Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Top-tier GEO (Generative Engine Optimization) expert agent for managing daily AI visibility operations.
SkillScore78/100
Test results 78
3/3 safety checks passed
17%78%of test cases passed +61 pts
Passed 18 of 23 test cases with the skill, and 4 of 23 without it.
14 fixed4 passed either way5 still failing0 broke
One test taskWrite 5 FAQ entries for our enterprise Cloud ERP product 'Kingdee Cloud-Galaxy' (金蝶云星空) targeting manufacturing mid-market buyers who ask AI platforms for ERP recommendations and deployment timelines.
Adds every file the skill has, pinned so you can update it. No account needed.
pip install "decimalai>=0.15"
decimalai skills add leoyeai-geo-claw
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-geo-claw")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")claude --plugin-dir "$(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 leoyeai-geo-clawThe 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/leoyeai-geo-claw/SKILL.md https://app.decimal.ai/s/leoyeai-geo-claw/SKILL.md.claude/skills/leoyeai-geo-claw/SKILL.mdThis gets SKILL.md only. The skill's 34 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 leoyeai-geo-clawimport 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawfrom 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawimport 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawimport 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawfrom 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawfrom 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawimport 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawfrom 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawfrom 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawimport 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawimport 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawfrom 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("leoyeai-geo-claw")
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/leoyeai-geo-claw/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/leoyeai-geo-claw/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 34 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 leoyeai-geo-clawNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/leoyeai-geo-claw/SKILL.md https://app.decimal.ai/s/leoyeai-geo-claw/SKILL.md.agents/skills/leoyeai-geo-claw/SKILL.mdThis gets SKILL.md only. The skill's 34 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 34 other files are not included.
Raw files: /s/leoyeai-geo-claw/SKILL.md · /s/leoyeai-geo-claw.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/leoyeai-geo-claw/SKILL.mdcurl -fsSL https://app.decimal.ai/s/leoyeai-geo-claw.jsonThis gets SKILL.md only. The skill's 34 other files are not included.
You don't need a DecimalAI account.
Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.
Claude Code reads files from your project, so DecimalAI config does not apply there.
On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.
On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.
On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.
On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.
On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.
Editors read files from your project, so DecimalAI config does not apply there.
Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.
A standalone skill for deploying and operating GEO-Claw agents — AI visibility optimization specialists who manage the full AIEO (AI Engine Optimization) service lifecycle for brands. Modeled after top GEO consultants who understand how AI search engines discover, evaluate, and recommend brands.
Bilingual / 双语: Detect the user's language and respond accordingly. 根据用户使用的语言进行回复。
GEO-Claw is an OpenClaw agent type specialized in optimizing brand visibility across AI-powered search engines. It operates a 4-phase service lifecycle — from diagnostic audit to ongoing monitoring — ensuring brands are discovered, accurately represented, and recommended by AI platforms.
Phase 1: DIAGNOSIS (Week 1-2) → AI visibility audit & baseline
Phase 2: POSITIONING (Week 3-4) → Brand positioning for AI era
Phase 3: CONTENT (Week 5-8) → AI-optimized content creation
Phase 4: MONITORING (Ongoing) → Performance tracking & optimization
| Skill | Phase | What It Does |
|---|---|---|
| AIEO Diagnosis (诊断) | 1 | Brand AI visibility audit across 7+ AI platforms, website technical audit, competitor analysis, baseline scoring |
| AIEO Positioning (定位) | 2 | April Dunford positioning methodology adapted for AI platforms, question library iteration, Schema strategy |
| AIEO Content (内容) | 3 | AI-optimized content plans, Answer-First FAQ creation, platform-specific content strategies |
| AIEO Monitoring (监控) | 4 | Ongoing AI visibility tracking, trend analysis, competitive dynamics, business metric correlation |
| Content Creator (创作) | Support | SEO/brand voice analysis, content optimization scripts, platform adaptation |
| Skill Creator (扩展) | Meta | Framework for creating new domain-specific GEO skills |
Testing and optimization across all major AI search engines:
If the user wants to deploy a GEO-Claw agent for a client, guide them through the agent-training lifecycle using the agent-training skill. This skill provides the template content. Read references/template-geo.md for the complete deployment template.
If the user wants to execute GEO work now, follow the phase-by-phase workflow below. Determine which phase the client is in and execute accordingly.
| User says... | Phase |
|---|---|
| "诊断", "audit", "AI visibility check", "baseline", "测试AI平台" | Phase 1: Diagnosis |
| "定位", "positioning", "品牌策略", "question library", "问题库" | Phase 2: Positioning |
| "内容", "content", "FAQ", "写文章", "content plan", "发布" | Phase 3: Content |
| "监控", "monitor", "tracking", "报告", "visibility trend" | Phase 4: Monitoring |
| "新客户", "new client", "onboard" | Start from Phase 1 |
These two rules apply to every phase. Follow them without exception.
Every output — reports, tables, FAQs, calendar entries — must use the actual brand name, competitor names, and URLs extracted from the conversation. Never write [品牌], [竞品A], [品牌名], or any other placeholder. If the user said "元気森林", every sentence says "元気森林". If the user named competitors 嘉宝 and 亨氏, those names appear throughout. A client-ready deliverable with placeholders still in it is not done. Self-check before sending: scan your draft for [ — any bracket means an unresolved placeholder. Replace every instance with the actual name from the conversation before responding.
For AI platform visibility testing (Phase 1 and Phase 4): use Playwright MCP to run actual queries on each platform and record the real responses. If Playwright MCP is not available in the current session, you must:
⚠️ 数据说明：本报告中的AI平台测试结果为专业预估，非实际测试数据。建议使用Playwright MCP执行真实测试以验证结果。(预估)Goal: Establish brand AI visibility baseline and identify gaps.
{品牌名}_GEO诊断报告_{YYYY-MM-DD}.md — Full diagnostic report{品牌名}_问题库_{YYYY-MM-DD}.md — Question library v1.0 (Tier 1/2/3)Read references/question-library.md for the full taxonomy:
Goal: Refine brand positioning for AI discoverability and recommendation.
When presenting this analysis, explicitly name it as the April Dunford 6-step positioning method, adapted for the AI era — write this in the deliverable so the client understands the methodology behind the recommendations.
Every piece of content must be understood by both humans AND AI systems. Write for the person, structure for the machine.
{品牌名}_AIEO产品定位分析_{YYYY-MM-DD}.md — Positioning strategy with AIEO statement{品牌名}_问题库_{YYYY-MM-DD}.md — Question library v2.0 (expanded with comparison, scenario, validation questions)Goal: Create and distribute AI-optimized content across platforms.
Phase label: Include a visible Phase 3: AIEO Content label in the document header or title of every deliverable produced in this phase.
AI platforms prefer content that gives a direct answer in the first 50 characters, then supports with evidence. Structure: Answer → Facts → Action suggestion.
After writing any FAQ batch: sample 5 answers at random and confirm each opens with ≤50 characters of factual statement about the brand. Rewrite any that start with preambles like "其实…", "很多人问…", "关于这个问题…", or a restatement of the question before sending.
Goal: Track performance, detect changes, optimize continuously.
| Layer | Metrics | Tools |
|---|---|---|
| Visibility | AI mention rate, first-recommendation rate, platform coverage, competitor dynamics | Playwright MCP |
| Quality | Content accuracy, positioning consistency, sentiment, information completeness | Manual + AI review |
| Business | Brand search volume, website traffic, AI-attributed conversions | Google Trends, 百度指数, GA4 |
Only report what the client explicitly provided. If the client says "mention rate dropped from 60% to 45%, worst on Doubao and Kimi" — you know: (a) overall rate changed, (b) Doubao and Kimi dropped most. You do NOT know exact per-platform figures.
When building a monitoring report with partial data:
[需Playwright MCP测试填入] for any figure the client did not provide{品牌名}_AIEO监控报告_{YYYY-MM-DD}.md — With trend arrows (↑/↓/→), platform details, competitive analysis, recommendationsRead references/question-library.md for industry templates:
| Industry | Focus Areas | Key Question Types |
|---|---|---|
| FMCG (快消品) | Product comparison, ingredient safety, usage scenarios | CR, CP, SC |
| B2B (企业服务) | Solution capability, case studies, ROI | BR, PD, CP |
| Healthcare (医疗健康) | Safety, efficacy, regulatory compliance | PD, BR, SV |
| Education (教育) | Course quality, outcomes, instructor credentials | BR, CR, PD |
| Finance (金融) | Security, returns, compliance, comparison | CP, PD, SV |
| Retail (零售) | Price, availability, reviews, recommendations | CR, SC, SV |
| File | When to Read |
|---|---|
references/template-geo.md | Deploying a new GEO-Claw agent — full SOUL.md/AGENTS.md templates, knowledge plan, guardrails, success metrics |
| File | When to Read |
|---|---|
references/diagnosis-checklist.md | Phase 1 quick reference — Printable checklist for website technical audit, AI platform testing, competitor analysis, and report output (use alongside phase1-diagnosis-full.md) |
references/phase1-diagnosis-full.md | Executing Phase 1 — Complete diagnosis workflow with Playwright MCP testing protocol, scoring rubrics, screenshot naming conventions, report generation steps. This is the full iterated diagnosis skill. |
references/phase2-positioning-full.md | Executing Phase 2 — Complete positioning workflow with April Dunford 6-step method, 三层属性分类, 价值三角, ICP双轨定义, question library v1.0→v2.0 iteration process |
references/phase3-content-full.md | Executing Phase 3 — Complete content creation workflow with Answer-First enforcement, content type matrix, AI platform differentiation, publishing strategy, content reuse patterns |
references/phase4-monitoring-full.md | Executing Phase 4 — Complete monitoring workflow with 12-metric framework, risk warning system, quick-check protocol, monitoring report generation |
references/content-creator-full.md | Content optimization support — Brand voice analysis, SEO-to-AIEO optimization, content consistency enforcement |
| File | When to Read |
|---|---|
references/positioning-methodology.md | Deep positioning work — 880-line comprehensive AIEO positioning methodology (paradigm shift theory, AI knowledge graph storage, 6-step method with examples, Schema system, verification & iteration, 90-day implementation checklist) |
references/brand-strategy-guide.md | Brand strategy by scale/industry — Large/Medium/Small brand strategies, industry-specific positioning, Answer-First templates, off-site optimization channels, budget & ROI reference |
references/content-guidelines.md | Writing content — Answer-First rules, content type guidelines (FAQ/Comparison/Guide/Scene), verifiable facts usage, competitor mention strategy, positioning consistency checks, content length guidelines, common errors |
references/industry-strategies.md | Industry-specific work — 8 industry categories (FMCG, B2B, Education, Healthcare, Finance, E-commerce, Tech/SaaS) with decision cycle analysis, content priorities, AI platform preferences, compliance requirements |
references/ai-platform-specs.md | Platform-specific optimization — Detailed specs for each AI platform's content preferences, source priorities, content adaptation examples, combined strategies by brand stage and industry, bot access configuration |
references/channel-specs.md | Multi-channel publishing — Channel requirements for official website, 知乎, 百度百科, 什么值得买, 小红书, WeChat, with content characteristics, format rules, KPIs per channel |
references/monitoring-metrics.md | Monitoring deep-dive — Detailed definitions for all 12 metrics (4 visibility + 4 quality + 4 business), evaluation standards, scoring rubrics |
references/tools-guide.md | Tool setup — Playwright MCP configuration, Google Trends/百度指数 integration, GA4 setup for AI traffic tracking |
| File | When to Read |
|---|---|
references/question-library.md | Building or expanding question libraries — full 7-category taxonomy (BR/CR/CP/SC/PD/HS/SV), 3-tier testing framework, 7 industry-specific question sets |
references/question-library-template.md | Creating new question libraries from scratch for a new client/brand |
| File | When to Read |
|---|---|
references/brand-guidelines.md | Brand voice development — archetypes, tone attributes, personality framework |
references/social-media-optimization.md | Social platform optimization — platform-specific best practices |
references/content-frameworks.md | Content strategy — reusable templates, repurposing matrices |
| File | When to Use |
|---|---|
assets/positioning_report_template.md | Generating Phase 2 positioning reports — complete structure with executive summary, competitive analysis, value mapping, AIEO statement |
assets/schema_templates.json | Deploying Schema markup — 7 JSON-LD templates (Organization, FAQPage, Product, Service, LocalBusiness, BreadcrumbList, HowTo) + Meta tag templates |
assets/faq_template.md | Creating FAQ content — 7 FAQ types with specific templates, examples, and writing checklist |
assets/comparison_template.md | Creating comparison content — full page structure with quick conclusion, comparison tables, brand intros, selection guide (includes 百威 vs 青岛啤酒 example) |
assets/guide_template.md | Creating selection guides — structure with selection highlights, brand recommendations, common misconceptions (includes 高端啤酒选购指南 example) |
assets/scene_template.md | Creating scenario content — scene recommendation structure with fit points, product recommendations, alternatives (includes 商务宴请/体育赛事/聚会 examples) |
assets/content_plan_template.md | Phase 3 planning — comprehensive content generation plan with diagnostic summary, positioning mapping, industry adaptation, publishing strategy, effect tracking |
assets/output_template.md | Standard content output — metadata, content summary, publishing recommendations, Schema marking, quality checklist |
assets/monitoring_report_template.md | Generating Phase 4 monitoring reports — trend tracking, platform details, competitive analysis |
assets/tracking_spreadsheet.md | Recording test results — spreadsheet template for ongoing monitoring |
assets/quick_check_template.md | Weekly quick monitoring — fast assessment checklist |
assets/content_calendar_template.md | Editorial calendar management — publishing schedule and tracking |
| File | When to Run |
|---|---|
scripts/brand_voice_analyzer.py | Analyzing existing content for brand voice characteristics — run with python scripts/brand_voice_analyzer.py |
scripts/seo_optimizer.py | SEO optimization recommendations for content — run with python scripts/seo_optimizer.py |
Automatically, when a task matches. Use this skill whenever someone wants to optimize brand visibility in AI search engines (ChatGPT, Perplexity, 豆包, Kimi, DeepSeek, 文心一言, Claude), run AIEO diagnostics, create AI-optimized content, monitor AI mention rates, build question libraries, or execute any GEO/AEO/AIEO workflow. Also trigger when users mention GEO-claw, AI搜索优化, 生成引擎优化, AI可见性, brand AI visibility, AI recommendation optimi
Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.