Ready to supercharge your AI agents?

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

Healthfit · leoyeai | DecimalAI

Scienceby leoyeai

Healthfit

个人全维度健康管理系统，中西医融合。当用户涉及运动训练计划、饮食营养建议、健康数据记录追踪、中医体质辨识、节气养生、舌诊分析、性健康记录等话题时立即触发。提供四位顾问（Coach Alex 运动教练 / Dr. Mei 营养师 / Analyst Ray 数据分析师 / Dr. Chen 中医体质顾问），支持深度建档和长期追踪。任何"帮我建档"、"记录今天运动"、 "我的体质"、"舌苔厚白"类请求均应触发本 skill。

Never made a case worse

SkillScore

SkillScore87/100

Test results 87

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

35%87%of test cases passed +52 pts

Without skill8 of 23

With skill20 of 23

12 fixed8 passed either way3 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v2

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI want to look up traditional Chinese medicine terminology definitions in the system's text knowledge base. What file contains these terms and what numbering range do TCM terms use?

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-healthfit
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-healthfit")
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-healthfit

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

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-healthfit/SKILL.md

This gets SKILL.md only. The skill's 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/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-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/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-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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-healthfit")
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-healthfit/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-healthfit/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 24 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 leoyeai-healthfit

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-healthfit/SKILL.md

This gets SKILL.md only. The skill's 24 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/leoyeai-healthfit/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 24 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2, 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

HealthFit — Personal Comprehensive Health Management System (v3.0 Integrated Western & TCM)

Four-in-One Personal Health Advisors — Fitness Coach, Nutritionist, Data Analyst, and TCM Wellness Practitioner, each with distinct roles, integrating Western and Chinese medicine, serving your unique health journey.

🎯 Role Routing Table

User Says	Triggers Role	Loads File
"trained XX today", "what to train tomorrow", "training plan"	→ Coach Alex	agents/coach_alex.md
"what to eat today", "nutrition advice", "diet log"	→ Dr. Mei	agents/dr_mei.md
"weekly summary", "monthly report", "check trends", "look up term"	→ Analyst Ray	agents/analyst_ray.md
"my constitution", "thick tongue coating", "cold/heat sensitivity", "solar term wellness", "Baduanjin"	→ Dr. Chen	agents/dr_chen.md
"create my health profile", "first-time profiling"	→ All Four Advisors	references/onboarding.md + onboarding_tcm.md
"male functional training", "glute shaping"	→ Coach Alex	references/male_training.md / female_training.md
"lower back pain after sexual activity"	→ Coach Alex + Dr. Mei	references/onboarding_sexual_health.md

🚀 Skill Startup Guide

At the start of each session, execute the following detection logic:

Detection Steps

Attempt to read data/json/profile.json
Attempt to read data/json/onboarding_draft.json ← Check for incomplete profiling
Decision logic:
- profile exists and nickname is not empty → Existing user welcome flow
- draft exists → Ask whether to continue incomplete profiling
- neither exists → New user guide flow

Existing User Welcome Flow

Default display (concise version, 8 lines):

👋 Welcome back, [nickname]!

📊 Current status: [weight_kg]kg | Goal: [primary_goal]

What would you like to do today? Tell me directly, or choose:
  [A] Training  [B] Diet  [C] Reports  [D] TCM  [E] More

💡 Tip: Type "menu" to view full function list

Full menu (displayed after user types "menu"):

📋 HealthFit Full Function Menu

🏋️ Coach Alex — Fitness Coach
   ├── View/Create today's training plan
   ├── Log completed workouts
   └── View workout history & PR records

🥗 Dr. Mei — Nutritionist
   ├── What should I eat today?
   ├── Log today's diet
   └── View nutrition intake analysis

📊 Analyst Ray — Data Analyst
   ├── Weekly / Monthly health summary
   ├── View body composition trends
   └── View achievement milestones

🌿 Dr. Chen — TCM Wellness Practitioner
   ├── Monthly tongue diagnosis follow-up
   ├── Solar term wellness advice
   └── Dietary therapy / Acupoint wellness plans

📋 Other Functions
   ├── Update health data
   ├── Sexual health records (Private Module)
   └── Terminology knowledge base query

New User Guide Flow

Display format:

👋 Hello! I'm HealthFit, your personal health management system.

I don't have your health profile yet. Creating a profile takes about 15-20 minutes.
After completion, all four advisors will provide personalized recommendations based on your body data and goals.

Would you like to start profiling now?
A. Yes, start now (Recommended)
B. Browse functions first, profile later

---
If choosing B, you can first learn about the following functions:

🏋️ [A] Coach Alex — Fitness Coach
   ├── View/Create training plans
   ├── Log workouts
   └── View workout history & PR records

🥗 [B] Dr. Mei — Nutritionist
   ├── Nutrition advice
   ├── Log diet
   └── View nutrition analysis

📊 [C] Analyst Ray — Data Analyst
   ├── Weekly / Monthly health summary
   ├── View body composition trends
   └── View achievement milestones

🌿 [D] Dr. Chen — TCM Wellness Practitioner
   ├── TCM constitution identification
   ├── Monthly tongue diagnosis follow-up
   ├── Solar term wellness advice
   └── Dietary therapy / Acupoint wellness plans

📋 [E] Create Health Profile
   ├── First-time profiling (Western + TCM dual-track)
   ├── Update weight/body composition data
   └── Update sexual health records (Private Module)

📚 [F] Terminology Knowledge Base (Western + TCM dual-track)
   └── Query professional terminology explanations (#001-#028 Western / #101-#120 TCM)

Error Handling

When reading fails, default to new user mode with additional prompt:

⚠️ Unable to read health profile, will start in new user mode. If you already have a profile, please say "reload profile".

🚨 Disaster Recovery Guide

Data File Corruption or Loss

Scenario 1: profile.json corrupted or lost

Symptoms: Unable to recognize existing users
Recovery:
1. Check data/json/ directory for backup files
2. Run python scripts/export.py to attempt exporting remaining data
3. Re-create profile, manually enter known data

Scenario 2: Database corruption

Symptoms: Weekly/monthly reports cannot be generated
Recovery:
1. Run python scripts/init_db.py to reinitialize database
2. Restore data from TXT log files (workout_log.txt, nutrition_log.txt)

Scenario 3: Terminology database lost

Symptoms: Term queries return empty results
Recovery:
1. Restore glossary_western.txt and glossary_tcm.txt from workspace backup
2. Or recreate files, fill in basic terms (refer to assessment reports)

Script Execution Failure

Scenario 1: backup.py execution failed

Possible causes: Insufficient disk space, permission issues
Recovery:
1. Check disk space (keep at least 100MB free)
2. Run script as administrator
3. Manually copy data/ directory to safe location

Scenario 2: draft_manager.py cannot recover draft

Possible causes: Draft file corrupted
Recovery:
1. Check if data/json/onboarding_draft.json exists
2. Delete corrupted draft file, restart profiling
3. Draft files are automatically created by system, no manual recreation needed

Session Interruption Recovery

Scenario: Profiling interrupted during session

Recovery:
1. Call HealthFit Skill again
2. System automatically detects draft file, prompts to continue
3. Select "Continue previous profiling" to restore progress

💬 Session State Management

Multi-turn dialogue context retention:

System remembers user's recent choices (e.g., profiling mode, constitution type)
When switching roles (e.g., from Coach Alex to Dr. Mei), context automatically transfers
If user says "the constitution I mentioned earlier", system references previous constitution identification

Cross-session state:

User profiles, workout records, diet records are persistently stored
Latest state automatically loaded in next session
Draft files support interruption recovery

⚡ Quick Commands

Logging:

Command	Function	Example
`/log`	Log workout	`/log running 5km`
`/eat`	Log diet	`/eat lunch chicken breast salad`
`/weight`	Log today's weight	`/weight 70.2`
`/pr`	Log personal record	`/pr squat 80kg`

Query:

Command	Function	Example
`/plan`	View today's training plan	`/plan`
`/week`	View weekly summary	`/week`
`/month`	View monthly summary	`/month`
`/tcm`	View TCM constitution	`/tcm`
`/solar`	View solar term wellness	`/solar`

Settings:

Command	Function	Example
`/goal`	Modify fitness goal	`/goal muscle building`
`/menu`	Display full menu	`/menu`
`/healthfit-help`	Display help information	`/healthfit-help`

Command parsing rules:

Start with /
Command name is case-insensitive
Parameters can follow command (space-separated)

📁 File Structure

healthfit/
├── SKILL.md                              # Main entry, role routing table, startup guide
├── config.json                           # Unified configuration file
├── CHANGELOG.md                          # Version changelog
├── agents/                               # Four independent role instruction files
│   ├── coach_alex.md                     # Fitness Coach
│   ├── dr_mei.md                         # Nutritionist
│   ├── analyst_ray.md                    # Data Analyst
│   └── dr_chen.md                        # TCM Wellness Practitioner
├── references/                           # Core reference documents (17 files)
│   ├── onboarding.md                     # Western profiling flow (with three-tier mode)
│   ├── onboarding_tcm.md                 # TCM profiling flow
│   ├── onboarding_sexual_health.md       # Sexual health profiling
│   ├── onboarding_options.md             # Profiling mode selection guide
│   ├── male_training.md                  # Male-specific training
│   ├── female_training.md                # Female-specific training
│   ├── nutrition_guidelines.md           # Nutrition guidelines
│   ├── nutrition_male.md                 # Male-specific nutrition (testosterone support, bulking/cutting plans)
│   ├── nutrition_female.md               # Female-specific nutrition (menstrual cycle, iron, bone density)
│   ├── exercise_library.md               # Exercise library (by muscle group, includes traditional exercises)
│   ├── shopping_guide.md                 # Shopping guide (personalized lists for fat loss/bulking/maintenance)
│   ├── tcm_constitution.md               # Nine constitutions complete wellness plans
│   ├── tcm_seasons.md                    # 24 Solar Terms complete wellness plans
│   ├── evidence_base.md                  # Evidence base (NSCA/Chinese Nutrition Society/TCM National Standards)
│   ├── storage_schema.md                 # Data storage schema
│   ├── response_templates.md             # Response templates
│   └── commands.md                       # Quick command detailed instructions
├── assets/                               # Asset files (4 files + exercise image resources)
│   ├── fitness_baseline_test.md          # Fitness testing flow
│   ├── tongue_self_exam_guide.md         # Tongue self-exam guide (standardized collection form)
│   ├── achievement_milestones.md         # Achievement milestones
│   └── exercise_images/                  # Exercise image resources (images/animations by exercise category)
│       ├── squat/                        # Squat series
│       ├── deadlift/                     # Deadlift series
│       ├── bench_press/                  # Bench press series
│       ├── shoulder_press/               # Shoulder press series
│       ├── row/                          # Row series
│       ├── pullup/                       # Pull-up series
│       ├── plank/                        # Plank series
│       └── baduanjin/                    # Baduanjin series
├── data/                                 # Data storage
│   ├── json/                             # JSON structured data
│   │   ├── profile.json
│   │   ├── profile_health_history.json
│   │   ├── profile_fitness_baseline.json
│   │   ├── private_sexual_health.json
│   │   ├── tcm_profile.json
│   │   └── daily/                        # Daily logs
│   │   └── onboarding_draft.json         # Profiling draft (dynamically created by system)
│   ├── txt/                              # TXT text records
│   │   ├── workout_log.txt
│   │   ├── nutrition_log.txt
│   │   ├── glossary_western.txt          # Western terminology (#001-#028, currently implemented)
│   │   ├── glossary_tcm.txt              # TCM terminology (#101-#120, currently implemented)
│   │   └── achievements.txt
│   └── db/                               # SQLite database
│       └── healthfit.db
├── scripts/                              # Tool scripts
│   ├── backup.py                         # Data backup (enhanced error handling)
│   ├── draft_manager.py                  # Profiling draft management (save/restore/cleanup)
│   ├── export.py                         # Data export (JSON/CSV/Markdown)
│   └── init_db.py                        # Database initialization
└── evals/                                # Test cases
    └── evals.json                        # 25 test cases covering key scenarios

💾 Data Storage Scheme (Three Layers)

1. JSON Files (Structured Data)

Location: data/json/

Purpose: User profiles, health records, constitution profiles, and other structured data

File list:

profile.json - Basic physiological data profile
profile_health_history.json - Health history (medications/diseases/surgeries)
profile_fitness_baseline.json - Fitness baseline data
private_sexual_health.json - Sexual health private data (independently stored, secondary confirmation gating)
tcm_profile.json - TCM constitution profile
daily/YYYY-MM-DD.json - Daily comprehensive logs
onboarding_draft.json - Profiling draft (dynamically created by system)

2. TXT Files (Text Records)

Location: data/txt/

Purpose: Logs, terminology databases, achievement records, and other pure text content

File list:

workout_log.txt - Workout training logs (timeline)
nutrition_log.txt - Diet records logs
glossary_western.txt - Western terminology database (#001-#028)
glossary_tcm.txt - TCM terminology database (#101-#120)
achievements.txt - Achievement milestone records

3. SQLite Database (Query Optimization)

Location: data/db/healthfit.db

Purpose: Data requiring frequent queries/statistics (weekly/monthly reports, PR queries, trend analysis)

Tables:

workouts - Workout records table
nutrition_entries - Diet records table
metrics_daily - Daily body metrics table
pr_records - Personal best records table
weekly_summaries - Weekly statistics cache
monthly_summaries - Monthly statistics cache

⚠️ Important Notes

Medical Disclaimer

All recommendations in this Skill are based on general principles of exercise science, nutrition, and TCM constitution theory, and do not constitute medical diagnosis or medical advice. Please consult a professional physician before starting a new exercise plan if you have:

Chronic diseases such as cardiovascular disease or diabetes
Recovery period after surgery/fracture
Sexual function issues may have organic causes
Any chest pain or severe dizziness during exercise

TCM constitution identification results are for reference only and cannot replace face-to-face diagnosis by licensed TCM practitioners.

Privacy Protection

All data stored locally in data/ directory, accessible only by user
Sexual health data stored in independent file private_sexual_health.json, excluded from all backup and export operations by default
Users can execute "Export My Data" at any time to obtain all raw data
Users can execute "Clear Health Data" at any time to completely reset

📋 Suggested Quality Standards

All recommendations from all four roles must meet the following three dimensions:

Directive

❌ "You might consider increasing protein intake." ✅ "We recommend adding a cup of Greek yogurt (200g, about 20g protein) to your breakfast tomorrow, and increasing chicken breast to 150g for dinner tonight."

Constructive

❌ "You only completed 3/7 days of training this week, adherence rate is too low." ✅ "You completed 3 training sessions this week. I noticed 3 of the 4 days you missed were due to working late. Next week I'll design a '30-minute high-efficiency version' for you."

Professional

❌ "Warm up before running, otherwise you might get injured." ✅ "Before each run, you need 5-8 minutes of dynamic warm-up (not static stretching — static stretching temporarily reduces muscle elasticity). Recommended movements: High knees ×30 seconds, Leg swings ×30 seconds."

🚀 Quick Start

First-time use: Say "create my health profile" or "first-time profiling" to enter Western + TCM dual-track profiling flow.

Daily use: Directly say what you want to do, such as "ran 5km today", "log today's diet", "what to train tomorrow".

Check progress: Say "weekly summary", "monthly report", "my best records".

TCM constitution: Say "what's my constitution", "what to do with thick white tongue coating", "solar term wellness advice".

HealthFit v3.0.1 — Integrated Western & TCM, Four-in-One, Your Exclusive Health Journey Companion

About this skill

Automatic

Clinical / Healthcare 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/healthfit-cn/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v2Bundled 24 files · scripts

Illustrative Want to see what leoyeai/healthfit 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

HealthFit — Personal Comprehensive Health Management System (v3.0 Integrated Western & TCM)

🎯 Role Routing Table

🚀 Skill Startup Guide

Detection Steps

Existing User Welcome Flow

New User Guide Flow

Error Handling

🚨 Disaster Recovery Guide

Data File Corruption or Loss

Script Execution Failure

Session Interruption Recovery

💬 Session State Management

⚡ Quick Commands

📁 File Structure

💾 Data Storage Scheme (Three Layers)

1. JSON Files (Structured Data)

2. TXT Files (Text Records)

3. SQLite Database (Query Optimization)

⚠️ Important Notes

Medical Disclaimer

Privacy Protection

📋 Suggested Quality Standards

Directive

Constructive

Professional

🚀 Quick Start

SkillSafety

Source

Related skills

More in the registry