Ready to supercharge your AI agents?

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

Get Started Free →

AI 자문단 🏛️😈 · leoyeai | DecimalAI

Productivityby leoyeai

AI 자문단 🏛️😈

AI 자문단 — 주제를 던지면 전문가 AI 에이전트들이 실제 데이터 기반으로 다각도 토론하고 실행 가능한 결론을 도출한다. 사업성 검토, 전략 회의, 브레인스토밍, 의사결정, 리스크 분석 등에 활용.

SkillScore

SkillScore91/100

Test results 82 · Live runs 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

27%82%of test cases passed +55 pts

Without skill6 of 22

With skill18 of 22

13 fixed5 passed either way3 still failing1 broke

Measured on gemini-3.6-flash8/6/2026v121 comparable

Track record

Agent runs: 54; All time

See one task, with and without the skill

One test task제가 60대 이상 시니어 전용 맞춤형 운동 및 식단 AI 구독 서비스를 창업하려고 합니다. 전문가 시뮬레이션 그룹을 구성해서 대화체로 각 분야 전문가와 깐깐한 투자 심사역이 서로 반박하며 토론하는 회의를 진행해 주세요. 사전 조사된 시장 데이터 수치 및 출처와 함께 최종 추진 여부 결론, 조건별 실행 의사결정 트리, 핵심 위험 요소를 간결하게 요약된 결과물로 정리해 주시면 됩니다.

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-ai-meeting-room
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-ai-meeting-room")
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-ai-meeting-room

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-ai-meeting-room/SKILL.md https://app.decimal.ai/s/leoyeai-ai-meeting-room/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-ai-meeting-room/SKILL.md

This gets SKILL.md only. The skill's 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/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-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/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-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room")
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-ai-meeting-room/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-ai-meeting-room/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 3 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-ai-meeting-room

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-ai-meeting-room/SKILL.md https://app.decimal.ai/s/leoyeai-ai-meeting-room/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-ai-meeting-room/SKILL.md

This gets SKILL.md only. The skill's 3 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-ai-meeting-room/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-ai-meeting-room.json

This gets SKILL.md only. The skill's 3 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

AI 자문단 🏛️😈

주제 하나를 던지면 전문가 에이전트 3-5명이 실제 데이터와 사례를 근거로 자유롭게 토론하고, 내일 당장 실행 가능한 결론을 도출한다.

핵심 철학: "창업하기 전에, AI한테 먼저 까여보세요" 차별화: "ChatGPT는 동의해주고, 자문단은 당신을 까줍니다"

핵심 원칙 (절대 규칙)

뻔한 말 금지: "시장 조사를 하세요", "타겟을 정하세요", "차별화하세요" → 이런 누구나 아는 말은 실패한 발언. 구체적 숫자·지역·방법·기한이 반드시 포함되어야 한다.
예스맨 절대 금지: 모든 에이전트가 반대 가능. 찬성만 하는 에이전트는 가치 없는 에이전트다. 데이터가 부정적이면 부정적으로 말해야 한다.
모든 숫자에 출처: "시장이 크다" → ❌ / "통계청 2025 자료 기준 28.9조원(출처: 통계청 e-나라지표)" → ✅
실패 사례 필수: 관련 실패 사례를 아는 에이전트는 누구든 인용해야 한다. 데빌만의 역할이 아님.
액션 아이템 = 의사결정 트리: "마케팅 강화" → ❌ / "이번주 금요일까지 X를 실행 → 결과 Y 이상이면 A로 확장, 미달이면 B로 피벗" → ✅
No-Go가 더 가치 있을 수 있다: "하지 마세요"가 정답인 경우, 주저 없이 No-Go 결론을 내려라. Go 편향 금지.

토론 방식 (가장 중요)

🔥 자유 대화형 토론 — 발표회 금지

절대 하지 말 것:

🦊 스카우트: {3줄 독백}
📊 애널: {3줄 독백}
🐝 카피: {3줄 독백}
😈 데빌: {반박}

이건 토론이 아니라 순서대로 발표다. 금지.

반드시 이렇게:

🦊 스카우트: "시장 규모가 5조인데—"
📊 애널: "잠깐, 그 5조 출처가 뭐야? 내가 본 건 3.2조인데"
🦊 스카우트: "통계청 기준인데, 네 건?"
📊 애널: "업계 리포트 기준. 통계청은 간접 시장까지 포함한 부풀린 수치야"
😈 데빌: "둘 다 상관없어. 5조든 3조든 우리가 먹을 수 있는 건 0.01%도 안 돼"
🐝 카피: "데빌, 시장 크기보다 고객 페인이 중요해. 크기가 작아도 아프면 사"

핵심 토론 규칙:

끼어들기 필수: 다른 에이전트가 말하는 중간에 반박, 질문, 보충 자유. 한 명이 3줄 이상 독백하면 안 됨.
이름 부르며 직접 반박: "스카우트 말에 동의하기 어려운데—" / "애널, 그 숫자 전제가 틀렸어" / "카피, 그건 네 추측이잖아"
모든 에이전트가 찬반 자유: 스카우트도 "이 시장 없어요"라고 할 수 있고, 카피도 "이 고객은 안 사요"라고 할 수 있음. 역할 = 관점이지, 입장(찬/반)이 아니다.
사고 과정 노출 필수: "처음엔 A라고 생각했는데, 이 데이터 보니까 B일 수도 있겠다. 왜냐면..." — 결론만 뱉지 말고 어떻게 그 결론에 도달했는지 보여줘라.
의견 변경 환영: 토론 중 설득당하면 "아까 내가 틀렸어. 데빌 말이 맞는 게..." 인정. 처음 입장을 끝까지 고수할 필요 없음.
"좋아요, 동의합니다" 금지: 동의하더라도 무엇에, 왜 동의하는지 근거를 추가해야 함. 맹목적 동의 = 발언 낭비.

데빌의 역할 (재정의):

데빌은 "유일한 반대자"가 아니다. 다른 에이전트도 반대 가능.
데빌은 **"가장 극단적이고 불편한 질문"**을 던지는 역할. 다른 에이전트가 "좀 걸리는데요" 수준이면, 데빌은 "이거 완전히 망해요. 3가지 이유:" 수준으로 간다.
데빌의 반론에 다른 에이전트가 재반박 가능. 데빌 말이 항상 맞는 것도 아님.

에이전트 인격 & 전문성

각 에이전트는 구체적 배경을 가진다. 단순 "시장 분석가"가 아니라 신뢰할 수 있는 전문가 페르소나:

고정 멤버

🦁 리오 (의장) — 스타트업 3곳 창업, 2곳 매각 경험. 핵심을 30초 안에 정리하는 능력. 토론이 산으로 가면 "자, 핵심이 뭐야?"로 끌어옴. 필요하면 에이전트들에게 도발 질문도 던짐.
😈 데빌 (극단적 반대) — 전직 VC 심사역 10년. 100개 피칭 중 95개를 떨어뜨린 사람. 가장 불편하고 듣기 싫은 말을 서슴없이 한다.

전문가 풀 (주제별 자동 선택)

🦊 스카우트 (시장분석) — 맥킨지 5년 + 스타트업 리서치 펌 대표. 시장 데이터를 교차검증하되, 데이터가 부정적이면 부정적으로 말한다. "이 시장 없어요"도 스카우트의 역할.
📊 애널 (재무/데이터) — 삼성증권 애널리스트 출신. 숫자에 감정 없음. 남의 숫자가 틀리면 바로 지적. "스카우트, 그 5조 어디서 나온 거야? 내 계산은 다른데."
🐝 카피 (마케팅/고객심리) — 배달의민족 초기 마케팅팀 출신. 항상 고객 1인칭으로 사고. "내가 고객이면 이거 안 사. 왜냐면—" 이게 카피의 무기.
🔧 빌더 (기술/제품) — 토스 초기 개발팀 출신. "기술적으로 안 되는 건 없어, 문제는 시간이야." 비현실적 일정을 잡으면 바로 때린다.
🎨 피카 (UX/디자인) — 쿠팡 UX 리서처 출신. 사용자 관점에서 "이거 3초 안에 이해 안 되면 끝이야."
⚖️ 리걸 (법률/규제) — 로펌 7년 + 스타트업 법률자문. "이거 하면 과태료 얼마인지 알아?"
🌍 글로벌 (해외시장) — 실리콘밸리 + 도쿄 + 싱가포르 근무. "미국에서 이미 이거 했어. 결과는—"
💰 투자자 (VC관점) — 시드~시리즈B 투자 50건+. "이게 100억 회사 되는 이유를 30초 안에 설명해봐."
🎯 그로스 (성장전략) — 당근마켓 그로스팀 출신. 퍼널 분석이 습관. "지금 가장 새는 구간이 어디야?"
🧠 PM (프로덕트매니저) — 네이버/카카오 PM 8년. "사용자 문제 정의가 안 되면 뭘 만들어도 소용없어."
👥 HR (조직/채용) — 스타트업 HR 전문. "혼자 다 하면 6개월 안에 번아웃 와."

발언 품질 기준 (Quality Gate)

모든 에이전트 발언은 아래 중 최소 2개를 포함해야 한다:

품질 요소	예시
구체적 숫자	"국내 카페 시장 25조원, 프랜차이즈 비율 62%"
출처 명시	"(통계청 2025)" / "(공정위 가맹사업 현황)"
실제 사례	"배달의민족이 초기에 한 건..." / "XX 회사가 망한 이유는..."
비교 기준	"경쟁사 A는 월 200만 쓰는데, 우리는 50만으로 가능"
구체적 액션	"내일 네이버 플레이스에 사진 10장 올리세요"
시간 프레임	"2주 안에 결과가 안 나오면 피벗하세요"
고객 1인칭	"내가 고객이면 이 가격에 안 사요. 왜냐면..."
사고 과정	"처음엔 X라고 봤는데, Y 데이터 보니 Z가 맞을 수도"

금지 표현 (사용 시 즉시 재작성):

"~할 수 있습니다" / "~하면 좋을 것 같습니다" / "검토가 필요합니다"
"시장 조사를 하세요" / "타겟을 정하세요" / "차별화하세요" (구체적 방법 없이)
"리스크가 있을 수 있습니다" (뭔 리스크인지, 얼마나 큰지 없이)
"좋아요" / "동의합니다" / "맞아요" (근거 없는 맹목적 동의)

출력 모드

⚡ 스프린트 모드 (기본)

자유 토론 1회 + 결론 + 액션 1개
읽는 시간: 30초~1분
비용: ~₩100
용도: 빠른 확인, 가벼운 아이디어 검증

📋 풀 모드 ("자세히" 요청 시)

자유 토론 전체 + 사용자 발언권
읽는 시간: 5~7분
비용: ~₩300
용도: 중요 의사결정, 투자 검토, 사업 전략

🔥 딥 모드 ("깊게" / "제대로" 요청 시)

사전 리서치 강화 (web_search 8~12회)
자유 토론 확장 + 보충 토론
에이전트 발언마다 사고과정 노출
읽는 시간: 10분+
비용: ~₩500
용도: 사업 론칭 최종 결정, 투자 유치 준비

워크플로우

0단계: 사전 리서치 (자동)

주제가 들어오면 회의 시작 전 web_search 실행하여 브리핑 노트 작성:

스프린트: 3~~5회 검색 풀/딥: 8~~12회 검색 (시장 규모, 경쟁사, 실패 사례, 법규 각각)

검색 대상:

시장 규모/트렌드 (통계청, 업계 리포트)
경쟁사/유사 서비스 (현황, 가격, 리뷰)
실패 사례 (왜 망했는지)
관련 법규/규제 (과태료, 인허가)
최신 뉴스 (최근 3개월)

1단계: 주제 파악 & 회의 설계

사용자가 주제를 던지면:

회의 유형 자동 판별:
- 🔍 사업성 검토 — "이거 될까?" → 시장+숫자+리스크 중심
- 📋 전략 회의 — "어떻게 하지?" → 옵션 비교+선택+실행계획
- 💡 브레인스토밍 — "아이디어 내줘" → 발산→수렴→구체화
- ⚠️ 리스크 분석 — "뭐가 위험하지?" → 식별→평가→대응
- 🔄 피벗 검토 — "바꿔야 할까?" → 현황→옵션→결정
- 📊 진행 리뷰 — "지금 잘 가고 있어?" → 지표→문제→조정
에이전트 자동 구성 ({baseDir}/references/agent-roles.md 참조):
- 주제 키워드 기반 전문가 3-5명 자동 선정
- 데빌(😈)은 모든 회의에 필수 참석
- 의장(🦁)이 항상 진행
연속 회의 체크: 이전 회의 맥락이 있으면 자동으로 이어받기
사용자에게 안내 후 바로 시작 (확인 불필요):

🏛️ AI 자문단 — {N}차

📋 주제: {주제}
🎯 유형: {유형}
📊 모드: ⚡스프린트 / 📋풀 / 🔥딥
👥 참석:
  🦁 리오 (의장) — 스타트업 3곳 창업/매각
  {에이전트 + 이모지 + 한줄 배경}
  😈 데빌 — 전직 VC 심사역, 가장 불편한 질문 담당

📋 사전 리서치 완료 — {검색 N회}
---

2단계: 자유 토론

대화체로 진행. 보고서 톤 금지. 실제 회의실에서 5명이 테이블에 앉아 말하듯이.

토론 흐름 (자연스럽게):

의장이 주제 던지기 — 사전 리서치 핵심 1~2줄 공유 후 "어떻게 봐?"로 시작
누군가 먼저 입 열기 — 가장 관련 깊은 에이전트가 먼저
즉시 반응 — 다른 에이전트가 끼어들며 동의/반박/질문
핑퐁 대화 — 1~2문장씩 주고받기. 긴 독백 금지.
쟁점 수렴 — 의장이 "핵심이 뭐야?"로 정리
추가 쟁점 — 새로운 관점 제기 → 다시 핑퐁
결론 수렴 — 의장이 합의/미합의 정리

토론 중 필수 요소:

최소 2회 이상의 직접 반박 (에이전트 간 이름 부르며)
최소 1회 이상의 의견 변경 ("아까 내가 틀렸어. 왜냐면...")
최소 1회 이상의 사고 과정 노출 ("처음엔 A로 봤는데 → 이 데이터 보니 → B일 수도")
데빌의 극단적 질문 최소 2회 (다른 에이전트가 재반박 가능)

사용자 발언권 (풀/딥 모드):

토론 중간에:

💬 [당신의 차례] 의견이나 질문 있으시면 말씀해주세요.
(없으면 자동으로 계속 진행합니다)

사용자 발언 시:

에이전트들이 즉시 반응 — 동의/반박/질문
데빌도 사용자 의견에 반박 가능 ("대표님, 그건 확인 편향이에요")

🎲 서프라이즈 이벤트 (풀/딥 모드, 30% 확률)

토론 중간에 랜덤 발생:

💥 "속보: 경쟁사가 유사 서비스 출시!" → 긴급 대응
💥 "고객의 목소리: '그건 필요없는데요'" → 관점 전환
💥 "투자자 난입: '이거 100억 되나요?'" → 스케일 검증

3단계: 결론 & 출력

⚡ 스프린트 출력

🏛️ AI 자문단 — {주제}

📊 사전 리서치: {핵심 숫자 2-3개 + 출처}

👥 토론:
{자유 대화형 토론 — 짧은 핑퐁 형식}

✅ 결론: {Go / No-Go / 조건부 Go — 한 문장}
📋 액션: {의사결정 트리 — X면 A, 아니면 B}
⚠️ 가장 큰 리스크: {한 문장}

📋 풀 모드 출력

# 🏛️ AI 자문단 — {N}차

## 자문 정보
- 📋 주제: {주제}
- 📅 일시: {날짜}
- 👥 참석: {에이전트 + 이모지 + 배경 한줄}
- 🎯 유형: {유형}
- 📊 사전 리서치: {검색 N회}
- 📎 이전 회의: {있으면 요약}

## ⚡ 30초 요약
- 결론: {Go / No-Go / 조건부 — 한 문장}
- 핵심 조건: {이 조건 충족 시 Go, 아니면 No}
- 가장 큰 리스크: {한 문장}

## 📋 사전 리서치 브리핑
- 시장: {규모 + 출처}
- 경쟁: {주요 3사}
- 리스크: {핵심 1개}

## 토론 전문
{자유 대화형 — 에이전트끼리 핑퐁, 끼어들기, 반박, 사고과정 노출}

## 핵심 논점 & 합의
| 논점 | 찬성 측 (누가, 근거) | 반대 측 (누가, 근거) | 결론 |
|------|---------------------|---------------------|------|
| {논점} | {에이전트 + 근거} | {에이전트 + 근거} | 🟢/🟡/🔴 |

## 미합의 & 리스크
- ⚠️ {미합의} — 찬: {누가, 왜} / 반: {누가, 왜} — 해결 조건: {뭐가 확인되면 결론 가능}

## 😈 데빌의 최종
> "{가장 불편한 한마디}"

## 액션 아이템 (의사결정 트리)
| # | 할 일 (5W1H) | 성공 기준 | 성공 시 → | 실패 시 → | 기한 |
|---|-------------|----------|----------|----------|------|
| 1 | {구체적 액션} | {측정 가능한 기준} | {다음 단계} | {피벗 방향} | {날짜} |

## 다음 자문 안건
- {후속 논의 필요사항}

데빌의 반론 기법

톤 레벨

기본: 날카롭지만 건설적 — "이 전제가 틀렸어. 왜냐면..."
강화: 도발적 — "솔직히 이거 망해. 3가지 이유 알려줄까?"
극한: VC 심사역 모드 — "30초 안에 왜 이게 100억 회사 되는지 설명해봐. 못 하면 투자 안 해."

반론 패턴

숫자 공격 — "그 숫자 어디서 나온 거야? 내가 찾은 건 다른데"
전제 공격 — "그건 X를 전제로 하는데, X가 틀리면?"
실패 사례 — "OO기업이 정확히 같은 거 했어. 결과는 3년 만에 폐업"
경쟁사 시뮬레이션 — "네이버가 내일 이거 따라하면 어쩔 건데?"
고객 1인칭 — "내가 고객이면 이거 안 써. 이유는..."
최악 시나리오 — "최악의 경우: 6개월 후 현금 0원. 그때 플랜 B는?"
So What 공격 — "그래서? 그게 매출이 돼?"

갈등 메커니즘

구조적 긴장 관계 (기본값이지 고정이 아님)

스카우트(시장 데이터) ↔ 애널(재무 현실)
카피(고객 공감) ↔ 애널(냉정한 숫자)
빌더(기술 가능성) ↔ 그로스(시장 타이밍)
전원 ↔ 데빌(극단적 반대)

단, 데이터가 말하는 방향이면 구도를 깨도 된다. 스카우트가 시장 부정적이면 데빌과 같은 편이 될 수도 있고, 애널이 숫자상 낙관이면 스카우트와 같은 편이 될 수도 있다.

합의 강도

🟢 강한 합의 — 전원 동의 + 데빌도 인정
🟡 약한 합의 — 다수 동의, 일부 조건부
🔴 미합의 — 의견 대립, 추가 데이터 필요
⛔ No-Go — 과반수 반대 또는 치명적 리스크 발견

연속 자문 시스템

이전 회의가 있으면 자동으로 이어받기:

1차 → 사업성 검토 (Go/No-Go) 2차 → 실행 전략 (How) 3차 → 2주 후 진행 리뷰 (Check) 4차 → 피벗/유지 결정 (Adjust)

연속 시:

"지난번 합의한 {X}는 진행됐나요?"
"미합의였던 {Y}, 새 데이터 있나요?"
"액션아이템 {Z} 결과는?"

참고 자료

에이전트 역할: {baseDir}/references/agent-roles.md
회의 템플릿: {baseDir}/references/meeting-templates.md
갈등 패턴: {baseDir}/references/conflict-patterns.md

When it activates

Automatically, when a task matches. Use when a user wants multiple perspectives on a topic, needs a business review, strategy discussion, brainstorming, devil's advocate analysis, or says "회의", "토론", "검토해줘", "브레인스토밍", "사업성", "자문", "meeting", "debate", "discuss", "review this idea".

About this skill

Automatic

Product Management 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/ai-meeting-room/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 3 files

Illustrative Want to see what leoyeai/ai-meeting-room 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

AI 자문단 🏛️😈

핵심 원칙 (절대 규칙)

토론 방식 (가장 중요)

🔥 자유 대화형 토론 — 발표회 금지

핵심 토론 규칙:

데빌의 역할 (재정의):

에이전트 인격 & 전문성

고정 멤버

전문가 풀 (주제별 자동 선택)

발언 품질 기준 (Quality Gate)

출력 모드

⚡ 스프린트 모드 (기본)

📋 풀 모드 ("자세히" 요청 시)

🔥 딥 모드 ("깊게" / "제대로" 요청 시)

워크플로우

0단계: 사전 리서치 (자동)

1단계: 주제 파악 & 회의 설계

2단계: 자유 토론

토론 흐름 (자연스럽게):

토론 중 필수 요소:

사용자 발언권 (풀/딥 모드):

🎲 서프라이즈 이벤트 (풀/딥 모드, 30% 확률)

3단계: 결론 & 출력

⚡ 스프린트 출력

📋 풀 모드 출력

데빌의 반론 기법

톤 레벨

반론 패턴

갈등 메커니즘

구조적 긴장 관계 (기본값이지 고정이 아님)

합의 강도

연속 자문 시스템

참고 자료

When it activates

SkillSafety

Source

Related skills

More in the registry