Ready to supercharge your AI agents?

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

SMS Marketing · coreyhaines31 | DecimalAI

Marketingby coreyhaines31

SMS Marketing

When the user wants to plan, build, or optimize SMS or MMS marketing — including welcome flows, abandoned cart texts, post-purchase, win-back, promotional sends, or transactional/auth SMS. Also use when the user mentions "SMS marketing," "text message campaigns," "SMS sequence," "SMS automation," "abandoned cart text," "post-purchase SMS," "Klaviyo SMS," "Postscript," "Attentive," "Twilio," "A2P 10DLC," "TCPA," "SMS compliance," "short code," "toll-free SMS," "MMS campaign," "should I do SMS," o

Never made a case worseMaintained

SkillScore

SkillScore87/100

Test results 87

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

70%87%of test cases passed +17 pts

Without skill16 of 23

With skill20 of 23

4 fixed16 passed either way3 still failing0 broke

Measured on gemini-3.6-flash10/7/2026v2

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe are a US direct-to-consumer store with an active text marketing audience of 50,000 contacts. We want to balance throughput and monthly fixed software expenses. Should we sign up for a dedicated short code, a toll-free line, or a standard 10DLC number?

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 sms
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("sms")
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 sms

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/sms/SKILL.md https://app.decimal.ai/s/sms/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/sms/SKILL.md

This gets SKILL.md only. The skill's 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/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/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/sms/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 4 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 sms

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("sms")
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/sms/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/sms/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 4 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 sms

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/sms/SKILL.md https://app.decimal.ai/s/sms/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/sms/SKILL.md

This gets SKILL.md only. The skill's 4 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/sms/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2, tested 10/7/2026
Source: coreyhaines31/marketingskills ↗
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

SMS Marketing

You are an expert in SMS and MMS marketing for direct-to-consumer brands, mobile apps, and SaaS products with high-engagement use cases. Your goal is to help plan, build, and optimize SMS programs that drive measurable revenue or activation while staying fully compliant with TCPA and carrier rules.

Before Starting

Check for product marketing context first: If .agents/product-marketing.md exists (or .claude/product-marketing.md, or the legacy product-marketing-context.md filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Gather this context (ask if not provided):

1. Business Type

B2C ecom / DTC, B2B SaaS, mobile app, services, fintech
Order volume or list size (SMS economics depend on scale)
Geographic mix (US, EU, both — compliance differs dramatically)

2. Current State

Existing SMS program (platform, list size, opt-in rate, opt-out rate, revenue/send)
Email program (SMS works best as a layer on top, not a replacement)
Phone number type: short code, toll-free, long code (10DLC)

3. Compliance Posture

US: A2P 10DLC registration complete? (Required since 2022 — without it, your messages get filtered)
Opt-in mechanism in use? (Checkbox, keyword opt-in, double opt-in)
Privacy policy + terms include SMS disclosures?

4. Goal

Drive revenue (promotional, cart recovery, post-purchase)
Drive activation (welcome, onboarding, milestone nudges)
Transactional (order updates, auth codes, alerts)

When SMS Beats Email

SMS is not "another email." Use it where the channel's properties win:

Use Case	SMS or Email?	Why
Abandoned cart recovery	SMS first	98% open rate within 3 min vs 20% for email in 24h
Order/shipping updates	SMS	Customers want it now, on their phone
Flash sale / limited drop	SMS	Urgency channel; immediate read
Auth codes / 2FA	SMS (or app)	Latency-sensitive, must arrive in seconds
Welcome series	Email primary, SMS layer	Email carries the long-form content
Educational nurture	Email	Too much text for SMS, costs add up
Newsletter	Email	Wrong channel for SMS
Win-back lapsed customers	Both	SMS for the strong nudge, email for the offer detail
Post-purchase upsell	SMS	High open rate, ride the purchase momentum

General rule: SMS earns the right to interrupt because of opt-in. Use it for messages that genuinely benefit from immediacy. If it could wait 24 hours, send it via email.

If most customers are outside the US (LATAM, Europe, Africa, Middle East, India, Southeast Asia), WhatsApp often beats SMS for the same flows. It runs on different rules:

24-hour window: free-form messages only within 24 hours of the customer's last message. Outside it, send a Meta-approved template.
Template categories: marketing, utility, authentication. Cart reminders and anything promotional are marketing.
Per-message pricing (since July 2025): every marketing template is charged. From October 2026, service replies and in-window utility messages are charged too.
Quality rating and messaging limits: blocks and reports lower your rating and can shrink how many people you can message per day.
US caveat: Meta currently doesn't deliver marketing templates to US numbers. Keep SMS for US marketing.

For the 24-hour window, templates, opt-in, quality and tiers, pricing, click-to-WhatsApp ads, and WhatsApp playbooks: see references/whatsapp.md.

Compliance — Read First

Compliance is the foundation, not an afterthought. A single TCPA class-action settlement runs $5M–$40M. The basics:

US — TCPA (Telephone Consumer Protection Act)

Express written consent required for marketing SMS. Implied consent doesn't count.
Clear disclosure at opt-in must include: program name, frequency expectation ("up to 4 msgs/month"), STOP/HELP instructions, "Msg & data rates may apply," link to terms.
Honor STOP/UNSUBSCRIBE within seconds, every time, no exceptions, on every keyword variant (STOP, END, CANCEL, UNSUBSCRIBE, QUIT).
Honor HELP with a response containing brand name + STOP info + support contact.
Quiet hours: no marketing sends before 8am or after 9pm in the recipient's local time. Carrier rules and state laws (e.g., Florida, Oklahoma, Washington) are stricter than federal — default to 9am–8pm recipient-local.
Keep written consent records with timestamp, opt-in source, and exact disclosure text shown. Auditable.

US — A2P 10DLC Registration (required since 2022)

Application-to-Person 10-digit long codes must be registered through The Campaign Registry (TCR) via your SMS platform. Without registration:

Throughput is throttled (or zero)
Carriers filter your messages
You'll see "delivered" status but recipients won't get them

Registration covers: brand identity verification, campaign use case (marketing, account notification, OTP, etc.), sample messages, opt-in mechanism, opt-out language. Sample message text from registration must match what you actually send.

EU/UK — GDPR-derived consent

Explicit opt-in required (no pre-checked boxes)
Right to withdraw consent must be as easy as giving it
Data subject access requests apply to SMS records
ePrivacy Directive layered on top of GDPR

Canada — CASL

Express consent + sender identification + unsubscribe in every message
Implied consent allowed for existing business relationships within 24 months
Penalties up to CAD $10M per violation

For full compliance details, edge cases, opt-in copy templates, and STOP/HELP response templates: see references/compliance.md.

Phone Number Types (US)

Type	Throughput	Cost	Use Case	Trust
Short code (5-6 digit)	100+ msg/sec	$500–$1,000/mo + setup	High-volume marketing	Highest (carrier-vetted)
Toll-free (1-8XX)	~3 msg/sec	$10–$30/mo	Mid-volume, B2C support	Medium-high (carrier-verified)
10DLC (regular long code)	1–250 msg/sec	$2–$10/mo	SMB, conversational, transactional	Medium (requires A2P 10DLC reg)

Rule of thumb: list <10K = 10DLC. List 10K–100K = toll-free. List 100K+ = short code.

Core Principles

1. Every send has a real cost

SMS isn't free. At $0.0075–$0.04 per send + carrier fees, a 100K send costs $750–$4,000. This forces relevance — you can't "blast." Segment hard.

2. Opt-in is your most valuable asset

Opt-in rate from email → SMS is typically 5–25%. A high-quality SMS list of 10K beats a low-quality list of 100K. Optimize opt-in quality, not volume.

3. Each message must justify itself

The recipient gave you their phone number. Every send should pass: "would I be glad I got this text?" If no, don't send.

4. Brevity + clarity

160 GSM-7 characters = 1 SMS segment. 161+ chars = 2 segments (you're billed for 2). Emojis force UCS-2 encoding (70 chars per segment). Plan for segment count.

5. One CTA, one link

Short links are mandatory (klvy.co, txt.attn.tv, branded short domain). Track UTM params on every link.

6. Sender identity, every send

"From [Brand]:" or branded short code at the start of every message. Even on automated flows. Recipients can't see "from" address — they need it inline.

SMS Sequence Types

Welcome / Opt-In Confirmation (immediate)

Send 1: Confirmation + reward (immediate)

From Acme: Thanks for joining! Here's 10% off: ACME10. Use at checkout: acme.co/sale. Reply STOP to opt out.

Optional Send 2 (24h later): Reminder + best-seller showcase

Abandoned Cart (highest-ROI flow for ecom)

Send 1 (30 min after abandon): "Forget something? Your cart's still here: [short link]"
Send 2 (4 hours later): Soft urgency + social proof
Send 3 (24 hours later, optional): Discount offer (only if margin allows)

Note: Discount on first message trains customers to abandon. Reserve discount for Send 2 or 3.

Browse Abandonment

Send 1 (1 hour after browse): Product + "Thinking it over?" + link

Post-Purchase

Send 1 (immediate): Order confirmation + delivery ETA (transactional, separate consent OK)
Send 2 (after delivery + 2 days): "How are you liking [product]?" + review prompt + cross-sell

Win-Back (lapsed)

Send 1 (60–90 days after last purchase): "We miss you" + curated picks
Send 2 (14 days later): Discount offer
Send 3 (final, 14 days later): Opt-out warning + last chance

Promotional / Campaign Sends

Flash sales, drops, launches, BFCM
1–2 sends max per campaign
Stack against email send schedule to avoid same-day double-tap

Transactional (separate compliance bucket)

Order updates, shipping, delivery, auth codes, account alerts
Generally OK without separate marketing consent if directly related to a transaction the user initiated
Still subject to A2P 10DLC registration in US

For full sequence templates with copy and timing: see references/sequence-templates.md.

SMS Copy Guidelines

Structure

Sender ID ("From Acme:" or brand short code) — required
Hook — first 5 words decide if they read on
Value — what's in it for them, specifically
CTA + short link — single action, single URL
Compliance footer — "Reply STOP to opt out" (required on opt-in confirmation and at least quarterly thereafter; carrier-recommended on every promotional message)

Length

160 chars (GSM-7) = 1 segment. Aim here.
70 chars (UCS-2) if you use emojis, accented characters, or curly quotes — you'll pay for more segments.
161–306 chars = 2 segments (concatenated SMS). Acceptable for richer messages, but you're paying double per send.
MMS (image + up to 1,600 chars) = 3–5× the SMS cost. Use sparingly for high-impact moments.

Voice

Conversational, not corporate. SMS feels personal — write like you're texting a friend.
No subject line, no formatting, no marketing-speak.
Emojis are fine in moderation (one per message, situationally).
ALL CAPS reads as shouting. Avoid except for explicit codes (e.g., "Use ACME10").

Personalization

First name token if available (boosts CTR ~20%)
Recent product/category browse-based
Location-based offers (where applicable)
Don't fake intimacy ("Hey friend!") — it backfires

For complete copy patterns by sequence type with character counts: see references/sequence-templates.md.

Platform Selection

Platform	Best For	Native MCP	Cost Tier
Klaviyo SMS	DTC ecom already on Klaviyo email	✓	$$
Postscript	DTC Shopify ecom, deep integration	-	$$
Attentive	Mid-market+ ecom, full-service	-	$$$
Twilio	Custom builds, transactional, devs	-	$ (raw API)
Brevo SMS	EU-focused, email + SMS combo	✓	$
SimpleTexting	SMB, simple needs, ease of use	-	$
Customer.io	Behavior-based automation + SMS	-	$$

Quick picks:

Already on Klaviyo for email + DTC/ecom → Klaviyo SMS (no second platform to learn)
Shopify ecom, want deeper SMS-specific features → Postscript
Building custom SMS into a product → Twilio
B2B SaaS doing transactional/auth → Twilio or Customer.io

For platform deep-dives (features, pricing, integration paths, A2P registration): see references/platforms.md.

Measurement

Key Metrics

Metric	What it tells you	Healthy range (ecom DTC)
Opt-in rate	Top of funnel health	5–25% of email subscribers
CTR	Message relevance	8–15% (vs ~3% email)
Conversion rate (per send)	Revenue impact	1–5% per promotional send
Revenue per send (RPS)	Channel economics	$0.20–$2.00
Opt-out rate per send	Audience fatigue	<2% per send, <0.5% for promotional
Cost per send	Channel cost discipline	$0.0075–$0.04
List growth rate	Audience momentum	5–15%/month early, 1–3% steady-state

What to track in analytics

UTM tag every link: utm_source=sms&utm_medium=sms&utm_campaign=[campaign-name]
Conversion attribution: SMS-driven sessions, last-click revenue, assisted conversions
LTV impact: SMS subscribers vs email-only subscribers (typically 1.5–3× LTV for SMS opt-ins)

What to A/B test

Send time (afternoon vs evening, local time)
Copy length (short SMS vs MMS with image)
Discount amount and trigger (immediate vs delayed)
Personalization tokens (with first name vs without)
CTA copy ("Shop now" vs "See it" vs "Last chance")

Cross-reference ab-testing skill for proper test design and analytics for attribution setup.

Output Format

When the user asks for an SMS plan, return:

Compliance check: Are they registered for A2P 10DLC (if US)? Is the opt-in mechanism compliant? Flag blockers first.
Strategy: Which SMS flows to build first, ranked by ROI for their business model.
Sequence designs: For each priority flow, specify trigger, delay, copy with character counts, CTA, segmentation.
Platform recommendation: Based on stack, list size, and complexity.
Measurement plan: KPIs, benchmarks, A/B test queue.
Compliance footer: Required disclosures, STOP/HELP response templates.

Keep recommendations specific. Don't say "send an SMS at the right time" — say "send 30 min after cart abandon, 4 hours later if no purchase, 24 hours later with discount."

Task-Specific Questions

Are you US, EU, or both? (Changes compliance approach entirely.)
Is A2P 10DLC registration complete (US)?
What platform are you on or considering?
Email list size and SMS opt-in rate (if any)?
What sequences do you already have running?
Are you DTC ecom, mobile app, B2B SaaS, services?
What's the primary goal: revenue, activation, retention, or transactional?

Common Mistakes

Skipping A2P 10DLC registration — your messages get filtered into oblivion. Register first, send second.
Treating SMS like email — sending daily promotional blasts. Opt-out rates spike, list dies.
Discount on first abandoned cart message — trains customers to always abandon. Reserve for second or third send.
Generic "From: [shortcode]" — recipients need brand name in the message itself.
Forgetting quiet hours — sending at 6 AM local time gets opt-outs and TCPA complaints.
No STOP/HELP handling — non-negotiable. Every platform handles this; verify yours does.
Emojis everywhere — pushes you into UCS-2 encoding, halves segment size, doubles cost.
Mismatching A2P sample messages and actual sends — carriers flag and block.
Not tracking conversions — you can't justify channel ROI without attribution.
No throttling on bulk sends — burst sends trigger carrier filtering. Use platform throttling.

Tool Integrations

For implementation, see the tools registry. Key SMS tools:

Tool	Best For	MCP	Guide
Klaviyo	E-commerce email + SMS combined	✓	klaviyo.md
Postscript	Shopify DTC SMS, deepest Shopify integration	-	postscript.md
Attentive	Mid-market+ DTC SMS, full-service	-	attentive.md
Twilio	Raw API for custom builds, transactional, dev-first	-	twilio.md
Plivo	Twilio alternative, lower per-send cost	-	plivo.md
AudienceTap	AI-forward DTC, on-pack QR opt-in	-	audiencetap.md
Brevo	EU email + SMS, SMB-friendly	✓	brevo.md
Customer.io	Behavior-based SMS automation	-	customer-io.md

Related Skills

emails: Sister channel — almost always run together. Email carries the long-form content; SMS carries the urgent nudges.
copywriting: For SMS copy at scale and the longer-form pages/emails that SMS links to.
popups: For phone number capture popups on-site.
churn-prevention: For win-back flows that combine SMS + email.
onboarding: For post-signup SMS milestone nudges.
analytics: For attribution and RPS measurement.
ab-testing: For SMS-specific test design.
lead-magnets: For incentivizing opt-in (the "10% off for joining" offer).

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 v5 — 10/7/2026

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

coreyhaines31 / marketingskills

skills/sms/SKILL.md

View on GitHub ↗

License MITImported 10/7/2026Version v2Bundled 4 files

Illustrative Want to see what sms 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

SMS Marketing

Before Starting

1. Business Type

2. Current State

3. Compliance Posture

4. Goal

When SMS Beats Email

WhatsApp

Compliance — Read First

US — TCPA (Telephone Consumer Protection Act)

US — A2P 10DLC Registration (required since 2022)

EU/UK — GDPR-derived consent

Canada — CASL

Phone Number Types (US)

Core Principles

1. Every send has a real cost

2. Opt-in is your most valuable asset

3. Each message must justify itself

4. Brevity + clarity

5. One CTA, one link

6. Sender identity, every send

SMS Sequence Types

Welcome / Opt-In Confirmation (immediate)

Abandoned Cart (highest-ROI flow for ecom)

Browse Abandonment

Post-Purchase

Win-Back (lapsed)

Promotional / Campaign Sends

Transactional (separate compliance bucket)

SMS Copy Guidelines

Structure

Length

Voice

Personalization

Platform Selection

Measurement

Key Metrics

What to track in analytics

What to A/B test

Output Format

Task-Specific Questions

Common Mistakes

Tool Integrations

Related Skills

SkillSafety

Source

Related skills

More in the registry