Ready to supercharge your AI agents?

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

graphic-ebook · varnan-tech | DecimalAI

Design & Mediaby varnan-tech

graphic-ebook

Creates professionally designed B2B SaaS e-books in HTML + CSS, exported as print-ready PDF. 3–10 pages, 9 style presets, 11 page layout types.

Maintained

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

42%77%of test cases passed +35 pts

Without skill11 of 26

With skill20 of 26

11 fixed9 passed either way4 still failing2 broke

Measured on gemini-3.6-flash8/18/2026v124 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskProvide the exact terminal command to run the PDF compilation script export-pdf.sh for an ebook located at ebook/cloud-security-guide/index.html.

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 varnan-tech-graphic-ebook
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("varnan-tech-graphic-ebook")
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 varnan-tech-graphic-ebook

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/varnan-tech-graphic-ebook/SKILL.md https://app.decimal.ai/s/varnan-tech-graphic-ebook/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/varnan-tech-graphic-ebook/SKILL.md

This gets SKILL.md only. The skill's 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/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/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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("varnan-tech-graphic-ebook")
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/varnan-tech-graphic-ebook/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/varnan-tech-graphic-ebook/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 5 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 varnan-tech-graphic-ebook

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/varnan-tech-graphic-ebook/SKILL.md https://app.decimal.ai/s/varnan-tech-graphic-ebook/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/varnan-tech-graphic-ebook/SKILL.md

This gets SKILL.md only. The skill's 5 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/varnan-tech-graphic-ebook/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/varnan-tech-graphic-ebook.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/18/2026
Source: varnan-tech/opendirectory ↗
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

graphic-ebook

Creates professionally designed B2B SaaS e-books — lead magnets, gated guides, nurture assets, white papers. HTML + CSS → print-ready PDF. 3–10 pages.

Critical Rules

Before any step, these rules are absolute:

Every page MUST fit within A4 canvas (1200×1697px). No content overflow.
All scalable font sizes use clamp(). Fixed px only for borders/structural elements.
Single self-contained HTML. All CSS inline. Font CDN <link> only external dependency.
Never dump HTML in chat. Save to file, show summary only.
Body copy is primary. Line-height ≥ 1.75 on all text-column and text-sidebar pages. Max-width ≤ 65ch for single-column body.
No generic AI slop: no Inter as display font, no purple-to-blue gradient on white, no "Thank You" closing.
Visual rhythm: never place 2+ text-column pages back-to-back. Break with chapter-intro, quote-callout, or stat-grid.
Before generating HTML, commit to a design direction: one tone, one signature element, one background system. Generic = failure. Each ebook must be distinctly designed for its audience and subject — not a template.
* { -webkit-print-color-adjust: exact !important; print-color-adjust: exact !important; } — mandatory global CSS. Chromium strips all background colors in PDF without this.
Every page except cover must have a page footer: page number + brand name. Absolute position at bottom of each .slide.

Step 1: Brief Intake

Four required fields. If all four are present in the user's prompt: skip to Step 2.

If any are missing, ask exactly:

"To create your ebook, I need four things:

Topic — what is the ebook about? (be specific: "5 ways to reduce CAC" not "marketing tips")

Audience — who reads it? (role, company size, pain point: "Customer Success Managers at 50–500 person SaaS companies struggling with churn")

Desired action — what should the reader do after? (book a demo, download a template, share with team)

Content — do you have existing content, or should I draft from the topic?"

Stop and wait. Do not read reference files. Do not generate any HTML or outline.

Step 2: Complete Intake

Ask all 9 questions in one message, grouped. Defaults apply if skipped.

Content

Page count — 3–5 (quick guide / checklist) / 6–8 (standard guide) / 9–10 (deep dive) (default: 6)
Key takeaways — 3–5 things the reader should know or do after reading (informs chapter structure)
Brand name — company or product name for cover and footer (or "skip")
Brand logo — URL or "none"

Design 5. Style — clean-slate / midnight-editorial / matt-gray / product-minimal / mint-pixel-corporate / warm-earth / brutalist / magazine-red / soft-cloud / "show me options" (default: clean-slate) 6. Chapter count — how many main sections? (default: derived from page count)

Output 7. CTA details — demo booking / newsletter signup / template download / other (default: "book a demo") 8. Contact info — email + URL for closing CTA page (or "I'll add later") 9. Slug — filename slug (e.g., "reduce-churn-guide-2025"; derived from topic if skipped)

Defaults:

Question	Default
Page count	6
Key takeaways	derive from topic
Brand name	none
Brand logo	none
Style	clean-slate
Chapter count	derived from page count
CTA details	book a demo
Contact info	placeholder (flagged in checklist)
Slug	kebab-case of topic

If style = "show me options": Generate 3 single-page HTML previews (cover page only) saved to .claude-design/previews/style-a.html, style-b.html, style-c.html. Open each automatically. Ask user to pick before Step 3.

Step 3: Internal Architecture

Derive internally. Never show this to the user.

Chapter → page mapping:

Pages	Typical structure
3	cover + [1 content page] + closing-cta
4	cover + [1 chapter-intro + 1 text-column] + closing-cta
5	cover + toc + [1 chapter-intro + 1 text-column] + closing-cta
6	cover + toc + [2 chapter-intros + 1 text-column] + closing-cta
8	cover + toc + [3 chapter-intros + 2 content pages] + closing-cta
10	cover + toc + [4 chapter-intros + 3 content pages] + key-takeaways + closing-cta

TOC rule: Include for ebooks ≥ 6 pages. For 3–5 page ebooks, use a "What's inside" bullet list on the cover page or skip entirely.

Three-point CTA architecture (for ebooks ≥ 6 pages):

Intro CTA (after page 2) — subtle 1-line inline mention: "explore our [tool] at [url]"
Mid-ebook CTA (after a stat-grid or chapter-intro) — small .callout--stat or .callout--tip box with 1-line CTA
Closing CTA (final page) — full-page, primary conversion action

Visual rhythm check: If 2+ consecutive text-column pages appear in the plan → insert quote-callout or stat-grid between them before proceeding.

Design direction (derive from style preset + audience — never shown to user):

Decision	Derive from
Tone	What emotional register does this audience expect? (authoritative, editorial, energetic, calm, warm…)
Signature element	ONE visual device used consistently: oversized decorative numerals, diagonal accent bar, dot-grid overlay, gradient mesh on cover, rule lines, geometric shape bleed. Pick one. Use it.
Background system	How do backgrounds vary across pages? Cover and chapter-intros = most distinctive. Content pages quieter but NOT all-white. Closing CTA = dark or full-accent inversion. No 3+ consecutive pages with identical background.
Motion style	What do `.reveal` animations do? Pick one and stay consistent: `translateY(16px) → 0`, `scale(0.97) → 1`, `translateX(-12px) → 0`. Stagger delays 0.1s apart.
Unforgettable detail	What is the ONE thing a reader will remember about the design? Name it before writing any CSS.

If no strong direction is derivable from style preset alone, ask yourself: what would a top-tier design agency produce for this specific audience and topic? Then execute that.

Body copy density limits:

text-column 1-col: 180–250 words max per page
text-column 2-col: 280–380 words max (140–190 per column)
text-sidebar: 140–180 words main + ≤70 words sidebar
chapter-intro: 40–60 words (teaser only)
quote-callout: 30–45 words
stat-grid: 3–6 metrics, minimal labels

Step 4: Page Structure

Read references/page-library.md before planning.

Output a numbered list with [layout-type] labels per page. Example for 6-pager:

Page 1: [cover] — title, subtitle, brand
Page 2: [toc] — 3 chapter titles + page numbers
Page 3: [chapter-intro] — Chapter 1 opener
Page 4: [text-column] — Chapter 1 body (1-column)
Page 5: [stat-grid] — 4 key metrics
Page 6: [closing-cta] — demo booking CTA + contact

Confirm with user before Step 5.

Step 5: Content Draft

Write per-page copy in plain text (no HTML). Rules per layout type:

cover: title (≤10 words, leads with value or tension — not a generic label) + subtitle (≤15 words) + optional category label + brand name
toc: chapter titles (≤6 words each) + corresponding section numbers. Clean, numbered list.
chapter-intro: chapter number (decorative) + chapter title (≤8 words) + teaser paragraph (2–3 sentences)
text-column (1-col): section heading + body paragraphs. Max 250 words. Prose > bullets. Every sentence earns its place.
text-column (2-col): same rules, 140–190 words per column. Use for comparisons, step pairs, dual perspectives.
text-sidebar: main body (140–180 words) + sidebar callout type (tip / warning / stat / quote / checklist) with max 70 words
quote-callout: pull quote ≤40 words + attribution (name, title, company or source)
stat-grid: 3–6 metrics — number + label + 1-line context. Optional: 1-sentence narrative below.
key-takeaways: 5–8 takeaways, ≤15 words each, imperative where possible
closing-cta: headline ≤5 words (imperative) + 1-sentence body + CTA action + email + URL (both required)

Forbidden words (no exceptions): "powerful", "seamless", "game-changing", "leverage", "innovative", "revolutionary", "transform", "cutting-edge", "robust", "unlock", "scalable" (as filler).

Step 6: HTML Generation

Read ALL of these before generating. Do not paraphrase or summarize them — read the actual files.

This skill's references:

references/design-system.md
references/page-library.md
references/style-presets.md

Bundled asset (exact path — include FULL verbatim contents in <style> block):

assets/viewport-base.css — bundled inside this skill's directory

Path resolution: All paths prefixed assets/ or scripts/ are relative to the directory containing this SKILL.md file. In Claude Code after install: ~/.claude/skills/graphic-ebook/assets/ and ~/.claude/skills/graphic-ebook/scripts/. Resolve the actual path from the SKILL.md file location before reading.

Generation Rules

Single self-contained HTML. All CSS inline. Font CDN <link> only external dependency.
Include FULL verbatim contents of viewport-base.css inside the <style> block.
Add A4 portrait overrides AFTER viewport-base.css (in the same <style> block):

/* A4 portrait overrides */
html { scroll-snap-type: none; scroll-behavior: auto; }
.slide {
  width: 100vw;
  height: 100vh;
  height: 100dvh;
  overflow: hidden;
  display: flex;
  flex-direction: column;
  position: relative;
  scroll-snap-align: none;
}
/* CRITICAL: prevents Chromium from stripping backgrounds in PDF */
* { -webkit-print-color-adjust: exact !important; print-color-adjust: exact !important; }

Each page = <section class="slide"> — required for export-pdf.sh page detection.
Comment each page: /* === PAGE N: LAYOUT-TYPE === */
Body text: clamp(0.875rem, 1.25vw, 1.05rem), line-height: 1.75, max-width: min(65ch, 100%) on all <p> in text-column and text-sidebar layouts.
Stat numbers: hero at clamp(3rem, 8vw, 5.5rem) in accent color. Supporting at clamp(2.5rem, 7vw, 5rem) in secondary color.
No images available → CSS-generated visuals only (gradients, geometric shapes, dot patterns, abstract elements). Never show placeholder boxes.
No SlidePresentation JS. Include only minimal IntersectionObserver for .reveal animations.
Chapter number decoration (on chapter-intro pages):

.chapter-number-deco {
  font-family: var(--font-display);
  font-size: clamp(6rem, 18vw, 14rem);
  font-weight: var(--display-weight);
  opacity: 0.06;
  position: absolute;
  top: -0.1em;
  right: var(--page-padding);
  line-height: 1;
  color: var(--accent);
  pointer-events: none;
  user-select: none;
}

Typed callout boxes (for text-sidebar pages):

.callout { border-left: 3px solid; border-radius: var(--card-radius, 4px); padding: clamp(0.75rem, 1.5%, 1.1rem); }
.callout-label { font-size: clamp(0.58rem, 0.8vw, 0.68rem); font-weight: 700; letter-spacing: 0.12em; text-transform: uppercase; margin-bottom: 0.5em; }
.callout--tip      { background: rgba(22, 163, 74, 0.07);  border-color: #16A34A; }
.callout--tip      .callout-label { color: #16A34A; }
.callout--warning  { background: rgba(217, 119, 6, 0.07);  border-color: #D97706; }
.callout--warning  .callout-label { color: #D97706; }
.callout--stat     { background: rgba(var(--accent-rgb, 100,100,100), 0.07); border-color: var(--accent); }
.callout--stat     .callout-label { color: var(--accent); }
.callout--quote    { background: var(--bg-elevated); border-color: var(--divider); font-style: italic; }
.callout--quote    .callout-label { color: var(--text-muted); }
.callout--checklist { background: rgba(8, 145, 178, 0.07);  border-color: #0891B2; }
.callout--checklist .callout-label { color: #0891B2; }

Page footer (on every page except cover):

.page-footer {
  position: absolute;
  bottom: 0; left: 0; right: 0;
  padding: clamp(0.5rem, 1%, 0.625rem) var(--page-padding);
  display: flex;
  justify-content: space-between;
  align-items: center;
  border-top: 1px solid var(--divider);
  font-family: var(--font-body);
  font-size: clamp(0.55rem, 0.75vw, 0.65rem);
  font-weight: 600;
  letter-spacing: 0.1em;
  text-transform: uppercase;
  color: var(--text-muted);
}

HTML: <div class="page-footer"><span>[Brand Name]</span><span>[N]</span></div>

2-column layout: display: grid; grid-template-columns: 1fr 1fr; gap: clamp(2rem, 4%, 3.5rem); with border-right: 1px solid var(--divider) on left column.
Text-sidebar layout: display: grid; grid-template-columns: 2fr 1fr; gap: clamp(1.5rem, 3%, 2.5rem);

Design Quality Rules (from frontend-design principles)

These govern the aesthetic ambition of every generated ebook. Applied after structural rules, before output.

Typography:

Display font must have character at large sizes. Plus Jakarta Sans 800, Instrument Serif, Syne, Lora, Fraunces — all acceptable. Inter at display weight = immediate slop signal.
Never use the same font weight for two consecutive hierarchy levels. Cover title (800) → chapter heading (700) → section heading (700, smaller size) → body (400/500).
Pair a display font with a refined body font when the preset supports it (e.g. Instrument Serif + Inter, Syne + IBM Plex Sans). Single-font stacks must use weight contrast instead.

Backgrounds and atmosphere:

Cover MUST have a significant decorative ::before or ::after pseudo-element creating visual depth: ghost letter at opacity: 0.04–0.06, geometric shape bleed, radial gradient overlay, or dot/line grid pattern.
Chapter-intro pages MUST visually contrast with adjacent content pages — use var(--bg-alt) or a style-appropriate alt treatment.
Content pages (text-column, text-sidebar) can be white/neutral, but the stat-grid and quote-callout pages should carry a distinct background (alt section bg, elevated card, or accent inversion).
Closing CTA: always dark or full-accent inversion — never light. It is the conversion moment.
CSS texture patterns when appropriate: radial-gradient(circle, var(--accent) 1px, transparent 1px) dot grids; repeating-linear-gradient rule lines; ::before with clipped geometric shapes.

Spatial composition:

Generous whitespace on chapter-intro pages — the visual openness signals a chapter break.
At least one element per ebook should break the standard grid: oversized chapter deco number that bleeds off-screen right, quote mark that overlaps content, stat number that dominates 60%+ of its column.
Avoid centered layouts unless the preset explicitly calls for it (quote-callout is the only centered-by-default layout).

Motion:

All .reveal animations use consistent direction derived from design direction step.
Stagger delays: 0.05s increments, max 0.5s cumulative. Nothing slower than 0.65s duration.
Stat items in stat-grid: stagger by index for cascade effect.
No animation on structural elements (footers, borders, rules). Animation = content appearing, not layout materializing.

The unforgettable detail rule: Before writing the first line of CSS, name the ONE element that makes this ebook unmistakably designed — not just competently assembled. That element gets the most CSS investment. If you cannot name it, you have not thought hard enough about the design.

Step 7: Self-QA

Fix every failure before proceeding to output. Do not skip this step.

Layout & rendering:

Every .slide has height:100vh; height:100dvh; overflow:hidden
* { -webkit-print-color-adjust: exact !important; print-color-adjust: exact !important; } present globally
All scalable font sizes use clamp()
No content overflows at 1200×1697 — review each page's density
No placeholder boxes visible
No -clamp(), -min(), -max() directly (wrap negatives in calc(-1 * ...))

Structure:

Page count matches Step 4 plan
Every page uses class="slide" on <section> only
All layout types from Step 4 present in correct order
TOC included for ebooks ≥ 6 pages

Reading quality:

Body text line-height ≥ 1.75 on text-column and text-sidebar pages
Single-column body text max-width ≤ 65ch
No 2+ consecutive text-column pages without visual break
TOC has chapter titles + section/page numbers
Chapter-intro pages have .chapter-number-deco (opacity 0.06–0.08)
Every page except cover has .page-footer with page number + brand name
Sidebar callout boxes use typed CSS class (.callout--tip/warning/stat/quote/checklist)

Design quality:

Content:

No forbidden words anywhere
Cover title ≤10 words, leads with value or tension
Quote callout ≤40 words
Closing CTA: imperative headline + email + URL (both mandatory — QA fails without both)
TOC matches actual page structure
Three-point CTA present for ebooks ≥ 6 pages

Step 8: Output

mkdir -p ebook/[slug]

Write main HTML: ebook/[slug]/index.html Open: open ebook/[slug]/index.html

Per-page split (always generate): Extract each <section class="slide"> into standalone HTML files with full <style> block, no JS: ebook/[slug]/page-01.html, page-02.html, … (zero-padded 2 digits)

PDF export (always run):

bash [skill-root]/scripts/export-pdf.sh \
  ebook/[slug]/index.html \
  ebook/[slug].pdf --portrait

[skill-root] = the directory containing this SKILL.md. Resolve it before running (e.g. ~/.claude/skills/graphic-ebook in Claude Code after install).

Cleanup: Delete .claude-design/previews/ if style preview files were generated in Step 2.

Summary (no HTML in chat):

## Ebook: [title]
Date: [today] | Style: [style] | Pages: [N] | Format: A4 portrait
Brand: [brand name] | Topic: [topic]

Files
  Main:      ebook/[slug]/index.html
  Per-page:  ebook/[slug]/page-01.html → page-0N.html
  PDF:       ebook/[slug].pdf

Checklist
- [ ] Replace contact info placeholders (email + URL on closing page)
- [ ] Replace brand logo initials with real asset
- [ ] Verify TOC section numbers match actual page positions
- [ ] Proof all stat accuracy (page [N])
- [ ] Review body copy — no page should feel overflowed
- [ ] Test PDF opens correctly (page count = [N])

When it activates

Automatically, when a task matches. Trigger when user says "create an ebook", "design a lead magnet", "make a PDF guide", "build a gated content piece", "write a B2B ebook", "design a white paper", "create a nurture asset", or "make a PDF report".

About this skill

Automatic

Marketing & Content 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

varnan-tech / opendirectory

skills/graphic-ebook/SKILL.md

View on GitHub ↗

License MITImported 10/17/2026Version v1Bundled 5 files · scripts

Illustrative Want to see what varnan-tech/graphic-ebook 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.

varnan-tech/graphic-case-studyGenerates a professionally designed case study PDF for B2B SaaS sales and marketing. Supports 7 page layouts, 9 style presets, 1-4 page output. Trigger when user says "create a case study", "write a customer story", "make a case study PDF", "design a success story", "turn this customer win into a PDF".Close match+27 pts pass-rate lift

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

graphic-ebook

Critical Rules

Step 1: Brief Intake

Step 2: Complete Intake

Step 3: Internal Architecture

Step 4: Page Structure

Step 5: Content Draft

Step 6: HTML Generation

Generation Rules

Design Quality Rules (from frontend-design principles)

Step 7: Self-QA

Step 8: Output

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry