Ready to supercharge your AI agents?

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

GCP DrawIO Diagram Generator · a5c-ai | DecimalAI

DevOpsby a5c-ai

GCP DrawIO Diagram Generator

Generates DrawIO XML diagrams for Google Cloud Platform architectures from text descriptions or images. Analyzes existing .drawio files to extract GCP components.

Never made a case worseMaintained

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

41%95%of test cases passed +55 pts

Without skill9 of 22

With skill21 of 22

12 fixed9 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/29/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe generated a `.drawio` file and want to validate its XML schema and structure using local CLI tools before exporting. Which python script in the scripts directory should be executed for structural validation?

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 a5c-ai-generating-gcp-diagrams
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("a5c-ai-generating-gcp-diagrams")
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 a5c-ai-generating-gcp-diagrams

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/a5c-ai-generating-gcp-diagrams/SKILL.md https://app.decimal.ai/s/a5c-ai-generating-gcp-diagrams/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/a5c-ai-generating-gcp-diagrams/SKILL.md

This gets SKILL.md only. The skill's 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/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/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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("a5c-ai-generating-gcp-diagrams")
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/a5c-ai-generating-gcp-diagrams/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/a5c-ai-generating-gcp-diagrams/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 17 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 a5c-ai-generating-gcp-diagrams

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/a5c-ai-generating-gcp-diagrams/SKILL.md https://app.decimal.ai/s/a5c-ai-generating-gcp-diagrams/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/a5c-ai-generating-gcp-diagrams/SKILL.md

This gets SKILL.md only. The skill's 17 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/a5c-ai-generating-gcp-diagrams/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/a5c-ai-generating-gcp-diagrams.json

This gets SKILL.md only. The skill's 17 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/29/2026
Source: a5c-ai/babysitter ↗
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

GCP DrawIO Diagram Generator

Generates professional DrawIO XML diagrams for Google Cloud Platform architectures.

Capabilities

Extract - Analyze existing DrawIO XML files to identify GCP shapes, connections, and structure
Identify - Recognize GCP service icons from architecture diagram images
Generate - Create valid DrawIO XML from images or text descriptions
Convert - Transform GCP architecture diagrams into editable DrawIO format

Quick Reference

GCP Shape Pattern

shape=mxgraph.gcp2.{service_name}

Note: GCP uses snake_case for shape names (e.g., cloud_run, cloud_sql, cloud_storage).

Icon Pattern: Unlike AWS, GCP uses a single icon pattern for all services — there is no service vs instance icon distinction. The same shape=mxgraph.gcp2.{name} is used whether labeling the service itself ("Cloud Run") or a specific instance ("Cloud Run (API Handler)"). Differentiate by label text only.

Common GCP Services

Service	Shape Code
Cloud Run	`mxgraph.gcp2.cloud_run`
BigQuery	`mxgraph.gcp2.bigquery`
Cloud Storage	`mxgraph.gcp2.cloud_storage`
Vertex AI	`mxgraph.gcp2.cloud_machine_learning`
Cloud Scheduler	`mxgraph.gcp2.cloud_scheduler`
Apigee	`mxgraph.gcp2.apigee_api_platform`
Pub/Sub	`mxgraph.gcp2.cloud_pubsub`
Cloud SQL	`mxgraph.gcp2.cloud_sql`
GKE	`mxgraph.gcp2.compute_engine`
Cloud Functions	`mxgraph.gcp2.cloud_functions`

GCP Container Types

Container	Use Case
gcp_project	Main project boundary (two-cell pattern)
gcp_vpc_sc	VPC Service Controls perimeter (green border)
gcp_region	Regional grouping
gcp_zone	Zone grouping
logical_group_dashed	Logical grouping with dashed border
logical_group_solid	Solid border grouping
subnet	Subnet boundary
firewall_rules	Firewall rules grouping
instance_group	Instance group container

Task 1: Analyze a DrawIO File

Use this workflow to extract and document all components from an existing DrawIO file.

Steps

Read the file - Load the .drawio XML file
Parse structure - Extract all <mxCell> elements
Identify shapes - Find cells with vertex="1"
Identify connections - Find cells with edge="1"
Extract styles - Parse style strings for each element
Map hierarchy - Build container/child relationships using parent attribute
Generate report - Output findings in structured format

Input

Path to .drawio file

Output

Generate a Markdown report with:

# DrawIO Analysis Report

## Summary
- Total shapes: X
- Total connections: Y
- Containers: Z

## Shape Inventory

| ID | Label | Type | Position | Parent |
|----|-------|------|----------|--------|
| abc | Cloud Run | mxgraph.gcp2.cloud_run | (100,200) | vpc1 |

## Connection Matrix

| From | To | Label | Type |
|------|-----|-------|------|
| Cloud Run | BigQuery | API | solid |

## Container Hierarchy

- VPC-SC (vpc1)
  - Cloud Run (run1)
  - Cloud Run (run2)
  - BigQuery (bq1)

## Style Analysis

### Unique Shapes Found
- mxgraph.gcp2.cloud_run (4 instances)
- mxgraph.gcp2.bigquery (2 instances)

Task 2: Convert Image to DrawIO

Use this workflow to recreate a GCP architecture diagram from an image.

Steps

Analyze image - Identify all visual elements:
- GCP service icons (shape, color, label)
- Containers/boundaries (color, border style)
- Connections (solid, dashed, arrows)
- Labels and text
Map to library - For each identified element:
- Look up in assets/gcp-icons.json by visual signature or label
- Match containers to assets/containers.json
- Note any unrecognized elements
Estimate layout - Determine positions:
- Identify container boundaries first
- Place icons within containers
- Estimate x,y coordinates and dimensions
- Standard icon size: 50x50 pixels
Generate XML - Build the DrawIO structure:
- Start with base template from assets/templates/drawio-base.xml
- Add containers first (they become parents)
- Add service icons with correct parent references
- Add connections between shapes
Create confidence report - Document accuracy:
- List all identified components
- Note any uncertain matches
- Flag potential issues

Input

GCP architecture diagram image (PNG/JPG)

Output

Valid .drawio XML file
Confidence report (Markdown)

Confidence Report Format

# Conversion Confidence Report

## Overall Confidence: 85%

## Identified Components

### High Confidence (>90%)
- Cloud Run x4 - Clear icon match
- BigQuery x2 - Clear icon match
- VPC-SC container - Green border, correct label

### Medium Confidence (70-90%)
- Vertex AI Search - Icon similar, label confirms

### Low Confidence (<70%)
- Unknown icon at position (300, 400) - Mapped to generic service

## Connection Accuracy
- 12/14 connections clearly visible
- 2 connections inferred from layout

## Notes
- "Same Instance" dashed container identified
- Bidirectional arrows on 3 connections

Task 3: Create DrawIO from Description

Use this workflow to generate a new GCP diagram from text specifications.

Steps

Parse requirements - Extract from description:
- Required GCP services
- Container/grouping needs
- Connection requirements
- Layout preferences
Select components - From libraries:
- Look up services in assets/gcp-icons.json
- Choose containers from assets/containers.json
- Select connection styles
Plan layout - Design the arrangement:
- Determine canvas size
- Position containers first
- Arrange services logically (left-to-right data flow, top-to-bottom hierarchy)
- Standard spacing: 100px between 50x50 icons
Generate XML - Build the diagram:
- Use assets/templates/drawio-base.xml as starting point
- Add elements in order: containers, services, connections
- Assign unique IDs to all elements
Validate - Check the output:
- All requested components present
- Connections reference valid IDs
- Layout is logical and readable

Input

Text description of desired GCP architecture

Output

Valid .drawio XML file

Example Input

Create a GCP architecture with:
- VPC-SC container
- Cloud Scheduler triggering Cloud Run
- Cloud Run connecting to BigQuery and Cloud Storage
- Vertex AI Search connected to BigQuery

Example Output Structure

<mxfile ...>
  <diagram name="GCP Architecture">
    <mxGraphModel ...>
      <root>
        <mxCell id="0" />
        <mxCell id="1" parent="0" />
        <!-- VPC-SC Container -->
        <mxCell id="vpc" value="VPC-SC" style="..." vertex="1" parent="1">
          <mxGeometry x="50" y="50" width="700" height="400" />
        </mxCell>
        <!-- Cloud Scheduler -->
        <mxCell id="sched" value="Cloud Scheduler" style="...mxgraph.gcp2.cloud_scheduler" vertex="1" parent="vpc">
          <mxGeometry x="50" y="100" width="50" height="50" />
        </mxCell>
        <!-- More shapes... -->
        <!-- Connections -->
        <mxCell id="conn1" edge="1" source="sched" target="run" style="..." />
      </root>
    </mxGraphModel>
  </diagram>
</mxfile>

Shape Library Reference

Looking Up a GCP Service

Open assets/gcp-icons.json
Search by service_name or recognition_keywords
Use the drawio_shape.full_style for complete styling
Or construct style using shape=mxgraph.gcp2.{shape_name}

Service Coverage:

46 GCP services across 11 categories
40 exact matches, 6 fallback icons
Categories: compute, database, storage, networking, ai_ml, integration, operations, api_management, data_analytics, devops, security

Note: 6 services use fallback icons (Workflows, Eventarc, Artifact Registry, Cloud Deploy, Secret Manager, Identity Platform) as they're newer services not yet in DrawIO's mxgraph.gcp2 stencil. See references/ICON-COMPATIBILITY.md for complete validation details.

GCP Service Categories

Category	Services
compute	Cloud Run, Compute Engine, GKE, Cloud Functions, App Engine
database	BigQuery, Cloud SQL, Firestore, Spanner, Bigtable, Memorystore
storage	Cloud Storage, Filestore, Persistent Disk
networking	VPC, Load Balancing, CDN, DNS, Armor, Cloud NAT
ai_ml	Vertex AI, AI Platform, Vision, NLP, Speech-to-Text
integration	Pub/Sub, Cloud Tasks, Workflows, Eventarc, Scheduler
operations	Logging, Monitoring, Trace, Error Reporting
api_management	Apigee, API Gateway
data_analytics	Dataflow, Dataproc, Cloud Composer
devops	Cloud Build, Artifact Registry, Container Registry, Cloud Deploy
security	Cloud KMS, Secret Manager, Identity Platform

Visual Best Practices (Summary)

For detailed visual design guidelines, see references/DIAGRAM-BEST-PRACTICES.md.

GCP Project Zone (Two-Cell Pattern)

The GCP Project container uses two cells, not one:

Container cell: Plain rectangle with fillColor=#F6F6F6;strokeColor=none; and HTML value <b>Google </b>Cloud Platform
Logo child cell: shape=mxgraph.gcp2.google_cloud_platform at 23x20px with relative=1 geometry

See assets/templates/node-template.xml for the exact template.

Font Colors

Service icon labels: fontColor=#424242 (dark gray)
GCP Project zone text: fontColor=#717171
VPC-SC container title: fontColor=#2E7D32 (dark green)
Dashed group labels: fontColor=#424242

Icon Spacing

Icon size: 50x50 pixels
Standard spacing: 100px between icons
Container padding: 20-30px

Connection Labels

Always add these properties to labeled connections:

labelBackgroundColor=#FFFFFF;fontSize=10;fontColor=#333333;

Connection Best Practices

Standard width: strokeWidth=1 for most connections
Thick width: strokeWidth=2 only for primary data paths (use sparingly - max 1-3 per diagram)
Orthogonal routing: edgeStyle=orthogonalEdgeStyle for professional appearance
When 3+ connections cross same corridor: consolidate into single connection

XML Structure Quick Reference

For complete XML examples and detailed structure, see references/xml-examples.md.

The key building blocks:

Shape: <mxCell id="..." value="Label" style="..." vertex="1" parent="1"> with <mxGeometry>
Connection: <mxCell id="..." edge="1" source="..." target="..." style="...">
Container: Shape with container=1 in style; children set parent to container ID
Root cells: Every diagram needs <mxCell id="0"/> and <mxCell id="1" parent="0"/>

For XML parsing and extraction techniques, see references/xml-parser-guide.md.

Troubleshooting

Icon Not Displaying

Verify shape name matches exactly: mxgraph.gcp2.cloud_run (underscore, not hyphen)
Check references/ICON-COMPATIBILITY.md for correct shape names
Ensure vertex="1" is present
Check that <mxGeometry> has valid width/height (50x50)
For Workflows/Eventarc, note these don't have exact icon matches in DrawIO's library

Connection Not Rendering

Verify source and target IDs exist
Ensure edge="1" is set
Check that source/target shapes are vertices

Shapes Not Inside Container

Set child's parent attribute to container's ID
Ensure container has container=1 in style
Position child coordinates relative to container (not absolute)

Label Not Showing

Check value attribute is set
Verify fontSize is reasonable (11-14)
Ensure fontColor=#424242 is set

File Won't Open in DrawIO

Validate XML structure (proper closing tags)
Ensure id="0" and id="1" root cells exist
Check for special characters in labels (use 
 for newlines)

Desktop Integration

After generating a .drawio file, you can validate and preview it:

Validate: python scripts/validate-drawio.py output.drawio --verbose
Analyze: python scripts/analyze-existing.py output.drawio --markdown
Validate Icons: python scripts/validate-gcp-icons.py
Export PNG: ./scripts/export-diagram.sh output.drawio png
Open in DrawIO: ./scripts/open-diagram.sh output.drawio

Requires DrawIO Desktop. Install on macOS: brew install drawio

Files in This Skill

File	Purpose
`SKILL.md`	This file - main instructions
Assets
`assets/gcp-icons.json`	GCP service icon database (46 services)
`assets/containers.json`	GCP container and connection styles
`assets/templates/drawio-base.xml`	Base XML template
`assets/templates/node-template.xml`	Shape insertion template
`assets/templates/connection-template.xml`	Connection template
References
`references/ICON-COMPATIBILITY.md`	Icon validation reference
`references/DIAGRAM-BEST-PRACTICES.md`	Visual design and layout guidelines
`references/xml-parser-guide.md`	Detailed XML parsing reference
`references/xml-examples.md`	Copy-paste XML examples
`references/coordinate-system.md`	Positioning and layout guide
`references/style-guide.md`	Style string reference
Scripts
`scripts/validate-drawio.py`	Validate .drawio XML structure
`scripts/validate-gcp-icons.py`	Validate GCP icon compatibility
`scripts/fix-gcp-icons.py`	Auto-fix icon shape names
`scripts/fix-drawio-icons.py`	Bulk fix icon references in .drawio files
`scripts/extract-shape-names.py`	Extract available shapes from DrawIO stencil
`scripts/analyze-existing.py`	Extract shapes/connections from .drawio files
`scripts/export-diagram.sh`	Export to PNG/PDF via DrawIO Desktop CLI
`scripts/open-diagram.sh`	Open .drawio file in DrawIO Desktop

When it activates

Automatically, when a task matches. Use for GCP architecture diagrams, cloud infrastructure documentation, or when converting GCP diagram images to editable DrawIO format.

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 — 8/10/2026

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

a5c-ai / babysitter

library/specializations/devops-sre-platform/skills/generating-gcp-diagrams/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1Bundled 17 files · scripts

Illustrative Want to see what a5c-ai/generating-gcp-diagrams 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.

a5c-ai/generating-aws-diagramsGenerates DrawIO XML diagrams for Amazon Web Services architectures from text descriptions or images. Analyzes existing .drawio files to extract AWS components. Use for AWS architecture diagrams, cloud infrastructure documentation, or when converting AWS diagram images to editable DrawIO format.Close match+23 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

GCP DrawIO Diagram Generator

Capabilities

Quick Reference

GCP Shape Pattern

Common GCP Services

GCP Container Types

Task 1: Analyze a DrawIO File

Steps

Input

Output

Task 2: Convert Image to DrawIO

Steps

Input

Output

Confidence Report Format

Task 3: Create DrawIO from Description

Steps

Input

Output

Example Input

Example Output Structure

Shape Library Reference

Looking Up a GCP Service

GCP Service Categories

Visual Best Practices (Summary)

GCP Project Zone (Two-Cell Pattern)

Font Colors

Icon Spacing

Connection Labels

Connection Best Practices

XML Structure Quick Reference

Troubleshooting

Icon Not Displaying

Connection Not Rendering

Shapes Not Inside Container

Label Not Showing

File Won't Open in DrawIO

Desktop Integration

Files in This Skill

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry