Ready to supercharge your AI agents?

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

Garmin Trainer · leoyeai | DecimalAI

Productivityby leoyeai

Garmin Trainer

Adaptive 12-week training plan generator using Garmin Connect data. Creates structured workouts and schedules them on your Garmin calendar.

Never made a case worse

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

50%77%of test cases passed +27 pts

Without skill11 of 22

With skill17 of 22

6 fixed11 passed either way5 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v118 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskFor a 12-week endurance plan scheduled in Garmin Connect, on which specific day of the week must the primary long run or long bike session be placed?

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 leoyeai-garmin-trainer
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("leoyeai-garmin-trainer")
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 leoyeai-garmin-trainer

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/leoyeai-garmin-trainer/SKILL.md https://app.decimal.ai/s/leoyeai-garmin-trainer/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-garmin-trainer/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/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/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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("leoyeai-garmin-trainer")
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/leoyeai-garmin-trainer/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-garmin-trainer/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 1 other file is 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 leoyeai-garmin-trainer

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/leoyeai-garmin-trainer/SKILL.md https://app.decimal.ai/s/leoyeai-garmin-trainer/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-garmin-trainer/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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/leoyeai-garmin-trainer/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-garmin-trainer.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
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

Garmin Trainer

Generate an adaptive 12-week training plan based on real Garmin Connect data. The plan accounts for all upcoming events (races across different sports), current fitness level, recent training load, and recovery status. Each run of this skill pulls fresh data so the plan stays current.

For all gccli command examples (data gathering, workout creation, scheduling), read references/gccli-commands.md.

Step 0: Choose a Training Philosophy

Before building the plan, ask the user which coaching philosophy to follow. Present these six options — each shapes how the plan balances intensity, volume, strength work, and recovery:

1. Joe Friel — Periodization Bible

Based on "The Triathlete's Training Bible". Classic structured periodization with distinct phases (base → build → peak → race). Strength training is integral, progressing from anatomical adaptation (high rep, low weight) through max strength to explosive power as the season advances. Includes year-round mobility work. Best for athletes who like structure and measurable progression.

Intensity split: ~75% easy / 5% tempo / 20% high intensity (shifts across phases)
Strength: 2-3x/week in base phase (full-body compound lifts), tapering to 1x/week maintenance closer to events
Mobility: dynamic stretching before sessions, 10-15min flexibility routine post-workout

2. Matt Fitzgerald — 80/20 Polarized

From "80/20 Triathlon". Strictly 80% of training time at low intensity (zones 1-2), 20% at moderate-to-high intensity (zones 3-5). No junk miles in between. Research-backed approach that builds a massive aerobic engine while keeping the hard sessions truly hard. Supplemental strength focused on injury prevention rather than performance.

Intensity split: 80% easy (strictly enforced) / 20% moderate-to-hard
Strength: 2x/week functional strength and injury prevention (single-leg work, hip stability, core)
Mobility: foam rolling and dynamic mobility as part of warmup/cooldown routines

3. Phil Maffetone — MAF Method

Heart rate-based aerobic development. All easy training stays below the MAF heart rate (180 minus age, adjusted for health/fitness). Build a huge aerobic base before adding any intensity. Holistic philosophy that treats nutrition, sleep, and stress management as part of training. Strength is bodyweight and functional movement focused.

Intensity split: 90-100% below MAF HR in base building, intensity added only when aerobic base plateaus
MAF HR formula: 180 - age (subtract 5 if recovering from illness/injury, add 5 if consistently training 2+ years injury-free)
Strength: 2x/week bodyweight and functional movement (planks, lunges, squats, hip bridges)
Mobility: daily 15-20min routine — yoga-style flows, hip openers, thoracic spine mobility. Treated as non-negotiable, not optional

4. Kristian Blummenfelt — Norwegian Method

Threshold-heavy, data-driven approach pioneered by coach Olav Aleksander Bu. High volume of lactate-guided threshold work — more time at threshold than traditional plans, but carefully controlled via lactate (or HR proxy). Double sessions common. Strength training is functional and explosive, supporting sport-specific power. Very demanding — best for experienced athletes with a solid training base.

Intensity split: ~75% easy / 20% threshold / 5% VO2max (notably more threshold than other methods)
Strength: 2-3x/week functional and explosive work (Olympic lift derivatives, plyometrics, heavy squats)
Mobility: integrated into warmup routines, focused on range of motion for swim/bike/run efficiency

5. Dan Lorang — Data-Driven Individualization

Coach of Jan Frodeno and Anne Haug (both Ironman world champions). Highly individualized, technology-driven approach that relies on power meters, lactate diagnostics, and continuous data analysis. Periodization is fluid rather than rigid — training blocks are adjusted based on real-time performance data, not fixed calendars. Combines high aerobic volume with precisely dosed threshold and VO2max work. Strength training is sport-specific and prevention-oriented, designed to support the demands of each discipline rather than build general strength.

Intensity split: ~80% low intensity / 15% threshold / 5% VO2max (but distribution shifts dynamically based on data)
Key principle: every session has a clear physiological purpose — no filler workouts. If the data says rest, you rest.
Strength: 2-3x/week sport-specific and preventive (core stability, hip/glute activation, rotator cuff for swim, single-leg work for run). Periodized — heavier in off-season/base, lighter and more explosive closer to events.
Mobility: daily activation and mobility routines (10-15min), focused on individual limiters identified through movement screening

6. Mark Allen — Balanced Holistic

Six-time Ironman world champion, trained under Phil Maffetone but added his own emphasis on mental preparation and whole-body balance. Combines aerobic base building with progressive race-specific intensity. Yoga and flexibility are core components, not afterthoughts. Strength work focuses on muscular balance and injury resilience.

Intensity split: ~80% aerobic base / 15% tempo-threshold / 5% race-pace and above
Strength: 2x/week — balanced full-body work emphasizing posterior chain and core stability
Mobility: 2-3x/week dedicated yoga or stretching sessions (30-45min), daily post-workout flexibility

If the user has previously selected a philosophy, remember it and mention it — but always offer to change. If the user doesn't care or is unsure, default to Matt Fitzgerald 80/20 as a well-rounded starting point.

Note: Dan Lorang's approach is the most adaptive — it naturally aligns with this skill's re-run behavior. When using Lorang's philosophy, lean even more heavily on the Garmin data (training status, HRV, training load tunnel) to decide session intensity day-by-day rather than following a rigid week-by-week plan.

Running Target Mode

The running target mode (heart rate or pace) is set automatically based on the chosen training philosophy. Cycling always uses power (watts).

Philosophy	Running Mode	Rationale
Joe Friel	Heart rate	Periodization phases are defined by HR zones; base building relies on staying in aerobic HR range
Matt Fitzgerald	Pace	80/20 intensity is enforced via pace zones; hard sessions need precise pace targets
Phil Maffetone	Heart rate	MAF method is entirely HR-driven (180-age formula)
Kristian Blummenfelt	Pace	Threshold work requires precise pace control; lactate-guided sessions translate to pace targets
Dan Lorang	Pace	Data-driven approach optimizes for measurable output; pace is the running equivalent of cycling power
Mark Allen	Heart rate	Built on Maffetone's aerobic base philosophy; HR keeps easy sessions honest

Derive the target values from the athlete's data:

HR zones: from recent activity HR zone data, resting HR, and max HR
Pace zones: from lactate threshold pace, recent race/tempo efforts, and easy run averages
Power zones: from FTP (cycling)

See references/gccli-commands.md for workout creation examples in both modes.

Workout Types Beyond Sport-Specific Training

Regardless of which events are on the calendar, every week should include strength and mobility sessions based on the chosen philosophy. These keep the athlete robust, prevent injury, and support long-term performance.

Strength and mobility volume should scale with the philosophy and training phase:

Reduce strength volume (but maintain frequency) during taper weeks
During recovery weeks, keep mobility sessions but make strength optional
In base phases, strength can be more ambitious (heavier, more volume)

Schedule strength on easy or rest-adjacent days (e.g., Tuesday and/or Friday). See references/gccli-commands.md for creation examples.

Workflow

Step 1: Gather Data

Collect all relevant data from Garmin Connect in parallel. Always use --json for parseable output. See references/gccli-commands.md — "Data Gathering" section for all commands.

Gather:

Events and existing scheduled workouts (next 84 days)
Recent activities (last 4-6 weeks, up to 50)
Current fitness: training status, training readiness, VO2max/max metrics, HRV, resting HR, sleep
Performance benchmarks: lactate threshold, cycling FTP
Splits and HR zones for the last 2-3 key activities per sport type

Step 2: Analyze the Athlete

From the gathered data, build an athlete profile:

Sport types trained: which sports appear in recent activities (running, cycling, swimming, etc.)
Weekly volume: average distance and duration per sport over the last 4 weeks
Intensity distribution: how much time at easy vs. threshold vs. high intensity (from HR zones)
Current paces/power: derive training zones from recent activity data, lactate threshold, and FTP
Training status: Garmin's training status value (1=detraining, 2=recovery, 3=maintaining, 4=productive, 5=peaking, 6=overreaching, 7=unproductive)
Weekly training load: current load vs. the optimal load tunnel (loadTunnelMin/Max)
Recovery signals: HRV trends, resting HR, sleep quality, training readiness score

Step 3: Map All Events

This is critical — scan ALL events in the 12-week window, not just the nearest one. Events drive the plan structure.

For each event, determine:

Date and sport type (running, cycling, trail_running, triathlon, etc.)
Distance (from completionTarget)
Goal time (from eventCustomization.customGoal if set)
Is it a race? (race: true)
Priority level — from eventCustomization in the JSON:
- Primary (isPrimaryEvent: true): the athlete's A-race, the main goal everything builds toward
- Training (isTrainingEvent: true): a B-race or preparation event, important but subordinate to the primary event
- Unclassified (both false): a C-event, treated as a training opportunity with no special plan adjustments

How priority shapes the plan:

Aspect	Primary (A)	Training (B)	Unclassified (C)
Taper	Full taper (1-2 weeks, volume -40-60%)	Short taper (3-5 days, volume -20-30%)	No taper
Recovery after	Full recovery week (volume -50%)	2-3 easy days	Continue normal training
Specificity	Dedicated build phase with race-pace sessions	Some sport-specific sessions woven in	Train through, no plan changes
Volume share	Gets the majority of weekly training volume	Moderate share alongside primary sport	Minimal — fit into existing schedule
Goal pacing	Workouts target goal pace/power if set	Workouts at moderate race effort	Easy/moderate effort on the day

When multiple events exist, the primary event anchors the plan. Training events are stepping stones — use them to practice race execution and build confidence, but don't sacrifice primary event preparation for them. Unclassified events are just dates on the calendar; schedule around them but don't restructure training for them.

Sort events chronologically. The plan must build toward each event with appropriate specificity and include recovery between events. For example, if a half marathon (Training) on week 6 is followed by a marathon (Primary) on week 10, the plan prioritizes the marathon:

Build phase with increasing volume (weeks 1-5)
Short taper + half marathon as race-pace dress rehearsal (week 6)
Brief recovery then peak training block (weeks 7-8)
Full taper for the marathon (weeks 9-10)
Recovery + base (weeks 11-12)

If no events exist in the window, build a general fitness plan based on the sports the athlete currently trains.

Step 4: Design the Plan

Apply the chosen training philosophy to structure the 12 weeks. The philosophy determines the intensity distribution, strength/mobility frequency, and how aggressively to periodize.

General structure per training block (leading to an event):

Base/Build phase: progressive overload, increase volume ~10% per week
Specific phase: race-pace workouts, event-specific sessions
Taper: reduce volume 40-60% while maintaining intensity, 1-2 weeks before the event
Recovery: easy week after a race event (reduce volume 50%)

Weekly pattern:

Monday is always a rest day
Sunday is the long session day (long run, long ride)
1-2 key quality sessions per sport on weekdays (intervals, tempo)
Strength sessions on easy or rest-adjacent days (e.g., Tuesday and/or Friday)
Mobility/yoga sessions per the philosophy's prescription
Easy/recovery sessions between hard days
Never schedule hard sessions on Saturday — keep it easy or off to prepare for Sunday's long session

Intensity distribution — follow the chosen philosophy's split (e.g., 80/20 for Fitzgerald, threshold-heavy for Norwegian) and apply it to the athlete's actual training zones derived from their data.

Multi-sport considerations:

When training for events in different sports, interleave sport-specific sessions
Avoid stacking hard sessions in different sports on consecutive days
The primary event gets the lion's share of training volume; training events get moderate share
Use cross-training benefits (e.g., cycling aerobic base supports running)
Strength and mobility sessions support all sports — don't drop them even when single-sport focused

Intensity targets — derive from the athlete's actual data:

Easy pace: from recent easy run data or ~60-70% max HR (for MAF: use 180-age formula)
Tempo/threshold: from lactate threshold or recent threshold efforts
Interval: from recent fast segments or ~90-95% max HR
Cycling power zones: from FTP if available

Step 5: Create Workouts and Schedule

For each workout in the plan, create it via gccli workouts create and then schedule it. Use the athlete's chosen running target mode (pace or HR). Cycling always uses power.

Read references/gccli-commands.md for full command syntax and examples covering all workout types (running pace/HR, cycling power, strength, mobility) and scheduling/cleanup operations.

Naming convention: prefix with the week number (W1, W2, ...) and include the session purpose and key metric, e.g. "W3 Tempo Run 25min @4:45", "W5 Long Run 16km", "W8 FTP Intervals 5x6min".

Step 6: Present the Plan

After scheduling all workouts, present a summary to the user:

Philosophy: which coaching philosophy is applied and what that means in practice
Event overview: list all events in the 12-week window with dates, goals, and priority (A/B/C)
Phase breakdown: which weeks are base, build, taper, recovery
Weekly summary table: for each week show planned sessions including strength and mobility, total volume per sport, and key workouts
Training zones used: the pace/power/HR values the plan is based on
Strength & mobility plan: weekly frequency and focus areas per phase
Adaptation notes: what changed compared to the previous plan if this is a re-run (e.g., "reduced volume in week 3 because recent training load is above the optimal tunnel")

Re-running the Plan

When the user re-runs this skill, the plan should adapt:

Pull all fresh data (Step 1) to see what actually happened vs. what was planned
Compare completed activities against scheduled workouts to assess adherence
If the athlete missed workouts or is behind on volume, don't try to "catch up" — adjust the remaining weeks to build gradually from where they actually are
If the athlete is ahead of schedule or training load is high, consider adding a recovery week
If training status shows overreaching, reduce intensity and volume
Check if any new events were added and restructure phases accordingly

Before scheduling new workouts, automatically remove all existing future scheduled workouts created by this skill (identifiable by the "W" prefix naming convention like "W3 Tempo Run"). Do not ask for confirmation — these are skill-managed workouts. For workouts that don't match the W-prefix pattern (user-created), leave them in place and schedule around them.

See references/gccli-commands.md — "Scheduling & Cleanup" section for commands.

Important Principles

Be conservative with volume increases. Never increase weekly volume more than 10-15% week-over-week. If the athlete's recent volume is low, start from where they are, not where they "should" be.
Recovery is training. Always include recovery weeks (every 3-4 weeks) and post-race recovery.
Specificity matters. The closer to an event, the more sport-specific the training should be.
Use real data. Every pace, power, and HR target should come from the athlete's actual Garmin data, not from generic tables.
Respect the schedule. Don't schedule workouts on days where the athlete already has non-training commitments visible in their calendar.
Respect user workouts. If existing scheduled workouts don't match the W-prefix pattern (i.e., the user manually scheduled them), leave them in place and plan around them.

When it activates

Automatically, when a task matches. Use this skill whenever the user asks about training plans, workout scheduling, race preparation, building fitness for upcoming events, or wants to generate/update their training calendar. Also triggers when the user mentions Garmin training, weekly workouts, taper plans, base building, interval sessions, or periodization.

About this skill

Automatic

Personal Assistant pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

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

LeoYeAI / openclaw-master-skills

skills/garmin-trainer/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 1 file

Illustrative Want to see what leoyeai/garmin-trainer 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

Garmin Trainer

Step 0: Choose a Training Philosophy

1. Joe Friel — Periodization Bible

2. Matt Fitzgerald — 80/20 Polarized

3. Phil Maffetone — MAF Method

4. Kristian Blummenfelt — Norwegian Method

5. Dan Lorang — Data-Driven Individualization

6. Mark Allen — Balanced Holistic

Running Target Mode

Workout Types Beyond Sport-Specific Training

Workflow

Step 1: Gather Data

Step 2: Analyze the Athlete

Step 3: Map All Events

Step 4: Design the Plan

Step 5: Create Workouts and Schedule

Step 6: Present the Plan

Re-running the Plan

Important Principles

When it activates

SkillSafety

Source

Related skills

More in the registry