Ready to supercharge your AI agents?

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

Campaign Planner · aaron-he-zhu | DecimalAI

Marketingby aaron-he-zhu

Campaign Planner

Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", or "launch a product with creators"; produces campaign objectives, platform and influencer-tier strategy, content requirements, a phased timeline, budget allocation, and KPI targets. Not for writing individual creator briefs — use brief-generator; not for the overall product-launch plan (tiering, calendar, press, community day) — use launch-tier-planner, which hands this skill the creator lane. A launch reques

Never made a case worseMaintained

SkillScore

SkillScore88/100

Test results 88

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

20%88%of test cases passed +68 pts

Without skill5 of 25

With skill22 of 25

17 fixed5 passed either way3 still failing0 broke

Measured on gemini-3.6-flash8/13/2026v1 · latest is v2

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskLuxeGlow Cosmetics has $120,000 for a holiday season campaign on Instagram and YouTube targeting beauty enthusiasts across 8 weeks. Outline the creative direction, platform deliverable counts, budget breakdown, and primary next step.

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 aaron-he-zhu-campaign-planner
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("aaron-he-zhu-campaign-planner")
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 aaron-he-zhu-campaign-planner

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/aaron-he-zhu-campaign-planner/SKILL.md https://app.decimal.ai/s/aaron-he-zhu-campaign-planner/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/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/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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("aaron-he-zhu-campaign-planner")
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/aaron-he-zhu-campaign-planner/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/aaron-he-zhu-campaign-planner/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 aaron-he-zhu-campaign-planner

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/aaron-he-zhu-campaign-planner/SKILL.md https://app.decimal.ai/s/aaron-he-zhu-campaign-planner/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/aaron-he-zhu-campaign-planner/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/aaron-he-zhu-campaign-planner/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/aaron-he-zhu-campaign-planner.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.

Version: v2 (v1 tested 8/13/2026)
Source: aaron-he-zhu/aaron-marketing-skills ↗
License: Apache-2.0

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

Campaign Planner

Designs an influencer campaign from strategy to execution plan — an actionable blueprint that ties business objectives to creative execution.

Scope edge — product launches: this skill owns the creator lane of a launch. The launch itself — tier/type decision, launch calendar, press motion, community launch day, readiness gate — belongs to the launch discipline (launch-tier-planner and siblings), which hands this skill the creator-channel sub-plan aligned to the launch-registry date and stage. "Launch a product with creators" starts here; "launch a product" starts there.

Quick Start

Create an influencer campaign plan for [product launch]

Plan an influencer campaign for [brand] with [budget] targeting [audience] during [timeframe]

Skill Contract

Reads: requested mode (plan-only | tracker-only | both); brand, product, audience, campaign type, budget, timeline, and constraints for plan authoring; and, for execution-ready tracking, an existing campaign_id, exact versioned campaign-plan reference/hash, locked §8 measurement contract, and locked non-empty creator scope. If memory-management is active, prior audience profiles and past-campaign benchmarks load from the hot cache.
Writes: the campaign plan inline by default. With exact save authorization, write it to memory/influencer/campaign-planner/YYYY-MM-DD-<topic>.md. For execution tracking, emit separate JSON artifacts that validate against the shared five-kind control schema (evidence observations, the locked measurement contract, action intents/receipts only for an actual executor action, and the Cycle Retro), then let the controller bind their exact refs/hashes to the selected run ancestry. The Markdown/YAML tracker in references/templates.md §10 is a deterministic read-only Influencer compatibility view, marked authoritative: false; its domain blocks are not themselves schema-valid control artifacts, and editing them never changes runtime state. Standalone hosts without the validator may save a semantic-only compatibility snapshot after exact WARM authorization, but it must be marked NOT_VERIFIED and cannot claim single-head, receipt, persistence, or close enforcement. Reuse an explicit upstream/user campaign_id; in a plan-authoring mode, generate one random campaign-<UUIDv4> if none exists and preserve it through the lineage. tracker-only never invents a missing ID, plan, contract, scope, or checkpoint. Every row preserves a stable opaque creator_ref; every saved live_post_ref is qualified-resolver-backed and opaque. Raw names, handles, URLs, shortcodes, provider IDs, and hidden locator maps remain transient.
Promotes: only with separate exact authorization, promote approved campaign name, objective, budget, go-live date, and KPI targets to memory/hot-cache.md; never promote tracker stages or payment state. After a creator row is closed, another exact authorization is required for each registry proposal containing evidence-backed actual rate, signed rights window/expiry, or measured performance baseline; only creator-registry can make those facts canonical. Forecast targets, stage, next_action, due_at, and payment_status remain WARM working state.
Done when:
- The selected mode is explicit: plan-only completes §§1–9, tracker-only completes only §10 from its required existing inputs, and both completes §§1–9 before §10.
- In a plan-authoring mode, objectives, strategy, influencer mix, deliverables, timeline, budget allocation, contingency, and KPIs are concrete only where the user supplied them or a compatible source-dated planning anchor supports them. Every unsupported required choice stays NEEDS_INPUT; the skill never fills it from a repository default. The §8 measurement design is execution-locked only when its campaign/plan binding, immutable plan hash/version, authorization, non-empty creator scope, and unique per-creator/deliverable checkpoints are present; otherwise report the exact lock inputs as NEEDS_INPUT/DONE_WITH_CONCERNS and do not create a close-eligible tracker.
- If tracking was requested, each creator has validated source artifacts and one deterministic non-authoritative projection block with stage, next action, due date, rights expiry, evidence references, and external-payment handoff state. The projection carries its source artifact refs/digests and current head; it is never hand-edited as the state source.
- Each tracker creator uses one stable opaque creator_ref; every identity resolution, publication, terminal-checkpoint resolution, creator close, campaign close, migration, and late event has an immutable ref plus exact campaign/creator scope and a single non-forked current head where applicable.
- Every saved live_post_ref is opaque and qualified-resolver-backed. External actions require current exact authority and matching intent/receipt artifacts; a prior save, plan, gate, path, capability, or projection never grants authority. Raw post locators and reusable blanket approvals never enter the artifact set or projection.
- A tracked live post has a receipt per required checkpoint, and each checkpoint's latest explicitly unsuperseded receipt controls the close gate; a mismatch, unknown disclosure, or changed/removed post is evidence for review, never silently treated as approved.
- A closed creator row points to its unique current close-receipt head. A closed campaign points to the unique current campaign-close head, proves exact equality with the locked non-empty creator scope, and passes the strict gates in template §10; neither closed value is treated as a synonym for success.
- A material late event is appended without rewriting prior receipts. A reference correction appends fresh close receipts when corrected gates still pass; a failed gate cannot receive a passing receipt, and manual reopen is reserved for new campaign-owned work under template §10's stage/action baseline.
- A plan-authoring result names brief generation and open approvals. A tracker-only result instead names the evidence/action owner implied by the current stage, or stops as chain-complete when nothing remains; it never routes backward to brief generation by default.
Primary next skill: in plan-only/both, brief-generator; in tracker-only, use the stage-specific handoff in Next Best Skill or stop when complete.

Handoff Summary

Emit the standard shape from skill-contract.md §Handoff Summary Format.

Data Sources

This family is Tier 1: every skill works with no live integrations. Supplied brand, audience, budget, and timeline support a plan skeleton, but do not determine messaging, platform/tier mix, content format, promo mechanics, contingency, rate, or KPI targets. Those choices require user direction or compatible source-dated planning evidence; otherwise retain NEEDS_INPUT.

Optional connectors that strengthen the plan when available:

~~influencer database — size the influencer mix and validate tier follower ranges.
~~social platform analytics — set platform-specific reach and engagement benchmarks.
~~CRM — align conversion targets and attribution with existing pipeline data.
~~analytics — pull past-campaign actuals for realistic KPI and budget-efficiency targets.

See CONNECTORS.md for the free/keyless data recipe per category. Without a connector, ask the user for the missing inputs and proceed only with fields supported by user-provided evidence; return a useful skeleton plus NEEDS_INPUT for the rest.

Instructions

Choose and state one mode before doing work. plan-only runs §§1–9 and does not instantiate §10. tracker-only runs only §10 and requires an existing campaign_id, exact versioned plan_ref plus plan hash, the current locked §8 measurement contract, and its locked non-empty creator scope; if any binding is missing, mismatched, forked, or unverified, return NEEDS_INPUT instead of rebuilding a plan or creating a placeholder tracker. both runs §§1–9 before §10. If creator selection is not yet locked, return the plan plus the exact missing scope/contract inputs and, only when explicitly requested, an inline non-close-eligible partial tracker header; do not invent creator identities or call it execution-ready. In plan-only or both, reuse an explicit upstream/user campaign_id; for a new campaign with none, generate random campaign-<UUIDv4> once and preserve it unchanged. In tracker-only, a missing ID is blocking; never generate or deterministically derive it from a campaign name, date, creator handle, or mutable plan content.

For plan-authoring modes, work the nine steps in order. Each has a fill-in template in references/templates.md — copy the matching block and assemble it in step 9. Replace brackets only with supplied or source-backed values; never invent a number, identity, benchmark, or fact to eliminate a placeholder. Keep an unresolved optional field Unknown, and return NEEDS_INPUT when a required field is absent.

Gather campaign requirements — capture campaign_id, brand, value prop, audience, campaign type, timeline, budget, and constraints (template §1).
Define objectives — one SMART primary objective plus secondary objectives, with explicit success and failure definitions (template §2).
Develop strategy — big idea, strategy statement, audience, key messages, campaign pillars, platform split, and differentiation only from user-approved canon or compatible source-dated evidence; otherwise preserve the decision fields as NEEDS_INPUT rather than defaulting to UGC, promo-code, or another tactic (template §3).
Define influencer criteria — tier mix, must-have and preferred selection criteria, exclusions, ideal profile, and relationship types. Use only a user-declared or compatible source-dated follower taxonomy; references/influencer-tiers.md supplies the recording contract, not universal ranges or performance claims (template §4).
Plan content requirements — deliverables by platform/format, required elements, creative direction, themes, and the approval chain from supplied decisions and current platform/rights evidence; do not invent a default UGC format, promo mechanic, or content mix (template §5).
Create the timeline — key dates, a four-phase week-by-week plan, and a Gantt view (template §6).
Allocate budget — break down the supplied total by category, declared follower band, and platform only from user-approved rules or compatible source-dated cost evidence. Add contingency, CPM/CPE, or cost-per-content targets only when their rule/anchor is supplied; otherwise use NEEDS_INPUT and do not invent a percentage or rate (template §7).
Establish success metrics — primary KPIs vs source-dated comparators, secondary and conversion metrics, reporting cadence, and a non-canonical pre-execution measurement contract covering the baseline, outcome unit, readback window, attribution basis, decision rule, decision owner, exact campaign/plan version/hash, lock authorization, non-empty creator scope, and structured unique per-creator/deliverable publication checkpoints (template §8). Every external comparator requires an opaque source ref, observation date, and comparable window/cohort; otherwise keep it Unknown/NEEDS_INPUT rather than presenting an “industry average.” A scope or contract change is a new immutable version plus explicit §10 migration; never edit the locked block in place.
Compile the plan document — executive summary, the full sections above, and an appendix with risk mitigation (template §9). Return it inline by default; save only after authorization for the exact WARM path.

For tracker-only or both, read references/templates.md §10 for the Influencer domain fields and compatibility view. On Governed hosts, validate the source control artifacts first and generate the tracker as a read-only projection; never accept a tracker edit as an append, migration, stage/evidence/pointer change, reopen, or close. Creator rows must equal the locked scope and keep the active block at exactly eight fields; identity and close pointers stay adjacent. Identity and state heads must be resolvable, same-scope, unique, and non-forked. Any scope/contract/identity/checkpoint/verification/receipt/close/late-event gap shows PARTIAL CHECKPOINT COVERAGE — NOT CLOSE-ELIGIBLE; elapsed time never advances state. On semantic-only hosts, return the same view inline or save a NOT_VERIFIED compatibility snapshot after exact path-scoped authorization. payment_status records external readiness/evidence only and never sends money.

Each publication checkpoint gets an immutable, same-campaign/creator/checkpoint domain publication_receipt under fresh host authorization for the append-publication-receipt view update and a single-head supersession chain. This YAML block maps to shared evidence-observation; it is not an action-receipt and does not prove that this skill published anything. A real publish needs a separate exact action-intent before the executor and matching action-receipt after it. live_post_ref is only a qualified-resolver-backed opaque ref; raw URLs/slugs/provider IDs stay transient, and unresolved input remains unknown. verified disclosure/version match requires the exact observation, frozen approved asset/auditor, and evidence refs. Missing, mismatched, cross-scope, or forked evidence blocks close and routes the asset to creator-content-auditor; never infer approval or mutation.

A creator closes only when each applicable checkpoint has one controlling verified publication receipt or evidence-backed terminal non-applicability resolution and every §10 gate passes. A fresh atomic close-creator authorization must name its receipt append, row/evidence changes, and pointer update; campaign close needs a separate equivalently scoped close-campaign authorization and an exact creator→current-close mapping. Any fork blocks both branches. Corrections preserve history, re-evaluate gates, and append newly authorized close heads only when warranted; a reference-only correction does not manually reopen work.

Late rights/post/attribution/payment/data evidence uses the campaign-bound §10 late_event_note under a fresh append-late-event authorization. Any accompanying stage/action/evidence/pointer mutation must be named in that atomic authorization or separately approved. supersede-artifact binds the exact old and replacement refs of the same scope and meaning. manual-reopen is only for new campaign-owned work; otherwise append the correction and, if gates pass, fresh close heads. Preserve history and never auto-reopen or invent a reopened stage.

When the user asks what needs attention, generate the template §10 exception queue from the validated source artifacts (or a clearly labeled semantic-only compatibility snapshot) using an explicit as_of time and user-selected rights horizon. It is a read-only projection—no cron, polling, automatic stage change, projection write-back, or external mutation.

Example

User: "Create a campaign plan for a new sustainable sneaker launch targeting Gen Z on TikTok and Instagram with a $50K budget"

Output: A plan skeleton preserving the supplied audience, platforms, and $50K total. Sustainability claims/message canon, creator mix, content format, promo/attribution mechanic, rates, contingency, KPI targets, and exact dates remain NEEDS_INPUT until the user supplies them or compatible source-dated anchors. No micro-heavy, UGC, promo-code, or percentage default is inferred. (Fuller walkthrough in references/templates.md.)

Reference Materials

references/templates.md — fill-in templates for all nine planning steps, the optional lightweight WARM tracker, the worked example, and success tips.
references/influencer-tiers.md — declaration contract for user/source-dated partner models and follower bands; it supplies no universal range or performance claim.
skill-contract.md — shared contract and handoff schema.
state-model.md — memory tiers and save-path conventions.
CONNECTORS.md — free/keyless data recipes per connector category.
audience-mapper — define the target audience this plan serves.
brief-generator — turn the plan into per-influencer briefs.
budget-optimizer — refine the budget allocation.
influencer-discovery — find influencers matching the criteria.

Next Best Skill

Plan-authoring primary: brief-generator — convert an approved plan into concrete influencer briefs.
Plan-authoring alternates: budget-optimizer to pressure-test the split; influencer-discovery to build or complete the locked creator scope.
Tracker-only, publication/approval blocker: creator-content-auditor — verify the cited live post against the frozen approved asset; this does not authorize an edit or amplification.
Tracker-only, readback/reconciliation due: performance-analyzer — produce the dated §8 readback artifact; final reporting may package that artifact only after the evidence exists.
Tracker-only, open operational item: hand off only to the named owner/skill required by the current next_action; do not route back to briefing for a late-stage row. If every close gate passes and no action remains, stop and report chain-complete.

Termination note: keep a visited-set of skills invoked this session. If the applicable next skill has already run this session, stop and report the chain complete rather than re-invoking. Do not chain deeper than 3 hops from the originating request.

About this skill

Automatic

Marketing & Content pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/9/2026

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

aaron-he-zhu / aaron-marketing-skills

influencer/target/campaign-planner/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 10/31/2026Version v2Bundled 2 files

Illustrative Want to see what aaron-he-zhu/campaign-planner would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Campaign Planner

Quick Start

Skill Contract

Handoff Summary

Data Sources

Instructions

Example

Reference Materials

Next Best Skill

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry