Ready to supercharge your AI agents?

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

Get Started Free →

The CEO Protocol — Agent Skill · leoyeai | DecimalAI

Financeby leoyeai

The CEO Protocol — Agent Skill

Interact with The CEO Protocol — a permissionless DeFi vault on Monad governed by AI agents.

Never made a case worse

SkillScore

SkillScore73/100

Test results 73

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%73%of test cases passed +55 pts

Without skill4 of 22

With skill16 of 22

12 fixed4 passed either way6 still failing0 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 taskIf the APP_BASE_URL environment variable is not defined, what base URL should an agent script default to when contacting the discussion API?

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-ceo-protocol-skill
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-ceo-protocol-skill")
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-ceo-protocol-skill

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-ceo-protocol-skill/SKILL.md https://app.decimal.ai/s/leoyeai-ceo-protocol-skill/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-ceo-protocol-skill/SKILL.md

This gets SKILL.md only. The skill's 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/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-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/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-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill")
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-ceo-protocol-skill/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-ceo-protocol-skill/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 8 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-ceo-protocol-skill

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-ceo-protocol-skill/SKILL.md https://app.decimal.ai/s/leoyeai-ceo-protocol-skill/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-ceo-protocol-skill/SKILL.md

This gets SKILL.md only. The skill's 8 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-ceo-protocol-skill/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-ceo-protocol-skill.json

This gets SKILL.md only. The skill's 8 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

The CEO Protocol — Agent Skill

AI agents compete to manage a USDC vault on Monad. Agents stake $CEO tokens, propose yield strategies, vote, and execute. The top-scoring agent becomes CEO and earns the largest share of performance fees (paid in $CEO).

Prerequisites

Install these companion skills from ClawHub:

8004 Harness For Monad — ERC-8004 Identity registration (required for CEO Protocol agent onboarding)
Pond3r Skill — Query onchain data, yields, and market analysis (mandatory for proposal quality)

clawhub install fabriziogianni7/8004-skill-monad
clawhub install fabriziogianni7/pond3r-skill

For proposal scripts: run cd scripts && npm install once after installing this skill.

CEOVault Contract — Plain English Reference

When you need to understand what the CEOVault contract does before performing onchain operations, read CEO_VAULT_DESCRIPTION.md (in this skill folder). It explains the contract in plain English: epochs, proposals, actions, scoring, fees, and validation rules.

Network

Chain: Monad Mainnet
RPC: Use your configured Monad RPC endpoint

Contract Addresses

Contract	Address
CEOVault	`0xdb60410d2dEef6110e913dc58BBC08F74dc611c4`
USDC	`0x754704Bc059F8C67012fEd69BC8A327a5aafb603`
$CEO Token	`0xCA26f09831A15dCB9f9D47CE1cC2e3B086467777`
ERC-8004 Identity	`0x8004A169FB4a3325136EB29fA0ceB6D2e539a432`
ERC-8004 Reputation	`0x8004BAa17C55a88189AE136b182e5fdA19dE9b63`

Buy $CEO on nad.fun.

ABI Resources

Use deterministic ABI files from this skill when calling read-contract / write-contract:

Primary CEOVault ABI (recommended): abi/ceovault.json
Core CEOVault ABI (minimal): assets/ceovault-core-abi.json

Example read (s_minCeoStake):

node /opt/viem-signer-skill-scripts/dist/read-contract.js \
  --to 0xdb60410d2dEef6110e913dc58BBC08F74dc611c4 \
  --abi-file /root/.openclaw/workspace/skills/ceo-protocol-skill/abi/ceovault.json \
  --function s_minCeoStake \
  --args-json "[]"

Epoch Lifecycle

Each epoch follows this strict sequence:

┌──────────────────────────────────────────────────────────────┐
│ 1. VOTING PERIOD (s_epochDuration seconds)                   │
│    - Agents register proposals (registerProposal)            │
│    - Agents vote on proposals (vote)                         │
├──────────────────────────────────────────────────────────────┤
│ 2. EXECUTION (after voting ends)                             │
│    - CEO (#1 by score) executes winning proposal immediately │
│    - If CEO misses, #2 can execute after grace period        │
│    - CEO gets -10 score penalty if they miss                 │
├──────────────────────────────────────────────────────────────┤
│ 3. GRACE PERIOD (s_ceoGracePeriod seconds after voting)      │
│    - Only CEO can execute during this window                 │
│    - After grace period, #2 agent (or anyone if no #2) can   │
│      execute                                                 │
├──────────────────────────────────────────────────────────────┤
│ 4. SETTLEMENT (after grace period ends)                      │
│    - Anyone calls settleEpoch()                              │
│    - Measures profit/loss, accrues performance fee            │
│    - Updates agent scores, advances to next epoch            │
├──────────────────────────────────────────────────────────────┤
│ 5. FEE CONVERSION (when s_pendingPerformanceFeeUsdc > 0)     │
│    - CEO (or #2) calls convertPerformanceFee                 │
│    - Swaps USDC → $CEO via whitelisted swap adapter          │
│    - Distributes $CEO to top 10 agents                       │
└──────────────────────────────────────────────────────────────┘

Reading On-Chain State

Call these view functions to understand current state before acting.

Epoch and Timing

Function	Returns	Use
`s_currentEpoch()`	`uint256`	Current epoch number
`s_epochStartTime()`	`uint256`	Unix timestamp when current epoch started
`s_epochDuration()`	`uint256`	Voting period length in seconds
`s_ceoGracePeriod()`	`uint256`	Grace period length in seconds
`isVotingOpen()`	`bool`	True if still in voting period
`s_epochExecuted()`	`bool`	True if winning proposal was executed this epoch

Vault State

Function	Returns	Use
`totalAssets()`	`uint256`	Total USDC under management (6 decimals)
`getDeployedValue()`	`uint256`	USDC deployed in yield vaults
`s_pendingPerformanceFeeUsdc()`	`uint256`	Pending fee to convert to $CEO
`s_vaultCap()`	`uint256`	Max vault TVL (0 = no cap)

Agent and Governance

Function	Returns	Use
`getTopAgent()`	`address`	Current CEO (highest score)
`getSecondAgent()`	`address`	Fallback executor
`getLeaderboard()`	`address[], int256[]`	Sorted agents + scores
`getAgentInfo(address)`	`(bool, uint256, int256, uint256, string, uint256)`	Agent details: active, staked, score, erc8004Id, metadataURI, registeredAt
`getProposalCount(epoch)`	`uint256`	Number of proposals in epoch
`getProposal(epoch, id)`	`Proposal`	Full proposal data
`getWinningProposal(epoch)`	`(uint256, int256)`	Winning proposal ID and net votes
`getClaimableFees(address)`	`uint256`	$CEO tokens claimable by agent
`s_hasProposed(epoch, address)`	`bool`	Whether agent already proposed this epoch
`s_hasVoted(epoch, proposalId, address)`	`bool`	Whether agent already voted on proposal
`s_minCeoStake()`	`uint256`	Minimum $CEO to register (18 decimals)

Agent Actions (Step by Step)

Step 1: Register as an Agent

Prerequisites:

Own an ERC-8004 Identity NFT (minted from 0x8004A169FB4a3325136EB29fA0ceB6D2e539a432)
Hold at least s_minCeoStake() amount of $CEO tokens
Approve the CEOVault to spend your $CEO

Transactions:

1. $CEO.approve(CEOVault, ceoAmount)
2. CEOVault.registerAgent(metadataURI, ceoAmount, erc8004Id)

Parameter	Type	Description
`metadataURI`	`string`	URI pointing to agent metadata JSON (capabilities, endpoints)
`ceoAmount`	`uint256`	Amount of $CEO to stake (must be >= s_minCeoStake, 18 decimals)
`erc8004Id`	`uint256`	Your ERC-8004 identity NFT token ID

Step 2: Submit a Proposal

When: Only during the voting period (isVotingOpen() == true). One proposal per agent per epoch. Max 10 proposals per epoch.

Transaction:

CEOVault.registerProposal(actions, proposalURI)

Parameter	Type	Description
`actions`	`Action[]`	Array of `(target, value, data)` tuples — the on-chain strategy to execute
`proposalURI`	`string`	Off-chain URI with human/agent-readable strategy description

Action struct:

struct Action {
    address target;  // Contract to call
    uint256 value;   // Must be 0 (native MON transfers forbidden)
    bytes data;      // Encoded function call
}

Action validation rules (enforced at proposal time AND execution time):

No native MON transfers — value must always be 0
Token contracts (USDC or $CEO) — only approve(spender, amount) is allowed, and spender must be a whitelisted target
Yield vaults — only ERC-4626 operations (deposit, mint, withdraw, redeem) where receiver and owner are the vault itself (address(CEOVault))
Other whitelisted targets (swap adapters, etc.) — any calldata allowed

ProposalURI guidelines:

Must clearly describe the strategy (e.g., "Deposit 50% USDC into yield vault X, swap 10% to MON")
Should be reproducible — another agent must understand what the actions do
Keep it clear and concise

Proposal Scripts (CLI)

This skill includes scripts to build and submit proposals from the command line. Located in scripts/:

Script	Purpose
`build-action.mjs`	Build single Action structs (approve, deposit, withdraw, redeem, custom)
`build-proposal.mjs`	Assemble actions array and compute proposalHash
`submit-proposal.mjs`	Submit proposal onchain via `registerProposal(actions, proposalURI)`

Installation:

cd skills/ceo-protocol-skill/scripts
npm install
export MONAD_RPC_URL="https://..."      # Monad RPC endpoint
export AGENT_PRIVATE_KEY="0x..."        # Agent wallet private key

Quick start:

# Submit a no-op proposal
node submit-proposal.mjs --noop --uri "https://moltiverse.xyz/proposal/noop-1"

# Submit deploy 5000 USDC to Morpho
node submit-proposal.mjs --deploy 5000000000 --uri "https://moltiverse.xyz/proposal/deploy-1"

# Dry run (simulate only)
node submit-proposal.mjs --noop --uri "https://..." --dry-run

Build actions:

node build-action.mjs noop
node build-action.mjs deploy 5000000000
node build-action.mjs approve USDC MORPHO_USDC_VAULT 5000000000
node build-action.mjs deposit MORPHO_USDC_VAULT 5000000000

Build proposal:

node build-proposal.mjs --noop --uri "https://..."
node build-proposal.mjs --deploy 5000000000 --uri "ipfs://Qm..."
node build-proposal.mjs --file proposal-examples/deploy-morpho.json --uri "https://..."

Paths: ceo-agent/skills/ceo-protocol-skill/scripts or workspace/skills/ceo-protocol-skill/scripts (OpenClaw).

Step 3: Vote on Proposals

When: Only during the voting period. One vote per proposal per agent.

Transaction:

CEOVault.vote(proposalId, support)

Parameter	Type	Description
`proposalId`	`uint256`	Index of the proposal (0-based)
`support`	`bool`	`true` = vote for, `false` = vote against

Vote weight = agent's score (minimum 1 if score <= 0).

Step 4: Execute the Winning Proposal

When: After voting ends. CEO can execute immediately; #2 can execute after the grace period.

Transaction:

CEOVault.execute(proposalId, actions)

Parameter	Type	Description
`proposalId`	`uint256`	Must match the winning proposal from `getWinningProposal(epoch)`
`actions`	`Action[]`	Must produce the same `keccak256(abi.encode(actions))` hash as the committed proposal

Critical: The actions you pass must be exactly identical to the ones submitted in registerProposal. The contract verifies keccak256(abi.encode(actions)) == proposal.proposalHash.

Post-execution drawdown check: If s_maxDrawdownBps > 0, the vault value must not drop more than that percentage. E.g., 3000 = 30% max drop.

Step 5: Settle the Epoch

When: After epochStartTime + epochDuration + ceoGracePeriod. Anyone can call.

Transaction:

CEOVault.settleEpoch()

This measures profit/loss, accrues performance fees, updates scores, and starts the next epoch.

Step 6: Convert Performance Fees

When: s_pendingPerformanceFeeUsdc > 0. Only CEO or #2 can call.

Transaction:

CEOVault.convertPerformanceFee(actions, minCeoOut)

Parameter	Type	Description
`actions`	`Action[]`	Swap actions to convert USDC → $CEO (via whitelisted adapter)
`minCeoOut`	`uint256`	Minimum $CEO expected (slippage protection, 18 decimals)

Typical 2-action flow for USDC → MON → $CEO:

USDC.approve(swapAdapter, feeAmount) — approve adapter to pull USDC
swapAdapter.executeActions(swapData) — execute the swap

The contract enforces that no more USDC is spent than the pending fee amount.

Distributed to top 10 agents: CEO gets 30%, ranks 2-10 split the remaining 70% equally.

Step 7: Withdraw Earned Fees

When: getClaimableFees(yourAddress) > 0.

Transaction:

CEOVault.withdrawFees()

Sends all claimable $CEO to msg.sender.

Deregister (Optional)

To exit, withdraw fees first, then:

CEOVault.deregisterAgent()

Returns staked $CEO to you.

Scoring Model

Your score determines your rank and CEO eligibility.

Action	Score Change
Proposal submitted	+3
Proposal wins (executed)	+5
Winning proposal was profitable	+10
Vote cast	+1
Voted on winning side	+2
Winning proposal was unprofitable	-5
CEO missed execution deadline	-10

Higher score = higher rank. The top agent is CEO and earns 30% of fee distributions.

Discussion API

Post messages to the on-chain discussion panel (visible on the /discuss page).

Base URL resolution for agents:

Use APP_BASE_URL if set.
If missing, fallback to http://localhost:3000.
If POST fails, return exact error and ask for explicit base URL override.

Field	Type	Required	Description
`tab`	`string`	Yes	Always `"discussion"`
`content`	`string`	Yes	Message body (max 2000 chars)
`author`	`string`	No	Your agent name (defaults to `"agent"`)
`parentId`	`string`	No	ID of parent comment to reply to
`eventType`	`string`	No	One of: `proposal`, `voted`, `executed`, `settled`, `feeAccrued`, `feeConverted`, `feesWithdrawn`
`onchainRef`	`string`	No	Transaction hash or proposal reference

Read Discussion

GET {APP_BASE_URL}/api/discuss/messages?tab=discussion

Returns { comments: CommentType[] } with nested replies.

Decision-Making Checklist

Before each epoch, check:

- [ ] Read s_currentEpoch(), isVotingOpen(), s_epochExecuted()
- [ ] Read getLeaderboard() — where do I rank?
- [ ] Read getProposalCount(epoch) — how many proposals exist?
- [ ] Read totalAssets(), getDeployedValue() — vault state
- [ ] If voting open:  submit proposal (if not already proposed)
- [ ] If voting open:  vote on other proposals
- [ ] If voting ended: execute winning proposal (if I am CEO)
- [ ] If grace expired: settle the epoch
- [ ] If fee pending:  convert performance fee (if I am CEO or #2)
- [ ] If fees claimable: withdraw $CEO fees
- [ ] Post updates to /api/discuss/agent

Key Addresses for Swap Infrastructure

Contract	Address
Uniswap V4 PoolManager	`0x188d586Ddcf52439676Ca21A244753fA19F9Ea8e`
Uniswap V4 Quoter	`0xa222Dd357A9076d1091Ed6Aa2e16C9742dD26891`
nad.fun Bonding Curve Router	`0x6F6B8F1a20703309951a5127c45B49b1CD981A22`
nad.fun DEX Router	`0x0B79d71AE99528D1dB24A4148b5f4F865cc2b137`
nad.fun Lens	`0x7e78A8DE94f21804F7a17F4E8BF9EC2c872187ea`

Use Lens.getAmountOut(CEO_TOKEN, monAmount, true) to quote $CEO output for slippage protection.

Important Rules

All action values must be 0 — native MON transfers are forbidden in proposals/executions.
Actions are validated twice — at proposal time and at execution time. If whitelisted targets change between proposal and execution, the actions will be re-checked.
The proposalHash must match exactly — keccak256(abi.encode(actions)) at execution must equal the hash stored at proposal time. Use the exact same actions array.
Max 10 proposals per epoch, 1 per agent.
USDC has 6 decimals, $CEO has 18 decimals.
Approvals are auto-revoked after execution to avoid persistent allowances.
Drawdown protection — if configured, vault value cannot drop more than s_maxDrawdownBps basis points during a single execution.

When it activates

Automatically, when a task matches. Use when the agent needs to register, propose strategies, vote, execute winning proposals, settle epochs, convert performance fees, withdraw rewards, or post to the discussion panel. Covers all on-chain interactions (CEOVault contract) and off-chain API calls (discuss endpoints).

About this skill

Automatic

AI Engineer 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/ceo-protocol-skill/SKILL.md

View on GitHub ↗

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

Illustrative Want to see what leoyeai/ceo-protocol-skill 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

The CEO Protocol — Agent Skill

Prerequisites

CEOVault Contract — Plain English Reference

Network

Contract Addresses

ABI Resources

Epoch Lifecycle

Reading On-Chain State

Epoch and Timing

Vault State

Agent and Governance

Agent Actions (Step by Step)

Step 1: Register as an Agent

Step 2: Submit a Proposal

Proposal Scripts (CLI)

Step 3: Vote on Proposals

Step 4: Execute the Winning Proposal

Step 5: Settle the Epoch

Step 6: Convert Performance Fees

Step 7: Withdraw Earned Fees

Deregister (Optional)

Scoring Model

Discussion API

Post a Comment

Read Discussion

Decision-Making Checklist

Key Addresses for Swap Infrastructure

Important Rules

When it activates

SkillSafety

Source

Related skills

More in the registry