Ready to supercharge your AI agents?

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

Email Newsletter · varnan-tech | DecimalAI

Marketingby varnan-tech

Email Newsletter

Drafts and designs a complete HTML email newsletter from a topic or content brief. Outputs paste-ready HTML for Loops, Mailchimp, Beehiiv, Resend, or any standard email platform. Includes subject line options and plain-text fallback.

Maintained

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

50%77%of test cases passed +27 pts

Without skill11 of 22

With skill17 of 22

8 fixed9 passed either way3 still failing2 broke

Measured on gemini-3.6-flash8/18/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhen saving a completed newsletter edition to disk, what file format should be generated alongside the `.html` file by default?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add varnan-tech-email-newsletter
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-email-newsletter")
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-email-newsletter

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-email-newsletter/SKILL.md https://app.decimal.ai/s/varnan-tech-email-newsletter/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/varnan-tech-email-newsletter/SKILL.md

This gets SKILL.md only. The skill's 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/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-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/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-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter")
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-email-newsletter/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/varnan-tech-email-newsletter/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 6 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-email-newsletter

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-email-newsletter/SKILL.md https://app.decimal.ai/s/varnan-tech-email-newsletter/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/varnan-tech-email-newsletter/SKILL.md

This gets SKILL.md only. The skill's 6 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-email-newsletter/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/varnan-tech-email-newsletter.json

This gets SKILL.md only. The skill's 6 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

Email Newsletter

Draft and design a complete HTML email newsletter from a topic or content brief. Output is paste-ready for Loops, Mailchimp, Beehiiv, Resend, or any standard email platform.

Critical rule: Table-based HTML with inline styles only. No CSS classes, no flexbox, no grid, no <style> blocks. Every element gets style="" directly. This is not optional -- email clients strip everything else.

Step 1: Brief Intake

Need three things to start. If all three present in the message: skip to Step 2.

If any missing, ask exactly:

"To get started, I need three things:

Topic -- what is this newsletter about?

Audience -- who is reading? (role, company size, how they know you)

Primary CTA -- what one action do you want readers to take?"

Wait for all three before continuing.

Step 2: Complete Intake

Ask all questions in one message, grouped by category. User can skip any -- defaults apply.

"A few questions before I draft -- answer what you know, skip the rest:

Content

Length -- brief (300 words, punchy) / standard (500-700) / deep dive (800+ words)?

Format -- editorial article / numbered breakdown / personal story / data report?

Issue context -- one-time send / part of weekly series / monthly digest?

CTA URL -- what's the actual link? (or I'll use a placeholder)

Brand 5. Company / brand name -- for header and footer 6. Tagline -- one-line description (optional, for footer) 7. City & country -- for footer (e.g. "San Francisco, US") 8. Primary brand color -- hex? (e.g. #856FE6) 9. Secondary accent -- keep default yellow-green (#D8F90A) / use brand color / something else?

Design 10. Background -- dark (editorial/SaaS) / light (clean/corporate) / custom hex? 11. Display font -- editorial serif (Instrument Serif) / clean modern sans / system fonts only? 12. Button style -- pill (very rounded) / softly rounded / sharp corners? 13. Visual style -- editorial / technical+data / warm+founder / bold+campaign?

Platform & Technical 14. Platform -- Loops / Mailchimp / Beehiiv / Resend / other? 15. Tone -- educational / conversational / bold+direct / formal / playful? 16. Personalization -- none / first name / first name + company? 17. Subject line -- have one / want 3 options? 18. Secondary sections -- sponsor block / product callout / event / quick links / none? 19. Plain-text version -- yes (recommended) / no?"

Defaults if skipped:

Question	Default
Length	standard (500-700 words)
Format	editorial article
Issue context	one-time send
CTA URL	`[CTA_URL]` placeholder
Company name	`[YOUR BRAND]` placeholder
Tagline	none
City & country	`[CITY, COUNTRY]` placeholder
Brand color	none (use `#D8F90A` for all accents)
Secondary accent	`#D8F90A` (yellow-green default)
Background	dark
Display font	Instrument Serif (editorial serif)
Button style	pill
Visual style	editorial
Platform	generic
Tone	conversational
Personalization	none
Subject line	generate 3 options
Secondary sections	none
Plain-text	yes

Step 2.5: Design Direction (internal -- not shown to user)

From Step 2 answers, determine:

Visual character (from question 13, or inferred from tone + format if skipped)
ONE unmissable element -- identify before Step 3
Template path (see Step 5)

Character defaults if question 13 skipped:

Educational / formal tone: Editorial
Metrics-heavy content (stats, benchmarks, reports): Technical/data-forward
Product launches, events, campaigns: Bold/campaign

Never ask the user for design direction separately -- derive it from their answers.

Step 3: Structure Design

Read references/html-email-guide.md for layout rules before choosing sections.

Based on topic + audience + CTA + secondary sections requested, select sections from this library:

Section	Include when
header	Always -- logo placeholder + issue number or date
hero	Always -- big headline + 1-2 sentence hook
intro	Conversational or educational tone -- short personal note
main-content	Primary article or insight (text-heavy)
stat-callout	There is a compelling stat, quote, or data point
secondary-section	Secondary CTA was requested
product-cta	Brand context present and soft product plug fits
sponsor-block	Sponsor section was requested
quick-links	Curated links section was requested
footer	Always -- unsubscribe link + company name

Output the chosen structure as a numbered list with one-line purpose per section:

Proposed structure:
1. Header -- logo + Issue #1 / [date]
2. Hero -- headline + hook paragraph
3. Intro -- short personal framing
4. Main Content -- [topic] breakdown
5. Stat Callout -- key data point from the story
6. CTA -- [cta text]
7. Footer -- unsubscribe + company

Does this structure work, or should I adjust any sections?

Wait for confirmation before Step 4.

Step 4: Content Draft

Write copy for each section in sequence. No HTML yet -- clean prose only.

Rules per section:

Header: Issue number + date. No copy needed.
Hero headline: 8 words max, outcome-focused, no starting with "I/We/Our"
Hero hook: 1-2 sentences, problem or curiosity gap, pulls reader in
Intro: 2-3 sentences, personal or contextual, not corporate-speak, contractions OK
Main content: 250-400 words, scannable -- use bold phrases for key points, short paragraphs (1-3 lines), no walls of text, no bullet overload
Stat callout: One stat or quote, 20 words max, punchy
Product CTA: 2-3 sentences, value-forward, not "Check out our product" -- tell them what changes for them
CTA button text: 3-5 words, action verb + benefit ("Read the full breakdown", "Save my seat", "Get the guide")
Footer: Unsubscribe link placeholder + company name

Read references/subject-line-formulas.md then write 3 subject line options (if subject line not provided by user):

Option A: Curiosity gap formula
Option B: Direct benefit formula
Option C: Number/list formula

Do not use em dashes. Do not use: "powerful", "seamless", "game-changing", "leverage", "innovative", "unlock", "transform", "elevate", "cutting-edge", "robust".

Step 5: HTML Generation

Read references/design-system.md and references/html-email-guide.md before generating HTML.

Template or custom -- decide based on Step 2 answers:

Use templates/dark-newsletter.html as base when ALL of:

background = dark (or not specified)
display font = Instrument Serif (or not specified)
no custom background hex provided

Use templates/light-newsletter.html as base when ALL of:

background = light OR tone = formal
display font = Instrument Serif (or not specified)
no custom background hex provided

Generate custom HTML from scratch when ANY of:

custom background hex provided (not dark, not white)
display font = modern sans or system fonts only
combination of answers produces a design neither template serves

For custom generation: use references/design-system.md Custom Generation Guide as the full token spec. Apply user's background/font/button/accent choices throughout.

Then (for template path):

Select only the sections needed from the template (based on Step 3 structure)
Fill in all [PLACEHOLDER] values with content from Step 4
Apply brand color substitution (see below)
Verify all [UNSUBSCRIBE_URL] placeholders are still present (platform tuning happens in Step 6)

Brand color substitution rules:

If brand_color is provided:

Replace brand strip bgcolor (#D8F90A in the height:2px row) with brand_color
Replace stat callout left border color with brand_color
Replace category label color with brand_color
If brand_color luminance is high (yellows, greens, oranges -- most neons): replace step badge #D8F90A with brand_color too
If brand_color luminance is low (dark navy, forest, charcoal): keep step badges and CTA button as #D8F90A, only use brand_color for strip + stat border

If brand_color is NOT provided: keep all #D8F90A values as-is.

Content substitution rules (from Step 2 answers):

If company_name provided: replace all [YOUR BRAND] and [COMPANY NAME] placeholders
If city_country provided: replace [CITY, COUNTRY] placeholder
If tagline provided: add as subtitle line in footer after company name
If cta_url provided: replace all [CTA_URL] placeholders with actual URL
If personalization = first_name: add platform-appropriate first name variable to hero greeting -- e.g. Hey %%first_name%%, on Beehiiv, Hey {{first_name}}, on Loops, Hey *|FNAME|*, on Mailchimp
If personalization = first_name + company: add both variables where contextually appropriate

Brand color visual tension check (on dark email):

Does the brand color visually pop on #111111? Test mentally: would it be visible as a 2px strip?

High-saturation colors (purples, blues, teals, pinks, yellows, oranges, greens): YES -- use for strip + stat border + category label
Low-saturation / near-neutral (warm greys, beige, off-white): strip only; category label reverts to #555555
Near-black (very dark navy, forest, charcoal below ~#2A2A2A): skip brand_color for ALL accent uses, fall back to #D8F90A for every element

Accent discipline rule: brand_color appears in AT MOST 3 places: brand strip, stat border, category label. Never in body copy, headlines, button backgrounds, or section backgrounds. Over-branding kills the premium feel.

CTA button text color:

On #D8F90A button background: always use #0A0A0A text (it's a light color)
On #111111 button background (inside yellow callout card): always use #F2F2F2 text
On brand_color button: use #0A0A0A if brand is light, #FFFFFF if brand is dark

Required on every <td> with a background color: Both the bgcolor= HTML attribute AND the inline background-color: style. Example:

<td bgcolor="#D8F90A" style="background-color:#D8F90A;">

The attribute handles Outlook. The style handles everything else. Never use just one.

Design excellence (frontend-design principles, email-adapted):

Email's table constraints don't limit design ambition. Push within them:

Typography to its extreme: 4-5 word headlines = 60px, -0.04em tracking. 6-7 word headlines = 56px, -0.03em. 8 words = 48px. Never size down for safety -- the headline is a poster, not a label. Instrument Serif italic on stat quotes adds literary weight no other element can match.
Density contrast as craft signal: Hero = maximum open space (64px top). Body paragraphs = tight and dense. CTA callout card = maximum open space again (64px). Open → tight → open is the rhythm that reads as intentional design, not template output.
Background depth via section alternation (all email-safe):
- Header: #0A0A0A
- Hero: #111111
- Stat callout outer: #111111, inner elevated card: #1A1A1A
- Body paragraphs: #161616 (subtle elevation creates depth without color)
- Step cards: #111111 (contrast with body)
- CTA callout card: #D8F90A (the ONLY bright element -- never dilute)
- Footer: #080808
Accent scarcity = luxury: One yellow callout card in a sea of dark reads premium. Yellow appearing in six places reads cheap. The CTA card's power comes entirely from being the single bright element in a dark email.
Unforgettable test: Before saving, state in one sentence what a reader would describe to a colleague 3 hours later. If it's vague ("it was dark and clean") -- the visual anchor isn't strong enough. Make it specific ("the yellow card with the big serif headline").
Stat callout as editorial pull quote: 4px left border (not 3px). 26px italic Instrument Serif on the quote text. 32px inner padding. This is the closest an email gets to a magazine pull quote. Treat it like one.

Step 6: Platform Tuning

Read references/platform-compat.md and apply platform-specific adjustments:

Platform	Action
Loops	Replace `[UNSUBSCRIBE_URL]` with `{{unsubscribe_url}}`. Replace `[FIRST_NAME]` refs with `{{first_name}}`
Mailchimp	Replace `[UNSUBSCRIBE_URL]` with `\|UNSUB\|`. Add `mc:edit="[section-name]"` to editable `<td>` blocks
Beehiiv	Replace `[UNSUBSCRIBE_URL]` with `%%unsubscribe_url%%`. Replace `[FIRST_NAME]` with `%%first_name%%`
Resend	Replace `[UNSUBSCRIBE_URL]` with `{unsubscribeUrl}`. Note: React Email `.tsx` output available on request
Generic/Other	Keep `[UNSUBSCRIBE_URL]` as placeholder with comment: `<!-- Replace with your unsubscribe link -->`

Step 7: Self-QA

Check the generated HTML before output. Fix every issue found -- do not skip.

Rendering checks:

All styles inline -- no <style> blocks, no class= attributes anywhere
All <table> have cellpadding="0" cellspacing="0" border="0"
Images (if any) have alt="", border="0", display:block in style
Max-width 600px enforced on container table
CTA button uses <table> + <td> structure with bgcolor= attribute, not just <a> with display:block
No flexbox, grid, position:, float:, CSS variables (--var), min-height, max-height in any inline style
border-radius on <td> only -- not on <table> or <a> (Outlook renders <td> radius)
Footer has unsubscribe link with platform-correct variable

Content checks:

Hero headline is 8 words or fewer
CTA button text is 3-5 words
No em dashes (-- is fine, not --)
No banned words: "powerful", "seamless", "game-changing", "leverage", "innovative", "unlock", "transform", "elevate", "cutting-edge", "robust"
Plain-text version strips all HTML cleanly (if requested)

Design quality checks:

ONE unmissable element from Step 2.5 is visually dominant -- not buried between equal-weight sections
Typography hierarchy clear: H1 >> H2 >> body -- size contrast at least 2:1 between each level
All spacing values from valid rhythm only: 8 / 16 / 20 / 24 / 32 / 40 / 52 / 64px -- no arbitrary values (18px, 22px, 30px, 45px, etc.)
Brand color appears in 3 or fewer places -- count instances; if more, remove from lowest-priority element
No email slop patterns -- check against the slop list in references/design-system.md

If any check fails: fix inline, then re-run the checklist mentally.

Step 8: Subject Line Presentation

If 3 subject line options were generated, present them with a recommendation:

**Subject Line Options**

A. [subject] -- [formula used, best for what audience/context]
B. [subject] -- [formula used]
C. [subject] -- [formula used]

Recommendation: [A/B/C] -- [one sentence reason based on audience and tone]

If user provided their own subject line, skip this step.

Step 9: Save Files + Present Summary

Save the HTML to a file first -- do not dump it in the chat.

mkdir -p docs/newsletters

Write the full HTML to: docs/newsletters/[topic-slug]-[YYYY-MM-DD].html

Where [topic-slug] is the topic lowercased with spaces replaced by hyphens (e.g. "AI B2B Sales" → ai-b2b-sales).

If a plain-text version was requested, also write it to: docs/newsletters/[topic-slug]-[YYYY-MM-DD].txt

Then present this summary in the chat (no HTML code fence):

## Newsletter: [topic slug]
Date: [today's date] | Platform: [platform] | Tone: [tone]

Saved to: docs/newsletters/[topic-slug]-[YYYY-MM-DD].html

---

### Subject Lines
A. [subject A] -- [formula]
B. [subject B] -- [formula]
C. [subject C] -- [formula]
Recommended: [letter] -- [one-sentence reason]

---

### Send Checklist
- [ ] Replace [CTA_URL] with your actual link
- [ ] Replace [COMPANY NAME] and [CITY, COUNTRY] in footer
- [ ] Replace [YOUR BRAND] in header with your brand name (or swap in a logo image)
- [ ] Verify unsubscribe variable works in [platform]
- [ ] Send a test email to yourself before launching

Do not print the HTML in the chat. The file path tells the user where to find it.

Section Reference

Section	Purpose
header	Logo + issue number or date
hero	Big headline + 1-2 sentence hook
intro	Short personal note or context
main-content	Primary article or insight (text-heavy)
image-block	Full-width image + caption
stat-callout	Highlighted stat or quote in a box
secondary-section	Second story or feature
product-cta	Soft product plug or feature highlight
sponsor-block	Sponsored content (clearly labeled)
quick-links	Curated links section (3-5 items)
footer	Unsubscribe link, company info, legal

Output Formats (on request)

Standard HTML (default): inline-styled, table-based, works everywhere
React Email: .tsx component output -- request explicitly, good for Resend + dev teams
Plain text: stripped fallback always included unless user opts out

When it activates

Automatically, when a task matches. Trigger when a user says "write a newsletter", "draft an email newsletter", "create an HTML email", "design an email for my subscribers", or "write a newsletter about [topic]".

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/email-newsletter/SKILL.md

View on GitHub ↗

License MITImported 10/17/2026Version v1Bundled 6 files

Illustrative Want to see what varnan-tech/email-newsletter would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Email Newsletter

Step 1: Brief Intake

Step 2: Complete Intake

Step 2.5: Design Direction (internal -- not shown to user)

Step 3: Structure Design

Step 4: Content Draft

Step 5: HTML Generation

Step 6: Platform Tuning

Step 7: Self-QA

Step 8: Subject Line Presentation

Step 9: Save Files + Present Summary

Section Reference

Output Formats (on request)

When it activates

SkillSafety

Source

Related skills

More in the registry