Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Central marketing operations hub for MarTech stack, automation, attribution, campaign orchestration, and skill routing.
SkillScore82/100
Test results 82
3/3 safety checks passed
27%82%of test cases passed +55 pts
Passed 18 of 22 test cases with the skill, and 6 of 22 without it.
12 fixed6 passed either way4 still failing0 broke
This benchmark measured an earlier version of the skill.
One test taskWrite the command line invocation for running the campaign budget allocator Python script against `campaigns.json` with a $100,000 budget using a balanced allocation strategy.
Adds every file the skill has, pinned so you can update it. No account needed.
pip install "decimalai>=0.15"
decimalai skills add borghei-marketing-ops
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")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.
/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai/decimalai:install borghei-marketing-opsThe plugin needs python3 and curl on your machine.
No Python or account. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/borghei-marketing-ops/SKILL.md https://app.decimal.ai/s/borghei-marketing-ops/SKILL.md.claude/skills/borghei-marketing-ops/SKILL.mdThis gets SKILL.md only. The skill's 3 other files are not included.
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.
pip install "decimalai[claude-agent-sdk]"
decimalai skills add borghei-marketing-opsimport 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.
pip install "decimalai[claude-agent-sdk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/borghei-marketing-ops/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.
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.
pip install "decimalai[openai-agents]"
decimalai skills add borghei-marketing-opsfrom 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.
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.
pip install "decimalai[openai-agents]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/borghei-marketing-ops/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.
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.
pip install "decimalai[openai]"
decimalai skills add borghei-marketing-opsimport 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.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.
pip install "decimalai[openai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/borghei-marketing-ops/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].messageThis gets SKILL.md only. The skill's 3 other files are not included.
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.
pip install "decimalai[anthropic]"
decimalai skills add borghei-marketing-opsimport 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()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.
pip install "decimalai[anthropic]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/borghei-marketing-ops/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.
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.
pip install "decimalai[google-genai]"
decimalai skills add borghei-marketing-opsfrom 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)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.
pip install "decimalai[google-genai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/borghei-marketing-ops/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.
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.
pip install "decimalai[langchain]" langchain-openai
decimalai skills add borghei-marketing-opsfrom 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!"}]})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.
pip install "decimalai[langchain]" langchain-openaifrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/borghei-marketing-ops/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.
CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add borghei-marketing-opsimport 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.
pip install "decimalai>=0.16" "crewai>=1.15.27"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom 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.
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.
pip install "decimalai[adk]"
decimalai skills add borghei-marketing-opsfrom 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.
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.
pip install "decimalai[adk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/borghei-marketing-ops/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.
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.
pip install "decimalai[pydantic-ai]"
decimalai skills add borghei-marketing-opsfrom 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.
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.
pip install "decimalai[pydantic-ai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/borghei-marketing-ops/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.
Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" deepagents
decimalai skills add borghei-marketing-opsimport 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.
pip install "decimalai>=0.16" deepagentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/borghei-marketing-ops/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.
Its own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" agent-framework
decimalai skills add borghei-marketing-opsimport 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.
pip install "decimalai>=0.16" agent-frameworkfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/borghei-marketing-ops/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.
Strands' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" strands-agents
decimalai skills add borghei-marketing-opsfrom 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.
pip install "decimalai>=0.16" strands-agentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("borghei-marketing-ops")
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.
.agents/skills/borghei-marketing-ops/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/borghei-marketing-ops/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.
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-opsNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/borghei-marketing-ops/SKILL.md https://app.decimal.ai/s/borghei-marketing-ops/SKILL.md.agents/skills/borghei-marketing-ops/SKILL.mdThis gets SKILL.md only. The skill's 3 other files are not included.
Give its text to your model as instructions. No account or package needed.
This gets SKILL.md only. The skill's 3 other files are not included.
Raw files: /s/borghei-marketing-ops/SKILL.md · /s/borghei-marketing-ops.json
Fetch the file and give its text to your model as instructions. No account or package needed.
curl -fsSL https://app.decimal.ai/s/borghei-marketing-ops/SKILL.mdcurl -fsSL https://app.decimal.ai/s/borghei-marketing-ops.jsonThis gets SKILL.md only. The skill's 3 other files are not included.
You don't need a DecimalAI account.
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.
Central command for marketing operations — routing questions, orchestrating campaigns, managing MarTech, and coordinating across all marketing functions.
marketing ops, marketing operations, MarTech stack, marketing automation, campaign orchestration, skill routing, marketing coordination, data management, attribution, marketing technology, campaign management, workflow automation, lead management, marketing analytics, marketing infrastructure, CRM integration, email automation, lead scoring
What most shapes this skill's output is what the user is trying to get done, and the stack and data it has to run on. 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.
campaign_budget_allocator.py splits a total budget across channels, and the same figure decides whether a new tool passes the cost criterion.The campaign steps below start by checking for marketing context. If a marketing context document exists (the one the marketing-context skill builds), start from it 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.
| User Says | Route To | Not This |
|---|---|---|
| "Write a blog post," "content ideas," "what should I write" | Content Strategy | Not Copywriting (that is for page copy) |
| "Write copy for my homepage," "landing page copy," "headline" | Copywriting | Not Content Strategy (that is for planning) |
| "Edit this copy," "proofread," "polish this" | Copy Editing | Not Copywriting (that is for writing new) |
| "Social media post," "LinkedIn post," "tweet" | Social Content | Not Content Strategy (that is for planning) |
| "Write an article end-to-end," "content production" | Content Production | Not Content Strategy (production has the full pipeline) |
| "Sounds too robotic," "make it human," "AI watermarks" | Content Humanizer | Not Copy Editing (that is for editorial quality) |
| "Marketing ideas," "brainstorm," "what else can I try" | Marketing Ideas | Not Content Strategy (that is for content specifically) |
| User Says | Route To | Not This |
|---|---|---|
| "SEO audit," "technical SEO," "on-page SEO" | SEO Specialist | Not AI SEO (that is for AI search engines) |
| "AI search," "ChatGPT visibility," "Perplexity," "GEO" | AI SEO | Not SEO Specialist (that is traditional SEO) |
| User Says | Route To | Not This |
|---|---|---|
| "Landing page," "campaign page," "lead capture page" | Landing Page Generator | Not Copywriting (generator includes structure + copy) |
| "Brand guidelines," "style guide," "brand voice" | Brand Guidelines | Not Marketing Context (guidelines are implementation) |
| User Says | Route To | Not This |
|---|---|---|
| "Paid ads," "Google Ads," "Meta ads," "ad campaign" | Paid Ads | Not Ad Creative (that is for copy, not strategy) |
| "Ad copy," "ad headlines," "ad variations," "RSA" | Ad Creative | Not Paid Ads (that is for campaign strategy) |
| "Cold email," "outreach," "prospecting email" | Cold Email | Not Content Production (cold email has different rules) |
| User Says | Route To | Not This |
|---|---|---|
| "Marketing context," "who is my customer," "ICP" | Marketing Context | Set up before other skills |
| "Marketing strategy," "how to market" | Marketing Ideas | Not Marketing Ops (ops is for execution routing) |
| "Psychology," "persuasion," "why people buy" | Marketing Psychology | Not Copywriting (psychology is the theory layer) |
Sequence:
1. Marketing Context (verify foundation exists)
2. Content Strategy (plan launch content)
3. Copywriting (write landing page and email copy)
4. Landing Page Generator (build the conversion page)
5. Ad Creative (create ad copy for paid promotion)
6. Paid Ads (set up campaign targeting and budget)
7. Social Content (create organic social posts)
8. Cold Email (targeted outreach to prospects)
9. Campaign Analytics (measure results)
Sequence:
1. Content Strategy (plan topics and calendar)
2. Content Production (research, write, optimize each piece)
3. Content Humanizer (polish for natural voice)
4. AI SEO (optimize for AI search citation)
5. Social Content (distribute across platforms)
6. Campaign Analytics (track performance)
Sequence:
1. Marketing Context (verify ICP and messaging)
2. Landing Page Generator (build conversion pages)
3. Ad Creative (generate ad variations)
4. Paid Ads (launch campaigns)
5. Cold Email (parallel outbound effort)
6. Campaign Analytics (measure and optimize)
Sequence:
1. Marketing Context (define brand foundation)
2. Brand Guidelines (establish visual and verbal standards)
3. Content Strategy (plan thought leadership content)
4. Social Content (build social presence)
5. Content Production (create pillar content)
6. Campaign Analytics (measure reach and engagement)
Sequence:
1. Marketing Psychology (identify behavioral levers)
2. Copy Editing (audit existing page copy)
3. Copywriting (rewrite underperforming sections)
4. Landing Page Generator (redesign conversion pages)
5. Campaign Analytics (set up A/B tests and track results)
| Category | Purpose | Common Tools | Integration Priority |
|---|---|---|---|
| CRM | Customer data management | Salesforce, HubSpot, Pipedrive | Critical |
| Marketing Automation | Email, workflows, scoring | HubSpot, Marketo, ActiveCampaign | Critical |
| Analytics | Traffic and behavior tracking | GA4, Mixpanel, Amplitude | Critical |
| Email Platform | Email sending and deliverability | SendGrid, Mailchimp, Customer.io | Critical |
| Ad Platforms | Paid advertising | Google Ads, Meta Ads, LinkedIn Ads | High |
| SEO Tools | Keyword research and tracking | Ahrefs, SEMrush, Moz | High |
| Social Management | Publishing and scheduling | Buffer, Hootsuite, Sprout Social | Medium |
| Content Management | Content creation and hosting | WordPress, Webflow, Ghost | High |
| Attribution | Multi-touch attribution | Attribution App, Dreamdata | Medium |
| ABM | Account-based marketing | Demandbase, 6sense, Terminus | Medium (B2B) |
When evaluating new tools:
| Criterion | Weight | Scoring |
|---|---|---|
| Does it solve a validated problem? | 30% | Clear need (3), Nice to have (2), Speculative (1) |
| Does it integrate with existing stack? | 25% | Native integration (3), API available (2), Manual export (1) |
| Total cost of ownership | 20% | Under budget (3), At budget (2), Over budget (1) |
| Time to value | 15% | Under 1 week (3), 1-4 weeks (2), 4+ weeks (1) |
| Team capability to use it | 10% | Self-serve (3), Training needed (2), Expert required (1) |
Rule: Never add a tool that does not integrate with your CRM. Disconnected data is worse than no data.
| Automation | Impact | Complexity | Build First |
|---|---|---|---|
| Welcome/onboarding email sequence | High | Low | Yes |
| Lead scoring | High | Medium | Yes |
| Abandoned cart/trial follow-up | High | Low | Yes |
| Event-triggered emails (usage milestones) | High | Medium | Second priority |
| Lead routing to sales | High | Low | Yes |
| Social media scheduling | Medium | Low | Second priority |
| Reporting dashboards | Medium | Medium | Second priority |
| Content personalization | Medium | High | Third priority |
| Predictive lead scoring | Medium | High | Third priority |
| Dynamic content insertion | Low-Medium | High | Later |
| Signal Type | Examples | Score |
|---|---|---|
| Demographic fit | Matches ICP (title, company size, industry) | +10 to +25 |
| Behavioral - high intent | Visited pricing page, requested demo, viewed case study | +15 to +25 |
| Behavioral - engagement | Opened 3+ emails, downloaded content, attended webinar | +5 to +15 |
| Behavioral - product | Used free trial, reached activation milestone | +20 to +30 |
| Negative signals | Competitor employee, student email, unsubscribed | -10 to -50 |
Lead score thresholds:
| Sequence | Trigger | Emails | Duration |
|---|---|---|---|
| Welcome | New signup | 5-7 | 14 days |
| Onboarding | Started trial | 4-6 | 14 days |
| Re-engagement | Inactive 30 days | 3-4 | 21 days |
| Win-back | Churned | 3-5 | 30 days |
| Nurture | Downloaded content | 5-7 | 45 days |
| Upsell | Reached plan limit | 2-3 | 7 days |
| Referral | 90 days active + high NPS | 2 | 7 days |
| Dimension | Definition | How to Measure |
|---|---|---|
| Completeness | Required fields are filled | % of records with complete required fields |
| Accuracy | Data matches reality | Sample audit against source of truth |
| Consistency | Same data, same format everywhere | Cross-system comparison |
| Timeliness | Data is current | % of records updated within defined freshness window |
| Uniqueness | No duplicate records | Duplicate rate in CRM |
| Task | Frequency | Owner |
|---|---|---|
| Deduplicate CRM records | Monthly | Marketing Ops |
| Verify email addresses | Before every campaign | Marketing Ops |
| Update firmographic data | Quarterly | Marketing Ops |
| Clean inactive contacts | Quarterly | Marketing Ops |
| Audit UTM parameter consistency | Monthly | Marketing Ops |
| Review lead scoring accuracy | Quarterly | Marketing + Sales |
| Sync CRM with marketing automation | Continuous (automated) | System |
Consistent UTM tagging is foundational for attribution:
utm_source: [platform] — google, linkedin, facebook, email, partner-name
utm_medium: [channel type] — cpc, organic, email, social, referral
utm_campaign: [campaign name] — product-launch-q1, blog-promo-march
utm_content: [variant] — headline-a, cta-blue, audience-cmo
utm_term: [keyword] — for paid search only
Rules:
| Model | How It Works | Best For | Limitation |
|---|---|---|---|
| First-touch | 100% credit to first interaction | Understanding acquisition channels | Ignores nurture touchpoints |
| Last-touch | 100% credit to final interaction | Understanding conversion triggers | Ignores awareness touchpoints |
| Linear | Equal credit to all touchpoints | Simple multi-touch understanding | Treats all touches equally |
| Time-decay | More credit to recent touchpoints | Long sales cycles | May undervalue awareness |
| Position-based (U-shaped) | 40% first, 40% last, 20% middle | Balanced view | Arbitrary weighting |
| Data-driven | ML-based weighting | Sophisticated programs | Requires large data volume |
| Area | What to Assess | Key Questions |
|---|---|---|
| Strategy | Positioning, ICP, messaging | Is our positioning differentiated? Do we know our ICP? |
| Content | Quality, quantity, performance | Is content driving traffic and conversions? |
| SEO | Rankings, technical health, content gaps | Are we visible for target keywords? |
| Paid | ROAS, CPA, channel mix | Are paid campaigns profitable? |
| List health, engagement, automation | Are sequences driving conversions? | |
| Social | Reach, engagement, brand consistency | Are we building audience and trust? |
| MarTech | Stack utilization, integration health | Are our tools connected and used? |
| Data | Quality, attribution, reporting | Can we trust our data and attribution? |
For each area, score 1-5:
| Score | Status | Action |
|---|---|---|
| 1 | Not present | Build from scratch |
| 2 | Basic but underperforming | Significant improvement needed |
| 3 | Functional | Optimize and iterate |
| 4 | Strong | Maintain and scale |
| 5 | Best-in-class | Protect and document |
Context first, always — Check that marketing context exists before any marketing work. Everything works better with context.
Route precisely — A question routed to the wrong skill produces wrong-shaped output. Use the routing matrix.
Orchestrate, do not fragment — Multi-skill campaigns need a sequence plan. Ad hoc execution produces inconsistent results.
Own the data — Marketing ops is responsible for data quality. Bad data produces bad decisions.
Standardize UTMs — Inconsistent UTM parameters make attribution impossible. Enforce standards before launching campaigns.
Audit tools annually — Every tool should justify its cost and usage. Cut tools nobody uses.
Automate the repeatable — If you do it every week, automate it. Manual processes do not scale.
Document everything — Campaign playbooks, automation logic, data flows, tool configurations. Tribal knowledge is fragile.
Align with sales — Marketing ops and sales ops must share data definitions, lead scoring criteria, and attribution models.
Measure what matters — Track leading indicators (MQLs, pipeline velocity) alongside lagging indicators (revenue, ROI).
| Symptom | Likely Cause | Resolution |
|---|---|---|
| Marketing and sales disagree on lead quality | Lead scoring thresholds not aligned or model not validated against outcomes | Run lead_scoring_simulator.py with historical data; validate that high-scored leads convert at 2x+ the rate of low-scored |
| MarTech stack costs growing 20%+ YoY without proportional ROI | Tool proliferation without consolidation; unused tools not audited | Run martech_stack_auditor.py quarterly; cut tools with <30% utilization; consolidate overlapping categories |
| Campaign data siloed across platforms, attribution impossible | No unified UTM standard; tools not integrated through CRM | Standardize UTM parameters (lowercase, hyphens, documented registry); require CRM integration for every tool |
| Lead routing to sales takes >24 hours | Manual handoff process; no automation between marketing automation and CRM | Implement automated lead routing rules; route hot leads (76+ score) within 15 minutes |
| Email deliverability dropping below 90% | List hygiene not maintained; bounced/inactive contacts not cleaned | Deduplicate monthly; verify addresses before campaigns; clean inactive contacts quarterly |
| Budget spent evenly across channels regardless of performance | No performance-based allocation framework in place | Use campaign_budget_allocator.py with historical ROAS data; shift budget quarterly toward highest performers |
| Multi-skill campaigns produce inconsistent messaging | No orchestration sequence defined; skills executed ad hoc | Follow campaign orchestration templates; always start with marketing context verification |
In Scope: Skill routing and orchestration, campaign sequencing, MarTech stack management and auditing, marketing automation (email sequences, lead scoring, lead routing), data quality management, UTM standardization, attribution framework setup, marketing audit methodology, budget allocation.
Out of Scope: Individual channel execution (see channel-specific skills), analytics implementation (see analytics-tracking skill), content creation (see content-creator skill), sales operations and CRM administration (sales ops function).
Limitations: Marketing ops is the coordination layer, not the execution layer. Tool auditing uses self-reported utilization data; actual usage may differ. Lead scoring models require minimum 50+ historical conversions for meaningful validation. Budget allocation assumes linear channel scaling; real channels have diminishing returns.
| Script | Purpose | Usage |
|---|---|---|
scripts/martech_stack_auditor.py | Audit MarTech stack for gaps, redundancies, and optimization opportunities | python scripts/martech_stack_auditor.py stack.json --demo |
scripts/campaign_budget_allocator.py | Allocate marketing budget across campaigns by priority and performance | python scripts/campaign_budget_allocator.py campaigns.json --budget 100000 --strategy balanced |
scripts/lead_scoring_simulator.py | Simulate and validate lead scoring models against actual outcomes | python scripts/lead_scoring_simulator.py leads.json --demo |
Automatically, when a task matches. Use when routing marketing questions, orchestrating multi-skill campaigns, or managing the MarTech stack and automation.
Published skills whose descriptions closely match this one, with their headline benchmark lift.
Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.