Ready to supercharge your AI agents?

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

Diagram Generator · jimliu | DecimalAI

Design & Mediaby jimliu

Diagram Generator

Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more.

Maintained

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

45%77%of test cases passed +32 pts

Without skill10 of 22

With skill17 of 22

9 fixed8 passed either way3 still failing2 broke

Measured on gemini-3.6-flash11/5/2026v2

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskIf I run `theme-switch.ts diagram.svg --theme=light` without specifying `--output`, what exact file name is created by default?

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 baoyu-diagram
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("baoyu-diagram")
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 baoyu-diagram

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/baoyu-diagram/SKILL.md https://app.decimal.ai/s/baoyu-diagram/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/baoyu-diagram/SKILL.md

This gets SKILL.md only. The skill's 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/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/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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("baoyu-diagram")
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/baoyu-diagram/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/baoyu-diagram/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 11 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 baoyu-diagram

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/baoyu-diagram/SKILL.md https://app.decimal.ai/s/baoyu-diagram/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/baoyu-diagram/SKILL.md

This gets SKILL.md only. The skill's 11 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/baoyu-diagram/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 11 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2, tested 11/5/2026
Source: jimliu/baoyu-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

Diagram Generator

Create SVG diagrams. Each SVG embeds its own styles, uses CSS custom properties for theming, and loads nothing over the network.

Output Files

For a diagram saved as <name>.svg, produce exactly these files:

File	What it is	Made by
`<name>.svg`	Source SVG, CSS variables with dark theme values	You (the LLM)
`<name>.light.svg`	Same markup with light theme values	`theme-switch.ts --theme=light`
`<name>@2x.png`	Dark PNG at 2x scale	`main.ts`
`<name>[email protected]`	Light PNG at 2x scale	`main.ts --theme light`

If the user asks for only one theme, or only SVG, produce just those files.

Themes

All colors are CSS custom properties defined in the :root block of the SVG's <style>; markup references them as var(--bg), var(--color-primary-fill), etc. Never hardcode color values in SVG attributes.

Theme values live in {baseDir}/themes/<name>.json — one flat JSON object mapping CSS property names (keys starting with --) to colors. Other keys (e.g. "description") are metadata, ignored by scripts. Built-in: dark.json, light.json.

Custom themes: drop a new .json into themes/ — no script changes needed:

// themes/my-brand.json
{
  "description": "Corporate brand theme",
  "--bg": "#ffffff",
  "--text": "#1a1a2e",
  "--text-muted": "#6b7280",
  "--arrow": "#9ca3af",
  "--color-primary-fill": "rgba(37,99,235,0.12)",
  "--color-primary-stroke": "#2563eb",
  "--color-secondary-fill": "rgba(22,163,74,0.12)",
  "--color-secondary-stroke": "#16a34a"
}

Apply with --theme=my-brand (theme-switch.ts, main.ts and flatten-vars.ts all support it). Variables omitted from a custom theme are not replaced. When generating SVGs for a custom theme, use its values in the :root block.

CSS Custom Properties

Variable	Dark Theme Default	Light Theme Value	Usage
`--bg`	`#0f172a`	`#f8fafc`	Page background
`--bg-grid`	`#1e293b`	`#e2e8f0`	Grid pattern stroke
`--mask`	`#0f172a`	`#f8fafc`	Opaque mask fill (same as --bg)
`--text`	`white`	`#0f172a`	Primary text color
`--text-muted`	`#94a3b8`	`#475569`	Secondary/sublabel text
`--arrow`	`#64748b`	`#64748b`	Arrow/connector lines (unchanged)
`--color-primary-fill`	`rgba(8,51,68,0.4)`	`rgba(6,182,212,0.12)`	Frontend, user-facing, inputs
`--color-primary-stroke`	`#22d3ee`	`#0891b2`	Primary border
`--color-secondary-fill`	`rgba(6,78,59,0.4)`	`rgba(5,150,105,0.12)`	Backend, services, processing
`--color-secondary-stroke`	`#34d399`	`#059669`	Secondary border
`--color-tertiary-fill`	`rgba(76,29,149,0.4)`	`rgba(124,58,237,0.12)`	Database, storage, persistence
`--color-tertiary-stroke`	`#a78bfa`	`#7c3aed`	Tertiary border
`--color-accent-fill`	`rgba(120,53,15,0.3)`	`rgba(217,119,6,0.12)`	Cloud, infrastructure, regions
`--color-accent-stroke`	`#fbbf24`	`#d97706`	Accent border
`--color-alert-fill`	`rgba(136,19,55,0.4)`	`rgba(225,29,72,0.12)`	Security, errors, warnings
`--color-alert-stroke`	`#fb7185`	`#e11d48`	Alert border
`--color-connector-fill`	`rgba(251,146,60,0.3)`	`rgba(234,88,12,0.12)`	Buses, queues, middleware
`--color-connector-stroke`	`#fb923c`	`#ea580c`	Connector border
`--color-neutral-fill`	`rgba(30,41,59,0.5)`	`rgba(100,116,139,0.12)`	External, generic, unknown
`--color-neutral-stroke`	`#94a3b8`	`#64748b`	Neutral border
`--color-highlight-fill`	`rgba(59,130,246,0.3)`	`rgba(59,130,246,0.12)`	Active state, focus, current step
`--color-highlight-stroke`	`#60a5fa`	`#3b82f6`	Highlight border

Design System

Typography

Use a locally installed monospace font stack. Do not @import web fonts or reference any remote resource: the SVG must render the same offline, and the PNG converter cannot fetch fonts.

<style>
  text { font-family: 'JetBrains Mono', 'SF Mono', 'Cascadia Code', 'Noto Sans Mono', 'DejaVu Sans Mono', monospace; }
</style>

Font sizes by role:

Title: 16px, weight 700, fill: var(--text)
Component name: 11-12px, weight 600, fill: var(--text)
Sublabel / description: 9px, weight 400, fill: var(--text-muted)
Annotation / note: 8px, weight 400
Tiny label (on arrows): 7-8px

Core Visual Elements

Background + Grid:

<defs>
  <pattern id="grid" width="40" height="40" patternUnits="userSpaceOnUse">
    <path d="M 40 0 L 0 0 0 40" fill="none" stroke="var(--bg-grid)" stroke-width="0.5"/>
  </pattern>
</defs>
<rect width="100%" height="100%" fill="var(--bg)"/>
<rect width="100%" height="100%" fill="url(#grid)"/>

Arrowhead marker (standard):

<marker id="arrow" markerWidth="10" markerHeight="7" refX="9" refY="3.5" orient="auto">
  <polygon points="0 0, 10 3.5, 0 7" fill="var(--arrow)"/>
</marker>

Arrowhead marker (colored) — create per-color as needed:

<marker id="arrow-primary" markerWidth="10" markerHeight="7" refX="9" refY="3.5" orient="auto">
  <polygon points="0 0, 10 3.5, 0 7" fill="var(--color-primary-stroke)"/>
</marker>

Open arrowhead (for async/return messages):

<marker id="arrow-open" markerWidth="10" markerHeight="7" refX="9" refY="3.5" orient="auto">
  <polyline points="0 0, 10 3.5, 0 7" fill="none" stroke="var(--arrow)" stroke-width="1.5"/>
</marker>

SVG Structure & Layering

Draw in this order (SVG paints back-to-front):

Background fill + grid pattern
Region/group boundaries (dashed outlines)
Connection arrows and lines
Opaque masking rects (same position as component boxes, fill="var(--mask)")
Component boxes (semi-transparent fill + stroke via CSS variables)
Text labels
Legend (bottom-right or bottom area, outside all boundaries)
Title block (top-left)

The opaque mask rect is required — semi-transparent component fills otherwise show arrows underneath:

<!-- Mask layer: opaque background to hide arrows -->
<rect x="100" y="100" width="160" height="60" rx="6" fill="var(--mask)"/>
<!-- Visual layer: styled component -->
<rect x="100" y="100" width="160" height="60" rx="6" fill="var(--color-primary-fill)" stroke="var(--color-primary-stroke)" stroke-width="1.5"/>
<text x="180" y="125" fill="var(--text)" font-size="11" font-weight="600" text-anchor="middle">API Gateway</text>
<text x="180" y="141" fill="var(--text-muted)" font-size="9" text-anchor="middle">Kong / Nginx</text>

Spacing Rules

Follow strictly to prevent overlaps:

Component box height: 50-70px (standard), 80-120px (large/complex)
Minimum gap between components: 40px vertical, 30px horizontal
Arrow label clearance: 10px from any box edge
Region boundary padding: 20px inside edges around contained components
Legend placement: At least 20px below the lowest diagram element
Title block: 20px from top-left, outside diagram content area
viewBox: Always extend to fit all content + 30px padding on all sides

Component Patterns

Standard box (service/process):

<rect x="X" y="Y" width="160" height="60" rx="6" fill="var(--mask)"/>
<rect x="X" y="Y" width="160" height="60" rx="6" fill="var(--color-primary-fill)" stroke="var(--color-primary-stroke)" stroke-width="1.5"/>
<text x="CX" y="Y+24" fill="var(--text)" font-size="11" font-weight="600" text-anchor="middle">Name</text>
<text x="CX" y="Y+40" fill="var(--text-muted)" font-size="9" text-anchor="middle">description</text>

Decision diamond (flowchart):

<g transform="translate(CX, CY)">
  <polygon points="0,-35 50,0 0,35 -50,0" fill="var(--mask)"/>
  <polygon points="0,-35 50,0 0,35 -50,0" fill="var(--color-accent-fill)" stroke="var(--color-accent-stroke)" stroke-width="1.5"/>
  <text y="4" fill="var(--text)" font-size="10" font-weight="600" text-anchor="middle">Condition?</text>
</g>

Database cylinder:

<g transform="translate(X, Y)">
  <rect x="0" y="10" width="120" height="50" rx="2" fill="var(--mask)"/>
  <ellipse cx="60" cy="10" rx="60" ry="12" fill="var(--mask)"/>
  <ellipse cx="60" cy="60" rx="60" ry="12" fill="var(--mask)"/>
  <rect x="0" y="10" width="120" height="50" fill="var(--color-tertiary-fill)"/>
  <ellipse cx="60" cy="10" rx="60" ry="12" fill="var(--color-tertiary-fill)" stroke="var(--color-tertiary-stroke)" stroke-width="1.5"/>
  <ellipse cx="60" cy="60" rx="60" ry="12" fill="var(--color-tertiary-fill)" stroke="var(--color-tertiary-stroke)" stroke-width="1.5"/>
  <line x1="0" y1="10" x2="0" y2="60" stroke="var(--color-tertiary-stroke)" stroke-width="1.5"/>
  <line x1="120" y1="10" x2="120" y2="60" stroke="var(--color-tertiary-stroke)" stroke-width="1.5"/>
  <text x="60" y="40" fill="var(--text)" font-size="11" font-weight="600" text-anchor="middle">PostgreSQL</text>
</g>

Region boundary:

<rect x="X" y="Y" width="W" height="H" rx="12" fill="none" stroke="var(--color-accent-stroke)" stroke-width="1" stroke-dasharray="8,4"/>
<text x="X+12" y="Y+16" fill="var(--color-accent-stroke)" font-size="9" font-weight="600">AWS us-east-1</text>

Security group:

<rect x="X" y="Y" width="W" height="H" rx="8" fill="none" stroke="var(--color-alert-stroke)" stroke-width="1" stroke-dasharray="4,4"/>
<text x="X+10" y="Y+14" fill="var(--color-alert-stroke)" font-size="8" font-weight="500">VPC / Security Group</text>

Diagram Types & Layout

Determine this SKILL.md file's directory path as {baseDir}. Before layout, read the type's reference in {baseDir}/references/ if one exists.

Type	When to use	Reference	Layout key points
Architecture	System components & relationships	`references/architecture.md`	LTR or TTB data flow; group related services in region boundaries; buses/connectors between layers; databases at bottom or right
Flowchart	Decision logic, process steps	`references/flowchart.md`	Top-to-bottom primary flow; diamonds with Yes/No labels on exit arrows; rounded rects for start/end; Highlight color for the happy path
Sequence	Time-ordered interactions between actors	`references/sequence.md`	Actor boxes at top, vertical dashed lifelines; horizontal messages (solid=sync, dashed=return); time flows down; activation bars; number messages if complex
Structural	Class/ER diagrams, org charts	`references/structural.md`	Compartmented boxes (name / attributes / methods); filled diamond=composition, empty diamond=aggregation, dashed arrow=dependency, solid triangle=inheritance
Mind Map	Brainstorming, topic exploration	—	Radiating layout from a central concept; cubic-bezier `<path>` branches; vary branch colors; font size decreases outward
Timeline	Chronological events	—	Horizontal or vertical axis; circle/diamond event markers, period spans; descriptions on alternating sides; color by event type
State Machine	State transitions, lifecycle	—	Rounded-rect states, double border for composite; filled circle = initial, bullseye = final; curved self-transitions; label transitions `event [guard] / action`
Illustrative	Conceptual explanations, comparisons	—	Free-form layout, icons, annotations, visual metaphors
Data Flow	Data transformation pipelines	—	Process bubbles, data stores, external entities

Output Rules

Each SVG is a single file with no external resources — no @import, web fonts, remote images or scripts
Set viewBox to fit all content with 30px padding; do NOT set fixed width/height attributes
Include xmlns="http://www.w3.org/2000/svg" on the root <svg>
Put all <style>, <defs>, markers, and patterns at the top
Use text-anchor="middle" for centered labels; text must not overflow boxes
Chinese text: use font-family: 'JetBrains Mono', 'Noto Sans SC', 'PingFang SC', sans-serif' and widen boxes — CJK characters are wider
CSS variables required: every color is a var(--...) reference so theme switching works
Save location: input is a file → {inputFileDir}/diagram/; otherwise {projectDir}/diagram/{topic-slug}/. Create the directory if missing

Scripts

Determine this SKILL.md file's directory path as {baseDir}. Scripts live in {baseDir}/scripts/:

theme-switch.ts — write the SVG with another theme's variable values
main.ts — convert an SVG to a @2x PNG
flatten-vars.ts — inline CSS variables into literal colors (only for other non-browser tools; main.ts does this itself)

Resolve ${BUN_X} runtime: if bun installed → bun; if npx available → npx -y bun; else suggest installing bun.

Theme switch

${BUN_X} {baseDir}/scripts/theme-switch.ts <svg-path> --theme=light [--output=path/to/output.svg]
${BUN_X} {baseDir}/scripts/theme-switch.ts <svg-path> --theme=dark
${BUN_X} {baseDir}/scripts/theme-switch.ts <svg-path> --theme=my-brand   # {baseDir}/themes/<name>.json

Replaces the :root { ... } definitions with the target theme's values; var(--...) references stay unchanged and the source is not modified. Without --output, writes <name>.<theme>.svg next to the input. The source already carries dark values, so --theme=dark on it is unnecessary.

Dependencies

main.ts needs sharp, pinned in {baseDir}/scripts/package.json with a lockfile. Install once:

cd {baseDir}/scripts && ${BUN_X} install

If sharp is missing, main.ts stops with an error that gives this command; it never installs anything itself. Then deliver the SVG files and tell the user how to enable PNG output. theme-switch.ts and flatten-vars.ts have no dependencies.

SVG → @2x PNG

${BUN_X} {baseDir}/scripts/main.ts <svg-path> [options]

Options:

-t, --theme <name> — Theme used to resolve CSS variables (default: dark; any {baseDir}/themes/<name>.json works)
-s, --scale <n> — Scale factor (default: 2)
-o, --output <path> — Custom output path (default: <input>@2x.png)
--json — JSON output

sharp (librsvg) does not understand CSS var(), so main.ts replaces every var(--xxx) with the theme's literal value and drops the :root block. It fails if the SVG references a variable that neither the theme nor the SVG defines. SVGs with hardcoded colors (legacy diagrams) are converted as-is.

To flatten without converting (e.g. for another renderer):

${BUN_X} {baseDir}/scripts/flatten-vars.ts <svg-path> <output-path> [--theme=<name>]

Process

Identify the diagram type; read its reference file if one exists
Plan the layout: list components, grouping and flow direction, calculate positions
Write the SVG in the layering order above, colors via CSS variables only, with the :root { ... } block using the dark defaults from the CSS Custom Properties table
Verify spacing rules — no overlaps, legends outside boundaries, viewBox large enough
Save as <name>.svg (the dark version)
Run ${BUN_X} {baseDir}/scripts/theme-switch.ts <name>.svg --theme=light → <name>.light.svg
Run ${BUN_X} {baseDir}/scripts/main.ts <name>.svg → <name>@2x.png
Run ${BUN_X} {baseDir}/scripts/main.ts <name>.svg --theme light -o <name>[email protected] → <name>[email protected]
Present the files listed in Output Files to the user

When it activates

Automatically, when a task matches. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when th

About this skill

Automatic

Design & UX Review pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/4/2026

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

jimliu / baoyu-skills

skills/baoyu-diagram/SKILL.md

View on GitHub ↗

License MITImported 11/4/2026Version v2Bundled 11 files · scripts

Illustrative Want to see what baoyu-diagram 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.

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

Diagram Generator

Output Files

Themes

CSS Custom Properties

Design System

Typography

Core Visual Elements

SVG Structure & Layering

Spacing Rules

Component Patterns

Diagram Types & Layout

Output Rules

Scripts

Theme switch

Dependencies

SVG → @2x PNG

Process

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry