Ready to supercharge your AI agents?

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

Get Started Free →

Render Skill · LeoYeAI | DecimalAI

DevOpsby LeoYeAI

Render Skill

Deploy and operate apps on Render (Blueprint + one-click Dashboard deeplink, same flow as Codex render-deploy).

SkillScore

SkillScore41/100

Test results 41

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

5%41%of test cases passed +36 pts

Without skill1 of 22

With skill9 of 22

8 fixed1 passed either way13 still failing0 broke

Measured on gemini-3.6-flash7/31/2026v121 comparable

Track record

Agent runs: 0; All time

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 render
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("render")
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 render

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/render/SKILL.md https://app.decimal.ai/s/render/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/render/SKILL.md

This gets SKILL.md only. The skill's 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/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/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/render/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 10 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 render

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("render")
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/render/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/render/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 10 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 render

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/render/SKILL.md https://app.decimal.ai/s/render/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/render/SKILL.md

This gets SKILL.md only. The skill's 10 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/render/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 10 other files are 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

Render Skill

Deploy and manage applications on Render using Blueprints (render.yaml), the Dashboard, or the API. This skill mirrors the Codex render-deploy flow: analyze codebase → generate/validate Blueprint → commit & push → one-click Dashboard deeplink → optional API/mcporter verify or re-deploy.

When to Use This Skill

Activate when the user wants to:

Deploy, host, or publish an application on Render
Create or edit a render.yaml Blueprint (new or existing repo)
Add web, static site, private, worker, or cron services; Postgres; or Key Value
Configure env vars, health checks, scaling, disks, or regions
Set up preview environments or projects
Validate a Blueprint or get Dashboard/API links

Deployment Method Selection

If RENDER_API_KEY is set → Prefer REST API or MCP (fastest; no user click). Use references/rest-api-deployment.md for request bodies, or mcporter if configured (see references/mcp-integration.md).
If no API key → Use Blueprint + deeplink (user commits, pushes, then clicks the deeplink to deploy).

Check for API key:

[ -n "$RENDER_API_KEY" ] && echo "RENDER_API_KEY is set" || echo "RENDER_API_KEY is not set"

Happy Path (New Users)

Before deep analysis, use this short sequence to reduce friction:

Ask whether they want to deploy from a Git repo (required for Blueprint and deeplink) or only get guidance. If no Git remote, they must create/push one first.
Ask whether the app needs a database, workers, cron, or other services so you can choose the right Blueprint shape.

Then follow Deploy to Render below (Blueprint → push → deeplink → verify).

Prerequisites Check

Git remote – Required for Blueprint deploy. Run git remote -v; if none, ask the user to create a repo on GitHub/GitLab/Bitbucket, add origin, and push.
Render CLI (optional) – For local validation: render blueprints validate render.yaml. Install: brew install render or Render CLI.
API key (optional) – For verifying deploys or triggering re-deploys: Dashboard → API Keys. Set RENDER_API_KEY in the environment.

Security Notes

Never commit secrets to render.yaml — always use sync: false for API keys, passwords, and tokens; the user fills them in the Dashboard.
Validate before suggesting deployment — run render blueprints validate render.yaml or use the Validate Blueprint API so invalid YAML is never pushed.
Validate user-provided values — when writing env vars or service names from user input into YAML, sanitize or quote as needed to avoid injection.

References

references/codebase-analysis.md (detect runtime, build/start commands, env vars)
references/blueprint-spec.md (root keys, service types, env vars, validation)
references/rest-api-deployment.md (direct API create service: ownerId, request bodies, type mapping)
references/mcp-integration.md (Render MCP tools, mcporter usage, supported runtimes/plans/regions)
references/post-deploy-checks.md (verify deploy status and health via API)
references/troubleshooting-basics.md (build/startup/runtime failures)
assets/ (example Blueprints: node-express.yaml, python-web.yaml, static-site.yaml, web-with-postgres.yaml)

Blueprint Basics

File: render.yaml at the root of the Git repository (required).
Root-level keys (official spec): services, databases, envVarGroups, projects, ungrouped, previews.generation, previews.expireAfterDays.
Spec: Blueprint YAML Reference. JSON Schema for IDE validation: https://render.com/schema/render.yaml.json (e.g. YAML extension by Red Hat in VS Code/Cursor).

Validation: render blueprints validate render.yaml (Render CLI v2.7.0+), or the Validate Blueprint API endpoint.

Service Types

type	Purpose
`web`	Public HTTP app or static site (use `runtime: static` for static)
`pserv`	Private service (internal hostname only, no public URL)
`worker`	Background worker (runs continuously, e.g. job queues)
`cron`	Scheduled job (cron expression; runs and exits)
`keyvalue`	Render Key Value instance (Redis/Valkey-compatible; defined in `services`)

Note: Private services use pserv, not private. Key Value is a service with type: keyvalue; do not use a separate root key for it in new Blueprints (some older blueprints use keyValueStores and fromKeyValueStore—prefer the official format).

Runtimes

Use runtime (preferred; env is deprecated): node, python, elixir, go, ruby, rust, docker, image, static. For static sites: type: web, runtime: static, and staticPublishPath (e.g. ./build or ./dist) required.

Minimal Web Service

services:
  - type: web
    name: my-app
    runtime: node
    buildCommand: npm install
    startCommand: npm start
    envVars:
      - key: NODE_ENV
        value: production

Python example: runtime: python, buildCommand: pip install -r requirements.txt, startCommand: uvicorn app.main:app --host 0.0.0.0 --port $PORT (or gunicorn). Set PYTHON_VERSION / NODE_VERSION in envVars when needed.

Static Site

- type: web
  name: my-blog
  runtime: static
  buildCommand: yarn build
  staticPublishPath: ./build

Optional: headers, routes (redirects/rewrites). See Static Sites.

Environment Variables

Literal: key + value (never hardcode secrets).
From Postgres: fromDatabase.name + fromDatabase.property (e.g. connectionString).
From Key Value or other service: fromService.type + fromService.name + fromService.property (e.g. connectionString, host, port, hostport) or fromService.envVarKey for another service’s env var.
Secret / user-set: sync: false (user is prompted in Dashboard on first create; add new secrets manually later). Cannot be used inside env var groups.
Generated: generateValue: true (base64 256-bit value).
Shared: fromGroup: <envVarGroups[].name> to attach an env var group.

Env groups cannot reference other services (no fromDatabase/fromService in groups) and cannot use sync: false. Put secrets and DB/KV references in service-level envVars, or reference a group and add service-specific vars alongside.

Databases (Render Postgres)

databases:
  - name: my-db
    plan: basic-256mb
    databaseName: my_app
    user: my_user
    region: oregon
    postgresMajorVersion: "18"

Plans (current): free, basic-256mb, basic-1gb, basic-4gb, pro-*, accelerated-*. Legacy: starter, standard, pro, pro plus (no new DBs on legacy). Optional: diskSizeGB, ipAllowList, readReplicas, highAvailability.enabled. Reference in services: fromDatabase.name, property: connectionString.

Key Value (Redis/Valkey)

Key Value instances are services with type: keyvalue (or deprecated redis). ipAllowList is required: use [] for internal-only, or - source: 0.0.0.0/0 to allow external.

services:
  - type: keyvalue
    name: my-cache
    ipAllowList:
      - source: 0.0.0.0/0
        description: everywhere
    plan: free
    maxmemoryPolicy: allkeys-lru

Reference in another service: fromService.type: keyvalue, fromService.name: my-cache, property: connectionString. Policies: allkeys-lru (caching), noeviction (job queues), etc. See Key Value.

Note: Some repos use root-level keyValueStores and fromKeyValueStore; the official spec uses services + fromService. Prefer the official form for new Blueprints.

Cron Jobs

- type: cron
  name: my-cron
  runtime: python
  schedule: "0 * * * *"
  buildCommand: "true"
  startCommand: python scripts/daily.py
  envVars: []

schedule is a cron expression (minute hour day month weekday). buildCommand is required (use "true" if no build). Free plan not available for cron/worker/pserv.

Env Var Groups

Share vars across services. No fromDatabase/fromService/sync: false inside groups—only literal values or generateValue: true.

envVarGroups:
  - name: app-env
    envVars:
      - key: CONCURRENCY
        value: "2"
      - key: APP_SECRET
        generateValue: true

services:
  - type: web
    name: api
    envVars:
      - fromGroup: app-env
      - key: DATABASE_URL
        fromDatabase:
          name: my-db
          property: connectionString

Health Check, Region, Pre-deploy

Web only: healthCheckPath: /health for zero-downtime deploys.
Region: region: oregon (default), ohio, virginia, frankfurt, singapore (set at create; cannot change later).
Pre-deploy: preDeployCommand runs after build, before start (e.g. migrations).

Scaling

Manual: numInstances: 2.
Autoscaling (Professional workspace): scaling.minInstances, scaling.maxInstances, scaling.targetCPUPercent or scaling.targetMemoryPercent. Not available with persistent disks.

Disks, Monorepos, Docker

Persistent disk: disk.name, disk.mountPath, disk.sizeGB (web, pserv, worker).
Monorepo: rootDir, buildFilter.paths / buildFilter.ignoredPaths, dockerfilePath / dockerContext.
Docker: runtime: docker (build from Dockerfile) or runtime: image (pull from registry). Use dockerCommand instead of startCommand when needed.

Preview Environments & Projects

Preview environments: Root-level previews.generation: off | manual | automatic, optional previews.expireAfterDays. Per-service previews.generation, previews.numInstances, previews.plan.
Projects/environments: Root-level projects with environments (each lists services, databases, envVarGroups). Use for staging/production. Optional ungrouped for resources not in any environment.

Common Deployment Patterns

Full stack (web + Postgres + Key Value)

Web service with fromDatabase for Postgres and fromService for Key Value. Add one databases entry and one type: keyvalue service; reference both from the web service envVars. See assets/web-with-postgres.yaml for Postgres; add a keyvalue service and fromService for Redis URL.

Microservices (API + worker + cron)

Multiple services in one Blueprint: type: web for the API, type: worker for a background processor, type: cron for scheduled jobs. Share envVarGroups or repeat env vars; use fromDatabase/fromService for shared DB/Redis. All use the same branch and buildCommand/startCommand as appropriate per runtime.

Preview environments for PRs

Set root-level previews.generation: automatic (or manual). Optionally previews.expireAfterDays: 7. Each PR gets a preview URL; per-service overrides with previews.generation, previews.numInstances, or previews.plan when needed.

Plans (Services)

plan: free | starter | standard | pro | pro plus (and for web/pserv/worker: pro max, pro ultra). Omit to keep existing or default to starter for new. Free not available for pserv, worker, cron.

Dashboard & API

Dashboard: https://dashboard.render.com — New → Blueprint, connect repo, select render.yaml.
Key Value: https://dashboard.render.com/new/redis

API Access

To use the Render API from the agent (verify deploys, trigger deploys, list services/logs):

Get an API key: Dashboard → Account Settings → API Keys.
Store as env var: Set RENDER_API_KEY in the environment (e.g. skills.entries.render.env or process env).
Authentication: Use Bearer token: Authorization: Bearer $RENDER_API_KEY on all requests.
API docs: https://api-docs.render.com — services, deploys, logs, validate Blueprint, etc.

Deploy to Render (same flow as Codex render-deploy skill)

Goal: get the app deployed by generating a Blueprint, then one-click via Dashboard deeplink; optionally trigger or verify via API when the user has RENDER_API_KEY.

Step 1: Analyze codebase and create render.yaml

Use references/codebase-analysis.md to determine runtime, build/start commands, env vars, and datastores.
Add or update render.yaml at repo root (see Blueprint sections above and references/blueprint-spec.md). Use sync: false for secrets. See assets/ for examples.
Validate before asking the user to push:
- CLI: render blueprints validate render.yaml (install: brew install render or Render CLI install).
- Or API: POST to Validate Blueprint with the YAML body.
Fix any validation errors before proceeding.

Step 2: Commit and push (required)

Render reads the Blueprint from the Git remote. The file must be committed and pushed.

git add render.yaml
git commit -m "Add Render deployment configuration"
git push origin main

If there is no Git remote, stop and ask the user to create a repo on GitHub/GitLab/Bitbucket, add it as origin, and push. Without a pushed repo, the Dashboard deeplink will not work.

Step 3: Dashboard deeplink (one-click deploy)

Get the repo URL and build the Blueprint deeplink:

git remote get-url origin

If the URL is SSH, convert to HTTPS (Render needs HTTPS for the deeplink):

SSH	HTTPS
`[email protected]:user/repo.git`	`https://github.com/user/repo`
`[email protected]:user/repo.git`	`https://gitlab.com/user/repo`
`[email protected]:user/repo.git`	`https://bitbucket.org/user/repo`

Pattern: replace git@<host>: with https://<host>/, remove .git suffix.

Deeplink format:

https://dashboard.render.com/blueprint/new?repo=<REPO_HTTPS_URL>

Example: https://dashboard.render.com/blueprint/new?repo=https://github.com/username/my-app

Give the user this checklist:

Confirm render.yaml is in the repo at the root (they just pushed it).
Click the deeplink to open Render Dashboard.
Complete Git provider OAuth if prompted.
Name the Blueprint (or accept default).
Fill in secret env vars (those with sync: false).
Review services/databases, then click Apply to deploy.

Deployment starts automatically. User can monitor in the Dashboard.

Step 4: Verify deployment (optional, needs API key)

If the user has set RENDER_API_KEY (e.g. in skills.entries.render.env or process env), the agent can verify after the user has applied the Blueprint:

List services: GET https://api.render.com/v1/services — Header: Authorization: Bearer $RENDER_API_KEY. Find the service by name.
List deploys: GET https://api.render.com/v1/services/{serviceId}/deploys?limit=1 — Check for status: "live" to confirm success.
Logs (if needed): Render API or Dashboard → service → Logs.

Example (exec tool or curl):

curl -s -H "Authorization: Bearer $RENDER_API_KEY" "https://api.render.com/v1/services" | head -100
curl -s -H "Authorization: Bearer $RENDER_API_KEY" "https://api.render.com/v1/services/{serviceId}/deploys?limit=1"

For a short checklist and common fixes, use references/post-deploy-checks.md and references/troubleshooting-basics.md.

Triggering deploys (re-deploy without push)

After repo is connected: Pushes to the linked branch trigger automatic deploys when auto-deploy is on.
Trigger via API: With RENDER_API_KEY, trigger a new deploy:
- POST https://api.render.com/v1/services/{serviceId}/deploys
- Header: Authorization: Bearer $RENDER_API_KEY
- Optional body: { "clearCache": "do_not_clear" } or "clear"
Deploy hook (no API key): Dashboard → service → Settings → Deploy Hook. User can set that URL as an env var (e.g. RENDER_DEPLOY_HOOK_URL); then the agent can run curl -X POST "$RENDER_DEPLOY_HOOK_URL" to trigger a deploy.

So: OpenClaw can deploy by (1) creating render.yaml, (2) having the user push and click the Blueprint deeplink (one-click), and optionally (3) triggering or verifying deploys via API or deploy hook when credentials are available.

Render from OpenClaw (no native MCP)

OpenClaw does not load MCP servers from config. Use one of:

Option A: REST API (recommended when API key is set)

Use RENDER_API_KEY and the Render REST API (curl/exec): create services, list services, trigger deploys, list deploys, list logs. Request bodies and endpoints: references/rest-api-deployment.md.

Option B: MCP via mcporter (if installed)

If the user has mcporter and Render configured (URL https://mcp.render.com/mcp, Bearer $RENDER_API_KEY), the agent can call Render MCP tools directly. Tool list and example commands: references/mcp-integration.md.

Example:

mcporter call render.list_services
mcporter call render.create_web_service name=my-api runtime=node buildCommand="npm ci" startCommand="npm start" repo=https://github.com/user/repo branch=main plan=free

Workspace must be set first (e.g. user: “Set my Render workspace to MyTeam”). Use mcporter list render --schema to see current tools and parameters.

Checklist for New Deploys

Add or update render.yaml with services (and optionally databases, envVarGroups, projects). Use runtime and official Key Value form (type: keyvalue in services, fromService for references).
Use sync: false for secrets in service envVars only; tell user to set them in Dashboard. Never put secrets in env groups.
For Key Value, set ipAllowList (required).
Validate: render blueprints validate render.yaml or API.
User must commit and push, then use the Blueprint deeplink (https://dashboard.render.com/blueprint/new?repo=<HTTPS_REPO_URL>) to deploy. Optionally verify or re-deploy via API if RENDER_API_KEY is set.

Rules

Prefer Blueprint for full app definition; suggest Dashboard/API only when Blueprint cannot express something.
Never commit real API keys or secrets; use sync: false and document which env vars the user must set.
Use runtime (not deprecated env). For Python/Node set PYTHON_VERSION/NODE_VERSION in envVars when required.
When referencing Key Value or other services, use fromService with correct type (e.g. keyvalue, pserv).

When it activates

Automatically, when a task matches. Use when the user wants to deploy, host, or publish an app; create or edit render.yaml; add web, static, workers, cron, Postgres, or Key Value; get the Blueprint deeplink to deploy; trigger or verify deploys via API when RENDER_API_KEY is set; connect Render MCP via mcporter for direct service creation; or configure env vars, health checks, scaling, previews, and projects.

About this skill

Automatic

DevOps & SRE 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/deploy-on-render/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 10 files

Illustrative Want to see what render 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

Render Skill

When to Use This Skill

Deployment Method Selection

Happy Path (New Users)

Prerequisites Check

Security Notes

References

Blueprint Basics

Service Types

Runtimes

Minimal Web Service

Static Site

Environment Variables

Databases (Render Postgres)

Key Value (Redis/Valkey)

Cron Jobs

Env Var Groups

Health Check, Region, Pre-deploy

Scaling

Disks, Monorepos, Docker

Preview Environments & Projects

Common Deployment Patterns

Full stack (web + Postgres + Key Value)

Microservices (API + worker + cron)

Preview environments for PRs

Plans (Services)

Dashboard & API

API Access

Deploy to Render (same flow as Codex render-deploy skill)

Step 1: Analyze codebase and create render.yaml

Step 2: Commit and push (required)

Step 3: Dashboard deeplink (one-click deploy)

Step 4: Verify deployment (optional, needs API key)

Triggering deploys (re-deploy without push)

Render from OpenClaw (no native MCP)

Option A: REST API (recommended when API key is set)

Option B: MCP via mcporter (if installed)

Checklist for New Deploys

Rules

When it activates

SkillSafety

Source

Related skills

More in the registry