Ready to supercharge your AI agents?

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

Mermaid Studio · tech-leads-club | DecimalAI

Documentationby tech-leads-club

Mermaid Studio

Expert Mermaid diagram creation, validation, and rendering with dual-engine output (SVG/PNG/ASCII). Supports all 20+ diagram types including C4 architecture, AWS architecture-beta with service icons, flowcharts, sequence, ERD, state, class, mindmap, timeline, git graph, sankey, and more. Features code-to-diagram analysis, batch rendering, 15+ themes, and syntax validation.

SkillScore

SkillScore55/100

Test results 55

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%55%of test cases passed +36 pts

Without skill4 of 22

With skill12 of 22

10 fixed2 passed either way8 still failing2 broke

Measured on gemini-3.6-flash8/9/2026v117 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe are using architecture-beta syntax to map an AWS cloud setup with API Gateway, Lambda, and DynamoDB using logos icon packs. What specific command flag must be passed to the render script so icons render properly?

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 tech-leads-club-mermaid-studio
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("tech-leads-club-mermaid-studio")
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 tech-leads-club-mermaid-studio

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/tech-leads-club-mermaid-studio/SKILL.md https://app.decimal.ai/s/tech-leads-club-mermaid-studio/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/tech-leads-club-mermaid-studio/SKILL.md

This gets SKILL.md only. The skill's 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/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/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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("tech-leads-club-mermaid-studio")
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/tech-leads-club-mermaid-studio/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/tech-leads-club-mermaid-studio/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 12 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 tech-leads-club-mermaid-studio

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/tech-leads-club-mermaid-studio/SKILL.md https://app.decimal.ai/s/tech-leads-club-mermaid-studio/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/tech-leads-club-mermaid-studio/SKILL.md

This gets SKILL.md only. The skill's 12 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/tech-leads-club-mermaid-studio/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/tech-leads-club-mermaid-studio.json

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/9/2026
Source: tech-leads-club/agent-skills ↗
License: NOASSERTION

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

Mermaid Studio

Expert-level Mermaid diagram creation, validation, and multi-format rendering. Creates diagrams from descriptions or code analysis, validates syntax, and renders to SVG, PNG, or ASCII with professional theming.

Golden Rules — Elegant Diagrams by Default

Every diagram MUST follow these principles. They are not optional — they define the difference between a mediocre diagram and a gold-standard one.

Rule 1: Always Use an Init Directive for Professional Styling

NEVER create a diagram without an %%{init} directive or frontmatter config. The default Mermaid theme produces harsh black lines and generic colors. Always apply a curated palette.

For general diagrams (flowchart, sequence, state, class, ERD):

%%{init: {'theme': 'base', 'themeVariables': {
  'primaryColor': '#4f46e5', 'primaryTextColor': '#ffffff',
  'primaryBorderColor': '#3730a3', 'lineColor': '#94a3b8',
  'secondaryColor': '#10b981', 'tertiaryColor': '#f59e0b',
  'background': '#ffffff', 'mainBkg': '#f8fafc',
  'nodeBorder': '#cbd5e1', 'clusterBkg': '#f1f5f9',
  'clusterBorder': '#e2e8f0', 'titleColor': '#1e293b',
  'edgeLabelBackground': '#ffffff', 'textColor': '#334155'
}}}%%

⚠️ Font Warning: Do NOT set fontFamily in theme variables. The Mermaid default font (trebuchet ms, verdana, arial, sans-serif) works everywhere. Setting system-ui, Segoe UI, or -apple-system will render as Times New Roman in headless Chromium (used by mmdc).

For C4 diagrams — see the dedicated C4 styling section below.

For architecture-beta diagrams — see the dedicated AWS/Architecture section below.

Rule 2: Soft Lines, Never Harsh Black

The single biggest visual improvement is using lineColor: '#94a3b8' (slate-400) instead of the default black. This creates a modern, breathable diagram. For dark themes, use lineColor: '#64748b' (slate-500).

Rule 3: Limit Density — Breathe

Maximum 15 nodes per diagram (not 20 — fewer is more elegant)
Use subgraph or boundaries to create whitespace and visual grouping
Prefer LR (left-right) for process flows — it reads more naturally
Use invisible links (A ~~~ B) to add spacing when the layout is cramped

Rule 4: Meaningful Labels and Consistent Style

Node IDs: camelCase (orderService, not s1 or os)
Labels: short, clear natural language ([Order Service])
Arrows: action verbs with protocol info ("Sends order via gRPC")
Descriptions: one-line, role-focused ("Handles order lifecycle")

Rule 5: Color Harmony Over Color Variety

Use max 3-4 colors per diagram. Map colors to meaning:

Blue tones (#4f46e5, #3b82f6) → primary systems, internal services
Green tones (#10b981, #059669) → success states, data stores
Amber tones (#f59e0b, #d97706) → external systems, warnings
Slate tones (#64748b, #94a3b8) → lines, borders, secondary elements
Red tones (#ef4444) → errors ONLY, never as decoration

Modes of Operation

This skill operates in three modes based on user intent:

Mode	Trigger	What happens
Create	"draw a diagram of...", "visualize my..."	Generates .mmd code only
Render	"render this mermaid", "convert to SVG/PNG/ASCII"	Renders existing .mmd
Full	"create and render...", ambiguous requests	Create → Validate → Render

Default to Full mode when intent is unclear.

Step 1: Understand the Request

Before writing any Mermaid code, determine:

What to diagram — system, flow, schema, architecture, code structure?
Which diagram type — use the Decision Matrix below
Output format — code only, SVG, PNG, or ASCII?
Theme preference — ask only if rendering; default to base theme with curated palette

Diagram Type Decision Matrix

User describes...	Diagram Type	Syntax keyword
Process, algorithm, decision tree, workflow	Flowchart	`flowchart TD/LR`
API calls, message passing, request/response	Sequence	`sequenceDiagram`
Database schema, table relationships	ERD	`erDiagram`
OOP classes, domain model, interfaces	Class	`classDiagram`
State machine, lifecycle, transitions	State	`stateDiagram-v2`
High-level system overview (C4 Level 1)	C4 Context	`C4Context`
Applications, databases, services (C4 Level 2)	C4 Container	`C4Container`
Internal components (C4 Level 3)	C4 Component	`C4Component`
Request flows with numbered steps	C4 Dynamic	`C4Dynamic`
Infrastructure, cloud deployment	C4 Deployment	`C4Deployment`
Cloud services with icons (AWS/GCP/Azure)	Architecture	`architecture-beta`
Project timeline, scheduling	Gantt	`gantt`
Proportional data, percentages	Pie	`pie`
Brainstorming, hierarchical ideas	Mindmap	`mindmap`
Historical events, chronology	Timeline	`timeline`
Branching strategy, git history	Git Graph	`gitGraph`
Flow quantities, resource distribution	Sankey	`sankey-beta`
X/Y data visualization	XY Chart	`xychart-beta`
Priority matrix, strategic positioning	Quadrant	`quadrantChart`
Layout control, grid positioning	Block	`block-beta`
Network packets, protocol headers	Packet	`packet-beta`
Task boards, kanban workflow	Kanban	`kanban`
User experience, satisfaction scoring	User Journey	`journey`
System requirements traceability	Requirement	`requirementDiagram`

If the user's description doesn't clearly map to one type, suggest 2-3 options with a brief rationale for each, then let them choose.

When to Load References

Load reference files ONLY when needed for the specific diagram type:

C4 diagrams → Read references/c4-architecture.md BEFORE writing code
AWS/Cloud architecture → Read references/aws-architecture.md BEFORE writing code
Code-to-diagram → Read references/code-to-diagram.md BEFORE analyzing
Theming/styling → Read references/themes.md when user requests custom themes
Syntax errors → Read references/troubleshooting.md when validation fails
Any diagram type details → Read references/diagram-types.md for comprehensive syntax

Step 2: Create the Diagram

2.1 — Write Mermaid Code

Follow these principles in order of priority:

Elegance first — every diagram must look professional with init directives and curated colors
Correctness — valid syntax that renders without errors
Clarity — meaningful labels, logical flow direction, clear relationships
Simplicity — under 15 nodes per diagram; split complex systems into multiple
Consistency — uniform naming (camelCase for IDs, descriptive labels in brackets)

2.2 — Structure Rules

%% Diagram: [Purpose] | Author: [auto] | Date: [auto]
%%{init: {'theme': 'base', 'themeVariables': { ... }}}%%
[diagramType]
    [content]

CRITICAL: The %%{init} directive MUST go on the very first non-comment line, BEFORE the diagram type declaration. Alternatively, use YAML frontmatter at the absolute start of the file.

Naming conventions:

Node IDs: camelCase, descriptive (orderService, not s1)
Labels: natural language in brackets ([Order Service])
Relationships: action verbs ("Sends order to", "Reads from")

Layout best practices:

TD (top-down) for hierarchical flows and processes
LR (left-right) for timelines, pipelines, and sequential processes
RL for right-to-left reading contexts
Use subgraph to group related nodes; name subgraphs meaningfully
Add direction inside subgraphs when needed for different flow

2.3 — Quick Reference Examples

Flowchart (with professional styling):

%%{init: {'theme': 'base', 'themeVariables': {
  'primaryColor': '#4f46e5', 'primaryTextColor': '#fff',
  'primaryBorderColor': '#3730a3', 'lineColor': '#94a3b8',
  'secondaryColor': '#10b981', 'tertiaryColor': '#f59e0b',
  'background': '#ffffff', 'mainBkg': '#f8fafc',
  'nodeBorder': '#cbd5e1', 'clusterBkg': '#f1f5f9',
  'clusterBorder': '#e2e8f0', 'titleColor': '#1e293b',
  'edgeLabelBackground': '#ffffff'
}}}%%
flowchart TD
    Start([Start]) --> Input[/User Input/]
    Input --> Validate{Valid?}
    Validate -->|Yes| Process[Process Data]
    Validate -->|No| Error[Show Error]
    Error --> Input
    Process --> Save[(Save to DB)]
    Save --> End([End])

For sequence diagram and ERD styling examples, read references/themes.md.

C4 Context (with MANDATORY elegant styling):

C4Context
    title System Context — E-Commerce Platform

    Person(customer, "Customer", "Places orders online")
    System(platform, "E-Commerce Platform", "Handles orders and payments")
    System_Ext(payment, "Payment Gateway", "Processes transactions")
    System_Ext(email, "Email Service", "Sends notifications")

    Rel(customer, platform, "Uses", "HTTPS")
    Rel(platform, payment, "Processes payments", "API")
    Rel(platform, email, "Sends emails", "SMTP")

    UpdateRelStyle(customer, platform, $textColor="#475569", $lineColor="#94a3b8")
    UpdateRelStyle(platform, payment, $textColor="#475569", $lineColor="#94a3b8")
    UpdateRelStyle(platform, email, $textColor="#475569", $lineColor="#94a3b8")

    UpdateLayoutConfig($c4ShapeInRow="3", $c4BoundaryInRow="1")

Architecture (AWS with Iconify icons):

architecture-beta
    group vpc(logos:aws-vpc)[VPC]

    service api(logos:aws-api-gateway)[API Gateway] in vpc
    service lambda(logos:aws-lambda)[Lambda] in vpc
    service db(logos:aws-dynamodb)[DynamoDB] in vpc
    service s3(logos:aws-s3)[S3 Bucket]

    api:R --> L:lambda
    lambda:R --> L:db
    lambda:B --> T:s3

IMPORTANT: Architecture-beta diagrams with logos:* icons require icon pack registration. When rendering with the render script, use the --icons logos flag. If rendering in a markdown viewer that doesn't support icon packs, use the built-in icons (cloud, database, disk, server, internet) as fallback. Read references/aws-architecture.md for the complete icon catalog and rendering instructions.

For comprehensive syntax of ALL diagram types, read references/diagram-types.md.

C4 Diagrams — Mandatory Styling Guide

C4 diagrams have fixed element styling (blue boxes for systems, gray for persons, etc.), but their relationship lines default to harsh black which creates visual noise. You MUST apply these styling rules:

The C4 Styling Pattern

Every C4 diagram MUST include these directives at the end:

    %% === MANDATORY STYLING ===
    %% Apply soft line colors to ALL relationships
    UpdateRelStyle(fromAlias, toAlias, $textColor="#475569", $lineColor="#94a3b8")
    %% Repeat for each Rel() in the diagram

    %% Optimize layout spacing
    UpdateLayoutConfig($c4ShapeInRow="3", $c4BoundaryInRow="1")

C4 Color Values Reference

Purpose	Color	Hex	Notes
Soft line color	Slate-400	`#94a3b8`	Replaces harsh default black
Line text color	Slate-600	`#475569`	Readable but not dominant
Accent line	Blue-400	`#60a5fa`	For highlighted or primary relationships
Warning line	Amber-500	`#f59e0b`	For external/risky connections
Custom element bg	Emerald	`#10b981`	For data stores or success highlights
Custom element bg	Indigo	`#4f46e5`	For primary system emphasis

C4 Layout Tips

CRITICAL — Maximum 6 Rel() per diagram. More than 6 relationships causes Dagre to route arrows through nodes, creating unreadable spaghetti. If your system needs more connections, split it into multiple focused diagrams.

Use $c4ShapeInRow="3" for most diagrams (prevents horizontal crowding)
Use $c4ShapeInRow="2" for diagrams with long labels
Use $c4BoundaryInRow="1" always (stacks boundaries vertically for clarity)
Apply $offsetY="-10" to UpdateRelStyle when labels overlap with elements
Prefer tree-shaped topologies (1 in, 1-2 out per node) over mesh topologies
Declare elements in flow order — the order of Container() declarations affects layout
Use directional Rel_D, Rel_R, etc. only as a last resort when auto-layout creates overlapping

For comprehensive C4 syntax, examples, and patterns, read references/c4-architecture.md.

Step 3: Validate

Before rendering, ALWAYS validate the Mermaid syntax:

node $SKILL_DIR/scripts/validate.mjs <file.mmd>

If validation fails:

Read the error message carefully
Consult references/troubleshooting.md for common fixes
Fix the syntax and re-validate
Maximum 3 fix attempts before asking the user for clarification

Step 4: Render

4.1 — Setup (First Run Only)

bash $SKILL_DIR/scripts/setup.sh

This auto-installs both rendering engines and icon pack dependencies. Run once per environment.

4.2 — Single Diagram Rendering

# SVG (default — best quality)
node $SKILL_DIR/scripts/render.mjs -i diagram.mmd -o diagram.svg

# PNG (for documents/presentations)
node $SKILL_DIR/scripts/render.mjs -i diagram.mmd -o diagram.png --width 1200

# ASCII (for terminals/READMEs)
node $SKILL_DIR/scripts/render-ascii.mjs -i diagram.mmd

# With icon packs (architecture-beta with AWS/tech icons)
node $SKILL_DIR/scripts/render.mjs -i diagram.mmd -o diagram.svg --icons logos,fa

The --icons flag registers Iconify packs before rendering. Packs: logos (AWS/tech), fa (Font Awesome). Use logos for AWS.

4.3 — Batch Rendering

For multiple diagrams at once:

node $SKILL_DIR/scripts/batch.mjs \
  --input-dir ./diagrams \
  --output-dir ./rendered \
  --format svg \
  --theme default \
  --workers 4

4.4 — Available Themes

mermaid-cli native (5): default | forest | dark | neutral | base

Custom theme: --theme base --config '{"theme":"base","themeVariables":{"primaryColor":"#4f46e5","lineColor":"#94a3b8"}}'

For the full theme catalog, read references/themes.md. The render script auto-selects the best engine (mmdc primary, beautiful-mermaid fallback, Puppeteer for icon packs).

Step 5: Code-to-Diagram (When Requested)

When the user asks to visualize existing code or architecture:

Read references/code-to-diagram.md for the analysis methodology
Analyze the codebase to identify the right diagram type:
- Module dependencies → Flowchart or Class diagram
- API routes and handlers → Sequence diagram
- Database models/schemas → ERD
- Service architecture → C4 Container or Architecture diagram
- State machines in code → State diagram
Generate the .mmd file with proper init directives (Golden Rule 1)
Validate and render as usual

Troubleshooting Quick Reference

Symptom	Likely Cause	Fix
Diagram won't render	Syntax error	Run validate.mjs, check brackets/quotes
Labels cut off	Text too long	Shorten labels or use line breaks `<br/>`
Layout looks wrong	Wrong direction	Try different TD/LR/BT/RL
Nodes overlap	Too many nodes	Split into subgraphs or multiple diagrams
Lines too dark/thick	No init directive	Add `%%{init}` with `lineColor: '#94a3b8'`
C4 lines overlapping	No styling applied	Add `UpdateRelStyle` with offsets to each Rel
AWS icons not showing	No icon pack	Use `--icons logos` flag or fallback to built-in icons
`mmdc` not found	Not installed	Run `setup.sh`
Theme not applied	Wrong engine	beautiful-mermaid themes only work with that engine

For comprehensive troubleshooting, read references/troubleshooting.md.

Output Conventions

Save .mmd source files alongside rendered outputs
Naming: {purpose}-{type}.mmd (e.g., auth-flow-sequence.mmd)
For batch: maintain input filename, change extension
Always provide both the .mmd source and rendered file to the user

When it activates

Automatically, when a task matches. Use when users ask to create diagrams, visualize architecture, render mermaid files, generate ASCII diagrams, document syste

About this skill

Automatic

Doc Ops pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

tech-leads-club / agent-skills

packages/skills-catalog/skills/(tooling)/mermaid-studio/SKILL.md

View on GitHub ↗

License CC-BY-4.0Imported 8/3/2026Version v1Bundled 12 files · scripts

Illustrative Want to see what tech-leads-club/mermaid-studio 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

Mermaid Studio

Golden Rules — Elegant Diagrams by Default

Rule 1: Always Use an Init Directive for Professional Styling

Rule 2: Soft Lines, Never Harsh Black

Rule 3: Limit Density — Breathe

Rule 4: Meaningful Labels and Consistent Style

Rule 5: Color Harmony Over Color Variety

Modes of Operation

Step 1: Understand the Request

Diagram Type Decision Matrix

When to Load References

Step 2: Create the Diagram

2.1 — Write Mermaid Code

2.2 — Structure Rules

2.3 — Quick Reference Examples

C4 Diagrams — Mandatory Styling Guide

The C4 Styling Pattern

C4 Color Values Reference

C4 Layout Tips

Step 3: Validate

Step 4: Render

4.1 — Setup (First Run Only)

4.2 — Single Diagram Rendering

4.3 — Batch Rendering

4.4 — Available Themes

Step 5: Code-to-Diagram (When Requested)

Troubleshooting Quick Reference

Output Conventions

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry