Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manages Google Workspace operations across 12 services (Gmail, Drive, Calendar, Docs, Sheets, Slides, Forms, Tasks, Contacts, Chat, Apps Script, Custom Search). Supports MCP tools or CLI via uvx workspace-mcp --cli. Provides tool routing, workflows, and parameter guidance for 114 tools. Triggers for "check my email", "find a file", "schedule a meeting", "update the spreadsheet", "share a doc", "create a presentation", "add a task", "look up a contact", or any mention of Google Workspace services
SkillScore77/100
Test results 77
3/3 safety checks passed
14%77%of test cases passed +64 pts
Passed 17 of 22 test cases with the skill, and 3 of 22 without it.
14 fixed3 passed either way5 still failing0 broke
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 11/1/2026 did not produce a publishable comparison (graded differently). The snapshot above is the previously measured run.
One test taskI need to update the source code of an existing script file within a Google Apps Script project. What tool and action parameter should I pass?
Adds every file the skill has, pinned so you can update it. No account needed.
pip install "decimalai>=0.15"
decimalai skills add taylorwilsdon-managing-google-workspace
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("taylorwilsdon-managing-google-workspace")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")claude --plugin-dir "$(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 taylorwilsdon-managing-google-workspaceThe 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/taylorwilsdon-managing-google-workspace/SKILL.md https://app.decimal.ai/s/taylorwilsdon-managing-google-workspace/SKILL.md.claude/skills/taylorwilsdon-managing-google-workspace/SKILL.mdThis gets SKILL.md only. The skill's 14 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 taylorwilsdon-managing-google-workspaceimport 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspacefrom 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspaceimport 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspaceimport 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspacefrom 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspacefrom 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspaceimport 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspacefrom 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspacefrom 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspaceimport 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspaceimport 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspacefrom 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("taylorwilsdon-managing-google-workspace")
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/taylorwilsdon-managing-google-workspace/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/taylorwilsdon-managing-google-workspace/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 14 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 taylorwilsdon-managing-google-workspaceNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/taylorwilsdon-managing-google-workspace/SKILL.md https://app.decimal.ai/s/taylorwilsdon-managing-google-workspace/SKILL.md.agents/skills/taylorwilsdon-managing-google-workspace/SKILL.mdThis gets SKILL.md only. The skill's 14 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 14 other files are not included.
Raw files: /s/taylorwilsdon-managing-google-workspace/SKILL.md · /s/taylorwilsdon-managing-google-workspace.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/taylorwilsdon-managing-google-workspace/SKILL.mdcurl -fsSL https://app.decimal.ai/s/taylorwilsdon-managing-google-workspace.jsonThis gets SKILL.md only. The skill's 14 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.
Detect which mode is available and use it.
If MCP tools from the google-workspace server are available, call them directly. The tool names in the tables below are the base names -- prefix with the server name as needed (e.g. google-workspace:search_gmail_messages).
If no MCP tools are available, call a running server via workspace-cli:
workspace-cli list
workspace-cli call <tool_name> key=value ...
user_google_email=USER_EMAIL only when the tool schema requires it (legacy OAuth 2.0 without USER_GOOGLE_EMAIL set). Omit it for OAuth 2.1 and trusted-gateway servers, which take it from the verified identity.key=value pairs; values are parsed as JSON when possible, so pass lists and objects as JSON (e.g. label_ids='["INBOX"]').http://localhost:8000/mcp (a server started with --transport streamable-http); override it with --url before the subcommand (workspace-cli --url <url> call ...) or WORKSPACE_MCP_URL. Plugin users on stdio can set WORKSPACE_MCP_HTTP_PORT to expose a loopback sidecar at http://127.0.0.1:<port>/mcp.workspace-cli is not on PATH, run uv run workspace-cli from a checkout of this repo. Installing it permanently (uv tool install . in that checkout) is a manual setup step for the user. Never use uvx workspace-cli: an unrelated, abandoned PyPI package squats that name.Before calling a tool, read the relevant reference file for exact parameter names and types. Only use parameters documented there -- do not invent parameters.
If a tool call fails with a credential error, walk the user through this setup.
Direct the user to Google Cloud Console:
Direct the user to edit ~/.claude/settings.local.json themselves (this file is gitignored and never shared). Do not ask the user to paste secrets into the conversation. Tell them to add the following to the env block:
{
"env": {
"GOOGLE_OAUTH_CLIENT_ID": "their-client-id",
"GOOGLE_OAUTH_CLIENT_SECRET": "their-secret"
}
}
If settings.local.json already exists, they should merge into the existing env object, not replace it. These env vars are inherited by all MCP servers and CLI processes that Claude Code spawns.
start_google_auth to open the browser OAuth flow~/.google_workspace_mcp/credentials (or as configured by WORKSPACE_MCP_CREDENTIALS_DIR) for future sessionsFor server options, transport, auth modes, tool filtering, and deployment: references/server-options.md
action parameter for create/update/delete.| Task | Tool |
|---|---|
| Search/find emails | search_gmail_messages |
| Read one email, or page a long body | get_gmail_message_content (page_offset, page_size, expected_sha256) |
| Read multiple emails | get_gmail_messages_content_batch |
| Read a thread | get_gmail_thread_content |
| Read multiple threads | get_gmail_threads_content_batch |
| Send email (new or reply) | send_gmail_message |
| Create draft | draft_gmail_message |
| Download attachment | get_gmail_attachment_content |
| Add/remove labels (one) | modify_gmail_message_labels |
| Add/remove labels (batch) | batch_modify_gmail_message_labels |
| Manage labels | manage_gmail_label |
| List labels | list_gmail_labels |
| Manage filters | manage_gmail_filter |
| List filters | list_gmail_filters |
For parameters: references/gmail.md
| Task | Tool |
|---|---|
| Search files/folders | search_drive_files |
| List items in folder | list_drive_items |
| Read file content | get_drive_file_content |
| Download file | get_drive_file_download_url |
| Create file | create_drive_file |
| Create folder | create_drive_folder |
| Copy file | copy_drive_file |
| Update file metadata | update_drive_file |
| Share / set permissions | set_drive_file_permissions |
| Manage access (add/remove) | manage_drive_access |
| Check permissions | get_drive_file_permissions |
| Get shareable link | get_drive_shareable_link |
| Check public access | check_drive_file_public_access |
| Import file to Google Doc | import_to_google_doc |
| Import spreadsheet (XLSX, CSV, ...) to Google Sheets | import_to_google_sheets |
| Import presentation (PPTX, ...) to Google Slides | import_to_google_slides |
For parameters: references/drive.md
| Task | Tool |
|---|---|
| List calendars | list_calendars |
| Create secondary calendar | create_calendar |
| Get events | get_events |
| Create/update/delete event | manage_event |
| Out of office (auto-decline) | manage_out_of_office |
| Focus time (auto-decline, DND) | manage_focus_time |
| Check availability | query_freebusy |
For parameters: references/calendar.md
| Task | Tool |
|---|---|
| Read doc as Markdown | get_doc_as_markdown |
| Read doc content (raw) | get_doc_content |
| Read plain text with link/chip targets and document segments | get_doc_content(preserve_context=True) |
| Create new doc | create_doc |
Modify text / apply styles (by index or by heading) | modify_doc_text |
| Insert elements (tables, lists, breaks) | insert_doc_elements |
| Insert image | insert_doc_image |
| Create table with data | create_table_with_data |
| Update paragraph styles | update_paragraph_style |
| Find and replace | find_and_replace_doc |
| Inspect structure | inspect_doc_structure |
| Batch update (multiple ops) | batch_update_doc |
| Headers/footers | update_doc_headers_footers |
| Manage tabs | manage_doc_tab |
| Export to PDF | export_doc_to_pdf |
| List docs in folder | list_docs_in_folder |
| Search docs | search_docs |
| Comments | manage_document_comment / list_document_comments |
| Debug table structure | debug_table_structure |
For parameters: references/docs.md
| Task | Tool |
|---|---|
| Read cell values | read_sheet_values |
| Write/append/clear values | modify_sheet_values |
| Insert smart chips | modify_sheet_values (chips) |
| Format cells | format_sheet_range |
| Conditional formatting | manage_conditional_formatting |
| Get spreadsheet info | get_spreadsheet_info |
| Create spreadsheet | create_spreadsheet |
| Create sheet (tab) | create_sheet |
| Rename/delete/hide/reorder/style tab | manage_sheet_tab |
| Resize/freeze/hide/insert/delete rows and columns | resize_sheet_dimensions |
| Move rows between sheets | move_sheet_rows |
| List structured tables | list_sheet_tables |
| Append rows to structured table | append_table_rows |
| Manage named ranges | manage_named_range |
| List spreadsheets | list_spreadsheets |
| Comments | manage_spreadsheet_comment / list_spreadsheet_comments |
For parameters: references/sheets.md
| Task | Tool |
|---|---|
| Get presentation | get_presentation |
| Get specific slide | get_page |
| Look at a slide (render to image) | render_page_to_image |
| Create presentation | create_presentation |
| Batch update | batch_update_presentation |
| Speaker notes | get_presentation (include_speaker_notes) + batch_update_presentation |
| Comments | manage_presentation_comment / list_presentation_comments |
For parameters: references/slides.md
| Task | Tool |
|---|---|
| Get form | get_form |
| Create form | create_form |
| Batch update form | batch_update_form |
| List responses | list_form_responses |
| Get one response | get_form_response |
| Publish settings | set_publish_settings |
For parameters: references/forms.md
| Task | Tool |
|---|---|
| List task lists | list_task_lists |
| Get task list | get_task_list |
| Manage task list (CRUD) | manage_task_list |
| List tasks | list_tasks |
| Get task | get_task |
| Manage task (CRUD/move) | manage_task |
For parameters: references/tasks.md
| Task | Tool |
|---|---|
| Search contacts | search_contacts |
| Get contact | get_contact |
| Manage contact (CRUD) | manage_contact |
| Batch manage contacts | manage_contacts_batch |
| List contact groups | list_contact_groups |
| Get contact group | get_contact_group |
| Manage contact group | manage_contact_group |
| List all contacts | list_contacts |
For parameters: references/contacts.md
| Task | Tool |
|---|---|
| List spaces | list_spaces |
| Get messages | get_messages |
| Search messages | search_messages |
| Send message | send_message |
| Edit a message already sent | send_message (message_name) |
| React to message | create_reaction |
| Download attachment | download_chat_attachment |
For parameters: references/chat.md
| Task | Tool |
|---|---|
| Projects/files (list/get) | get_script_project (action) |
| Projects (create/delete) | manage_script_project (action) |
| File content (update) | manage_script_content (action="update") |
| Run function | run_script_function |
| Generate trigger code | generate_trigger_code |
| Deployments (list) | list_script_deployments |
| Deployments (create/update/delete) | manage_deployment (action) |
| Versions (list/get) | get_script_version (action) |
| Versions (create) | manage_script_version (action="create") |
| Execution metrics / process history | get_script_activity (action="metrics" / "processes") |
| Current user's triggers (list/delete) | manage_script_trigger (action) |
For parameters: references/apps-script.md
| Task | Tool |
|---|---|
| Web search | search_custom |
| Get search engine info | get_search_engine_info |
For parameters: references/search.md
| Task | Tool |
|---|---|
| Start OAuth flow | start_google_auth |
Legacy OAuth 2.0 only -- disabled when OAuth 2.1 is enabled. In most cases, just call the tool you need and auth happens automatically. For parameters: references/server-options.md
search_gmail_messages -- find the emailget_gmail_message_content -- read it (get message_id and thread_id)send_gmail_message -- reply using thread_id; omit reply headers to target the latest non-draft, non-trash message with an RFC Message-IDsearch_drive_files -- find the filemanage_drive_access -- share itget_drive_shareable_link -- get the linkget_spreadsheet_info -- get sheet namesread_sheet_values -- read current datamodify_sheet_values -- write updated dataread_sheet_values -- verify the updatecreate_doc -- create the docmodify_doc_text -- add text with formattinginsert_doc_elements -- add tables, lists, page breaksupdate_paragraph_style -- apply heading stylesget_doc_as_markdown -- verify the resultsearch_gmail_messages -- find the emailget_gmail_message_content -- get attachment metadataget_gmail_attachment_content -- download the attachmentget_doc_as_markdown -- read current contentinspect_doc_structure -- find insertion points and indicesmodify_doc_text / insert_doc_elements -- make changesget_doc_as_markdown -- verify the resultworkspace-cli list shows which tools the running server exposes.Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.