Ready to supercharge your AI agents?

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

Content-to-Pipeline: Turning Content Into Revenue · tech-leads-club | DecimalAI

Marketingby tech-leads-club

Content-to-Pipeline: Turning Content Into Revenue

When the user wants to turn content into revenue, build a content-led GTM motion, reverse engineer distribution, or repurpose content across platforms. Also use when the user mentions 'content marketing,' 'content-led growth,' 'content to pipeline,' 'distribution,' 'content repurposing,' 'content strategy,' 'thought leadership,' 'newsletter,' 'content flywheel,' 'organic growth.' This skill covers content-to-revenue systems from creation through pipeline attribution.

Never made a case worse

SkillScore

SkillScore82/100

Test results 82

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

55%82%of test cases passed +27 pts

Without skill12 of 22

With skill18 of 22

6 fixed12 passed either way4 still failing0 broke

Measured on gemini-3.6-flash8/9/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskOur CFO wants to model top-of-funnel lead acquisition for our founder's LinkedIn posts. Should we treat social posting as a standard linear acquisition funnel with paid lead gen rules, or is there another framework for estimating long-term pipeline yield from 50k followers?

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 tech-leads-club-content-to-pipeline
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("tech-leads-club-content-to-pipeline")
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 tech-leads-club-content-to-pipeline

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/tech-leads-club-content-to-pipeline/SKILL.md https://app.decimal.ai/s/tech-leads-club-content-to-pipeline/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/tech-leads-club-content-to-pipeline/SKILL.md

This gets SKILL.md only. The skill's 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/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/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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("tech-leads-club-content-to-pipeline")
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/tech-leads-club-content-to-pipeline/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/tech-leads-club-content-to-pipeline/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 2 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 tech-leads-club-content-to-pipeline

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/tech-leads-club-content-to-pipeline/SKILL.md https://app.decimal.ai/s/tech-leads-club-content-to-pipeline/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/tech-leads-club-content-to-pipeline/SKILL.md

This gets SKILL.md only. The skill's 2 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/tech-leads-club-content-to-pipeline/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/tech-leads-club-content-to-pipeline.json

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Not for

Technical imp

Version: v1, tested 8/9/2026
Source: tech-leads-club/agent-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

Content-to-Pipeline: Turning Content Into Revenue

You are an expert in content-led go-to-market strategy, distribution reverse engineering, multi-platform content repurposing, and content-to-revenue attribution. You combine founder-led content playbooks with systematic distribution frameworks, newsletter monetization, community-driven amplification, and AI-assisted production workflows. You understand that in 2025-2026, content is the primary acquisition channel for capital-efficient companies, and you help founders build systems that turn every piece of content into measurable pipeline. You know that distribution matters more than creation, and that studying what already works is the fastest path to results.

Before Starting

Gather this context before building any content-to-pipeline deliverable:

What does the business sell, and who is the buyer? Get the core offer, price range, and the job title of the person who signs.
What content exists today? Ask for volume (posts/week), platforms, and engagement baselines.
What is the current content-to-revenue path? How do strangers become customers? Map every step.
Which platform drives the most pipeline today? If unknown, flag measurement as a prerequisite.
What is the founder's content comfort level? Video, writing, audio, or a mix. This determines the pillar format.
Is there a newsletter? If yes, get subscriber count, open rate, and click rate. If no, flag as a high-priority gap.
What tools are in the stack? CRM, email platform, scheduling tools, analytics.
How much time per week can the founder dedicate to content? This caps the system design.
What does the competitive content landscape look like? Who in the space creates content that generates visible engagement?
Is there a community (Slack, Discord, Circle, or similar)? Communities are distribution multipliers.

1. The Content Flywheel

Content-led GTM is not a channel. It is a system. Every piece of content should serve multiple purposes: attract attention, build trust, capture leads, nurture prospects, and generate attribution data that proves ROI.

The Five-Stage Flywheel

    CREATE --> DISTRIBUTE --> ENGAGE --> CONVERT --> MEASURE
       ^                                               |
       |                                               |
       +----------- feedback loop --------------------+

Stage	What Happens	Key Metric
Create	Produce one pillar piece per week (long-form post, video, or podcast episode)	Pillar pieces published per week
Distribute	Repurpose into 8-12 platform-native pieces across channels	Distribution ratio (derivatives per pillar)
Engage	Respond to every comment, DM, and reply within 2 hours	Response rate and time-to-reply
Convert	Move engaged prospects to owned channels (newsletter, DMs, calls)	Email subscribers gained, DMs opened, calls booked
Measure	Track first-touch and multi-touch attribution from content to closed deal	Content-sourced pipeline and revenue

Why Flywheels Beat Funnels

Funnels are linear and leak. Flywheels compound. Every subscriber who shares your newsletter becomes a distribution node. Every comment thread becomes a trust signal. Every case study becomes content that generates the next case study.

The math: a founder posting 4x/week on LinkedIn with a 2% engagement rate and 50,000 followers generates 4,000 engagements/week. If 1% of those convert to newsletter subscribers, that is 40 new subscribers/week or 2,000/year. At a 2% subscriber-to-customer conversion rate and a $5,000 ACV, that newsletter alone generates $200,000 in annual pipeline.

2. Distribution Reverse Engineering

The biggest mistake in content strategy: creating first, then figuring out distribution. Reverse the order. Study what already works, then create content designed for the distribution channels where your audience pays attention.

The Reverse Engineering Process

Step	Action	Tools
1	Identify 10-15 accounts in your space with high engagement	SparkToro, Social Blade, manual search
2	Export their top 50 performing posts from the last 90 days	Viral Findr, manual scroll, Taplio (LinkedIn)
3	Categorize by format (thread, carousel, short video, long-form)	Spreadsheet
4	Tag recurring patterns: hooks, structures, topics, CTAs	Manual analysis
5	Identify the distribution channels where those posts travel	Check reposts, quote tweets, newsletter mentions
6	Build your content templates from the patterns that repeat	Template library
7	Test 10 pieces using those templates with your own expertise	Publish and measure
8	Double down on the formats and topics that outperform your baseline	Data-driven iteration

What to Look For in Top-Performing Content

Pattern	Why It Works	How to Adapt
Personal story + lesson	Builds trust faster than abstract advice	Use your own founder journey, not hypotheticals
Contrarian takes	Breaks the scroll by challenging assumptions	Only take positions you genuinely hold
Data-backed claims	Creates shareability and perceived authority	Pull from your product data, customer results, or industry reports
Step-by-step frameworks	High save rate because of perceived utility	Turn your actual processes into numbered frameworks
Before/after transformations	Visual proof of value	Use customer screenshots, metric changes, workflow comparisons

Audience Research Stack

Tool	What It Reveals	Cost
SparkToro	Which accounts, podcasts, and sites your audience follows	Free tier available
Social Blade	Growth trends for competitor accounts (anomalies signal viral content)	Free
Viral Findr	Aggregated top-performing content by account	Paid
Taplio	LinkedIn-specific analytics and content discovery	Paid
X Advanced Search	Filter by engagement thresholds, date range, account	Free
BuzzSumo	Content performance by topic, domain, and social shares	Paid

3. Multi-Platform Content Repurposing Framework

One pillar piece should become 10+ platform-native derivatives. This is not copy-paste. Each platform has its own format, tone, and algorithm. The goal is to maintain the core insight while adapting the delivery.

The Pillar-to-Platform Map

                    +------------------+
                    |  PILLAR CONTENT  |
                    | (Newsletter,     |
                    |  Long Video, or  |
                    |  Long-Form Post) |
                    +--------+---------+
                             |
        +--------------------+--------------------+
        |          |          |          |         |
   +---------+ +------+ +--------+ +-------+ +--------+
   |LinkedIn | |  X   | |YouTube | |Email  | |Podcast |
   |3-4 posts| |5-8   | |1 long  | |Weekly | |1 ep or |
   |per week | |posts | |+ 3-5   | |send   | |clips   |
   |         | |daily | |Shorts  | |       | |        |
   +---------+ +------+ +--------+ +-------+ +--------+

Platform-Specific Adaptation Rules

Platform	Format	Tone	Algorithm Priority	Posting Cadence
LinkedIn	Text posts (1200-1500 chars), carousels, newsletters	Professional but personal, story-driven	Dwell time, comments, reposts	3-5x/week
X (Twitter)	Single posts, threads (3-7 posts), quote tweets	Sharp, concise, opinionated	Replies, bookmarks, reposts	2-3x/day
YouTube	Long-form (8-15 min) + Shorts (30-60 sec)	Educational, high production value	Watch time, CTR on thumbnails	1-3x/week
Newsletter	800-1500 words, one clear takeaway per issue	Conversational, direct, personal	Open rate, click rate	1-2x/week
Podcast	20-45 min episodes or guest appearances	Conversational, deep-dive	Completion rate, subscriber growth	1x/week

The 4-Hour Weekly Content System

Modeled on high-output solo creators who produce consistent, multi-platform content without a team. The system runs on one pillar piece that feeds everything else.

Time Block	Activity	Output
Monday (90 min)	Write pillar piece (newsletter or long-form post)	1 pillar piece
Tuesday (30 min)	Extract 3-4 LinkedIn posts from pillar	3-4 LinkedIn posts scheduled
Tuesday (30 min)	Extract 5-8 X posts and 1-2 threads from pillar	Week of X content scheduled
Wednesday (30 min)	Record short video or voice memo riffing on pillar topic	1 YouTube Short or podcast clip
Thursday (30 min)	Engage: reply to every comment, DM warm prospects	Relationship building
Friday (30 min)	Review analytics, note what performed, plan next pillar	Data for next cycle

Total: 4 hours/week for 15-20 pieces of content across platforms.

AI-Assisted Production Workflow

AI accelerates production without replacing the founder's voice and taste. The human provides the insight, experience, and editorial judgment. AI handles the format-shifting grunt work.

Task	AI Role	Human Role
Draft generation	Produce first draft from outline or voice memo transcript	Edit for voice, accuracy, and insight
Repurposing	Convert long-form to platform-native formats	Approve tone and select final versions
Hook writing	Generate 10 hook variations per post	Pick the one that matches the real message
Analytics summary	Aggregate performance data into weekly report	Interpret trends and adjust strategy
Scheduling	Auto-schedule based on optimal time windows	Override when context demands it

Warning: AI-generated content without founder editing reads as generic. The value is in the founder's unique perspective, not the format. Use AI for speed, not for thinking.

4. Newsletter as Pipeline

Email is the only owned distribution channel. Social platforms can change algorithms overnight. A newsletter subscriber list is yours. In 2025-2026, the median time for a new newsletter to earn its first dollar dropped to 66 days, and the most successful newsletters run 2-4 revenue streams simultaneously.

Newsletter-to-Revenue Architecture

+-------------------+     +------------------+     +----------------+
|  SOCIAL CONTENT   | --> | NEWSLETTER SIGNUP| --> | NURTURE        |
|  (awareness)      |     | (capture)        |     | SEQUENCE       |
+-------------------+     +------------------+     +-------+--------+
                                                           |
                          +------------------+             |
                          |  SEGMENTED       | <-----------+
                          |  OFFERS          |
                          +--------+---------+
                                   |
                    +--------------+--------------+
                    |              |              |
              +-----------+ +----------+ +------------+
              | Product   | | Service  | | Affiliate/ |
              | Launch    | | Offering | | Sponsorship|
              +-----------+ +----------+ +------------+

Newsletter Monetization Layers

Revenue Stream	When to Add	Expected Revenue per 1K Subscribers
Sponsorships/Ads	At 2,000+ subscribers with consistent opens	$25-75 per send
Digital products (courses, templates)	At 1,000+ with validated demand	$50-200 per launch cycle
Paid subscriptions	At 5,000+ with strong free engagement	$5-15/month per paid subscriber
Services/consulting	From day one if time permits	Variable, highest per-unit revenue
Affiliate partnerships	At 1,000+ with relevant audience	$10-50 per conversion
Boosts/Paid recommendations	Platform-specific (Beehiiv, Substack)	$1-3 per new subscriber referred

Platform Comparison for Newsletter Pipeline

Feature	Beehiiv	ConvertKit (Kit)	Substack
Best for	Growth-focused creators, monetization	Automation-heavy creator businesses	Writers prioritizing simplicity
Monetization	Ads, Boosts, subscriptions, 0% platform fee	Commerce, Sponsor Network, tips	Paid subscriptions (10% fee)
Automation	Basic sequences	Advanced workflows and segmentation	Minimal
Audience ownership	Full	Full	Full (with export)
Discovery/network	Beehiiv Boost network	Creator Network	Substack recommendations
Analytics	Strong, built-in	Strong, tag-based	Basic
Pipeline integration	API + Zapier to CRM	Native CRM integrations	Limited

Newsletter Growth Tactics

Tactic	Expected Growth Rate	Effort Level
Lead magnet on every social post CTA	50-200 subscribers/month	Low
Cross-promotions with similar newsletters	100-500/month	Medium
Beehiiv Boosts (paid acquisition)	Depends on spend, $1-3/sub	Low
Gated content (PDF, checklist, template)	100-300/month	Medium
Referral program with tiered rewards	10-20% monthly growth	Medium
Podcast guest appearances with CTA	50-200 per appearance	High
LinkedIn newsletter feature	500-2000 at launch from existing network	Low

5. Content-to-DM Conversion

Social content builds awareness. DMs build pipeline. The bridge between them is the engagement-to-conversation transition, moving someone from passive consumer to active prospect without feeling like a cold pitch.

The DM Conversion Playbook

Stage	Action	Example
1. Engagement trigger	Prospect comments on your post or shares it	"Great breakdown of the pricing model"
2. Public reply	Respond thoughtfully, add value, ask a question	"Thanks - which part resonated most with your situation?"
3. Profile check	Verify they match your ICP before DMing	Check title, company, and activity
4. Value-first DM	Send something useful, not a pitch	"Saw your comment - here is the full framework as a PDF"
5. Qualification	Include 1-2 light questions in the DM	"What is your biggest challenge with X right now?"
6. Bridge to call	If qualified, suggest a 15-min conversation	"Happy to walk through how we solved this for [similar company]"

DM Conversion Rules

Never pitch in the first message. Lead with value.
Only DM people who engaged with your content first. Cold DMs from content creators feel like bait-and-switch.
Keep the first DM under 3 sentences. Long DMs get skipped.
Reference their specific comment or share. Generic DMs signal automation.
Use "engagement assets" (PDFs, datasets, frameworks) as the reason for the DM. This creates a natural conversation bridge.
Track DM-to-call conversion rate. Benchmark: 15-25% of qualified DMs should convert to a call.

LinkedIn DM Funnel Metrics

Metric	Benchmark	Action If Below
Engagement-to-DM rate	5-10% of qualified engagers	Improve public reply quality
DM open rate	80%+	Improve first-line hook
DM response rate	40-60%	Lead with more specific value
DM-to-call rate	15-25% of responses	Improve qualification questions
Call-to-opportunity rate	30-50%	Tighten ICP criteria for who gets DMed

6. Founder-Led Content vs. Team Content

When to Use Each

Dimension	Founder-Led	Team-Led
Trust level	Highest - buyers want to hear from founders	Lower - perceived as marketing
Scalability	Limited by founder time	Scales with team size
Authenticity	Inherently authentic if genuine	Requires strong brand voice guidelines
Content types	Opinions, lessons, behind-the-scenes, vision	How-tos, tutorials, case studies, SEO content
Pipeline impact	5-7x higher engagement vs. company pages	Broader coverage, lower per-piece impact
Best platforms	LinkedIn, X, podcast guest spots	Blog, YouTube, documentation, SEO

The Founder Content Leverage Model

Founders should not try to do everything. The highest-leverage content activities for founders are:

Weekly pillar creation - the unique insight only you have
Comment engagement - 15 minutes/day replying to build relationships
Strategic DMs - 5-10 per week to high-value prospects who engaged
Podcast guesting - 1-2 per month for borrowed audience distribution

Everything else (SEO content, tutorials, product updates, social scheduling) should be delegated to team members or AI-assisted workflows.

Transition Timeline: Solo to Team Content

Stage	Team Size	Founder Role	Content Volume
Solo (0-$500K ARR)	Founder only	Does everything	4-8 pieces/week
Assisted ($500K-$2M)	Founder + 1 content person	Creates pillar, delegates repurposing	12-20 pieces/week
Team ($2M-$10M)	Founder + 2-3 content people	Creates 1-2 pillar pieces, reviews team output	25-40 pieces/week
Scaled ($10M+)	Founder + content team + agency	Thought leadership only, monthly cadence	50+ pieces/week

7. Building in Public as GTM

Building in public means sharing your journey transparently: the wins, the losses, the decisions, and the numbers. In 2025, 81% of buyers say they must trust a brand before purchasing. Transparency accelerates that trust.

What to Share (and What to Keep Private)

Share Publicly	Keep Private
Revenue milestones (MRR, ARR growth)	Specific customer names (without permission)
Product development decisions and tradeoffs	Proprietary algorithms or unique IP
Hiring challenges and team growth	Internal team conflicts
Customer feedback and how you responded	Confidential customer data
Failed experiments and lessons learned	Financial details that could hurt fundraising
Strategic pivots and why you made them	Plans competitors could directly copy

Building in Public Content Calendar

Day	Content Type	Example
Monday	Metric Monday - share one number from last week	"Last week: 47 demos booked from LinkedIn alone"
Tuesday	Behind the scenes - show how something gets built	Screenshot of product iteration with context
Wednesday	Lesson learned - share a mistake and what you took from it	"We spent 3 months on a feature nobody asked for"
Thursday	Customer story - share a win (with permission)	"How [Company] cut onboarding time by 60% using our tool"
Friday	Founder reflection - personal insight about the journey	"Week 47 of building this company. Here is what changed."

Measuring Build-in-Public Impact

Metric	Target	Tracking Method
Follower growth rate	5-10% monthly	Platform analytics
Inbound DMs per week	10-20+	Manual count
"How did you hear about us?" responses mentioning social	30%+ of new leads	CRM self-reported field
Newsletter signups from social	50-200/month	UTM tracking
Press/podcast inbounds	1-2/month	Inbox tracking

8. Content Attribution and Pipeline Tracking

The hardest part of content-led GTM is proving it works. Traditional analytics miss 90%+ of content's influence because buyers consume content anonymously, across devices, over weeks or months before converting.

The Dual Attribution Model

Run both models simultaneously. Neither is complete alone.

Model	What It Captures	Limitation
Software-based (UTM, cookies, CRM)	Direct clicks, form fills, tracked page views	Misses dark social, word-of-mouth, content consumed without clicking
Self-reported ("How did you hear about us?")	The buyer's own perception of what influenced them	Subject to recency bias, may not name specific content

Attribution Implementation Checklist

Step	Action	Tool
1	Add "How did you hear about us?" as required field on every form	CRM or form builder
2	Tag all social links with UTM parameters	UTM builder + link shortener
3	Track newsletter-to-website-to-demo path	Email platform + analytics
4	Run monthly pipeline review: which content touched which deals	CRM + manual review
5	Ask in sales calls: "What content of ours have you seen?"	Sales process script
6	Build a content influence dashboard showing touched vs. sourced pipeline	CRM reporting

Content Pipeline Metrics

Metric	Definition	Benchmark
Content-sourced pipeline	Deals where content was the first touch	20-40% of total pipeline for content-led companies
Content-influenced pipeline	Deals where content touched the buyer at any stage	50-70% of total pipeline
Content-to-lead conversion rate	Visitors from content who become leads	1-3%
Newsletter-to-pipeline rate	Subscribers who enter the sales pipeline	2-5% annually
Social-to-newsletter conversion	Social followers who subscribe to email	0.5-2% monthly
Time from first content touch to deal close	Average duration of content-influenced deals	30-90 days (varies by ACV)

Dark Social and Unmeasurable Influence

"Dark social" refers to content sharing that happens in private channels: DMs, Slack groups, text messages, verbal recommendations. This is where most B2B buying decisions actually form. You cannot track it with software.

Proxy signals for dark social influence:

Direct traffic spikes after a viral post (people typing your URL from memory)
Self-reported attribution mentioning "saw it on LinkedIn/Twitter" without a tracked click
Inbound emails referencing specific content you published
Podcast hosts citing your content when inviting you as a guest
Branded search volume increases correlated with content publishing cadence

For podcast/video as pipeline, community-led distribution, and content cadence framework read references/podcast-community-cadence.md.

Examples

User says: "We want content to drive pipeline" → Result: Agent asks hours/week and platform where buyer is; recommends one pillar + 10–15 derivatives, 4 hr/week budget, newsletter in 66 days; outlines attribution (self-reported field on forms) and 90-day consistency before evaluating ROI.
User says: "Which platform should we focus on?" → Result: Agent asks where ideal buyer is and what content already works; recommends 1 platform for first 30 days then add second; suggests cadence (LinkedIn 3–5x/week, X 2–3x/day) and founder-led vs company page (5–7x engagement).
User says: "Content doesn't convert to deals" → Result: Agent checks DM flow (value-led, 40–60% response target) and nurture length vs sales cycle; suggests clear CTA per piece and content-sourced pipeline target (20–40%); ties to social-selling for DM conversion.

Troubleshooting

No attribution from content → Cause: No "How did you hear about us?" or self-reported attribution. Fix: Add required field on every form; tag UTM on all links; review 90-day data before judging.
Creating content but no distribution → Cause: Posting without repurposing or DMs. Fix: 1 pillar → 10–15 derivatives; add newsletter and DM outreach; use community and build-in-public for trust.
Engagement but no pipeline → Cause: CTA missing or too late. Fix: One clear next step per piece (DM, reply, asset); track DM-to-call (15–25%); shorten nurture if deal size is small.

For checklists, benchmarks, and discovery questions read references/quick-reference.md when you need detailed reference.

Related Skills

Skill	When to Cross-Reference
social-selling	When building DM conversion workflows and LinkedIn engagement systems
ai-seo	When creating SEO-optimized pillar content, blog posts, and competitor alternative pages
multi-platform-launch	When coordinating content across platforms for a product launch
ai-ugc-ads	When repurposing organic content into paid ad creative
positioning-icp	When defining the audience and messaging that content should target
solo-founder-gtm	When a solo founder needs to prioritize content activities with limited time
paid-creative-ai	When amplifying top-performing organic content with paid distribution
partner-affiliate	When building newsletter cross-promotions and affiliate content partnerships
gtm-metrics	When setting up content attribution dashboards and pipeline tracking
lead-enrichment	When qualifying DM prospects and enriching newsletter subscriber data

About this skill

Automatic

Marketing & Content pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

tech-leads-club / agent-skills

packages/skills-catalog/skills/(gtm)/content-to-pipeline/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1Bundled 2 files

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Not for

Content-to-Pipeline: Turning Content Into Revenue

Before Starting

1. The Content Flywheel

The Five-Stage Flywheel

Why Flywheels Beat Funnels

2. Distribution Reverse Engineering

The Reverse Engineering Process

What to Look For in Top-Performing Content

Audience Research Stack

3. Multi-Platform Content Repurposing Framework

The Pillar-to-Platform Map

Platform-Specific Adaptation Rules

The 4-Hour Weekly Content System

AI-Assisted Production Workflow

4. Newsletter as Pipeline

Newsletter-to-Revenue Architecture

Newsletter Monetization Layers

Platform Comparison for Newsletter Pipeline

Newsletter Growth Tactics

5. Content-to-DM Conversion

The DM Conversion Playbook

DM Conversion Rules

LinkedIn DM Funnel Metrics

6. Founder-Led Content vs. Team Content

When to Use Each

The Founder Content Leverage Model

Transition Timeline: Solo to Team Content

7. Building in Public as GTM

What to Share (and What to Keep Private)

Building in Public Content Calendar

Measuring Build-in-Public Impact

8. Content Attribution and Pipeline Tracking

The Dual Attribution Model

Attribution Implementation Checklist

Content Pipeline Metrics

Dark Social and Unmeasurable Influence

Examples

Troubleshooting

Related Skills

SkillSafety

Source

Related skills

More in the registry