Ready to supercharge your AI agents?

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

Marketing Context · borghei | DecimalAI

Marketingby borghei

Marketing Context

Create and maintain the foundational context doc (positioning, ICP, competitive landscape, brand voice, customer language) that other marketing skills read first.

Never made a case worseMaintained

SkillScore

SkillScore74/100

Test results 74

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

22%74%of test cases passed +52 pts

Without skill5 of 23

With skill17 of 23

12 fixed5 passed either way6 still failing0 broke

Measured on gemini-3.6-flash8/21/2026v1 · latest is v2

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe need to run our context document audit tool on `context.md` inside a CI pipeline to parse results programmatically. Which tool and flag should we execute?

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 borghei-marketing-context
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("borghei-marketing-context")
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 borghei-marketing-context

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/borghei-marketing-context/SKILL.md https://app.decimal.ai/s/borghei-marketing-context/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/borghei-marketing-context/SKILL.md

This gets SKILL.md only. The skill's 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/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/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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("borghei-marketing-context")
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/borghei-marketing-context/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/borghei-marketing-context/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 3 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 borghei-marketing-context

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/borghei-marketing-context/SKILL.md https://app.decimal.ai/s/borghei-marketing-context/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/borghei-marketing-context/SKILL.md

This gets SKILL.md only. The skill's 3 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/borghei-marketing-context/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/borghei-marketing-context.json

This gets SKILL.md only. The skill's 3 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2 (v1 tested 8/21/2026)
Source: borghei/claude-skills ↗
License: NOASSERTION

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Marketing Context

The foundational context document that every marketing skill reads before starting. Captures positioning, ICP, competitive landscape, brand voice, and customer language in one place.

Keywords
Clarify First
Quick Start
Core Workflows
Context Sections
Customer Research Methodology
Competitive Analysis Framework
Switching Dynamics (JTBD Four Forces)
Context Maintenance
Best Practices
Integration Points

Keywords

marketing context, brand voice, target audience, ICP, ideal customer profile, positioning, customer insights, competitive analysis, market research, customer language, brand personality, buyer persona, product marketing, go-to-market, messaging framework, competitive landscape, objection handling, proof points, switching dynamics, value proposition

Clarify First

What most shapes this skill's output is whether a context document already exists and how much of it can rest on real customer evidence rather than internal assumptions. Settle the inputs below before producing anything. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

Existing document: if one exists, the job is a targeted update that keeps the accurate sections. If not, it is a fresh build. Rewriting a document that is mostly right throws away verbatim customer language that is hard to collect again.
Source material: a repository with a README, landing pages and docs supports the auto-draft path. Customer interviews, sales calls and reviews are what fill the customer language, objections and switching dynamics sections; without them those sections are guesses, and the document says so.
Product and audience scope: one product for one segment gives a single ICP and persona set. Several products or segments change how many personas, anti-personas and competitor sets the document needs.
What it feeds next: if the immediate need is ads or cold email, the ICP, pain points and customer language come first. If it is content or SEO, the keyword and competitive sections matter more. This decides which sections get depth when time is short.

If the user already has a context document, read it first (context_completeness_checker.py shows which sections are missing or thin) and ask only about the gaps. Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.

Quick Start

Auto-Draft from Codebase

Study the repository: README, landing pages, marketing copy, about pages, docs
Draft a V1 context document based on what exists
Present the draft and ask: "What needs correcting? What is missing?"
Iterate through corrections until the document is accurate

Guided Interview

Walk through each section conversationally, one at a time
Ask focused questions (not all at once)
Capture exact customer language, not polished summaries
Validate each section before moving to the next

Update Existing Context

Read the current context document
Summarize what is captured
Ask which sections need updating
Make targeted updates while preserving accurate sections

Core Workflows

Workflow 1: Build Context from Scratch

Step 1: Gather Product Foundation

## Product Overview
- One-line description: [What it is in one sentence]
- What it does: [2-3 sentences explaining the product]
- Product category: [The "shelf" — how customers search for you]
- Product type: [SaaS / Marketplace / E-commerce / Service / Platform]
- Business model: [Subscription / Freemium / Usage-based / One-time]
- Pricing: [Starting price / tier structure]
- Stage: [Pre-launch / Early / Growth / Scale / Mature]

Step 2: Define Target Audience

## Target Audience
- Target company type: [Industry, size, stage, geography]
- Target decision-makers: [Roles, departments, seniority levels]
- Primary use case: [The main problem you solve]
- Jobs to be done (3-5):
  1. [Job]: [What they hire your product to do]
  2. [Job]: [What they hire your product to do]
  3. [Job]: [What they hire your product to do]
- Specific scenarios: [2-3 situations where they need you most]

Step 3: Build Buyer Personas

For each stakeholder involved in the buying decision:

## Persona: [Role Name]
- Title: [Job title]
- Role in purchase: [User / Champion / Decision Maker / Financial Buyer / Technical Influencer]
- What they care about: [Their top 3 priorities]
- Their challenge: [Specific problem related to your product]
- Value you promise them: [What you deliver to this persona]
- Language they use: [Exact phrases they use to describe their problem]
- Where they research: [Channels, communities, publications they trust]

Step 4: Document Problems and Pain Points

## Problems & Pain Points
- Core challenge: [What customers face before finding you]
- Why current solutions fail: [Specific shortcomings of alternatives]
- Cost of the problem:
  - Time cost: [Hours/week wasted]
  - Financial cost: [Money lost or spent inefficiently]
  - Opportunity cost: [What they cannot do while dealing with this]
- Emotional tension: [Stress, fear, frustration, doubt they experience]

Step 5: Map Competitive Landscape

## Competitive Landscape

### Direct Competitors (same solution, same problem)
| Competitor | Positioning | Weakness for Our ICP |
|-----------|------------|---------------------|
| [Name] | [How they position] | [Where they fall short] |

### Secondary Competitors (different solution, same problem)
| Competitor | Their Approach | Why Ours is Better |
|-----------|---------------|-------------------|
| [Name] | [Their method] | [Our advantage] |

### Indirect Competitors (do nothing, spreadsheets, manual process)
| Alternative | Why Customers Use It | Why They Should Switch |
|------------|---------------------|---------------------|
| [Name] | [Inertia reason] | [Switching benefit] |

Step 6: Define Differentiation

## Differentiation
- Key differentiators (3-5):
  1. [Capability]: [What we do that alternatives cannot]
  2. [Capability]: [What we do that alternatives cannot]
  3. [Capability]: [What we do that alternatives cannot]
- How we solve it differently: [Our unique approach or mechanism]
- Why that matters: [Benefit of our approach vs. alternatives]
- Why customers choose us: [Top 3 reasons from actual customer feedback]

Step 7: Capture Objections and Anti-Personas

## Objections
| Objection | Frequency | Response |
|-----------|-----------|----------|
| "[Objection 1]" | Common | [How to address it] |
| "[Objection 2]" | Occasional | [How to address it] |
| "[Objection 3]" | Rare but important | [How to address it] |

## Anti-Personas (Who is NOT a Good Fit)
- [Type]: [Why they should not buy]
- [Type]: [Why they should not buy]

Step 8: Document Customer Language

## Customer Language (Verbatim)
- How they describe the problem:
  - "[Exact quote from customer]"
  - "[Exact quote from customer]"
- How they describe our solution:
  - "[Exact quote from customer]"
  - "[Exact quote from customer]"
- Words TO use: [List of customer-approved terms]
- Words to AVOID: [Terms that confuse or alienate]
- Glossary: [Product-specific terms with definitions]

Step 9: Establish Brand Voice

## Brand Voice
- Tone: [Professional / Casual / Playful / Authoritative]
- Communication style: [Direct / Conversational / Technical / Storytelling]
- Personality (3-5 adjectives): [e.g., Confident, Clear, Warm]
- Voice DOs: [What we always do in writing]
- Voice DON'Ts: [What we never do in writing]
- Example paragraph: [A paragraph that perfectly captures our voice]

Step 10: Compile Proof Points

## Proof Points
- Key metrics: [Numbers we cite regularly]
- Notable customers: [Logos we have permission to use]
- Testimonial snippets:
  - "[Quote]" — [Name], [Title] at [Company]
  - "[Quote]" — [Name], [Title] at [Company]
- Awards and recognition: [Current, with year]
- Certifications: [Active compliance certifications]

Step 11: Content and SEO Context

## Content & SEO Context
- Target keywords by cluster:
  - Cluster 1: [keyword 1], [keyword 2], [keyword 3]
  - Cluster 2: [keyword 1], [keyword 2], [keyword 3]
- Writing examples (best-performing pieces):
  - [URL 1]: [Why it works well]
  - [URL 2]: [Why it works well]
- Content tone: [Educational / Authoritative / Conversational]
- Preferred content length: [Short-form / Long-form / Mix]

Step 12: Define Goals

## Goals
- Primary business goal: [What success looks like]
- Key conversion action: [What you want people to do]
- Current metrics: [Baseline numbers if available]
- Target metrics: [What you are working toward]

Customer Research Methodology

Research Sources Ranked by Quality

Source	Quality	What You Get	Time Required
Customer interviews (6-10)	Highest	Deep understanding of language, pain, decision process	6-10 hours
Sales call recordings	High	Pre-purchase questions, objections, language	2-4 hours
Support ticket analysis	High	Post-purchase confusion, unmet expectations	1-2 hours
Product reviews (yours + competitors)	High	Candid praise and complaints	1-2 hours
Customer surveys	Medium-High	Quantitative validation of qualitative findings	2-3 hours
Community forums	Medium	Questions, debates, misconceptions	1-2 hours
Competitor content analysis	Medium	Positioning gaps, messaging angles	2-3 hours
Social listening	Medium	Trending topics, sentiment, language	1 hour
Analytics data	Medium	Behavioral patterns, not motivations	1 hour

Interview Question Framework

Opening (establish context):

"Walk me through how you handled [problem area] before using our product."
"What was the moment you decided to look for a solution?"

Problem exploration:

"What was the hardest part about [problem area]?"
"What did you try before finding us?"
"What did those alternatives get wrong?"

Decision process:

"What made you choose us over the alternatives?"
"What almost stopped you from signing up?"
"Who else was involved in the decision?"

Language capture:

"How would you explain what we do to a colleague?"
"If you were recommending us, what would you say?"

Outcome validation:

"What has changed since you started using us?"
"Can you put a number on the impact?"

Competitive Analysis Framework

Three-Layer Analysis

Layer 1: Positioning

How do they describe themselves? (Tagline, hero copy, meta description)
What category do they claim? (The "shelf" they put themselves on)
Who do they target? (ICP signals from their copy, pricing, case studies)

Layer 2: Messaging

What benefits do they lead with?
What proof points do they emphasize?
What objections do they proactively address?
What is conspicuously absent from their messaging?

Layer 3: Execution

Content: What topics do they cover? What formats? What frequency?
Channels: Where are they active? (SEO, social, paid, events)
Social proof: Who are their reference customers?
Pricing: How are they positioned on price?

Competitive Positioning Map

                    Premium
                      |
         Enterprise   |   Innovator
         (Salesforce)  |   (Your positioning?)
                      |
    Simple ———————————+——————————— Complex
                      |
         Budget       |   Technical
         (Competitor B)|  (Competitor C)
                      |
                   Affordable

Switching Dynamics (JTBD Four Forces)

Understanding why customers switch (or do not) is critical for messaging:

The Four Forces

PUSH ————————————> <———————————— HABIT
(Frustration with        (Comfort with
 current solution)        current approach)

PULL ————————————> <———————————— ANXIETY
(Attraction to           (Fear about
 your product)            switching)

Push (maximize in messaging):

What frustrations drive them away from the current solution?
What is the breaking point that triggers the search?

Pull (amplify in messaging):

What attracts them to your product specifically?
What is the "aha moment" they imagine?

Habit (address in messaging):

What keeps them stuck with the current approach?
What switching costs (real and perceived) exist?

Anxiety (reduce in messaging):

What worries them about switching?
What could go wrong during the transition?
How do you make switching feel safe?

Context Maintenance

Freshness Rules

Section	Review Frequency	Staleness Signal
Product overview	When features change	New features not reflected
Target audience	Quarterly	Win/loss data shows new segments
Competitive landscape	Monthly	New competitors emerging, positioning shifts
Customer language	Quarterly	New patterns in sales calls and reviews
Proof points	Monthly	New case studies, metrics, logos available
Brand voice	Semi-annually	Brand evolution or rebranding
Goals	Quarterly	Business priorities shift

Update Triggers

Flag a context review when:

A major product launch changes positioning
Win rate shifts significantly (new objections emerging)
A new competitor enters the market
Customer language patterns change (new terminology)
The ICP shifts (moving upmarket, new verticals)
Proof points become outdated (old metrics, former customer logos)

Best Practices

Be specific, not polished — "I wish I knew this before we migrated" is more useful than "Customers value our migration support." Capture exact words.
Validate with real customers — Every positioning claim should be traceable to customer feedback. If customers do not say it, it might not be true.
Update incrementally — Do not wait for a full overhaul. Update individual sections as new information becomes available.
Include anti-personas — Knowing who is NOT a good fit prevents wasted marketing spend on the wrong audience.
Capture switching dynamics — Understanding push/pull/habit/anxiety produces better messaging than listing features.
Keep it usable — A 50-page context document nobody reads is worse than a 5-page one everyone references. Be concise.
Document customer language verbatim — Do not paraphrase. The exact words customers use should appear in your copy.
Link to proof — Every claim should reference its source (customer interview, survey, case study, metric).
Share across teams — Marketing context should be accessible to sales, product, and customer success. Shared language improves alignment.
Review quarterly minimum — Set a calendar reminder. Stale context produces stale messaging.

Integration Points

Copywriting — Reads brand voice and customer language from this context for page copy.
Content Strategy — Reads target keywords, personas, and competitive landscape for topic planning.
Ad Creative — Reads ICP, value proposition, and proof points for ad messaging.
Cold Email — Reads ICP, pain points, and customer language for outreach personalization.
Marketing Ops — Routes marketing questions using context as the foundation.
Social Content — Reads brand voice and audience details for platform-specific content.
Brand Guidelines — Aligns brand voice and personality between context and visual standards.
Paid Ads — Reads audience targeting details and value proposition for campaign setup.

Troubleshooting

Symptom	Likely Cause	Resolution
Marketing copy sounds generic across all channels	Context document missing customer language section with verbatim quotes	Conduct 6-10 customer interviews; capture exact phrases used to describe problem and solution
Sales and marketing using different messaging	Context document exists but not shared cross-functionally, or multiple conflicting versions	Consolidate into single source of truth; share with sales, product, and CS; version-control updates
ICP keeps expanding until it includes everyone	No anti-persona defined; pressure to broaden targeting	Document who is NOT a good fit and why; validate ICP against top 20% customers by LTV
Competitive positioning feels reactive	Landscape section only updated after losing deals, not proactively	Set monthly competitive review cadence; monitor competitor websites, pricing, and job postings
Context document becomes stale within 2 months	No update triggers or review schedule defined	Assign section owners; set quarterly review calendar; flag automatic updates on product launches or ICP shifts
New team members cannot find or understand the context	Document too long (50+ pages) or buried in wiki structure	Keep context under 10 pages; use templates with clear headers; include in onboarding checklist

Success Criteria

Context completeness score above 80% on context_completeness_checker.py (all 12 sections present with minimum depth)
Every positioning claim traceable to specific customer feedback or data source
Customer language section contains 10+ verbatim quotes (not paraphrased summaries)
Context document reviewed and updated at least quarterly, with change log
100% of marketing skills reference context before starting work
ICP definition validated against actual customer data: A-fit customers have lowest churn and fastest close
Anti-personas defined with clear exclusion criteria to prevent wasted marketing spend

Scope & Limitations

In Scope: Product positioning documentation, ICP definition and validation, buyer persona creation, competitive analysis framework, customer language capture, brand voice establishment, proof point compilation, objection handling, switching dynamics (JTBD Four Forces), content and SEO context, context maintenance and freshness management.

Out of Scope: Brand visual identity (see brand-guidelines skill), marketing execution and campaign management (see marketing-ops skill), product strategy and roadmap (see product-team skills), market sizing and TAM analysis (see c-level-advisor skills).

Limitations: Marketing context is only as accurate as the inputs — garbage in, garbage out. Context derived solely from internal assumptions (without customer interviews) will have blind spots. Competitive analysis is point-in-time; markets shift and require continuous monitoring.

Scripts

Script	Purpose	Usage
`scripts/icp_fit_scorer.py`	Score prospects against ICP criteria with A/B/C/D grading	`python scripts/icp_fit_scorer.py prospects.json --icp icp_config.json --demo`
`scripts/competitive_landscape_mapper.py`	Map competitive positioning, features, pricing, and identify gaps	`python scripts/competitive_landscape_mapper.py competitors.json --demo`
`scripts/context_completeness_checker.py`	Audit marketing context document for missing or thin sections	`python scripts/context_completeness_checker.py context.md --json`

When it activates

Automatically, when a task matches. Use when setting up context, defining the ICP, or setting brand voice.

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 v8 — 10/25/2026

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

borghei / claude-skills

marketing/marketing-context/SKILL.md

View on GitHub ↗

License MITImported 10/25/2026Version v2Bundled 3 files · scripts

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

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Marketing Context

Table of Contents

Keywords

Clarify First

Quick Start

Auto-Draft from Codebase

Guided Interview

Update Existing Context

Core Workflows

Workflow 1: Build Context from Scratch

Customer Research Methodology

Research Sources Ranked by Quality

Interview Question Framework

Competitive Analysis Framework

Three-Layer Analysis

Competitive Positioning Map

Switching Dynamics (JTBD Four Forces)

The Four Forces

Context Maintenance

Freshness Rules

Update Triggers

Best Practices

Integration Points

Troubleshooting

Success Criteria

Scope & Limitations

Scripts

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry