Ready to supercharge your AI agents?

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

Get Started Free →

Warden Agent Builder · leoyeai | DecimalAI

Agent Toolingby leoyeai

Warden Agent Builder

Build original LangGraph agents for Warden Protocol and prepare them for publishing in Warden Studio.

Never made a case worse

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%91%of test cases passed +59 pts

Without skill7 of 22

With skill20 of 22

13 fixed7 passed either way2 still failing0 broke

Measured on gemini-3.6-flash8/6/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat CLI command should I run to initialize a new TypeScript project named gas-optimizer with a custom description using the repo initialization script?

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-warden-agent-builder
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-warden-agent-builder")
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-warden-agent-builder

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

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-warden-agent-builder/SKILL.md

This gets SKILL.md only. The skill's 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/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-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/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-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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-warden-agent-builder")
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-warden-agent-builder/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-warden-agent-builder/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 7 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-warden-agent-builder

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-warden-agent-builder/SKILL.md

This gets SKILL.md only. The skill's 7 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-warden-agent-builder/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-warden-agent-builder.json

This gets SKILL.md only. The skill's 7 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

Warden Agent Builder

Build and deploy LangGraph agents for Warden Protocol's Agentic Wallet ecosystem.

⚠️ IMPORTANT: About Example Agents

The Warden community repository contains example agents for learning, not templates to recreate:

Weather Agent - Study this to learn simple data fetching patterns
CoinGecko Agent - Study this to learn Schema-Guided Reasoning (SGR)
Portfolio Agent - Study this to learn complex multi-source integration

DO NOT BUILD THESE AGENTS - they already exist. Instead:

Study their code to understand patterns
Learn from their architecture and workflows
Build something NEW and original for the incentive programme

Your agent must be unique and solve a different problem to be eligible for the incentive programme.

Overview

Warden Protocol is an "Agentic Wallet for the Do-It-For-Me economy" with an active Agent Builder Incentive Programme open to OpenClaw agents that deploy to Warden. All agents must be LangGraph-based and API-accessible.

Key Resources:

Community Agents Repository: https://github.com/warden-protocol/community-agents
Documentation: https://docs.wardenprotocol.org
Discord: #developers channel for support

Requirements Checklist

Before building, ensure your agent meets these mandatory requirements:

✓ Framework: Built with LangGraph (TypeScript or Python) ✓ Deployment: LangSmith Deployments OR custom infrastructure ✓ Access: API-accessible (no UI required - Warden provides UI) ✓ Isolation: One agent per LangGraph instance ✓ Security Limitations (Phase 1):

Cannot access user wallets
Cannot store data on Warden infrastructure

✓ Functionality: Can implement any workflow:

Web3/Web2 automation
API integrations
Database connections
External tool interactions

Understanding the Example Agents

The community-agents repository contains reference examples to learn from, NOT templates to recreate:

Example Agent 1: LangGraph Quick Start (Study for Basics)

Location: agents/langgraph-quick-start (TypeScript) or agents/langgraph-quick-start-py (Python) Learn: LangGraph fundamentals, minimal agent structure Study: Single-node chatbot with OpenAI integration

git clone https://github.com/warden-protocol/community-agents.git
cd community-agents/agents/langgraph-quick-start

Example Agent 2: Weather Agent (Study for Structure)

Location: agents/weather-agent Learn: Simple data fetching, API integration, user-friendly responses Study:

How to fetch data from external APIs (WeatherAPI)
Processing and formatting results
Clear scope and structure ⚠️ DO NOT BUILD: This already exists. Study it, then build something NEW.

Example Agent 3: CoinGecko Agent (Study for SGR Pattern)

Location: agents/coingecko-agent Learn: Schema-Guided Reasoning, complex workflows Study:

5-step SGR workflow: Validate → Extract → Fetch → Validate → Analyze
Comparative analysis patterns
Error handling and data validation ⚠️ DO NOT BUILD: This already exists. Study the pattern, apply to new use cases.

Example Agent 4: Portfolio Analysis Agent (Study for Advanced Patterns)

Location: agents/portfolio-agent Learn: Multi-source data synthesis, production architecture Study:

Integrating multiple APIs (CoinGecko + Alchemy)
Multi-chain support (EVM and Solana)
Complex SGR workflows
Comprehensive reporting ⚠️ DO NOT BUILD: This already exists. Study the architecture for your own complex agent.

IMPORTANT: Build Something NEW

These examples exist to teach patterns and best practices. For the incentive programme, you MUST create an original, unique agent that solves a different problem. Do NOT simply recreate the Weather Agent, CoinGecko Agent, or Portfolio Agent.

Building Your Original Agent

Step 1: Study Examples and Choose Your Approach

DO NOT clone an example to modify it. Instead:

Study the examples to understand patterns:
- Simple data fetching → Study Weather Agent
- Complex analysis → Study CoinGecko Agent
- Multi-source synthesis → Study Portfolio Agent
Identify YOUR unique use case:
- What problem will your agent solve?
- What APIs or data sources will it use?
- What makes it different from existing agents?
Plan your agent's workflow:
- Simple request-response?
- Schema-Guided Reasoning (SGR)?
- Multi-step analysis?

Step 2: Initialize Your NEW Agent

Use the initialization script to create a fresh project:

# Create your unique agent
python scripts/init-agent.py my-unique-agent \
  --template typescript \
  --description "Description of what YOUR agent does"

# Navigate to project
cd my-unique-agent

# Install dependencies
npm install  # TypeScript
# OR
pip install -r requirements.txt  # Python

This creates a clean starting point, not a copy of existing agents.

Step 3: Understand LangGraph Agent Structure

Every LangGraph agent follows this basic structure:

your-agent/
├── src/
│   ├── agent.ts/py          # Main agent logic (YOUR CODE)
│   ├── graph.ts/py          # LangGraph workflow definition (YOUR CODE)
│   └── tools.ts/py          # Tool implementations (YOUR CODE)
├── package.json / requirements.txt
├── langgraph.json           # LangGraph configuration
└── README.md

Key files to implement:

graph.ts/py - Define your workflow (validate → process → respond)
agent.ts/py - Implement your core logic
tools.ts/py - Integrate external APIs specific to YOUR agent's purpose

Step 4: Implement Your Custom Agent Logic

Study patterns from examples, apply to YOUR use case:

If building a simple data fetcher (like Weather Agent pattern):

// Define workflow
const workflow = new StateGraph({
  channels: agentState
})
  .addNode("fetch", fetchYourData)      // YOUR API
  .addNode("process", processYourData)  // YOUR logic
  .addNode("respond", generateResponse);

workflow
  .addEdge(START, "fetch")
  .addEdge("fetch", "process")
  .addEdge("process", "respond")
  .addEdge("respond", END);

If building complex analysis (like CoinGecko Agent pattern - SGR):

// Define 5-step SGR workflow
const workflow = new StateGraph({
  channels: agentState
})
  .addNode("validate", validateYourInput)     // YOUR validation
  .addNode("extract", extractYourParams)      // YOUR extraction
  .addNode("fetch", fetchYourData)            // YOUR APIs
  .addNode("analyze", analyzeYourData)        // YOUR analysis
  .addNode("generate", generateYourResponse); // YOUR formatting

workflow
  .addEdge(START, "validate")
  .addEdge("validate", "extract")
  .addEdge("extract", "fetch")
  .addEdge("fetch", "analyze")
  .addEdge("analyze", "generate")
  .addEdge("generate", END);

Key Principles:

Keep workflows linear and predictable
Validate inputs at each stage
Handle errors gracefully
Use OpenAI for natural language generation
Structure responses consistently

CRITICAL: This should be YOUR implementation solving YOUR problem, not a copy of the example agents.

Step 5: Configure Environment

Create .env file:

# Required
OPENAI_API_KEY=your_openai_key

# Required for LangSmith Deployments (cloud)
LANGSMITH_API_KEY=your_langsmith_key

# Optional - based on your tools
WEATHER_API_KEY=your_weather_key
COINGECKO_API_KEY=your_coingecko_key
ALCHEMY_API_KEY=your_alchemy_key

Getting LangSmith API Key:

Create account at https://smith.langchain.com
Navigate to Settings → API Keys
Create new API key
Add to .env file

Update langgraph.json:

{
  "agent_id": "[YOUR-AGENT-NAME]",
  "python_version": "3.11",  // or omit for TypeScript
  "dependencies": ["."],
  "graphs": {
    "agent": "./src/graph.ts"  // or .py
  },
  "env": ".env"
}

Step 6: Test Locally

# TypeScript
npm run dev

# Python
langgraph dev

Test your agent's API:

curl -X POST http://localhost:8000/invoke \
  -H "Content-Type: application/json" \
  -d '{"input": "test query"}'

Deployment Options

Option 1: LangSmith Deployments (Recommended)

Pros: Fastest, simplest, managed infrastructure Requirements: LangSmith API key

Steps:

1. Push your agent repository to GitHub.
2. Create a new deployment in LangSmith Deployments.
3. Connect the repo, set environment variables, and deploy.

Your agent receives:

API endpoint URL
Automatic authentication (uses your LangSmith API key)
Automatic scaling and monitoring

Authentication for API calls: When calling your deployed agent, include your LangSmith API key:

curl AGENT_URL/runs/wait \
  --request POST \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: [YOUR-LANGSMITH-API-KEY]' \
  --data '{
    "assistant_id": "[YOUR-AGENT-ID]",
    "input": {
      "messages": [{"role": "user", "content": "test query"}]
    }
  }'

Option 2: Self-Hosted Infrastructure

Pros: Full control over runtime Requirements:

Docker container hosting
Exposed API endpoint
SSL certificate (HTTPS)
Monitoring and logging

Basic Docker Setup:

FROM node:18
WORKDIR /app
COPY package*.json ./
RUN npm install
COPY . .
EXPOSE 8000
CMD ["npm", "start"]

Deploy and note your:

API URL: https://your-domain.com/agent
API Key: Generated for authentication

Register with Warden Studio

Once your agent is deployed and reachable via HTTPS, register it in Warden Studio:

Provide API Details:
- API URL
- API key
Add Metadata:
- Agent name
- Description
- Skills/capabilities list
- Avatar image
Publish: Agent appears in Warden's Agent Hub for millions of users

No additional setup required - your API-accessible agent is ready!

Next step (separate skill): If the user asks to publish in Warden Studio or needs guided UI steps, switch to the OpenClaw skill "Deploy Agent on Warden Studio": https://www.clawhub.ai/Kryptopaid/warden-studio-deploy

Best Practices

1. Agent Design

Study the Weather Agent structure to learn patterns
Use Schema-Guided Reasoning for complex workflows
Keep responses concise and actionable
Handle API failures gracefully
Validate all inputs

2. API Integration

Use environment variables for API keys
Implement rate limiting
Cache responses when appropriate
Log errors for debugging
Return structured JSON responses

3. Testing

Test locally before deploying
Verify all API endpoints work
Test edge cases and errors
Ensure responses are user-friendly
Validate against Warden requirements

4. Documentation

Write clear README with:
- Agent purpose and capabilities
- Required API keys
- Setup instructions
- Example queries
- Known limitations

Common Patterns

Pattern 1: Simple Data Fetcher

// Fetch → Format → Respond
async function agent(input: string) {
  const data = await fetchAPI(input);
  const formatted = formatData(data);
  return generateResponse(formatted);
}

Pattern 2: Multi-Step Analysis

// Validate → Extract → Fetch → Analyze → Generate
async function agent(input: string) {
  const validated = await validateInput(input);
  const params = await extractParams(validated);
  const data = await fetchData(params);
  const analysis = await analyzeData(data);
  return generateReport(analysis);
}

Pattern 3: Comparative Analysis

// Parse → Fetch Multiple → Compare → Summarize
async function agent(input: string) {
  const items = await parseItems(input);
  const dataArray = await Promise.all(
    items.map(item => fetchData(item))
  );
  const comparison = compareData(dataArray);
  return generateComparison(comparison);
}

Troubleshooting

Common Issues

"Agent not accessible via API"

Verify deployment completed successfully
Check firewall/security group settings
Ensure API endpoint is publicly accessible
Test with curl or Postman

"LangGraph errors during build"

Verify Node.js version (18+) or Python (3.11+)
Check all dependencies installed
Validate langgraph.json syntax
Review error logs in deployment console

"OpenAI API errors"

Verify API key is valid
Check rate limits not exceeded
Ensure sufficient credits
Review error messages for details

"Agent responses are slow"

Optimize API calls (parallelize where possible)
Implement caching for repeated queries
Reduce LLM token usage
Consider upgrading infrastructure

Incentive Programme Tips

The incentive programme is open to OpenClaw agents that deploy to Warden.

Be Original: Create something NEW that doesn't exist yet
- Don't recreate Weather Agent, CoinGecko Agent, or Portfolio Agent
- Study their patterns, apply to different problems
Solve Real Problems: Focus on useful, unique functionality
- What gap exists in the Warden ecosystem?
- What would users actually want?
Start Simple: Better to do one thing exceptionally well
- Don't try to build everything at once
- Simple, focused agents often win
Quality Over Features: Reliability beats complexity
- Test thoroughly
- Handle errors gracefully
- Provide clear, helpful responses
Study the Examples: Learn patterns, don't copy implementations
- Weather Agent → Simple data fetching pattern
- CoinGecko Agent → SGR workflow pattern
- Portfolio Agent → Multi-source integration pattern
Document Well: Clear README with examples and setup instructions
Join Discord: Get feedback in #developers channel before submitting

Example Agent Ideas (Build These!)

These are NEW agent ideas that don't exist yet in the Warden ecosystem. Build one of these (or create your own unique idea):

Web3 Use Cases:

Gas price optimizer (predict best times to transact)
NFT rarity analyzer (evaluate NFT traits and rarity scores)
DeFi yield comparator (compare yields across protocols)
Wallet health checker (analyze wallet security and diversification)
Transaction explainer (decode and explain complex transactions)
Token price alerts (customizable price movement notifications)
Smart contract auditor (basic security checks)
Liquidity pool finder (identify best liquidity opportunities)
Bridge fee comparator (find cheapest cross-chain bridges)
Airdrop tracker (find and track airdrop eligibility)

General Use Cases:

Crypto news aggregator (filter and summarize crypto news)
Research assistant (gather and analyze crypto research)
Regulatory tracker (track crypto regulations by region)
Data visualizer (create charts from on-chain data)
API orchestrator (combine multiple crypto data sources)
Workflow automator (automate common crypto tasks)

Remember: These are IDEAS for new agents. Study the example agents (Weather, CoinGecko, Portfolio) to learn patterns, then build something from this list or create your own unique concept.

Additional Resources

Documentation:

LangGraph TypeScript Guide: community-agents/docs/langgraph-quick-start-ts.md
LangGraph Python Guide: community-agents/docs/langgraph-quick-start-py.md
Deployment Guide: community-agents/docs/deploy.md

Example Agents:

Weather Agent README: agents/weather-agent/README.md
CoinGecko Agent README: agents/coingecko-agent/README.md
Portfolio Agent README: agents/portfolio-agent/README.md

Support:

Discord: #developers channel
GitHub Issues: https://github.com/warden-protocol/community-agents/issues
Documentation: https://docs.wardenprotocol.org

Quick Reference Commands

# Study example agents (DON'T BUILD THESE)
git clone https://github.com/warden-protocol/community-agents.git
cd community-agents/agents/weather-agent  # Study the code
cd community-agents/agents/coingecko-agent  # Study the patterns

# Create YOUR new agent
python scripts/init-agent.py my-unique-agent \
  --template typescript \
  --description "YOUR unique agent description"

# Install dependencies (TypeScript)
npm install

# Install dependencies (Python)
pip install -r requirements.txt

# Test locally
npm run dev  # or: langgraph dev

# Deploy (LangSmith Deployments)
# Use the LangSmith Deployments UI after pushing to GitHub

# Build Docker image (for self-hosting)
docker build -t my-warden-agent .

# Run Docker container
docker run -p 8000:8000 my-warden-agent

Success Checklist

Before submitting to incentive programme:

When it activates

Automatically, when a task matches. Use this skill when users want to: (1) Create new Warden agents (not community examples), (2) Build LangGraph-based crypto/Web3 agents, (3) Deploy agents via LangSmith Deployments or custom infra, (4) Participate in the Warden Agent Builder Incentive Programme (open to OpenClaw agents), or (5) Integrate with Warden Studio for Agent Hub publishing.

About this skill

Automatic

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/build-warden-agent/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 7 files · scripts

Illustrative Want to see what leoyeai/warden-agent-builder 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

Warden Agent Builder

⚠️ IMPORTANT: About Example Agents

Overview

Requirements Checklist

Understanding the Example Agents

Example Agent 1: LangGraph Quick Start (Study for Basics)

Example Agent 2: Weather Agent (Study for Structure)

Example Agent 3: CoinGecko Agent (Study for SGR Pattern)

Example Agent 4: Portfolio Analysis Agent (Study for Advanced Patterns)

IMPORTANT: Build Something NEW

Building Your Original Agent

Step 1: Study Examples and Choose Your Approach

Step 2: Initialize Your NEW Agent

Step 3: Understand LangGraph Agent Structure

Step 4: Implement Your Custom Agent Logic

Step 5: Configure Environment

Step 6: Test Locally

Deployment Options

Option 1: LangSmith Deployments (Recommended)

Option 2: Self-Hosted Infrastructure

Register with Warden Studio

Best Practices

1. Agent Design

2. API Integration

3. Testing

4. Documentation

Common Patterns

Pattern 1: Simple Data Fetcher

Pattern 2: Multi-Step Analysis

Pattern 3: Comparative Analysis

Troubleshooting

Common Issues

Incentive Programme Tips

Example Agent Ideas (Build These!)

Additional Resources

Quick Reference Commands

Success Checklist

When it activates

SkillSafety

Source

Related skills

More in the registry