Ready to supercharge your AI agents?

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

Kalshi Command Center · leoyeai | DecimalAI

Financeby leoyeai

Kalshi Command Center

Complete Kalshi trading command interface — portfolio P&L, live market scanning with edge scoring, trade execution, and risk management through your OpenClaw agent. Built-in safety: $25 max trade, 100 contract cap, $50 daily loss cutoff. Scan 600+ markets, query positions, execute trades with configurable blocklists and retry logic. Part of the OpenClaw Prediction Market Trading Stack — pairs with Kalshalyst for intelligent execution and feeds portfolio data to Market Morning Brief.

SkillScore

SkillScore83/100

Test results 83

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

13%83%of test cases passed +71 pts

Without skill3 of 24

With skill20 of 24

19 fixed1 passed either way2 still failing2 broke

Measured on gemini-3.6-flash8/8/2026v122 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI need to place a direct limit buy for 10 YES contracts at 35 cents each on ticker ECON-INFL-2026. What exact CLI syntax executes this order?

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-kalshi-command-center
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-kalshi-command-center")
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-kalshi-command-center

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-kalshi-command-center/SKILL.md https://app.decimal.ai/s/leoyeai-kalshi-command-center/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/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-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/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-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center")
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-kalshi-command-center/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center

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-kalshi-command-center/SKILL.md https://app.decimal.ai/s/leoyeai-kalshi-command-center/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-kalshi-command-center/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-kalshi-command-center/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-kalshi-command-center.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 8/8/2026
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

Kalshi Command Center

A complete command-line interface for Kalshi prediction market trading. Provides portfolio visibility, live market scanning, trade execution, and risk management through a unified command API.

Overview

The Kalshi Command Center bridges your OpenClaw AI assistant with Kalshi's API. Core capabilities:

Portfolio Management: Real-time P&L tracking with emoji-annotated positions
Live Market Scanning: Heuristic edge scoring across 600+ open markets
Market Queries: Fetch live bid/ask data before trading
Trade Execution: Buy/sell with Kelly sizing, risk validation, and audit logging
Risk Management: Hard caps on trade size, position count, and daily loss
Research Cache: Store opportunity rankings for quick reference

Available Commands

All commands are exposed through kalshi_commands.py with argparse routing. Use the module directly or import individual handlers.

Portfolio & Positions

python kalshi_commands.py portfolio
python kalshi_commands.py positions

Output: Cash balance, open positions with P&L, cost basis, and current value. Positions sorted by absolute P&L. Emoji indicators: 🔥 (>20% gain), ✅ (>5% gain), 📉 (break-even), ⚠️ (>15% loss).

Example:

📈 P&L: +$42.50 across 3 positions
💵 Cash: $1,234.56  ·  Deployed: $123.45  ·  Value: $165.95

🔥 Will US inflation exceed 4%?: 10x YES @ $50.00 → $62.50 (+25%)
✅ Tech market gains: 5x NO @ $40.00 → $42.10 (+5%)
➖ Political uncertainty: 25x YES @ $25.00 → $25.00 (0%)

Live Market Scanning

python kalshi_commands.py scan            # macro/default markets

Output: Top 8 markets ranked by heuristic edge score. Shows bid/ask, spread (%), volume, OI, days to expiration, and composite score.

Heuristic Scoring Algorithm:

Spread tightness (25% weight): Markets with tight spreads = better price discovery
Distance from extremes (35% weight): Markets in 20-80 range = actionable
Liquidity (25% weight): Volume + Open Interest, log-scaled
Time value (15% weight): Sweet spot 14-60 days to close

See references/scoring.md for detailed algorithm.

Example:

🎯 Live Scan — 600 markets scanned, 47 passed filters:

1. Will US inflation exceed 4%?
   35¢/37¢ (spread 2¢ = 5.8%) | vol 1,234 | OI 5,678 | 45d
   Score: 78.5 | ECON-INFL-2026

2. Tech sector rally this quarter?
   42¢/44¢ (spread 2¢ = 4.8%) | vol 892 | OI 3,456 | 60d
   Score: 75.2 | TECH-Q1-2026

Market Data Queries

python kalshi_commands.py get TICKER

Output: Live bid/ask for both YES and NO sides, last price, 24h volume, status, and actionable guidance.

Example:

📊 Will US inflation exceed 4%? (ECON-INFL-2026)
Status: open | Close: 2026-04-15

YES — Bid: 35¢ | Ask: 37¢ | Spread: 2¢
NO  — Bid: 63¢ | Ask: 65¢ | Spread: 2¢
Last: 35¢ | Vol 24h: 1,234 | Total vol: 12,345

💡 To sell YES contracts: sell at yes_bid (35¢) for instant fill, or post ask at 36¢ for better price.

Cached Opportunities

python kalshi_commands.py markets          # macro-heavy default
python kalshi_commands.py markets all      # everything in cache

Output: Top 8 opportunities from research cache with live price refresh. Shows source, edge %, confidence, and reasoning.

Order Management

python kalshi_commands.py orders           # list all open/resting orders
python kalshi_commands.py cancel ORDER_ID

Trade Execution

Direct trade placement (low-level):

python kalshi_commands.py buy TICKER yes 10 35    # buy 10x YES @ 35¢
python kalshi_commands.py sell TICKER no 5 63     # sell 5x NO @ 63¢

Intelligent execution from cache (high-level):

python kalshi_commands.py execute 1              # buy pick #1 with Kelly sizing
python kalshi_commands.py execute 2 qty 25       # buy pick #2 with manual 25 contracts
python kalshi_commands.py execute 3 15 contracts # buy pick #3 with manual override

The execute handler:

Looks up the pick from research cache
Fetches live market data
Calculates Kelly-sized position (if available)
Validates risk limits
Places the order with audit logging

Brier Score Calibration

python kalshi_commands.py brier           # 90 day full report
python kalshi_commands.py brier claude    # filter by Claude estimator
python kalshi_commands.py brier 30        # 30 day lookback

Prerequisites

System Requirements

Python 3.10+

API SDK

pip install kalshi-python

Authentication & Configuration

Set environment variables OR edit your OpenClaw config:

Option 1: Environment Variables

export KALSHI_KEY_ID="your-api-key-id"
export KALSHI_KEY_PATH="/path/to/your/private.key"

Option 2: Config File (`~/.openclaw/config.yaml`)

kalshi:
  enabled: true
  api_key_id: "your-key-id"
  private_key_file: "keys/kalshi-private.key"  # relative to ~/.openclaw

  # Optional: friendly names for common tickers
  ticker_names:
    ECON-INFL-2026: "Will US inflation exceed 4%?"
    TECH-Q1-2026: "Tech sector rally this quarter?"

Key Path Resolution:

If private_key_file is set: expand as ~/.openclaw/keys/{value} if relative
Fallback to private_key_path (legacy, deprecated)
Try standard paths if neither set

Optional: Kelly Position Sizing & Risk Validation

If available, the execute handler will use:

proactive.triggers.kelly_size for position sizing
proactive.triggers.validate_risk for risk gate approval

If modules are unavailable, defaults to:

Quantity: 10 contracts (fallback)
Risk validation: disabled (log-only)

Market Filtering

Blocked Categories

The scanner excludes these categories automatically:

Weather: KXTEMP, KXRAIN, KXSNOW, KXWIND, KXWEATH (irrational/unhedgeable)
Entertainment: KXCELEB, KXMOVIE, KXYT, KXTIKTOK (low signal)
Social Media: KXTWIT, KXSTREAM (low volume)
Index Futures: INX, NASDAQ, FED-MR (not Kalshi core)

See references/blocklist.md for complete list.

Sports Filter

Sports markets are intentionally excluded from the production stack. Recent evaluation did not show durable model edge there, so the system does not route sports markets into scanning or execution.

Time Window

Default scan: 7-180 days to expiration (interactive trading sweet spot)
Includes volume floor (>10 contracts traded)
Markets with tight spreads and high OI ranked first

Risk Limits

Hard caps enforced on all trades:

Limit	Value	Enforced By
Max single trade cost	$25.00 USD	`_check_risk()`
Max position size	100 contracts	`_check_risk()`
Max daily loss	$50.00 USD	Kelly sizing + risk validator (if available)

Trade Audit Log: All trades (accepted/blocked/failed) logged to ~/.openclaw/logs/trades.jsonl.

Example audit entry:

{
  "timestamp": "2026-02-26T14:35:22.123456+00:00",
  "event": "trade_placed",
  "ticker": "ECON-INFL-2026",
  "side": "yes",
  "quantity": 10,
  "price_cents": 35,
  "cost_estimate": 3.50
}

See references/risk-limits.md for full risk framework.

Heuristic Edge Scoring

The scan command ranks markets by a 4-factor composite score:

1. Spread Tightness (25% weight)

spread_score = max(0, 20 - spread_pct) / 20

Score 1.0 at 0% spread (mid = bid = ask)
Score 0.5 at 10% spread
Score 0.0 at 20%+ spread

Rationale: Tight spreads = more efficient price discovery, easier entry/exit.

2. Distance from Extremes (35% weight)

centrality = 1 - abs(mid - 50) / 50
if mid < 15 or mid > 85: centrality *= 0.3

Score 1.0 at exactly 50¢ (maximum uncertainty)
Score 0.5 at 25¢ or 75¢ (moderate certainty)
Score 0.0 at 0¢ or 100¢ (resolved)
Heavy penalty (<30% of base score) for near-settled markets

Rationale: Markets in the 20-80 range offer actionable edge. Extremes are near-certain and illiquid.

3. Liquidity (25% weight)

liq_score = log(1 + volume) * 0.6 + log(1 + oi) * 0.4

Log-scaled to avoid mega-markets dominating. Weights recent volume (60%) over open interest (40%).

4. Time Value (15% weight)

if days_to_close < 14: time_score = days_to_close / 14
elif days_to_close > 60: time_score = max(0.3, 1 - (days_to_close - 60) / 120)
else: time_score = 1.0

Sweet spot: 14-60 days to close (score 1.0)
Below 14d: linear ramp (less time = lower score)
Above 60d: logarithmic decay (floor 0.3)

Rationale: Too-short markets have liquidity spikes; too-long markets lack catalysts. 14-60d is where directional bets play out.

Composite Score

edge_score = (
    spread_score * 25
    + centrality * 35
    + liq_score * 25
    + time_score * 15
)

Weighted sum of 0-100 scale. Top 8 markets by score displayed.

See references/scoring.md for worked examples.

Output Formatting

All output strips Markdown for iMessage compatibility. Emoji indicators:

Emoji	Meaning
📈	Positive P&L or bullish signal
📉	Negative P&L or bearish signal
🔥	High gains (>20%) or strong edge
✅	Moderate gains (>5%) or approved
⚠️	Warning (>15% loss) or risk issue
🔻	Moderate loss (>0%)
➖	Break-even
🎯	Live scan results
🏀	Sports excluded / blocked
💵	Cash/financial data
📊	Market data
📎	Ticker link
💰	Proceeds/proceeds

Error Handling & Retry Logic

The _get_client() function retries on transient failures:

_get_client(_retries=1, _backoff=2.0)

Failure Classification:

network: Timeout, connection reset → retry with 2s backoff
auth: 401/403, invalid key → fail immediately
rate_limit: 429 → retry with backoff
unknown: Other errors → fail immediately

User-Facing Messages:

Network: "Can't reach Kalshi API — network timeout or connection reset."
Auth: "Kalshi auth failed — API key may be expired or invalid."
Rate limit: "Kalshi rate limited — too many requests. Try again in a minute."

Usage Examples

Daily Portfolio Check

python kalshi_commands.py portfolio

Returns cash, positions, total P&L with emoji-coded performance.

Find New Edge Right Now

python kalshi_commands.py scan

Scans 600 markets, ranks by heuristic score, shows top 8 with bid/ask and days to close.

Check Before Buying

python kalshi_commands.py get ECON-INFL-2026

Live bid/ask, spread, volume, and guidance on limit price strategy.

Execute from Research Cache

python kalshi_commands.py execute 1 qty 15

Looks up pick #1, fetches live market data, places buy order with 15 contracts (manual override skips Kelly).

Monitor Orders

python kalshi_commands.py orders

Lists all open/resting limit orders with price and remaining count.

Exit a Position

python kalshi_commands.py get ECON-INFL-2026  # check live bid
python kalshi_commands.py sell ECON-INFL-2026 yes 10 35

Sell 10 contracts at bid (35¢).

File Structure

kalshi-command-center/
├── SKILL.md                          # This file
├── scripts/
│   └── kalshi_commands.py            # Standalone CLI implementation (1100+ lines)
└── references/
    ├── risk-limits.md                # Risk framework documentation
    ├── blocklist.md                  # Complete market blocklist
    └── scoring.md                    # Heuristic scoring algorithm

Implementation Reference

Source: kalshi_commands.py (standalone implementation)

Env var support for API credentials
CLI routing via argparse
Full retry logic and error classification
Trade audit logging
Kelly sizing integration (optional)
Risk validation gates (optional)

Key Functions (all available in kalshi_commands.py):

portfolio_command() — cash + positions + P&L
scan_command() — live scan with heuristic scoring
markets_command() — cached research results
get_market_command(ticker) — live bid/ask for single market
buy_command(), sell_command() — direct order placement
execute_pick_command() — intelligent execution from cache
get_open_orders_command() — list resting orders
cancel_order_command() — cancel by order ID
_get_client() — API client with retry logic
_classify_kalshi_error() — user-friendly error messages

Troubleshooting

"Kalshi is not enabled"

Set kalshi.enabled: true in ~/.openclaw/config.yaml.

"Kalshi key_id not configured"

Set KALSHI_KEY_ID env var OR kalshi.api_key_id in config file.

"Kalshi private key not found"

Set KALSHI_KEY_PATH env var (absolute path) OR kalshi.private_key_file in config.

"Auth failed — API key may be expired"

Verify key and private key file exist and are readable. Check Kalshi account for key status.

"Can't reach Kalshi API — network timeout"

Transient network issue or Kalshi infrastructure down. Retry in 30s.

"Kalshi rate limited — too many requests"

Back off for 1 minute. The scanner makes ~50-100 API calls per scan.

No markets after filtering

All 600 open markets filtered out by spread/volume/timeframe. This stack intentionally excludes sports; try widening your non-sports filters instead.

Advanced Usage

Custom Ticker Names

Edit ~/.openclaw/config.yaml:

kalshi:
  ticker_names:
    ECON-INFL-2026: "Inflation >4%?"
    TECH-Q1-2026: "Tech rally Q1"
    CRYPTO-BTC-2026: "BTC >$100k?"

All commands will use friendly names in output.

Audit Log Inspection

Trade execution is fully logged to ~/.openclaw/logs/trades.jsonl:

tail -20 ~/.openclaw/logs/trades.jsonl | python -m json.tool

Parse to monitor trade velocity, P&L, and blocked trades.

Dry-Run Scanning

To scan without placing orders:

python kalshi_commands.py scan
# Review output; do NOT call execute

OpenClaw Ecosystem Integration

The Kalshi Command Center is your execution layer in the Prediction Market Trading Stack.

Connected Skill	How It Connects
Kalshalyst	Feeds edge opportunities → execute trades via `execute` command
Market Morning Brief	Reads your portfolio for the daily P&L digest
Portfolio Drift Monitor	Monitors positions you open through this command center
Prediction Market Arbiter	Flags cross-platform divergences → trade on the Kalshi side here

Install the complete stack:

clawhub install kalshalyst kalshi-command-center polymarket-command-center prediction-market-arbiter xpulse portfolio-drift-monitor market-morning-brief personality-engine

Agent Bug-Fix Protocol

CRITICAL: When you (the agent) discover and fix a bug in any script during a conversation, you MUST write the fix to the source file on disk using file editing tools. Showing the fix in chat is NOT sufficient — the next scheduled run starts a fresh session and will not have your conversational fix.

Checklist after finding a bug:

Edit the actual .py file on disk (e.g., ~/skills/kalshi-command-center/scripts/kalshi_commands.py)
Also update the installed copy at ~/.openclaw/skills/kalshi-command-center/scripts/kalshi_commands.py
Confirm both files are written before telling the user the fix is done
If the fix is significant, stage a git commit in ~/skills/

Never say "fixed" if you only demonstrated the fix in conversation output.

Attribution

Author: KingMadeLLC Version: 1.0.0

Feedback & Issues

Found a bug? Have a feature request? Want to share results?

GitHub Issues: github.com/kingmadellc/openclaw-prediction-stack/issues
X/Twitter: @KingMadeLLC

Part of the OpenClaw Prediction Stack — the first prediction market skill suite on ClawHub.

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/kalshi-command-center/SKILL.md

View on GitHub ↗

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

Illustrative Want to see what leoyeai/Kalshi Command Center 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

Kalshi Command Center

Overview

Available Commands

Portfolio & Positions

Live Market Scanning

Market Data Queries

Cached Opportunities

Order Management

Trade Execution

Brier Score Calibration

Prerequisites

System Requirements

API SDK

Authentication & Configuration

Option 1: Environment Variables

Option 2: Config File (~/.openclaw/config.yaml)

Optional: Kelly Position Sizing & Risk Validation

Market Filtering

Blocked Categories

Sports Filter

Time Window

Risk Limits

Heuristic Edge Scoring

1. Spread Tightness (25% weight)

2. Distance from Extremes (35% weight)

3. Liquidity (25% weight)

4. Time Value (15% weight)

Composite Score

Output Formatting

Error Handling & Retry Logic

Usage Examples

Daily Portfolio Check

Find New Edge Right Now

Check Before Buying

Execute from Research Cache

Monitor Orders

Exit a Position

File Structure

Implementation Reference

Troubleshooting

"Kalshi is not enabled"

"Kalshi key_id not configured"

"Kalshi private key not found"

"Auth failed — API key may be expired"

"Can't reach Kalshi API — network timeout"

"Kalshi rate limited — too many requests"

No markets after filtering

Advanced Usage

Custom Ticker Names

Audit Log Inspection

Dry-Run Scanning

OpenClaw Ecosystem Integration

Agent Bug-Fix Protocol

Attribution

Feedback & Issues

SkillSafety

Source

Related skills

More in the registry

Option 2: Config File (`~/.openclaw/config.yaml`)