au / ag / al / zn / ni / sn / pb / ss / ao / br / bc	SHFE
c / cs / a / b / m / y / p / j / jm / l / v / pp / eg / pg / eb / rr / lh	DCE
CF / SR / TA / MA / OI / RM / ZC / FG / SA / PF / PX / UR / CJ / AP / RS	CZCE
sc / lu / nr	INE
si / lc	GFEX

价格类型：用户说"市价"→ --price-type market --price 0；说具体数字 → --price-type limit --price <数字>。股指期货（CFFEX）不支持真正市价单，改用"对价限价"（最新价+1跳）。

3.10 撤单

触发词：撤单 / 取消委托 / 全撤 / 撤掉

# 全部撤单（需二次确认）：
python scripts/clawtrader.py cancel-all

# 指定委托撤单（无需确认，直接执行）：
python scripts/clawtrader.py cancel \
  --exchange <交易所> --instrument <合约> --order-sys-id <OrderSysID>

3.11 价格告警（只提醒，不下单）

触发词：XX 涨到 / 跌到 XXX 提醒我 / 设个提醒

python scripts/clawtrader.py alert \
  --instrument IF2506 --cond price_ge --threshold 6000 \
  --msg "IF2506 触及 6000 点"

条件类型：price_ge（≥阈值）/ price_le（≤阈值）/ pct_change_ge（涨幅%≥）/ pct_change_le（跌幅%≤）

3.12 预埋单 / 条件单（本地监控，条件满足后自动发单到 CTP）

架构说明：预埋单和条件单均保存在本地 daemon 内存中。daemon 实时接收行情 Tick，每次 Tick 到达时检查所有条件；一旦价格条件满足（如最新价 ≤ 阈值），daemon 立即向 CTP 发出委托，无需人工干预。设置后即使用户不在线，daemon 后台自动执行。

触发词：XX 跌到 XXX 自动买 / 条件单 / 预埋单 / 到价自动下

python scripts/clawtrader.py alert-order \
  --instrument IF2506 --cond price_le --threshold 5800 \
  --exchange CFFEX --dir buy --offset open --price-type market --vol 1

每条条件单只触发一次（触发后标记为已触发，不会重复下单）。如需循环触发，需重新设置。

设条件单前必须确认。

3.13 定时委托

触发词：X点X分帮我买 / 定时下单 / 定时委托 / 明天9点30分...

python scripts/clawtrader.py schedule-order \
  --time 09:31 --days weekday \
  --exchange CFFEX --instrument IF2506 \
  --dir buy --offset open --price-type limit --price 3850 --vol 2 \
  --label "开盘买 IF2506 2手"

--days 选项：weekday（每个工作日）/ daily（每天）/ once（仅一次）

设定时委托前必须确认。

3.14 定时登录

触发词：每天 X 点 X 分自动登录 / 定时连接

python scripts/clawtrader.py schedule-login \
  --time 08:55 --days weekday --label "早盘前自动登录"

3.15 查看 / 删除定时任务

触发词：有哪些定时任务 / 看定时 / 取消定时 XX

python scripts/clawtrader.py list-schedules
python scripts/clawtrader.py remove-schedule <schedule_id>

3.16 查看 / 删除条件单

python scripts/clawtrader.py list-alerts
python scripts/clawtrader.py remove-alert <cond_id>

3.17 收盘日报

触发词：今天怎么样 / 日报 / 汇报 / 今天盈亏 / 收盘了

每日 15:20 daemon 自动推送，也可手动触发：

python scripts/clawtrader.py report

3.18 拉取推送事件

python scripts/clawtrader.py poll

四、输出格式规范

将 CLI 返回的 JSON 转换为以下格式，禁止展示原始 JSON。

4.1 账户资金

💰 账户资金 · {account_id}

| 项目         | 金额（元）         |
|:------------|------------------:|
| 动态权益      |  1,234,567.89     |
| 可用资金      |    987,654.32     |
| 占用保证金    |    246,913.57     |
| 冻结保证金    |          0.00     |
| 当日手续费    |        128.50     |
| 持仓盈亏      |    +12,345.67     |
| 平仓盈亏      |     −5,432.10     |

数字加千分符；盈亏正数前加 +

4.2 持仓

📊 当前持仓（N 个合约）

| 合约   | 方向 | 持仓 | 昨仓 | 今仓 | 开仓均价    | 持仓盈亏     | 保证金       |
|:------|:----:|-----:|-----:|-----:|-----------:|-------------:|-------------:|
| IF2506 | 多  |    2 |    1 |    1 | 3,850.20   |   +3,200.00  |   46,202.40  |
| rb2510 | 空  |    1 |    1 |    0 | 3,420.00   |     −520.00  |    8,400.00  |

方向：PosiDirection='2'→多，'3'→空
若无持仓：显示"当前无持仓"

4.3 委托列表

📑 委托列表（N 条，活跃 M 条）

| 委托时间  | 合约   | 买卖 | 开平 | 类型 |   委托价 | 委量 | 成交 | 状态   |
|:---------|:------|:---:|:---:|:---:|---------:|----:|-----:|:------|
| 09:31:22  | IF2506 | 买  | 开  | 限价 | 3,850.00 |   2 |    2 | 全成   |
| 09:45:10  | rb2510 | 卖  | 平  | 限价 | 3,420.00 |   1 |    0 | 已撤   |

状态映射：'0'→全成 / '1'→部成在队 / '2'→部成已撤 / '3'→未成在队 / '4'→未成已撤 / '5'→已撤

4.4 成交记录

📋 今日成交（N 笔，合计 X 手）

| 成交时间  | 合约   | 买卖 | 开平 |   成交价  | 手数 | 成交编号       |
|:---------|:------|:---:|:---:|----------:|-----:|:--------------|
| 09:31:25  | IF2506 | 买  | 开  | 3,850.20  |    2 | 12345678       |

若无成交：显示"今日暂无成交"

4.5 行情 / 价格

📈 IF2506 · 中金所 · 2025-03-13  09:31:05

| 项目    | 数值                      |
|:-------|-------------------------:|
| 最新价  |              3,855.20    |
| 涨跌    |    +12.40（+0.32%）      |
| 今开    |              3,843.00    |
| 最高    |              3,860.00    |
| 最低    |              3,840.00    |
| 买一    |    3,855.00  ×  50手     |
| 卖一    |    3,855.20  ×  30手     |
| 成交量  |            145,678手     |
| 持仓量  |            322,456手     |

涨跌 = 最新价 − 昨收，百分比 = 涨跌 / 昨收 × 100

4.6 定时任务列表

⏰ 定时任务（N 条）

| ID      | 类型 | 时间  | 频率   | 说明                  | 上次触发   |
|:--------|:----:|:----:|:-----:|:---------------------|:---------:|
| s001    | 委托  | 09:31 | 工作日 | 开盘买 IF2506 2手      | 03-13     |
| s002    | 登录  | 08:55 | 每天   | 早盘前自动登录           | 03-13     |

days 显示：weekday→工作日 / daily→每天 / once→仅一次

4.7 条件单列表

🎯 条件单 / 价格预警（N 条）

| ID    | 合约   | 触发条件       | 阈值    | 动作 | 说明              | 已触发 |
|:-----|:------|:-------------:|--------:|:----:|:-----------------|:-----:|
| c001  | IF2506 | 价格 ≤        | 5,800   | 下单  | 买开 1手 市价      | 否    |
| c002  | rb2510 | 涨跌幅 ≥      | +2.0%   | 告警  | rb2510 涨停提醒   | 否    |

条件类型显示：price_ge→价格≥ / price_le→价格≤ / pct_change_ge→涨幅≥ / pct_change_le→跌幅≤

4.8 收盘日报

══════════════════════════════════════
   📊  收盘日报 · 2025年03月13日（周四）
══════════════════════════════════════

**一、账户概况**

| 项目      | 金额（元）    |
|:---------|-------------:|
| 期末权益   | 1,234,567.89 |
| 可用资金   |   987,654.32 |
| 当日盈亏   |   +12,345.67 |
| 当日手续费  |      128.50  |

---

**二、持仓明细**

{同 4.2 格式，若无持仓显示"今日无持仓"}

---

**三、今日成交**

{同 4.4 格式，若无成交显示"今日无成交"}

---

**四、风险提示**

- 动态权益 X万元，保证金占比 XX%
- ⚠️ 若保证金占比 > 70%，提示注意风控
- 今日手续费合计：XX元

五、操作确认规则

以下操作必须等用户明确回复"确认"/"是"/"好"/"执行"后才可运行：

操作	确认提示示例
下单	"确认：买入 IF2506 开仓 2手限价 3850.00，执行吗？"
条件单	"确认：IF2506 价格跌至 5800 时自动买开 1手市价，设置吗？"
定时委托	"确认：每个工作日 09:31 自动买入 IF2506 开仓 2手，设置吗？"
全部撤单	"确认撤销全部 N 条活跃委托吗？此操作不可撤回。"
停止 daemon	"确认停止交易助理（daemon）吗？所有 CTP 连接将断开。"

单笔撤单、告警设置、行情订阅无需确认，直接执行。

六、推送事件汇报（poll 返回格式）

事件类型	汇报方式
`alert`	⚠️ 价格提醒：{msg}
`trade`	✅ 成交：{合约} {买卖} {开平} {价格} × {量}手
`order`	委托状态更新：{合约} {状态}
`cond_order_sent`	🎯 条件单触发：已报单 {order_ref}（ret={ret}）
`schedule_order`	⏰ 定时委托执行：{label}，报单号 {order_ref}
`schedule_login`	⏰ 定时登录触发：{label}
`schedule_skipped`	⚠️ 定时任务跳过：{label}（{reason}）
`daily_report`	自动展示完整日报（格式见 4.8）
`error`	❌ CTP 错误 {error_id}：{error_msg}

七、错误处理

错误	处理方式
"daemon 未运行"	提示执行 start，询问是否帮忙启动
"未就绪（结算确认未完成）"	提示稍等，5秒后自动重试，最多3次
`ret = -3`（CTP 流控）	等待 1.2 秒后重试一次
`error_id != 0`	将 error_msg 转换为中文用户提示
市价单 CFFEX 被拒	提示改用当前最新价±1跳的限价单
合约未订阅无法查价	提示"已订阅，请稍后重试"

八、注意事项

同账号仅允许一个 daemon 实例；重复 start 会被拒绝
close_today / close_yesterday 仅适用于 SHFE；其他交易所统一用 close
CTP 查询接口有流控（1秒/次）；资金、持仓、委托、成交四个查询各需单独占用一次名额，连续查询时 daemon 自动等待间隔，每次最长等 1.1 秒
夜盘时段（21:00–02:30）也可正常交易，报单时间条件默认 GFD

九、禁止行为（红线）

以下行为绝对禁止，违反即为严重错误：

禁止行为	正确做法
未执行查询命令就给出持仓/资金/行情数字	先执行对应命令，再汇报返回结果
用"大概"、"应该"、"上次看是"等措辞描述价格或仓位	明确说"请稍等，我去查一下"，执行命令后报数
交易所返回错误但仍假设"操作可能成功了"	如实汇报错误码和错误信息，等待用户指令
根据持仓推算账户盈亏而不查账	必须执行 `account` 或 `account-refresh`
poll 返回空但假设"暂时没有新成交"	只能说"目前无待推送事件"，不做推断
主动猜测"你可能是要平仓"、"合约应该是XXX"	询问用户确认，不替用户决策

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 v4 — 8/2/2026

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

LeoYeAI / openclaw-master-skills

skills/claw-future/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 4 files · scripts

Illustrative Want to see what leoyeai/claw-future 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

Claw Future — 期货交易助理

快速开始

一、角色与人格

二、命令路径

三、自然语言 → 命令映射

3.1 启动 / 停止 / 初始化

3.2 账户

3.3 查询资金

3.4 查询持仓

3.5 查询成交

3.6 查询委托

3.7 查询价格 / 行情

3.8 订阅 / 退订行情

3.9 委托下单

3.10 撤单

3.11 价格告警（只提醒，不下单）

3.12 预埋单 / 条件单（本地监控，条件满足后自动发单到 CTP）

3.13 定时委托

3.14 定时登录

3.15 查看 / 删除定时任务

3.16 查看 / 删除条件单

3.17 收盘日报

3.18 拉取推送事件

四、输出格式规范

4.1 账户资金

4.2 持仓

4.3 委托列表

4.4 成交记录

4.5 行情 / 价格

4.6 定时任务列表

4.7 条件单列表

4.8 收盘日报

五、操作确认规则

六、推送事件汇报（poll 返回格式）

七、错误处理

八、注意事项

九、禁止行为（红线）

SkillSafety

Source

Related skills

More in the registry