Ready to supercharge your AI agents?

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

Medo App Builder · LeoYeAI | DecimalAI

Codingby LeoYeAI

Medo App Builder

Create, modify, generate, and deploy websites, web apps, dashboards, SaaS products, internal tools, interactive web pages, Weixin mini program , games on the Baidu Medo platform using natural-language instructions.

Never made a case worse

SkillScore

SkillScore68/100

Test results 68

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

0%68%of test cases passed +68 pts

Without skill0 of 22

With skill15 of 22

15 fixed0 passed either way7 still failing0 broke

Measured on gemini-3.6-flash7/31/2026v119 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI need to get the configuration details for app-222 as fast as possible, and I don't need the conversation ID included in the response. What command should I use?

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 medo-app-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("medo-app-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 medo-app-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/medo-app-builder/SKILL.md https://app.decimal.ai/s/medo-app-builder/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/medo-app-builder/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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 medo-app-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("medo-app-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/medo-app-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/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-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/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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("medo-app-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/medo-app-builder/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/medo-app-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 1 other file is 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 medo-app-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/medo-app-builder/SKILL.md https://app.decimal.ai/s/medo-app-builder/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/medo-app-builder/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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/medo-app-builder/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/medo-app-builder.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/31/2026
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

Medo App Builder

Medo is a chat-driven full-stack application builder. Official website: https://www.medo.dev

Users describe what they want in natural language and Medo generates a production-ready web product, including:

frontend UI
backend services
database schema
integrations
deployable hosting

Typical outputs include:

websites
web applications
dashboards
SaaS products
admin panels
internal tools
landing pages
interactive web pages
browser games and mini games

This skill enables AI agents to interact with the Medo platform to create, iterate, generate, and deploy applications.

All platform operations must be executed through the packaged CLI script:

python scripts/medo_api.py <command> [options]

Do not call platform APIs directly. Always use the CLI commands provided by this skill.

When to Use This Skill

Use this skill whenever the user wants to:

create a website
create a webpage
build a web application
build a dashboard
create a SaaS product
build an admin panel
build an internal tool
create a landing page
build an interactive web page
create a browser game
create a mini game
generate an MVP web product
modify an existing Medo project
publish or deploy a Medo application

Do not use this skill for unrelated programming tasks.

Routing Keywords

Trigger this skill if the request includes concepts such as:

build a website
create a webpage
build a web app
create a SaaS
build a dashboard
create an admin panel
build an internal tool
create a landing page
build a browser game
create a mini game
generate a web product
make a snake game webpage
build a todo web app
create a blog site

Example Requests

Examples that should route to this skill:

"Create a todo list web app"
"Build a personal blog website"
"Make a dashboard for sales analytics"
"Create a SaaS landing page"
"Build an admin panel"
"Write a snake game webpage"
"Create a browser game"
"Build a mini web game"
"Modify my Medo project"
"Publish this Medo app"

Stateless Execution Model

The CLI script is stateless.

It does not store workflow state between calls.

Application workflow state is maintained by the Medo platform and must be inferred from:

appId
conversationId
application detail
conversation trajectory events

Agents must pass the appropriate identifiers when continuing conversations or modifying applications.

Application Lifecycle Rules

Medo applications follow a strict lifecycle.

Agents must follow these rules.

Initial Creation

For a new application:

Start with a chat request describing the product.
The application enters the PRD refinement stage.
Continue chatting to refine the specification.
When the trajectory contains a Generate App button (type":"button" and event":{"name":"generateApp"} in result.artifact.parts[].data.actions[]), trigger application generation using generate-app.

Generation is required only once during the initial creation.

Multi-Round Modification

After an application has already been generated:

Do not call generate-app again.
Continue using chat with the same appId and conversationId.

Normal chat messages modify the existing application.

Publishing

Publishing is allowed after the application has been generated at least once.

Rules:

Publishing does not require another generation step
Publishing may happen anytime after the first generation
Publishing must be followed by status polling (or use --wait flag)

Typical deployment flow:

publish → publish-status polling

Or use the --wait flag to auto-poll:

publish --wait

Stop polling when the status becomes:

SUCCESS
FAILED

Application URLs

Medo provides two types of URLs during the lifecycle.

Project Preview (Editor / Development)

After the application is created, the project can be accessed at:

https://www.medo.dev/projects/<app_id>

This URL can be shared with the user for:

viewing the project
editing the application
previewing the generated result

The preview URL becomes available once an appId is created.

Production Deployment URL

After publishing succeeds, the application is accessible at:

https://<app_id>.appmedo.com

This is the public production URL of the deployed application.

Only return this URL after publishing completes successfully.

Standard Workflow

Create New Application

chat → PRD refinement → generate-app → publish

Modify Existing Generated Application

chat → chat → chat

(no additional generation step required)

Deploy Application

publish → publish-status polling

Or:

publish --wait

Available Commands

All commands are executed via the CLI script.

Important: Always set the MEDO_API_KEY environment variable before running commands.

export MEDO_API_KEY="your_api_key_here"

list-apps

List all applications belonging to the authenticated user.

Usage:

python scripts/medo_api.py list-apps [--brief]

Optional Parameters:

--brief: Output only key fields: appId, name, type, appFocus, host, updatedAt. Recommended for agents to reduce token usage.
--name NAME: Filter by app name (substring)
--page PAGE: Page number (default: 1)
--size SIZE: Page size (default: 12)

Example:

export MEDO_API_KEY="sk_xxxxx"

# Brief mode (recommended for agents)
python scripts/medo_api.py list-apps --brief

# Full mode
python scripts/medo_api.py list-apps

Returns: JSON array of applications with appId, name, type, etc.

app-detail

Get detailed information about a specific application. Automatically injects conversationId into the response by default — no need to call get-context-id separately.

Usage:

python scripts/medo_api.py app-detail --app-id <app_id> [--no-context]

Required Parameters:

--app-id APP_ID: Application ID

Optional Parameters:

--no-context: Skip auto-fetching conversationId from trajectory (faster, but response will not contain conversationId)

Example:

export MEDO_API_KEY="sk_xxxxx"
python scripts/medo_api.py app-detail --app-id app-abc123xyz

Returns: JSON object with application details, configuration, and status. data.conversationId is automatically populated.

get-context-id

Recover the conversationId for an existing app by reading its trajectory. Useful when the conversationId has been lost after a session reset.

Usage:

python scripts/medo_api.py get-context-id --app-id <app_id>

Required Parameters:

--app-id APP_ID: Application ID

Optional Parameters:

--fetch-timeout SECONDS: Request timeout in seconds (default: 10)

Example:

export MEDO_API_KEY="sk_xxxxx"
python scripts/medo_api.py get-context-id --app-id app-abc123xyz

Returns: {"appId": "app-abc123xyz", "conversationId": "conv-def456uvw"}

Use Cases:

Need to modify a previously created app in a new session but conversationId is lost
Use the returned conversationId with chat --app-id --context-id to resume modification

conversation-history

Show a human/agent-readable summary of past interactions for an app. More convenient than trajectory or fetch-trajectory for quickly understanding what happened in previous sessions.

Usage:

python scripts/medo_api.py conversation-history --app-id <app_id> [options]

Required Parameters:

--app-id APP_ID: Application ID

Optional Parameters:

--full: Show full content instead of truncated summaries (default: truncate at 200 chars)
--limit N: Only show the last N conversation turns
--fetch-timeout SECONDS: Request timeout in seconds (default: 10)

Example:

export MEDO_API_KEY="sk_xxxxx"

# View conversation history summary
python scripts/medo_api.py conversation-history --app-id app-abc123xyz

# Only show the last 3 turns
python scripts/medo_api.py conversation-history --app-id app-abc123xyz --limit 3

# Show full content without truncation
python scripts/medo_api.py conversation-history --app-id app-abc123xyz --full

Returns: JSON Lines, one entry per meaningful turn:

{"eventId": 5, "role": "user", "type": "message", "content": "创建一个待办事项应用..."}
{"eventId": 865, "role": "agent", "type": "file", "content": "[file: 需求文档.md]"}
{"eventId": 880, "role": "user", "type": "message", "content": "生成应用"}

Use Cases:

Quickly understand what happened in previous sessions before resuming work
Determine which phase the app is in (PRD refinement / generated / modified)
Check for unfinished modifications or cancelled tasks

chat

Start or continue a conversation to create or modify an application.

Usage:

python scripts/medo_api.py chat --text "description" [options]

Required Parameters:

--text TEXT: The message/instruction to send

Optional Parameters:

--context-id CONTEXT_ID: Conversation ID of an existing app.
--app-id APP_ID: Application ID of an existing app.
--query-mode QUERY_MODE: Query mode (default: deep_mode)
--input-field-type INPUT_FIELD_TYPE: Input field type (default: web)
--poll-interval SECONDS: Seconds between trajectory polls (default: 2.0)
--fetch-timeout SECONDS: Per-request timeout for each trajectory fetch (default: 10)
--no-stream: Return raw chat POST response without trajectory polling
--prompt-generate: After polling, interactively ask whether to submit app generation if text was returned

⚠️ IMPORTANT — --app-id and --context-id must always be used together.

Intent --app-id --context-id
Create a brand-new app omit omit
Continue / modify an existing app required required (conversationId)

Passing --app-id without --context-id will NOT modify the existing app. The platform will silently create a new app every time. The CLI will now raise an error in this case to prevent accidental app proliferation.

Intent	`--app-id`	`--context-id`
Create a brand-new app	omit	omit
Continue / modify an existing app	required	required (conversationId)

Examples:

1. Create a new application:

export MEDO_API_KEY="sk_xxxxx"
python scripts/medo_api.py chat --text "创建一个待办事项管理应用"

Response includes appId and contextId for subsequent calls.

2. Continue conversation (refine PRD):

python scripts/medo_api.py chat \
  --text "添加优先级标记功能" \
  --app-id app-abc123xyz \
  --context-id conv-def456uvw

3. Modify existing generated app:

python scripts/medo_api.py chat \
  --text "把按钮颜色改成蓝色" \
  --app-id app-abc123xyz \
  --context-id conv-def456uvw

Important Notes:

Extract appId and contextId from the response and save them
Use these IDs for all subsequent operations on the same app
The first chat creates the app and starts PRD refinement
After generation, chat directly modifies the app (no generate-app needed)

trajectory

Poll trajectory events until the task reaches a terminal state.

Usage:

python scripts/medo_api.py trajectory --app-id <app_id> [options]

Required Parameters:

--app-id APP_ID: Application ID

Optional Parameters:

--last-event-id EVENT_ID: Start eventId; -1 = all events from beginning (default: -1)
--poll-interval SECONDS: Seconds between polls (default: 2.0)
--fetch-timeout SECONDS: Per-request timeout in seconds (default: 10)
--sse: Use legacy SSE streaming instead of polling

Example:

export MEDO_API_KEY="sk_xxxxx"
python scripts/medo_api.py trajectory --app-id app-abc123xyz

Use Cases:

Monitor conversation / generation progress
Detect when PRD refinement is complete (look for Generate App button in result.artifact.parts[].data.actions[])
Verify generation has completed

fetch-trajectory

Fetch one batch of trajectory events (single request, no polling loop).

Usage:

python scripts/medo_api.py fetch-trajectory --app-id <app_id> [options]

Required Parameters:

--app-id APP_ID: Application ID

Optional Parameters:

--last-event-id EVENT_ID: Fetch events after this eventId; -1 = all (default: -1)
--fetch-timeout SECONDS: Request timeout in seconds (default: 10)

Example:

# First call — get all events (note maxEventId from stderr)
python scripts/medo_api.py fetch-trajectory --app-id app-abc123xyz

# Subsequent calls — incremental fetch
python scripts/medo_api.py fetch-trajectory --app-id app-abc123xyz --last-event-id 345

Events are printed to stdout as JSON lines; {"maxEventId": N, "isTerminal": bool} is printed to stderr.

Generate App readiness: Inspect result.artifact.parts[].data.actions[] for an action with "type":"button" and "event":{"name":"generateApp"}. Example:

{"type":"button","label":"Generate App","value":"Generate App","event":{"name":"generateApp"}}

When this button appears, PRD is ready and generate-app may be called.

generate-app

Submit app-generation confirmation and return immediately with appId/conversationId.

Usage:

python scripts/medo_api.py generate-app --app-id <app_id> --context-id <context_id> [options]

Required Parameters:

--app-id APP_ID: Application ID

Optional Parameters:

--context-id CONTEXT_ID: Conversation ID (default: "")
--query-mode QUERY_MODE: Query mode (default: deep_mode)
--watch: Block and poll trajectory until generation completes (default: return immediately)
--poll-interval SECONDS: Seconds between polls when --watch is set (default: 2.0)
--fetch-timeout SECONDS: Per-request timeout in seconds when --watch is set (default: 10)

Example:

export MEDO_API_KEY="sk_xxxxx"
# Submit and return immediately — check status later with fetch-trajectory
python scripts/medo_api.py generate-app \
  --app-id app-abc123xyz \
  --context-id conv-def456uvw

# Submit and block until generation finishes
python scripts/medo_api.py generate-app \
  --app-id app-abc123xyz \
  --context-id conv-def456uvw \
  --watch

Important:

Only call this once during initial creation
Call only when trajectory contains a Generate App button in result.artifact.parts[].data.actions[]: an action with "type":"button" and "event":{"name":"generateApp"} (label may vary by locale; use event name for the check). This indicates PRD is ready.
Do not call again for modifications after the first generation
After this command, use chat to modify the generated app

publish

Trigger deployment to production.

Usage:

python scripts/medo_api.py publish --app-id <app_id> [options]

Required Parameters:

--app-id APP_ID: Application ID to publish

Optional Parameters:

--env ENV: Target environment (default: PRODUCE)
--wait: Auto-poll publish status until SUCCESS or FAILED

Examples:

1. Publish and manually check status:

export MEDO_API_KEY="sk_xxxxx"
python scripts/medo_api.py publish --app-id app-abc123xyz

Returns releaseId immediately. Then poll with publish-status.

2. Publish and auto-wait for completion (recommended):

export MEDO_API_KEY="sk_xxxxx"
python scripts/medo_api.py publish --app-id app-abc123xyz --wait

This polls automatically and exits when deployment succeeds or fails.

Important:

Application must be generated at least once before publishing
After successful publish, the app is live at: https://<app_id>.appmedo.com

publish-status

Check the status of a deployment.

Usage:

python scripts/medo_api.py publish-status --release-id <release_id>

Required Parameters:

--release-id RELEASE_ID: Release ID from publish command

Example:

export MEDO_API_KEY="sk_xxxxx"
python scripts/medo_api.py publish-status --release-id app_release_record-xyz789abc

Returns: JSON with status: PROCESSING, RUNNING, SUCCESS, or FAILED

Usage Pattern:

# Get release ID from publish
RELEASE_ID=$(python scripts/medo_api.py publish --app-id app-abc123xyz | jq -r '.releaseId')

# Poll status
while true; do
  STATUS=$(python scripts/medo_api.py publish-status --release-id $RELEASE_ID | jq -r '.status')
  echo "Status: $STATUS"
  if [[ "$STATUS" == "SUCCESS" || "$STATUS" == "FAILED" ]]; then
    break
  fi
  sleep 5
done

Tip: Use publish --wait to avoid manual polling.

Complete Workflow Examples

Example 1: Create and Deploy a New App

export MEDO_API_KEY="sk_xxxxx"
cd ~/.openclaw/skills/medo-app-builder

# Step 1: Create app via chat (returns appId + conversationId on first line)
FIRST=$(python scripts/medo_api.py chat --text "创建一个简单的计数器应用" | head -1)
APP_ID=$(echo $FIRST | jq -r '.appId')
CONTEXT_ID=$(echo $FIRST | jq -r '.conversationId')

# Step 2: Generate the app (returns immediately; use fetch-trajectory to check progress)
python scripts/medo_api.py generate-app \
  --app-id $APP_ID \
  --context-id $CONTEXT_ID

# Step 3: Poll until generation finishes
python scripts/medo_api.py trajectory --app-id $APP_ID

# Step 4: Publish (with auto-wait)
python scripts/medo_api.py publish --app-id $APP_ID --wait

# Done! App is live at:
echo "https://$APP_ID.appmedo.com"

Example 2: Modify an Existing App

IMPORTANT — Always update CONTEXT_ID from each chat response.

Each chat call prints a JSON header line {"appId": "...", "conversationId": "..."}. The platform may return an updated conversationId in this response. Always capture it and use it for the next chat call, or the next round will create a brand-new app.

export MEDO_API_KEY="sk_xxxxx"
cd ~/.openclaw/skills/medo-app-builder

APP_ID="app-abc123xyz"

# Step 1: Get app detail — conversationId is auto-injected
DETAIL=$(python scripts/medo_api.py app-detail --app-id $APP_ID)
CONTEXT_ID=$(echo $DETAIL | jq -r '.data.conversationId')

# Abort early if conversationId is missing (app may have no history yet)
if [ -z "$CONTEXT_ID" ] || [ "$CONTEXT_ID" = "null" ]; then
  echo "Error: could not retrieve conversationId. Try: get-context-id --app-id $APP_ID"
  exit 1
fi

# Step 2 (optional): Review conversation history to understand previous work
python scripts/medo_api.py conversation-history --app-id $APP_ID

# Step 3a: First modification — capture the UPDATED conversationId from the response header
CHAT_RESULT=$(python scripts/medo_api.py chat \
  --text "把背景颜色改成深色模式" \
  --app-id $APP_ID \
  --context-id $CONTEXT_ID | head -1)
CONTEXT_ID=$(echo $CHAT_RESULT | jq -r '.conversationId')   # ← UPDATE for next round

# Step 3b: Second modification — uses the updated CONTEXT_ID
CHAT_RESULT=$(python scripts/medo_api.py chat \
  --text "添加暗黑模式切换按钮" \
  --app-id $APP_ID \
  --context-id $CONTEXT_ID | head -1)
CONTEXT_ID=$(echo $CHAT_RESULT | jq -r '.conversationId')   # ← UPDATE again

# Step 4: Re-publish
python scripts/medo_api.py publish --app-id $APP_ID --wait

Command Semantics

chat

Used to:

create a new application
refine PRD specifications
modify an existing generated application

For a new application, chat creates the project and begins the PRD stage.

For an existing application, chat performs iterative modifications.

trajectory

Streams conversation progress and system events.

Use this to determine:

whether PRD generation is ongoing
whether the app is ready for generation (see generate-app condition below)
whether generation has completed

generate-app

Triggers application generation.

Call only when trajectory contains a Generate App button in result.artifact.parts[].data.actions[]: an action with "type":"button" and "event":{"name":"generateApp"}. This indicates PRD is ready. Do not rely on text alone—the button structure is the authoritative signal.

Call once during initial creation. Do not call again for modifications.

publish

Triggers application deployment.

Use --wait flag to auto-poll status (recommended).

publish-status

Polls deployment progress until the release completes.

Not needed if using publish --wait.

Error Handling

IAM AccessKey Validation Failed

Symptom:

IAM access key validation failed.

Cause:

The configured MEDO_API_KEY is invalid or missing.

Resolution:

Go to the Medo official website:

https://www.medo.dev
In the left navigation panel, apply for an available access key.
Set the key as the environment variable:
```
export MEDO_API_KEY="sk_xxxxx"
```

Or create a .env file in the skill directory:

echo "MEDO_API_KEY=sk_xxxxx" > ~/.openclaw/skills/medo-app-builder/.env

NotOpenSSLWarning

Symptom:

NotOpenSSLWarning: urllib3 v2 only supports OpenSSL 1.1.1+,
currently the 'ssl' module is compiled with 'LibreSSL 2.8.3'

Cause:

macOS uses LibreSSL by default, but urllib3 v2 recommends OpenSSL.

Impact:

This is a warning only. API calls still work correctly.

Resolution (optional):

If you want to suppress the warning:

pip3 install 'urllib3<2'

Or ignore it - it doesn't affect functionality.

Error Handling Guidance

Agents should handle the following situations:

generation requested before the platform indicates readiness
publish requested before generation has completed
missing appId or conversationId (use get-context-id to recover a lost conversationId)
interrupted trajectory stream
failed deployment status
incorrect or missing parameter values

If workflow state is unclear, inspect the trajectory or application detail before taking the next action.

Pro Tips:

Always check command --help when unsure about parameters
Use --wait flag with publish to simplify deployment
Save appId and contextId from first chat response
Only call generate-app once during initial creation
After generation, use chat directly for modifications

Application Sharing Rule (IMPORTANT)

You must share your application only using the production deployment URL (after it has been published). Do not share the editor (development) URL.

Production deployment URL format:

https://<app_id>.appmedo.com

If the application has not been published, you must publish it before sharing with others.

Example publish command:

python scripts/medo_api.py publish --app-id <app_id> --wait

The project editor URL (https://www.medo.cn/projects/<app_id>) is visible only to yourself. Other users cannot access your editor environment. Never use the editor URL for sharing with others.

Editor URL is for:

your own development
preview
internal editing only

Editor URL must NOT be used for:

external/public sharing
distribution to others or end users

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

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/medo-app-builder/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 1 file · scripts

Illustrative Want to see what medo-app-builder would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

leoyeai/miaoda-app-builderCreate, modify, generate, and deploy websites, web apps, dashboards, SaaS products, internal tools, interactive web pages, Weixin mini program , games on the Baidu Miaoda (秒哒) platform using natural-language instructions.Close match+59 pts pass-rate lift

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

Medo App Builder

When to Use This Skill

Routing Keywords

Example Requests

Stateless Execution Model

Application Lifecycle Rules

Initial Creation

Multi-Round Modification

Publishing

Application URLs

Project Preview (Editor / Development)

Production Deployment URL

Standard Workflow

Create New Application

Modify Existing Generated Application

Deploy Application

Available Commands

list-apps

app-detail

get-context-id

conversation-history

chat

trajectory

fetch-trajectory

generate-app

publish

publish-status

Complete Workflow Examples

Example 1: Create and Deploy a New App

Example 2: Modify an Existing App

Command Semantics

chat

trajectory

generate-app

publish

publish-status

Error Handling

IAM AccessKey Validation Failed

NotOpenSSLWarning

Error Handling Guidance

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry