Ready to supercharge your AI agents?

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

Get Started Free →

Zapier Workflows Skill · davila7 | DecimalAI

Agent Toolingby davila7

Zapier Workflows Skill

Manage and trigger pre-built Zapier workflows and MCP tool orchestration.

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

45%77%of test cases passed +32 pts

Without skill10 of 22

With skill17 of 22

7 fixed10 passed either way5 still failing0 broke

Measured on gemini-3.6-flash8/12/2026v118 comparable

Track record

Agent runs: 13; All time

See one task, with and without the skill

One test taskI just had you use Perplexity to research 3 competitors and then format and write the findings into Google Sheets. That combination worked great. What should we do now to make sure you remember this workflow for next time?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add davila7-zapier-workflows
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install davila7-zapier-workflows

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/davila7-zapier-workflows/SKILL.md https://app.decimal.ai/s/davila7-zapier-workflows/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/davila7-zapier-workflows/SKILL.md

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

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add davila7-zapier-workflows

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

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

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add davila7-zapier-workflows

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

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

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add davila7-zapier-workflows

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

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

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add davila7-zapier-workflows

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add davila7-zapier-workflows

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

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

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add davila7-zapier-workflows

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add davila7-zapier-workflows

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

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

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add davila7-zapier-workflows

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

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

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add davila7-zapier-workflows

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

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

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add davila7-zapier-workflows

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add davila7-zapier-workflows

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

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

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add davila7-zapier-workflows

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("davila7-zapier-workflows")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/davila7-zapier-workflows/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

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

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add davila7-zapier-workflows

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/davila7-zapier-workflows/SKILL.md https://app.decimal.ai/s/davila7-zapier-workflows/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/davila7-zapier-workflows/SKILL.md

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

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/davila7-zapier-workflows/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/davila7-zapier-workflows.json

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

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/12/2026
Source: davila7/claude-code-templates ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Zapier Workflows Skill

The Problem This Solves

Zapier MCP gives Claude access to 8,000+ individual tools (every Zapier action), but there are critical limitations:

❌ No memory - Claude doesn't remember which tools YOU use or why ❌ No context - Doesn't know when to use specific tools for your workflows ❌ Only one-off actions - Can't trigger your complex, multi-step Zaps ❌ Fresh start every session - All context lost between conversations

The Two Types of Zapier Automation

1. MCP Tools (One-Off Actions)

Individual Zapier actions (Add row to sheet, Send email, etc.)
Available via Zapier MCP at https://mcp.zapier.com/mcp/servers
Great for flexible, on-the-fly automation
Problem: 8,000+ choices with no guidance on which to use or when

2. Multi-Step Zaps (Webhook-Triggered)

Complex workflows you've built in Zapier dashboard
Multiple actions chained together, pre-optimized
Triggered via webhook URL (POST request)
Problem: Claude can't trigger these - they're not in the MCP

What This Skill Does

This skill solves both problems by giving Claude persistent memory for your Zapier workflows:

✅ Remembers your MCP tool preferences - "Use Google Sheets for expenses, Notion for tasks" ✅ Knows when/why to use each tool - "Search with Perplexity when researching, not Google" ✅ Triggers multi-step Zaps - "Run my daily digest" = webhook POST to your complex Zap ✅ Self-learning - Claude updates the skill as you teach it, never forgets ✅ Cross-session persistence - Works across all conversations (global install)

What You Get

For Multi-Step Zaps:

Store webhook URLs and what they do
Trigger complex workflows just by asking
Remember when/why to use each Zap
Document costs, timing, outputs

For MCP Tools:

Document which tools you prefer for which tasks
Build reusable workflow patterns
Store tool-specific preferences (sheet names, formats, etc.)
Create multi-tool orchestration sequences

Self-Learning:

Claude automatically updates skill files when you teach it
Changes persist forever (global install) or per-project (local install)
No manual editing required - just talk to Claude

Installation & Setup

Installation Location

Global (~/.claude/skills/) - RECOMMENDED:

Learned patterns persist across ALL projects
One Zap library for everything
Preferences carry over to all projects

Project-level (./.claude/skills/):

Learned patterns ONLY in this project
Isolated from other projects
Useful for project-specific workflows

⚠️ Security Warning

IMPORTANT: This skill stores webhook URLs and workflow details in plain text files.

Webhook URLs contain authentication tokens. If someone has your webhook URL, they can trigger your Zaps.

Best practices:

✅ Install globally at ~/.claude/skills/ (not in project repos)
✅ Add .claude/ to your .gitignore if installed in a project
✅ Never commit skill files with real webhook URLs to public repos
✅ Regenerate webhook URLs if accidentally exposed
✅ Use Zapier's webhook authentication features when available

If you need to share this skill:

Remove real webhook URLs first
Replace with placeholder examples
Or use separate webhook URLs for sharing/testing

Prerequisites

Required:

Claude Code
Zapier account (for webhooks and MCP tools)

Optional:

Additional MCP tools based on your workflows (Perplexity Search, Google Sheets, etc.)

Setting Up Zapier MCP

To connect Zapier's MCP tools to Claude Code:

Go to Zapier MCP servers:
- Visit https://mcp.zapier.com/mcp/servers
- Login to your Zapier account if prompted
Create a new MCP server:
- Click "New MCP Server" button (top left)
- In "MCP Client (required)" dropdown, select Claude Code
- Give your server a name (e.g., "My Zapier Tools")
Add tools:
- Click "Add tools" button
- Select as many Zapier actions as you want (each becomes an MCP tool)
- Common tools: Run Zap, Add Row to Google Sheets, Send Email, etc.

Connect to Claude Code:

Click "Connect" button
You'll see a command like this:

claude mcp add zapier https://mcp.zapier.com/api/mcp/mcp -t http -H "Authorization: Bearer ZjFmZGJkN..................1NjBhYzc2MDRlYg=="

Copy and run this command in your terminal

Restart Claude Code:
- Close and reopen Claude Code
- Your Zapier MCP tools are now available

Tip: You can add more tools later by editing your MCP server in Zapier and running the connect command again.

Creating Webhook-Triggered Zaps

For pre-built, optimized workflows that you want to trigger on-demand:

In Zapier dashboard:
- Create a new Zap
- Choose "Webhooks by Zapier" as trigger
- Select "Catch Hook"
- Copy the webhook URL provided
Build your workflow:
- Add whatever actions you want (API calls, data processing, etc.)
- Test and optimize the Zap
Document it in this skill:
- Tell Claude about the new Zap (webhook URL, what it does, trigger phrases)
- Claude will add it to references/zaps.md automatically
- Now you can trigger it by just asking Claude!

Webhook vs MCP Tools:

Webhooks: Pre-built, multi-step Zaps you trigger with a POST request. Great for complex, optimized workflows.
MCP Tools: Individual Zapier actions called directly. Great for flexible, on-the-fly automation.

Self-Improvement Protocol

CRITICAL: This skill can and should edit itself to learn from user feedback.

When the user teaches you something new or corrects your approach:

Identify what to update:
- New Zap to document → Edit references/zaps.md
- MCP tool preference → Edit references/mcp-patterns.md
- New workflow pattern → Edit references/mcp-patterns.md
Make the edit using Claude Code tools:
- Read the file first with the Read tool
- Update with the Edit tool (specify exact old_string and new_string)
- Confirm the change to the user

Update format:

User: "Use Apollo instead of Clearbit for company data"
Claude: [uses Read tool on references/mcp-patterns.md]
        [uses Edit tool to update the preference]
        "Updated! I'll use Apollo for company enrichment from now on.
         This change is now permanent in the skill."

What to capture in skill updates:

✅ Tool preferences (which tool for which task)
✅ Workflow sequences (step-by-step patterns)
✅ Error handling approaches
✅ Data formatting requirements
✅ New Zaps and their details
❌ One-off requests (don't clutter the skill)
❌ Temporary context (use memory instead)

Decision Logic

When to Use Webhook-Triggered Zaps

Use webhooks when:

Task is complex, multi-step, and already refined
User mentions a specific Zap name (check references/zaps.md)
Deterministic execution is critical
Task involves 5+ API calls or complex orchestration
Cost/time efficiency matters (pre-built Zaps are optimized)

When to Use MCP Tool Orchestration

Use MCP tools when:

Task is simple (1-3 actions)
Flexibility is needed (parameters change)
Testing a new workflow pattern
User explicitly asks to use specific MCP tools

Execution Pattern

Listen for triggers: Workflow names, "run", "trigger", "search", "research", etc.
Check references: Use Read tool on appropriate reference file for details
Check prerequisites:
- If MCP tools needed but not available: Provide Zapier MCP setup instructions (see below)
- If MCP tools available but not documented: Trigger tool discovery protocol (see below)
- If webhook URL needed but not in references: Provide webhook extraction instructions (see below)
Execute:
- For webhook-triggered Zaps: Use Bash tool with curl to POST to webhook URL (webhooks are created in Zapier dashboard with "Catch Hook" trigger)
- For MCP tool workflows: Call the appropriate Zapier MCP tool directly (configured via https://mcp.zapier.com/mcp/servers)
Confirm: Tell user what happened in natural language
Learn: If user corrects you, use Edit tool to update the skill files
Suggest pattern saving: After successful tool use, offer to save the pattern (see below)

Proactive Pattern Detection & Learning

CRITICAL: After you successfully help the user with MCP tools or workflows, proactively suggest saving valuable patterns.

When to Suggest Saving Patterns

After completing a task using MCP tools, check if this is a pattern worth saving:

Look for:

Multi-step tool sequences that worked well
Specific parameter combinations the user liked
Repeated workflows or use cases
Tool preferences the user expressed during the task
Successful solutions to user problems

Suggest saving if:

You used 2+ MCP tools in sequence
User expressed satisfaction with the result
This seems like something user might repeat
User gave specific preferences during the interaction

How to Suggest Pattern Saving

After completing the task successfully:

"That worked well! I noticed I [describe what you did, e.g., 'used Perplexity to research, then saved results to Google Sheets'].

Would you like me to save this as a pattern? If you tell me:
- What trigger words to listen for
- When/why to use this workflow
- Any preferences or variations

I'll remember it and do this automatically next time!"

Document the Pattern

If user says yes:

Use Read tool on references/mcp-patterns.md
Use Edit tool to add new pattern with:
- Pattern name
- Trigger phrases
- When/why to use it
- Step-by-step workflow
- Parameters/preferences
- Example
Confirm: "Saved! Next time you [trigger], I'll [workflow]."

Examples of patterns worth saving:

"Research and document" (Perplexity → summarize → Google Sheets)
"Expense tracking" (Extract amount/description → format → add to sheet)
"Competitive analysis" (Search competitor → analyze → save insights)
"Daily briefing" (Multiple searches → synthesize → deliver)

Don't save:

One-off requests
Highly specific/unique situations
Simple single-tool uses (unless user asks)

Setup Detection & Instructions

If Zapier MCP Not Detected

When user requests MCP tool functionality but Zapier MCP is not connected, tell them:

"I don't see the Zapier MCP tools connected. Here's how to set them up:

1. Go to https://mcp.zapier.com/mcp/servers
2. Login to your Zapier account
3. Click 'New MCP Server' (top left)
4. Select 'Claude Code' in the MCP Client dropdown
5. Give it a name (e.g., 'My Zapier Tools')
6. Click 'Add tools' and select the Zapier actions you want
7. Click 'Connect' and copy the command shown
8. Run that command in your terminal (it looks like):
   claude mcp add zapier https://mcp.zapier.com/api/mcp/mcp -t http -H "Authorization: Bearer [your-token]"
9. Restart Claude Code

Once setup, I'll be able to use those Zapier actions directly!"

When Zapier MCP Is Connected - Tool Discovery & Documentation

IMPORTANT: When Zapier MCP is connected (tools starting with mcp__zapier__ are available), proactively help the user document them with rich context:

List available tools:
- Check what Zapier MCP tools are available
- List them out for the user

Prompt for detailed documentation:

"I see you have these Zapier MCP tools available:
- mcp__zapier__google_sheets_create_spreadsheet_row
- mcp__zapier__perplexity_chat_completion
- [etc.]

To help me use these effectively, I need to understand:

For each tool you want me to use, please tell me:

1. WHEN should I use this tool?
   - What trigger words or phrases?
   - What situations or contexts?
   - What types of requests?

2. WHY should I use this tool vs alternatives?
   - What's it best for?
   - When should I NOT use it?

3. HOW should I use it?
   - Any specific parameters or preferences?
   - Default values I should use?
   - Sheet names, formats, or other specifics?

4. Any PATTERNS or workflows involving this tool?
   - Multi-step sequences?
   - Common combinations with other tools?

Take your time - the more detail you give me, the better I can serve you!"

Document in skill:
- Use Read tool on references/mcp-patterns.md
- Use Edit tool to add comprehensive documentation:
  - Tool name and purpose
  - Trigger phrases (when)
  - Use cases (why)
  - Parameters and preferences (how)
  - Workflow patterns if mentioned
- Confirm to user what was documented

When to trigger this:

First time user mentions Zapier or workflows after MCP setup
User explicitly asks "what tools do I have?" or "what can you do with Zapier?"
When you detect new Zapier MCP tools that aren't documented in references/mcp-patterns.md

If User Wants to Add a Webhook-Triggered Zap

When user mentions creating or adding a multi-step Zap for webhook triggering, provide these instructions:

"To get your webhook URL from an existing Zap:

1. Go to your Zap in the Zapier dashboard
2. Make sure the trigger is a 'Webhooks by Zapier' node
3. In the 'Trigger Event' dropdown, select 'Catch Hook'
4. Go to the 'Test' tab
5. Copy the 'Webhook URL' shown
6. Give me that URL and tell me:
   - What the Zap does (step-by-step)
   - What trigger phrases you want to use
   - Any other details (timing, cost, etc.)

I'll add it to my knowledge so you can trigger it anytime just by asking!"

Quick Reference

All Zaps: See references/zaps.md
MCP Patterns: See references/mcp-patterns.md
Common workflows: Both files contain examples

Usage Examples

Triggering a Zap:

User: "Run my daily digest"
Claude: [uses Read tool on references/zaps.md for webhook details]
        [uses Bash tool to trigger webhook with curl POST]
        "Started your Daily AI Digest. You'll get the report via email
         in ~3 minutes, with SMS alerts for any high-priority items."

Using MCP orchestration:

User: "Research the latest on quantum computing"
Claude: [uses Read tool on references/mcp-patterns.md]
        [calls Perplexity Search MCP tool]
        [analyzes results, identifies gaps]
        [calls Perplexity Search again for deeper dive]
        "Here's what I found... [summary]"

Learning and updating:

User: "No, when tracking expenses use my 'Personal Budget' sheet, not 'Expenses'"
Claude: [uses Read tool on references/mcp-patterns.md]
        [uses Edit tool to update the Google Sheets section]
        "Got it - updated the skill. I'll use 'Personal Budget' sheet
         for expense tracking from now on."

FAQ & Troubleshooting

"Claude isn't detecting my Zapier MCP tools"

Check if MCP is connected:

Look for tools starting with mcp__zapier__ in your available tools
Try asking: "What Zapier tools do I have?"

If not showing up:

Verify you ran the connection command from https://mcp.zapier.com/mcp/servers
Restart Claude Code completely (not just reload)
Check your Claude Code MCP settings
Verify the authorization token in the command was correct

"Claude isn't suggesting to save patterns"

Pattern detection triggers when:

You use 2+ MCP tools in sequence
The task completes successfully
It seems repeatable (not a one-off request)

Try explicitly asking:

"Can you save this as a pattern?"
"Remember this workflow for next time"

"Webhook URL not triggering my Zap"

Common issues:

Wrong URL - Make sure you copied the full URL from Test tab
Zap not turned on - Enable the Zap in Zapier dashboard
Trigger node incorrect - Must be "Webhooks by Zapier" → "Catch Hook"
Firewall/network - Check if curl command works from terminal first

Test manually:

curl -X POST https://hooks.zapier.com/hooks/catch/[your-url]

"Claude keeps asking to document tools I already documented"

Likely causes:

Tools documented but file not saved properly
Using different Claude Code instance/installation
Skill installed at project level, not global

Fix:

Check references/mcp-patterns.md has your tools
Verify skill location: ~/.claude/skills/ (global) vs ./.claude/skills/ (project)
If project-level, copy to global for cross-project persistence

"How do I know if the skill is working?"

Signs it's working:

When you mention Zapier/workflows, Claude mentions checking references
Claude asks detailed questions (WHEN/WHY/HOW) about tools
After using tools, Claude suggests saving patterns
Claude successfully triggers your webhooks

Quick test:

Ask: "What Zapier tools do I have?"
Add a fake webhook and tell Claude about it
Check if it was added to references/zaps.md

"Skill files getting too large / slow to load"

If reference files grow too large:

Review and remove outdated/unused patterns
Consolidate similar workflows
Keep only actively-used tools documented
Consider splitting into multiple skill instances for different domains

Performance tips:

Keep trigger phrases concise and specific
Avoid documenting one-off workflows
Use pattern categories to organize

"I want to reset the skill to template state"

To start fresh:

Backup your current skill files (if you want to keep anything)
Delete the skill directory
Re-clone from GitHub: https://github.com/AlexBoudreaux/claude-zapier-skill
Copy fresh template to ~/.claude/skills/

"Can I use this skill without Zapier MCP?"

Yes! The skill works with:

Only webhooks - Trigger multi-step Zaps without MCP
Only MCP tools - Document tool usage without webhooks
Both - Get full functionality

Each mode is independent and valuable on its own.

"Security: I accidentally committed webhook URLs"

Immediate actions:

Remove the commit from git history (git rebase, BFG Repo-Cleaner)
Regenerate webhook URLs in Zapier dashboard:
- Edit the Zap
- Delete and re-add the webhook trigger node
- Get new webhook URL
Update skill files with new URLs
Add .claude/ to .gitignore

Prevention:

Install skill globally (~/.claude/skills/)
Never commit .claude/ directory in projects
Use placeholder URLs in shared examples

Important Notes

Webhooks don't need payloads - Zaps get their data from Zapier Tables
Always read reference files before executing - they contain critical details
Update skill files when learning something new - don't just remember it for this conversation

Claude Code Tools Used

This skill uses the following Claude Code tools:

Read - To view reference files (zaps.md, mcp-patterns.md)
Edit - To update skill files with new workflows, patterns, or preferences
Bash - To trigger Zapier webhooks using curl POST requests
MCP Tools - To call Perplexity Search, Google Sheets, and other integrations

When it activates

Automatically, when a task matches. Use when user mentions workflows, Zaps, automations, daily digest, research, search, lead tracking, expenses, or asks to "run" any process. Also handles Perplexity-based research and Google Sheets data tracking.

About this skill

Automatic

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

davila7 / claude-code-templates

cli-tool/components/skills/development/zapier-workflows/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 2 files

Illustrative Want to see what davila7/zapier-workflows would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Zapier Workflows Skill

The Problem This Solves

The Two Types of Zapier Automation

What This Skill Does

What You Get

Installation & Setup

Installation Location

⚠️ Security Warning

Prerequisites

Setting Up Zapier MCP

Creating Webhook-Triggered Zaps

Self-Improvement Protocol

Decision Logic

When to Use Webhook-Triggered Zaps

When to Use MCP Tool Orchestration

Execution Pattern

Proactive Pattern Detection & Learning

When to Suggest Saving Patterns

How to Suggest Pattern Saving

Document the Pattern

Setup Detection & Instructions

If Zapier MCP Not Detected

When Zapier MCP Is Connected - Tool Discovery & Documentation

If User Wants to Add a Webhook-Triggered Zap

Quick Reference

Usage Examples

FAQ & Troubleshooting

"Claude isn't detecting my Zapier MCP tools"

"Claude isn't suggesting to save patterns"

"Webhook URL not triggering my Zap"

"Claude keeps asking to document tools I already documented"

"How do I know if the skill is working?"

"Skill files getting too large / slow to load"

"I want to reset the skill to template state"

"Can I use this skill without Zapier MCP?"

"Security: I accidentally committed webhook URLs"

Important Notes

Claude Code Tools Used

When it activates

SkillSafety

Source

Related skills

More in the registry