Ready to supercharge your AI agents?

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

Get Started Free →

Agent Council · leoyeai | DecimalAI

Agent Toolingby leoyeai

Agent Council

Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw.

Never made a case worseMaintained

SkillScore

SkillScore86/100

Test results 86

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%86%of test cases passed +55 pts

Without skill7 of 22

With skill19 of 22

12 fixed7 passed either way3 still failing0 broke

Measured on gemini-3.6-flash8/6/2026v2 · latest is v420 comparable

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhere should daily logs be stored within an agent's workspace located at `/home/user/agents/watson` for the date February 1, 2026?

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-agent-council
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-agent-council")
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-agent-council

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-agent-council/SKILL.md https://app.decimal.ai/s/leoyeai-agent-council/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/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-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/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-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council")
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-agent-council/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-agent-council/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-agent-council

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-agent-council/SKILL.md https://app.decimal.ai/s/leoyeai-agent-council/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-agent-council/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-agent-council/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-agent-council.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: v4 (v2 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

Agent Council

Complete toolkit for creating and managing autonomous AI agents with Discord integration for OpenClaw.

What This Skill Does

Agent Creation:

Creates autonomous AI agents with self-contained workspaces
Generates SOUL.md (personality & responsibilities)
Generates HEARTBEAT.md (cron execution logic)
Sets up memory system (hybrid architecture)
Configures gateway automatically
Binds agents to Discord channels (optional)
Sets up daily memory cron jobs (optional)

Discord Channel Management:

Creates Discord channels via API
Configures OpenClaw gateway allowlists
Sets channel-specific system prompts
Renames channels and updates references
Optional workspace file search

Installation

# Install from ClawHub
clawhub install agent-council

# Or manual install
cp -r . ~/.openclaw/skills/agent-council/
openclaw gateway config.patch --raw '{
  "skills": {
    "entries": {
      "agent-council": {"enabled": true}
    }
  }
}'

Part 1: Agent Creation

Quick Start

scripts/create-agent.sh \
  --name "Watson" \
  --id "watson" \
  --emoji "🔬" \
  --specialty "Research and analysis specialist" \
  --model "anthropic/claude-opus-4-5" \
  --workspace "$HOME/agents/watson" \
  --discord-channel "1234567890"

Workflow

1. Gather Requirements

Ask the user:

Agent name (e.g., "Watson")
Agent ID (lowercase, hyphenated, e.g., "watson")
Emoji (e.g., "🔬")
Specialty (what the agent does)
Model (which LLM to use)
Workspace (where to create agent files)
Discord channel ID (optional)

2. Run Creation Script

scripts/create-agent.sh \
  --name "Agent Name" \
  --id "agent-id" \
  --emoji "🤖" \
  --specialty "What this agent does" \
  --model "provider/model-name" \
  --workspace "/path/to/workspace" \
  --discord-channel "1234567890"  # Optional

The script automatically:

✅ Creates workspace with memory subdirectory
✅ Generates SOUL.md and HEARTBEAT.md
✅ Updates gateway config (preserves existing agents)
✅ Adds Discord channel binding (if specified)
✅ Restarts gateway to apply changes
✅ Prompts for daily memory cron setup

3. Customize Agent

After creation:

SOUL.md - Refine personality, responsibilities, boundaries
HEARTBEAT.md - Add periodic checks and cron logic
Workspace files - Add agent-specific configuration

Agent Architecture

Self-contained structure:

agents/
├── watson/
│   ├── SOUL.md              # Personality and responsibilities
│   ├── HEARTBEAT.md         # Cron execution logic
│   ├── memory/              # Agent-specific memory
│   │   ├── 2026-02-01.md   # Daily memory logs
│   │   └── 2026-02-02.md
│   └── .openclaw/
│       └── skills/          # Agent-specific skills (optional)

Memory system:

Agent-specific memory: <workspace>/memory/YYYY-MM-DD.md
Shared memory access: Agents can read shared workspace
Daily updates: Optional cron job for summaries

Cron jobs: If your agent needs scheduled tasks:

Create HEARTBEAT.md with execution logic
Add cron jobs with --session <agent-id>
Document in SOUL.md

Examples

Research agent:

scripts/create-agent.sh \
  --name "Watson" \
  --id "watson" \
  --emoji "🔬" \
  --specialty "Deep research and competitive analysis" \
  --model "anthropic/claude-opus-4-5" \
  --workspace "$HOME/agents/watson" \
  --discord-channel "1234567890"

Image generation agent:

scripts/create-agent.sh \
  --name "Picasso" \
  --id "picasso" \
  --emoji "🎨" \
  --specialty "Image generation and editing specialist" \
  --model "google/gemini-3-flash-preview" \
  --workspace "$HOME/agents/picasso" \
  --discord-channel "9876543210"

Health tracking agent:

scripts/create-agent.sh \
  --name "Nurse Joy" \
  --id "nurse-joy" \
  --emoji "💊" \
  --specialty "Health tracking and wellness monitoring" \
  --model "anthropic/claude-opus-4-5" \
  --workspace "$HOME/agents/nurse-joy" \
  --discord-channel "5555555555"

Part 2: Discord Channel Management

Channel Creation

Quick Start

python3 scripts/setup_channel.py \
  --name research \
  --context "Deep research and competitive analysis"

Workflow

Run setup script:

python3 scripts/setup_channel.py \
  --name <channel-name> \
  --context "<channel-purpose>" \
  [--category-id <discord-category-id>]

Apply gateway config (command shown by script):

openclaw gateway config.patch --raw '{"channels": {...}}'

Options

With category:

python3 scripts/setup_channel.py \
  --name research \
  --context "Deep research and competitive analysis" \
  --category-id "1234567890"

Use existing channel:

python3 scripts/setup_channel.py \
  --name personal-finance \
  --id 1466184336901537897 \
  --context "Personal finance management"

Channel Renaming

Quick Start

python3 scripts/rename_channel.py \
  --id 1234567890 \
  --old-name old-name \
  --new-name new-name

Workflow

Run rename script:

python3 scripts/rename_channel.py \
  --id <channel-id> \
  --old-name <old-name> \
  --new-name <new-name> \
  [--workspace <workspace-dir>]

Apply gateway config if systemPrompt needs updating (shown by script)
Commit workspace file changes (if --workspace used)

With Workspace Search

python3 scripts/rename_channel.py \
  --id 1234567890 \
  --old-name old-name \
  --new-name new-name \
  --workspace "$HOME/my-workspace"

This will:

Rename Discord channel via API
Update gateway config systemPrompt
Search and update workspace files
Report files changed for git commit

Complete Multi-Agent Setup

Full workflow from scratch:

# 1. Create Discord channel
python3 scripts/setup_channel.py \
  --name research \
  --context "Deep research and competitive analysis" \
  --category-id "1234567890"

# (Note the channel ID from output)

# 2. Apply gateway config for channel
openclaw gateway config.patch --raw '{"channels": {...}}'

# 3. Create agent bound to that channel
scripts/create-agent.sh \
  --name "Watson" \
  --id "watson" \
  --emoji "🔬" \
  --specialty "Deep research and competitive analysis" \
  --model "anthropic/claude-opus-4-5" \
  --workspace "$HOME/agents/watson" \
  --discord-channel "1234567890"

# Done! Agent is created and bound to the channel

Configuration

Discord Category ID

Option 1: Command line

python3 scripts/setup_channel.py \
  --name channel-name \
  --context "Purpose" \
  --category-id "1234567890"

Option 2: Environment variable

export DISCORD_CATEGORY_ID="1234567890"
python3 scripts/setup_channel.py --name channel-name --context "Purpose"

Finding Discord IDs

Enable Developer Mode:

Settings → Advanced → Developer Mode

Copy IDs:

Right-click channel → Copy ID
Right-click category → Copy ID

Scripts Reference

create-agent.sh

Arguments:

--name (required) - Agent name
--id (required) - Agent ID (lowercase, hyphenated)
--emoji (required) - Agent emoji
--specialty (required) - What the agent does
--model (required) - LLM to use (provider/model-name)
--workspace (required) - Where to create agent files
--discord-channel (optional) - Discord channel ID to bind

Output:

Creates agent workspace
Generates SOUL.md and HEARTBEAT.md
Updates gateway config
Optionally creates daily memory cron

setup_channel.py

Arguments:

--name (required) - Channel name
--context (required) - Channel purpose/context
--id (optional) - Existing channel ID
--category-id (optional) - Discord category ID

Output:

Creates Discord channel (if doesn't exist)
Generates gateway config.patch command

rename_channel.py

Arguments:

--id (required) - Channel ID
--old-name (required) - Current channel name
--new-name (required) - New channel name
--workspace (optional) - Workspace directory to search

Output:

Renames Discord channel
Updates gateway systemPrompt (if needed)
Lists updated files (if workspace search enabled)

Gateway Integration

This skill integrates with OpenClaw's gateway configuration:

Agents:

{
  "agents": {
    "list": [
      {
        "id": "watson",
        "name": "Watson",
        "workspace": "/path/to/agents/watson",
        "model": {
          "primary": "anthropic/claude-opus-4-5"
        },
        "identity": {
          "name": "Watson",
          "emoji": "🔬"
        }
      }
    ]
  }
}

Bindings:

{
  "bindings": [
    {
      "agentId": "watson",
      "match": {
        "channel": "discord",
        "peer": {
          "kind": "channel",
          "id": "1234567890"
        }
      }
    }
  ]
}

Channels:

{
  "channels": {
    "discord": {
      "guilds": {
        "YOUR_GUILD_ID": {
          "channels": {
            "1234567890": {
              "allow": true,
              "requireMention": false,
              "systemPrompt": "Deep research and competitive analysis"
            }
          }
        }
      }
    }
  }
}

Agent Coordination

Your main agent coordinates with specialized agents using OpenClaw's built-in session management tools.

List Active Agents

See all active agents and their recent activity:

sessions_list({
  kinds: ["agent"],
  limit: 10,
  messageLimit: 3  // Show last 3 messages per agent
})

Send Messages to Agents

Direct communication:

sessions_send({
  label: "watson",  // Agent ID
  message: "Research the competitive landscape for X"
})

Wait for response:

sessions_send({
  label: "watson",
  message: "What did you find about X?",
  timeoutSeconds: 300  // Wait up to 5 minutes
})

Spawn Sub-Agent Tasks

For complex work, spawn a sub-agent in an isolated session:

sessions_spawn({
  agentId: "watson",  // Optional: use specific agent
  task: "Research competitive landscape for X and write a report",
  model: "anthropic/claude-opus-4-5",  // Optional: override model
  runTimeoutSeconds: 3600,  // 1 hour max
  cleanup: "delete"  // Delete session after completion
})

The sub-agent will:

Execute the task in isolation
Announce completion back to your session
Self-delete (if cleanup: "delete")

Check Agent History

Review what an agent has been working on:

sessions_history({
  sessionKey: "watson-session-key",
  limit: 50
})

Coordination Patterns

1. Direct delegation (Discord-bound agents):

User messages agent's Discord channel
Agent responds directly in that channel
Main agent doesn't need to coordinate

2. Programmatic delegation (main agent → sub-agent):

// Main agent delegates task
sessions_send({
  label: "watson",
  message: "Research X and update memory/research-X.md"
})

// Watson works independently, updates files
// Main agent checks later or Watson reports back

3. Spawn for complex tasks:

// For longer-running, isolated work
sessions_spawn({
  agentId: "watson",
  task: "Deep dive: analyze competitors A, B, C. Write report to reports/competitors.md",
  runTimeoutSeconds: 7200,
  cleanup: "keep"  // Keep session for review
})

4. Agent-to-agent communication: Agents can send messages to each other:

// In Watson's context
sessions_send({
  label: "picasso",
  message: "Create an infographic from data in reports/research.md"
})

Best Practices

When to use Discord bindings:

✅ Domain-specific agents (research, health, images)
✅ User wants direct access to agent
✅ Agent should respond to channel activity

When to use sessions_send:

✅ Programmatic coordination
✅ Main agent delegates to specialists
✅ Need response in same session

When to use sessions_spawn:

✅ Long-running tasks (>5 minutes)
✅ Complex multi-step work
✅ Want isolation from main session
✅ Background processing

Example: Research Workflow

// Main agent receives request: "Research competitor X"

// 1. Check if Watson is active
const agents = sessions_list({ kinds: ["agent"] })

// 2. Delegate to Watson
sessions_send({
  label: "watson",
  message: "Research competitor X: products, pricing, market position. Write findings to memory/research-X.md"
})

// 3. Watson works independently:
//    - Searches web
//    - Analyzes data
//    - Updates memory file
//    - Reports back when done

// 4. Main agent retrieves results
const results = Read("agents/watson/memory/research-X.md")

// 5. Share with user
"Research complete! Watson found: [summary]"

Communication Flow

Main Agent (You) ↔ Specialized Agents:

User Request
    ↓
Main Agent (Claire)
    ↓
sessions_send("watson", "Research X")
    ↓
Watson Agent
    ↓
- Uses web_search
- Uses web_fetch
- Updates memory files
    ↓
Responds to main session
    ↓
Main Agent synthesizes and replies

Discord-Bound Agents:

User posts in #research channel
    ↓
Watson Agent (bound to channel)
    ↓
- Sees message directly
- Responds in channel
- No main agent involvement

Hybrid Approach:

User: "Research X" (main channel)
    ↓
Main Agent delegates to Watson
    ↓
Watson researches and reports back
    ↓
Main Agent: "Done! Watson found..."
    ↓
User: "Show me more details"
    ↓
Main Agent: "@watson post your full findings in #research"
    ↓
Watson posts detailed report in #research channel

Troubleshooting

Agent Creation Issues:

"Agent not appearing in Discord"

Verify channel ID is correct
Check gateway config bindings section
Restart gateway: openclaw gateway restart

"Model errors"

Verify model name format: provider/model-name
Check model is available in gateway config

Channel Management Issues:

"Failed to create channel"

Check bot has "Manage Channels" permission
Verify bot token in OpenClaw config
Ensure category ID is correct (if specified)

"Category not found"

Verify category ID is correct
Check bot has access to category
Try without category ID (creates uncategorized)

"Channel already exists"

Use --id <channel-id> to configure existing channel
Or script will auto-detect and configure it

Use Cases

Domain specialists - Research, health, finance, coding agents
Creative agents - Image generation, writing, design
Task automation - Scheduled monitoring, reports, alerts
Multi-agent systems - Coordinated team of specialized agents
Discord organization - Structured channels for different agent domains

Advanced: Multi-Agent Coordination

For larger multi-agent systems:

Coordination Patterns:

Main agent delegates tasks to specialists
Agents report progress and request help
Shared knowledge base for common information
Cross-agent communication via sessions_send

Task Management:

Integrate with task tracking systems
Route work based on agent specialty
Track assignments and completions

Documentation:

Maintain agent roster in main workspace
Document delegation patterns
Keep runbooks for common workflows

Best Practices

Organize channels in categories - Group related agent channels
Use descriptive channel names - Clear purpose from the name
Set specific system prompts - Give each channel clear context
Document agent responsibilities - Keep SOUL.md updated
Set up memory cron jobs - For agents with ongoing work
Test agents individually - Before integrating into team
Update gateway config safely - Always use config.patch, never manual edits

Requirements

Bot Permissions:

Manage Channels - To create/rename channels
View Channels - To read channel list
Send Messages - To post in channels

System:

OpenClaw installed and configured
Node.js/npm via nvm
Python 3.6+ (standard library only)
Discord bot token (for channel management)

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

Agent Council

What This Skill Does

Installation

Part 1: Agent Creation

Quick Start

Workflow

1. Gather Requirements

2. Run Creation Script

3. Customize Agent

Agent Architecture

Examples

Part 2: Discord Channel Management

Channel Creation

Quick Start

Workflow

Options

Channel Renaming

Quick Start

Workflow

With Workspace Search

Complete Multi-Agent Setup

Configuration

Discord Category ID

Finding Discord IDs

Scripts Reference

create-agent.sh

setup_channel.py

rename_channel.py

Gateway Integration

Agent Coordination

List Active Agents

Send Messages to Agents

Spawn Sub-Agent Tasks

Check Agent History

Coordination Patterns

Best Practices

Example: Research Workflow

Communication Flow

Troubleshooting

Use Cases

Advanced: Multi-Agent Coordination

Best Practices

Requirements

See Also

When it activates

SkillSafety

Source

Related skills

More in the registry