Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →When the user wants to build a partner program, launch an affiliate program, design integration partnerships, or create distribution partnerships. Also use when the user mentions 'partnerships,' 'affiliate program,' 'referral program,' 'partner ecosystem,' 'integration partner,' 'reseller,' 'co-marketing,' 'PartnerStack,' or 'revenue share.' This skill covers partner and affiliate program design from recruitment through performance optimization.
SkillScore86/100
Test results 86
3/3 safety checks passed
59%86%of test cases passed +27 pts
Passed 19 of 22 test cases with the skill, and 13 of 22 without it.
6 fixed13 passed either way3 still failing0 broke
One test taskWe are designing our top-tier Solution Partner tier for system integrators and agencies that commit to co-selling, dedicated resources, and quarterly business reviews. What revenue share percentage is standard for this top tier?
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-partner-affiliate
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.
/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai/decimalai:install tech-leads-club-partner-affiliateThe plugin needs python3 and curl on your machine.
No Python or account. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/tech-leads-club-partner-affiliate/SKILL.md https://app.decimal.ai/s/tech-leads-club-partner-affiliate/SKILL.md.claude/skills/tech-leads-club-partner-affiliate/SKILL.mdThis gets SKILL.md only. The skill's 2 other files are not included.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[claude-agent-sdk]"
decimalai skills add tech-leads-club-partner-affiliateimport asyncio
from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
async def main():
question = "Hello!"
async with support.run(question) as run: # one user message, one run
async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
print(message)
# In a notebook or async code: await main()
asyncio.run(main())Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.
The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[claude-agent-sdk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
import asyncio
from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
async def main():
question = "Hello!"
async with support.run(question) as run: # one user message, one run
async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
print(message)
# In a notebook or async code: await main()
asyncio.run(main())Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.
No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[openai-agents]"
decimalai skills add tech-leads-club-partner-affiliatefrom agents import Agent, Runner
from decimalai.openai_agents import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = Agent(
name=support.name,
instructions=support.instructions, # your prompt, then the skill list
tools=[*support.tools], # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.
The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[openai-agents]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
from agents import Agent, Runner
from decimalai.openai_agents import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = Agent(
name=support.name,
instructions=support.instructions, # your prompt, then the skill list
tools=[*support.tools], # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.
No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[openai]"
decimalai skills add tech-leads-club-partner-affiliateimport json
from openai import OpenAI
from decimalai.openai import agent_config
client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
def lookup_order(order_id: str) -> str:
return f"Order {order_id} shipped yesterday."
# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
"name": "lookup_order",
"description": "Look up the status of an order.",
"parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
"required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}
question = "Where is order A1001?"
with support.run(question) as run: # one user message, one run
# run.system is your prompt, then the skill list.
messages = [{"role": "system", "content": run.system}, run.message]
while True:
reply = client.chat.completions.create(
model="gpt-5.4-mini",
messages=messages,
tools=[*TOOLS, *run.tools], # your tools, then load_skill
).choices[0].message
messages.append(reply)
if not reply.tool_calls:
break
for call in reply.tool_calls:
# load_skill is answered by the run; your own tools by FUNCTIONS.
function = FUNCTIONS.get(call.function.name)
messages.append(run.tool_result(call) or {
"role": "tool", "tool_call_id": call.id,
"content": function(**json.loads(call.function.arguments)) if function
else f"There is no tool named {call.function.name!r}.",
})
print(reply.content)
# The Responses API takes run.response_tools instead of run.tools.The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[openai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
import json
from openai import OpenAI
from decimalai.openai import agent_config
client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
def lookup_order(order_id: str) -> str:
return f"Order {order_id} shipped yesterday."
# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
"name": "lookup_order",
"description": "Look up the status of an order.",
"parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
"required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}
question = "Where is order A1001?"
with support.run(question) as run: # one user message, one run
# run.system is your prompt, then the skill list.
messages = [{"role": "system", "content": run.system}, run.message]
while True:
reply = client.chat.completions.create(
model="gpt-5.4-mini",
messages=messages,
tools=[*TOOLS, *run.tools], # your tools, then load_skill
).choices[0].message
messages.append(reply)
if not reply.tool_calls:
break
for call in reply.tool_calls:
# load_skill is answered by the run; your own tools by FUNCTIONS.
function = FUNCTIONS.get(call.function.name)
messages.append(run.tool_result(call) or {
"role": "tool", "tool_call_id": call.id,
"content": function(**json.loads(call.function.arguments)) if function
else f"There is no tool named {call.function.name!r}.",
})
print(reply.content)
# The Responses API takes run.response_tools instead of run.tools.No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/SKILL.md").read_text()
reply = client.chat.completions.create(
model="gpt-5.4-mini",
messages=[
{"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
{"role": "user", "content": "Hello!"},
],
).choices[0].messageThis gets SKILL.md only. The skill's 2 other files are not included.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[anthropic]"
decimalai skills add tech-leads-club-partner-affiliateimport anthropic
from decimalai.anthropic import agent_config
client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
question = "Hello!"
with support.run(question) as run: # one user message, one run
answer = client.beta.messages.tool_runner(
model="claude-haiku-5-5",
max_tokens=4096,
system=run.system, # your prompt, then the skill list
tools=[*run.tools], # your tools, then load_skill
messages=[{"role": "user", "content": question}],
).until_done()The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[anthropic]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
import anthropic
from decimalai.anthropic import agent_config
client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
question = "Hello!"
with support.run(question) as run: # one user message, one run
answer = client.beta.messages.tool_runner(
model="claude-haiku-5-5",
max_tokens=4096,
system=run.system, # your prompt, then the skill list
tools=[*run.tools], # your tools, then load_skill
messages=[{"role": "user", "content": question}],
).until_done()No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[google-genai]"
decimalai skills add tech-leads-club-partner-affiliatefrom google import genai
from google.genai import types
from decimalai.google_genai import agent_config
client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
def lookup_order(order_id: str) -> str:
return f"Order {order_id} shipped yesterday."
# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
"name": "lookup_order",
"description": "Look up the status of an order.",
"parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
"required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}
question = "Where is order A1001?"
with support.run(question) as run: # one user message, one run
config = types.GenerateContentConfig(
system_instruction=run.system, # your prompt, then the skill list
tools=[*TOOLS, *run.tool_params], # your functions, then load_skill
)
contents = [{"role": "user", "parts": [{"text": run.message}]}]
while True:
response = client.models.generate_content(
model="gemini-3.5-flash", contents=contents, config=config,
)
if not response.function_calls:
break
contents.append(response.candidates[0].content)
parts = []
for call in response.function_calls:
# load_skill is answered by the run; your own functions by FUNCTIONS.
# A loop of your own rather than automatic function calling, which
# raises KeyError when the model asks for a function you did not pass.
function = FUNCTIONS.get(call.name)
parts.append(run.tool_result(call) or {"function_response": {
"name": call.name, "id": call.id,
"response": {"result": function(**(call.args or {})) if function
else f"There is no function named {call.name!r}."},
}})
contents.append({"role": "user", "parts": parts})
print(response.text)The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[google-genai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
from google import genai
from google.genai import types
from decimalai.google_genai import agent_config
client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
def lookup_order(order_id: str) -> str:
return f"Order {order_id} shipped yesterday."
# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
"name": "lookup_order",
"description": "Look up the status of an order.",
"parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
"required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}
question = "Where is order A1001?"
with support.run(question) as run: # one user message, one run
config = types.GenerateContentConfig(
system_instruction=run.system, # your prompt, then the skill list
tools=[*TOOLS, *run.tool_params], # your functions, then load_skill
)
contents = [{"role": "user", "parts": [{"text": run.message}]}]
while True:
response = client.models.generate_content(
model="gemini-3.5-flash", contents=contents, config=config,
)
if not response.function_calls:
break
contents.append(response.candidates[0].content)
parts = []
for call in response.function_calls:
# load_skill is answered by the run; your own functions by FUNCTIONS.
# A loop of your own rather than automatic function calling, which
# raises KeyError when the model asks for a function you did not pass.
function = FUNCTIONS.get(call.name)
parts.append(run.tool_result(call) or {"function_response": {
"name": call.name, "id": call.id,
"response": {"result": function(**(call.args or {})) if function
else f"There is no function named {call.name!r}."},
}})
contents.append({"role": "user", "parts": parts})
print(response.text)No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[langchain]" langchain-openai
decimalai skills add tech-leads-club-partner-affiliatefrom langchain.agents import create_agent
from decimalai.langchain import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = create_agent(
"openai:gpt-5.4-mini",
tools=[], # your tools; the middleware adds load_skill
middleware=[support.middleware], # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[langchain]" langchain-openaifrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
from langchain.agents import create_agent
from decimalai.langchain import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = create_agent(
"openai:gpt-5.4-mini",
tools=[], # your tools; the middleware adds load_skill
middleware=[support.middleware], # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add tech-leads-club-partner-affiliateimport decimalai.crewai
from crewai import Agent, Crew, Task
agent = Agent(
role="Support", goal="Help the customer", backstory="A support agent.",
llm=llm, # your own CrewAI LLM
skills=decimalai.crewai.skills(), # the installed folder
tools=decimalai.crewai.skill_tools(), # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" "crewai>=1.15.27"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
import decimalai.crewai
from crewai import Agent, Crew, Task
agent = Agent(
role="Support", goal="Help the customer", backstory="A support agent.",
llm=llm, # your own CrewAI LLM
skills=decimalai.crewai.skills(), # the installed folder
tools=decimalai.crewai.skill_tools(), # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from crewai import Agent, Crew, Task
agent = Agent(
role="Support", goal="Help the customer", backstory="A support agent.",
llm=llm, # your own CrewAI LLM
skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()This gets SKILL.md only. The skill's 2 other files are not included.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[adk]"
decimalai skills add tech-leads-club-partner-affiliatefrom decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = LlmAgent(
name="support", # ADK needs a Python identifier
model="gemini-3.5-flash",
instruction=support.instruction, # your prompt, then the skill list
tools=[*support.tools], # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.
The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[adk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = LlmAgent(
name="support", # ADK needs a Python identifier
model="gemini-3.5-flash",
instruction=support.instruction, # your prompt, then the skill list
tools=[*support.tools], # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.
No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[pydantic-ai]"
decimalai skills add tech-leads-club-partner-affiliatefrom pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = Agent(
"openai:gpt-4o-mini",
name=support.name,
tools=[], # your tools; the capability adds load_skill
capabilities=[support], # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.
The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.
pip install "decimalai[pydantic-ai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")
agent = Agent(
"openai:gpt-4o-mini",
name=support.name,
tools=[], # your tools; the capability adds load_skill
capabilities=[support], # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.
No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" deepagents
decimalai skills add tech-leads-club-partner-affiliateimport decimalai.deepagents
from deepagents import create_deep_agent
agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).
The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" deepagentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
import decimalai.deepagents
from deepagents import create_deep_agent
agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).
No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
Its own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" agent-framework
decimalai skills add tech-leads-club-partner-affiliateimport asyncio
from agent_framework import Agent
from decimalai.agent_framework import skills
agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))It caches skills by default, so restart the process after decimalai skills update.
The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" agent-frameworkfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
import asyncio
from agent_framework import Agent
from decimalai.agent_framework import skills
agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))It caches skills by default, so restart the process after decimalai skills update.
No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
Strands' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" strands-agents
decimalai skills add tech-leads-club-partner-affiliatefrom decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell
agent = Agent(
model=model, # always pass one: the default is Amazon Bedrock
system_prompt="You are a helpful agent.",
tools=[file_editor, shell],
plugins=[skills()],
)
agent("Hello!")Strands loads an agent's skills once, so build the agent again after decimalai skills update.
The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" strands-agentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tech-leads-club-partner-affiliate")
if result.exit_code:
raise SystemExit(result.problems)
from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell
agent = Agent(
model=model, # always pass one: the default is Amazon Bedrock
system_prompt="You are a helpful agent.",
tools=[file_editor, shell],
plugins=[skills()],
)
agent("Hello!")Strands loads an agent's skills once, so build the agent again after decimalai skills update.
No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.
.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/tech-leads-club-partner-affiliate/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.
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-partner-affiliateNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/tech-leads-club-partner-affiliate/SKILL.md https://app.decimal.ai/s/tech-leads-club-partner-affiliate/SKILL.md.agents/skills/tech-leads-club-partner-affiliate/SKILL.mdThis gets SKILL.md only. The skill's 2 other files are not included.
Give its text to your model as instructions. No account or package needed.
This gets SKILL.md only. The skill's 2 other files are not included.
Raw files: /s/tech-leads-club-partner-affiliate/SKILL.md · /s/tech-leads-club-partner-affiliate.json
Fetch the file and give its text to your model as instructions. No account or package needed.
curl -fsSL https://app.decimal.ai/s/tech-leads-club-partner-affiliate/SKILL.mdcurl -fsSL https://app.decimal.ai/s/tech-leads-club-partner-affiliate.jsonThis gets SKILL.md only. The skill's 2 other files are not included.
You don't need a DecimalAI account.
Technical implementation, code revi
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.
You are an expert in partner ecosystem strategy, affiliate program design, integration partnerships, and channel revenue optimization. You understand the 2025-2026 shift from linear reseller programs to multi-directional co-creation ecosystems. You help founders and GTM leaders build partner programs that generate sourced revenue, not just brand awareness. You know the tooling landscape (PartnerStack, Impact.com, Rewardful, FirstPromoter, Crossbeam) and can design programs from first affiliate signup through scaled partner-sourced pipeline.
Gather this context before designing any partner or affiliate program:
The partner landscape has shifted decisively. Traditional reseller models where partners simply mark up and resell your product are giving way to co-creation ecosystems where partners build on, extend, and customize your product for their verticals.
| Dimension | Traditional Reseller Model | Co-Creation Ecosystem Model |
|---|---|---|
| Partner role | Resells your product as-is | Builds on your product, extends it for their vertical |
| Compensation | Margin-based (15-25% discount) | Performance-based revenue share (10-40%) |
| Partner enablement | Train partner on your product | Partner has API access, sandbox, and GTM support |
| Post-sale alignment | Low - partner moves to next deal | High - shared revenue creates ongoing alignment |
| Integration depth | White-label or bundle | Native API integration, joint product development |
| Scalability | Linear - each deal requires partner effort | Compounding - integration drives organic adoption |
| Data sharing | Minimal - lead handoff only | Bi-directional - shared customer insights via Crossbeam |
| Time to first revenue | 3-6 months (training + pipeline build) | 6-12 months (integration + GTM ramp) |
| Long-term value | Flat - margin stays constant | Growing - deeper integration increases switching cost |
| Scenario | Recommended Model | Rationale |
|---|---|---|
| Product under $500/mo ACV | Affiliate/referral | Low deal value cannot support partner training overhead |
| Complex enterprise product | Integration + solution partner | High ACV justifies deep partner investment |
| Platform with API | Co-creation ecosystem | Partners extend the platform, creating network effects |
| Vertical SaaS | Solution partner with vertical specialization | Partners bring domain expertise you lack |
| Horizontal tool | Affiliate + integration partner mix | Broad market needs volume (affiliate) plus depth (integration) |
Design your program in three tiers. Partners self-select based on their investment level and capability. Each tier unlocks progressively better economics and support.
Tier 1: Referral Partner (Entry Level)
| Element | Details |
|---|---|
| Compensation | 10-15% of first-year revenue per referred customer |
| Requirements | Signed partner agreement, completed onboarding module |
| Support provided | Referral link, basic marketing assets, monthly newsletter |
| Expected volume | 1-5 referrals per quarter |
| Partner type | Consultants, freelancers, happy customers, content creators |
| Tracking | UTM links, referral codes, cookie-based attribution |
| Payout timing | Net-30 after customer payment clears, with 60-day clawback on churn |
Tier 2: Integration Partner (Mid Level)
| Element | Details |
|---|---|
| Compensation | 20-25% of joint customer revenue, ongoing for customer lifetime |
| Requirements | Live integration, 3+ joint customers, co-marketing commitment |
| Support provided | API sandbox, dedicated partner manager, co-marketing budget ($2K-$10K/quarter), joint case study |
| Expected volume | 5-20 joint customers per quarter |
| Partner type | Complementary SaaS products, platforms, workflow tools |
| Tracking | API usage monitoring, Crossbeam overlap reporting, deal registration |
| Payout timing | Monthly revenue share, no clawback after 90-day retention threshold |
Tier 3: Solution Partner (Top Level)
| Element | Details |
|---|---|
| Compensation | 30-40% of revenue from their customer base, shared product roadmap influence |
| Requirements | 10+ joint customers, dedicated team member, quarterly business review |
| Support provided | Priority API access, engineering office hours, joint GTM planning, executive sponsor, early feature access |
| Expected volume | 20+ joint customers per quarter |
| Partner type | System integrators, vertical platforms, agencies with deep client relationships |
| Tracking | Full CRM integration, joint pipeline reviews, Crossbeam account mapping |
| Payout timing | Monthly revenue share with quarterly true-up, no clawback |
| Your Revenue Model | Referral Commission | Integration Commission | Solution Commission |
|---|---|---|---|
| Monthly subscription | 15% of month-1 revenue, or 10% recurring for 12 months | 20% recurring for customer lifetime | 30-40% recurring for customer lifetime |
| Annual subscription | 10-15% of first-year ACV | 20-25% of ACV, renewed annually | 30-40% of ACV, renewed annually |
| Usage-based | 10% of first 12 months usage | 20% of ongoing usage | 30% of ongoing usage |
| Outcome-based | 10% of first outcome payment | 20% of ongoing outcome payments | 35% of ongoing outcome payments |
| Policy | Referral Tier | Integration Tier | Solution Tier |
|---|---|---|---|
| Clawback window | 60 days | 90 days | None |
| Customer churn trigger | Full commission returned | Pro-rated return | No return, partner helps with retention |
| Deal overlap resolution | First-touch attribution | Multi-touch with registration priority | Joint pipeline, split credit |
| Direct sale overlap | Partner loses if deal registered after direct contact | Deal registration within 14 days protects partner | Protected account list reviewed quarterly |
| Platform | Best For | Pricing (Starting) | Key Strengths | Limitations |
|---|---|---|---|---|
| PartnerStack | B2B SaaS, multi-partner-type programs | Custom (mid-market+) | Manages affiliates, referrals, and resellers in one platform. Automated global payouts. Large B2B marketplace network. | Higher cost. Overkill for simple referral programs. |
| Impact.com | Enterprise, large-scale affiliate programs | Custom (enterprise) | Vast partner network, granular attribution, custom recurring commissions. | Steep learning curve. Requires dedicated admin. |
| Rewardful | Early-stage SaaS, Stripe-first companies | $49/month | Fast Stripe integration, simple setup, affordable. 30+ integrations. | No built-in email automation. Limited as programs scale. |
| FirstPromoter | Growth-stage SaaS, MRR-focused teams | $99/month | Strong recurring billing tracking, 18+ detailed metrics, built-in fraud protection, email automation. | Higher price than Rewardful. Fewer marketplace features. |
| Refgrow | Bootstrapped SaaS | $0-49/month | Free tier available, simple widget-based setup | Limited features at lower tiers |
START: What is your monthly revenue?
|
+--> Under $10K MRR
| |
| +--> Using Stripe? --> Rewardful ($49/mo)
| +--> Not using Stripe? --> Refgrow (free tier)
|
+--> $10K-$100K MRR
| |
| +--> Need email automation? --> FirstPromoter ($99/mo)
| +--> Stripe-only, keep it simple? --> Rewardful ($49/mo)
|
+--> $100K-$500K MRR
| |
| +--> Multi-partner-type program? --> PartnerStack
| +--> Affiliate-only focus? --> FirstPromoter
|
+--> $500K+ MRR
|
+--> Enterprise, complex attribution? --> Impact.com
+--> B2B SaaS ecosystem play? --> PartnerStack
| Phase | Action | Timeline |
|---|---|---|
| Week 1 | Define commission structure (flat vs. recurring, percentage, tiers) | Day 1-3 |
| Week 1 | Choose and configure affiliate platform | Day 3-5 |
| Week 1 | Create affiliate agreement (terms, payment, clawback, brand guidelines) | Day 5-7 |
| Week 2 | Build affiliate portal: signup page, dashboard, asset library | Day 8-10 |
| Week 2 | Create marketing assets: banners, email templates, social copy, landing page copy | Day 10-14 |
| Week 3 | Recruit first 10-20 affiliates from existing customers, advisors, content creators | Day 15-18 |
| Week 3 | Send onboarding sequence (welcome, platform walkthrough, first campaign guide) | Day 18-21 |
| Week 4 | Monitor first conversions, adjust tracking if attribution gaps appear | Day 22-28 |
| Month 2 | Analyze top performer patterns, create case study from first successful affiliate | Day 30-60 |
| Month 3 | Scale recruitment, launch tiered commission structure based on performance data | Day 60-90 |
Integration partnerships have become the fastest-growing partnership category because they create product-level lock-in, not just commercial relationships. When your product is deeply integrated with a partner's product, joint customers have higher retention, higher NPS, and higher LTV.
Use this scoring model to decide which integrations to build first.
| Factor | Weight | Scoring Criteria |
|---|---|---|
| Customer overlap | 30% | Crossbeam or manually surveyed overlap. 50+ shared accounts = 100pts, 20-49 = 75pts, 10-19 = 50pts, under 10 = 25pts |
| Strategic fit | 25% | Adjacent in the workflow (100pts), complementary but separate (60pts), tangential (25pts) |
| Partner GTM commitment | 20% | Co-marketing budget committed (100pts), willing to co-market (60pts), integration-only (25pts) |
| Technical feasibility | 15% | API available, under 2 weeks to build (100pts), API available, 2-8 weeks (60pts), no API or 8+ weeks (25pts) |
| Market signal | 10% | Customers actively requesting (100pts), competitor has it (60pts), nice-to-have (25pts) |
Score = Sum of (Factor Weight x Points). Prioritize integrations scoring 70+.
Step 1: Discovery Call (Week 1)
- Validate customer overlap via Crossbeam or manual account mapping
- Confirm technical feasibility (API docs, sandbox access)
- Align on GTM commitment level
|
Step 2: Technical Build (Weeks 2-6)
- Exchange API credentials and sandbox environments
- Build integration (bidirectional data flow preferred)
- QA testing with 2-3 beta customers
|
Step 3: GTM Launch (Weeks 7-8)
- Co-authored blog post or case study
- Joint webinar or demo video
- Listing in each other's integration directory/marketplace
- Email announcement to overlapping customer base
|
Step 4: Ongoing Optimization (Monthly)
- Monthly partner sync on pipeline and adoption metrics
- Quarterly co-marketing campaign (webinar, content, joint offer)
- Annual partnership review with executive sponsors
For integration strategy, marketplace, recruitment, co-marketing, attribution, channel conflict, AI partnerships, operations, and implementation playbook read references/implementation-guide.md.
For checklists, benchmarks, and discovery questions read references/quick-reference.md when you need detailed reference.
| Skill | When to Cross-Reference |
|---|---|
| expansion-retention | When designing partner retention incentives and expanding partner-sourced accounts |
| multi-platform-launch | When coordinating partner program launch across channels and marketplaces |
| sales-motion-design | When aligning partner-sourced leads with your sales process and deal stages |
| content-to-pipeline | When building co-marketing content that generates pipeline through partner channels |
| gtm-metrics | When measuring partner program ROI, attribution, and revenue contribution |
| ai-pricing | When designing commission structures that account for AI model costs and margin |
| lead-enrichment | When enriching partner-referred leads with firmographic and intent data |
| gtm-engineering | When automating partner attribution, deal registration, and commission calculations |
| positioning-icp | When ensuring partner messaging aligns with your positioning and targets the right ICP |
Published skills whose descriptions closely match this one, with their headline benchmark lift.
Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.