Ready to supercharge your AI agents?

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

ISO 13485 Certification Documentation Assistant · FreedomIntelligence | DecimalAI

Legalby FreedomIntelligence

ISO 13485 Certification Documentation Assistant

Comprehensive toolkit for preparing ISO 13485 certification documentation for medical device Quality Management Systems.

SkillScore

SkillScore36/100

Test results 36

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

5%36%of test cases passed +32 pts

Without skill1 of 22

With skill8 of 22

7 fixed1 passed either way14 still failing0 broke

Measured on gemini-3.6-flash7/26/2026v1

Track record

Agent runs: 50; All time

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 iso-13485-certification
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("iso-13485-certification")
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 iso-13485-certification

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/iso-13485-certification/SKILL.md https://app.decimal.ai/s/iso-13485-certification/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/iso-13485-certification/SKILL.md

This gets SKILL.md only. The skill's 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/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/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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("iso-13485-certification")
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/iso-13485-certification/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/iso-13485-certification/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 5 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 iso-13485-certification

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/iso-13485-certification/SKILL.md https://app.decimal.ai/s/iso-13485-certification/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/iso-13485-certification/SKILL.md

This gets SKILL.md only. The skill's 5 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/iso-13485-certification/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/iso-13485-certification.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/26/2026
Source: FreedomIntelligence/OpenClaw-Medical-Skills ↗
License: MIT license

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

ISO 13485 Certification Documentation Assistant

Overview

This skill helps medical device manufacturers prepare comprehensive documentation for ISO 13485:2016 certification. It provides tools, templates, references, and guidance to create, review, and gap-analyze all required Quality Management System (QMS) documentation.

What this skill provides:

Gap analysis of existing documentation
Templates for all mandatory documents
Comprehensive requirements guidance
Step-by-step documentation creation
Identification of missing documentation
Compliance checklists

When to use this skill:

Starting ISO 13485 certification process
Conducting gap analysis against ISO 13485
Creating or updating QMS documentation
Preparing for certification audit
Transitioning from FDA QSR to QMSR
Harmonizing with EU MDR requirements

Core Workflow

1. Assess Current State (Gap Analysis)

When to start here: User has existing documentation and needs to identify gaps

Process:

Collect existing documentation:
- Ask user to provide directory of current QMS documents
- Documents can be in any format (.txt, .md, .doc, .docx, .pdf)
- Include any procedures, manuals, work instructions, forms

Run gap analysis script:

python scripts/gap_analyzer.py --docs-dir <path_to_docs> --output gap-report.json

Review results:
- Identify which of the 31 required procedures are present
- Identify missing key documents (Quality Manual, MDF, etc.)
- Calculate compliance percentage
- Prioritize missing documentation
Present findings to user:
- Summarize what exists
- Clearly list what's missing
- Provide prioritized action plan
- Estimate effort required

Output: Comprehensive gap analysis report with prioritized action items

2. Understand Requirements (Reference Consultation)

When to use: User needs to understand specific ISO 13485 requirements

Available references:

references/iso-13485-requirements.md - Complete clause-by-clause breakdown
references/mandatory-documents.md - All 31 required procedures explained
references/gap-analysis-checklist.md - Detailed compliance checklist
references/quality-manual-guide.md - How to create Quality Manual

How to use:

For specific clause questions:
- Read relevant section from iso-13485-requirements.md
- Explain requirements in plain language
- Provide practical examples
For document requirements:
- Consult mandatory-documents.md
- Explain what must be documented
- Clarify when documents are applicable vs. excludable
For implementation guidance:
- Use quality-manual-guide.md for policy-level documents
- Provide step-by-step creation process
- Show examples of good vs. poor implementation

Key reference sections to know:

Clause 4: QMS requirements, documentation, risk management, software validation
Clause 5: Management responsibility, quality policy, objectives, management review
Clause 6: Resources, competence, training, infrastructure
Clause 7: Product realization, design, purchasing, production, traceability
Clause 8: Measurement, audits, CAPA, complaints, data analysis

3. Create Documentation (Template-Based Generation)

When to use: User needs to create specific QMS documents

Available templates:

Quality Manual: assets/templates/quality-manual-template.md
CAPA Procedure: assets/templates/procedures/CAPA-procedure-template.md
Document Control: assets/templates/procedures/document-control-procedure-template.md

Process for document creation:

Identify what needs to be created:
- Based on gap analysis or user request
- Prioritize critical documents first (Quality Manual, CAPA, Complaints, Audits)
Select appropriate template:
- Use Quality Manual template for QM
- Use procedure templates as examples for SOPs
- Adapt structure to organization's needs
Customize template with user-specific information:
- Replace all placeholder text: [COMPANY NAME], [DATE], [NAME], etc.
- Tailor scope to user's actual operations
- Add or remove sections based on applicability
- Ensure consistency with organization's processes
Key customization areas:
- Company information and addresses
- Product types and classifications
- Applicable regulatory requirements
- Organization structure and responsibilities
- Actual processes and procedures
- Document numbering schemes
- Exclusions and justifications
Validate completeness:
- All required sections present
- All placeholders replaced
- Cross-references correct
- Approval sections complete

Document creation priority order:

Phase 1 - Foundation (Critical):

Quality Manual
Quality Policy and Objectives
Document Control procedure
Record Control procedure

Phase 2 - Core Processes (High Priority): 5. Corrective and Preventive Action (CAPA) 6. Complaint Handling 7. Internal Audit 8. Management Review 9. Risk Management

Phase 3 - Product Realization (High Priority): 10. Design and Development (if applicable) 11. Purchasing 12. Production and Service Provision 13. Control of Nonconforming Product

Phase 4 - Supporting Processes (Medium Priority): 14. Training and Competence 15. Calibration/Control of M&M Equipment 16. Process Validation 17. Product Identification and Traceability

Phase 5 - Additional Requirements (Medium Priority): 18. Feedback and Post-Market Surveillance 19. Regulatory Reporting 20. Customer Communication 21. Data Analysis

Phase 6 - Specialized (If Applicable): 22. Installation (if applicable) 23. Servicing (if applicable) 24. Sterilization (if applicable) 25. Contamination Control (if applicable)

4. Develop Specific Documents

Creating a Quality Manual

Process:

Read the comprehensive guide:
- Read references/quality-manual-guide.md in full
- Understand structure and required content
- Review examples provided
Gather organization information:
- Legal company name and addresses
- Product types and classifications
- Organizational structure
- Applicable regulations
- Scope of operations
- Any exclusions needed
Use template:
- Start with assets/templates/quality-manual-template.md
- Follow structure exactly (required by ISO 13485)
- Replace all placeholders
Complete required sections:
- Section 0: Document control, approvals
- Section 1: Introduction, company overview
- Section 2: Scope and exclusions (critical - must justify exclusions)
- Section 3: Quality Policy (must be signed by top management)
- Sections 4-8: Address each ISO 13485 clause at policy level
- Appendices: Procedure list, org chart, process map, definitions
Key requirements:
- Must reference all 31 documented procedures (Appendix A)
- Must describe process interactions (Appendix C - create process map)
- Must define documentation structure (Section 4.2)
- Must justify any exclusions (Section 2.4)
Validation checklist:
- All required content per ISO 13485 Clause 4.2.2
- Quality Policy signed by top management
- All exclusions justified
- All procedures listed in Appendix A
- Process map included
- Organization chart included

Creating Procedures (SOPs)

General approach for all procedures:

Understand the requirement:
- Read relevant clause in references/iso-13485-requirements.md
- Understand WHAT must be documented
- Identify WHO, WHEN, WHERE for your organization
Use template structure:
- Follow CAPA or Document Control templates as examples
- Standard sections: Purpose, Scope, Definitions, Responsibilities, Procedure, Records, References
- Keep procedures clear and actionable
Define responsibilities clearly:
- Identify specific roles (not names)
- Define responsibilities for each role
- Ensure coverage of all required activities
Document the "what" not excessive "how":
- Procedures should define WHAT must be done
- Detailed HOW-TO goes in Work Instructions (Tier 3)
- Strike balance between guidance and flexibility
Include required elements:
- All elements specified in ISO 13485 clause
- Records that must be maintained
- Responsibilities for each activity
- References to related documents

Example: Creating CAPA Procedure

Read ISO 13485 Clauses 8.5.2 and 8.5.3 from references
Use assets/templates/procedures/CAPA-procedure-template.md
Customize:
- CAPA prioritization criteria for your organization
- Root cause analysis methods you'll use
- Approval authorities and responsibilities
- Timeframes based on your operations
- Integration with complaint handling, audits, etc.
Add forms as attachments:
- CAPA Request Form
- Root Cause Analysis Worksheet
- Action Plan Template
- Effectiveness Verification Checklist

Creating Medical Device Files (MDF)

What is an MDF:

File for each medical device type or family
Replaces separate DHF, DMR, DHR (per FDA QMSR harmonization)
Contains all documentation about the device

Required contents per ISO 13485 Clause 4.2.3:

General description and intended use
Label and instructions for use specifications
Product specifications
Manufacturing specifications
Procedures for purchasing, manufacturing, servicing
Procedures for measuring and monitoring
Installation requirements (if applicable)
Risk management file(s)
Verification and validation information
Design and development file(s) (when applicable)

Process:

Identify each device type or family
Create MDF structure (folder or binder)
Collect or create each required element
Ensure traceability between documents
Maintain as living document (update with changes)

5. Conduct Comprehensive Gap Analysis

When to use: User wants detailed assessment of all requirements

Process:

Use comprehensive checklist:
- Open references/gap-analysis-checklist.md
- Work through clause by clause
- Mark status for each requirement: Compliant, Partial, Non-compliant, N/A
For each clause:
- Read requirement description
- Identify existing evidence
- Note gaps or deficiencies
- Define action required
- Assign responsibility and target date
Summarize by clause:
- Calculate compliance percentage per clause
- Identify highest-risk gaps
- Prioritize actions
Create action plan:
- List all gaps
- Prioritize: Critical > High > Medium > Low
- Assign owners and dates
- Estimate resources needed
Output:
- Completed gap analysis checklist
- Summary report with compliance percentages
- Prioritized action plan
- Timeline and milestones

Common Scenarios

Scenario 1: Starting from Scratch

User request: "We're a medical device startup and need to implement ISO 13485. Where do we start?"

Approach:

Explain the journey:
- ISO 13485 requires comprehensive QMS documentation
- Typically 6-12 months for full implementation
- Can be done incrementally
Start with foundation:
- Quality Policy and Objectives
- Quality Manual
- Organization structure and responsibilities
Follow the priority order:
- Use Phase 1-6 priority list above
- Create documents in logical sequence
- Build on previously created documents
Key milestones:
- Month 1-2: Foundation documents (Quality Manual, policies)
- Month 3-4: Core processes (CAPA, Complaints, Audits)
- Month 5-6: Product realization processes
- Month 7-8: Supporting processes
- Month 9-10: Internal audits and refinement
- Month 11-12: Management review and certification audit

Scenario 2: Gap Analysis for Existing QMS

User request: "We have some procedures but don't know what we're missing for ISO 13485."

Approach:

Run automated gap analysis:
- Ask for document directory
- Run scripts/gap_analyzer.py
- Review automated findings
Conduct detailed assessment:
- Use comprehensive checklist for user's specific situation
- Go deeper than automated analysis
- Assess quality of existing documents, not just presence
Provide prioritized gap list:
- Missing mandatory procedures
- Incomplete procedures
- Quality issues with existing documents
- Missing records or forms
Create remediation plan:
- High priority: Safety-related, regulatory-required
- Medium priority: Core QMS processes
- Low priority: Improvement opportunities

Scenario 3: Creating Specific Document

User request: "Help me create a CAPA procedure."

Approach:

Explain requirements:
- Read ISO 13485 Clauses 8.5.2 and 8.5.3 from references
- Explain what must be in CAPA procedure
- Provide examples of good CAPA processes
Use template:
- Start with CAPA procedure template
- Explain each section's purpose
- Show what needs customization
Gather user-specific info:
- How are CAPAs initiated in their organization?
- Who are the responsible parties?
- What prioritization criteria make sense?
- What RCA methods will they use?
- What are appropriate timeframes?
Create customized procedure:
- Replace all placeholders
- Adapt to user's processes
- Ensure completeness
Add supporting materials:
- CAPA request form
- RCA worksheets
- Action plan template
- Effectiveness verification checklist

Scenario 4: Updating for Regulatory Changes

User request: "We need to update our QMS for FDA QMSR harmonization."

Approach:

Explain changes:
- FDA 21 CFR Part 820 harmonized with ISO 13485
- Now called QMSR (effective Feb 2, 2026)
- Key change: Medical Device File replaces DHF/DMR/DHR
Review current documentation:
- Identify documents referencing QSR
- Find separate DHF, DMR, DHR structures
- Check for ISO 13485 compliance gaps
Update strategy:
- Update references from QSR to QMSR
- Consolidate DHF/DMR/DHR into Medical Device Files
- Add any missing ISO 13485 requirements
- Maintain backward compatibility during transition
Create transition plan:
- Update Quality Manual
- Update MDF procedure
- Reorganize device history files
- Train personnel on changes

Scenario 5: Preparing for Certification Audit

User request: "We have our documentation ready. How do we prepare for the certification audit?"

Approach:

Conduct readiness assessment:
- Use comprehensive gap analysis checklist
- Review all documentation for completeness
- Verify records exist for all required items
- Check for consistent implementation
Pre-audit checklist:
- All 31 procedures documented and approved
- Quality Manual complete with all required content
- Medical Device Files complete for all products
- Internal audit completed with findings addressed
- Management review completed
- Personnel trained on QMS procedures
- Records maintained per retention requirements
- CAPA system functional with effectiveness demonstrated
- Complaints system operational
Conduct mock audit:
- Use ISO 13485 requirements as audit criteria
- Sample records to verify consistent implementation
- Interview personnel to verify understanding
- Identify any non-conformances
Address findings:
- Correct any deficiencies
- Document corrections
- Verify effectiveness
Final preparation:
- Brief management and staff
- Prepare audit schedule
- Organize evidence and records
- Designate escorts and support personnel

Best Practices

Document Development

Start at policy level, then add detail:
- Quality Manual = policy level
- Procedures = what, who, when
- Work Instructions = detailed how-to
- Forms = data collection
Maintain consistency:
- Use same terminology throughout
- Cross-reference related documents
- Keep numbering scheme consistent
- Update all related documents together
Write for your audience:
- Clear, simple language
- Avoid jargon
- Define technical terms
- Provide examples where helpful
Make procedures usable:
- Action-oriented language
- Logical flow
- Clear responsibilities
- Realistic timeframes

Exclusions

When you can exclude:

Design and development (if contract manufacturer only)
Installation (if product requires no installation)
Servicing (if not offered)
Sterilization (if non-sterile product)

Justification requirements:

Must be in Quality Manual
Must explain why excluded
Cannot exclude if process performed
Cannot affect ability to provide safe, effective devices

Example good justification:

"Clause 7.3 Design and Development is excluded. ABC Company operates as a contract manufacturer and produces medical devices according to complete design specifications provided by customers. All design activities are performed by the customer and ABC Company has no responsibility for design inputs, outputs, verification, validation, or design changes."

Example poor justification:

"We don't do design." (Too brief, doesn't explain why or demonstrate no impact)

Common Mistakes to Avoid

Copying ISO 13485 text verbatim
- Write in your own words
- Describe YOUR processes
- Make it actionable for your organization
Making procedures too detailed
- Procedures should be stable
- Excessive detail belongs in work instructions
- Balance guidance with flexibility
Creating documents in isolation
- Ensure consistency across QMS
- Cross-reference related documents
- Build on previously created documents
Forgetting records
- Every procedure should specify records
- Define retention requirements
- Ensure records actually maintained
Inadequate approval
- Quality Manual must be signed by top management
- All procedures must be properly approved
- Train staff before documents become effective

Resources

scripts/

gap_analyzer.py - Automated tool to analyze existing documentation and identify gaps against ISO 13485 requirements

references/

iso-13485-requirements.md - Complete breakdown of ISO 13485:2016 requirements clause by clause
mandatory-documents.md - Detailed list of all 31 required procedures plus other mandatory documents
gap-analysis-checklist.md - Comprehensive checklist for detailed gap assessment
quality-manual-guide.md - Step-by-step guide for creating a compliant Quality Manual

assets/templates/

quality-manual-template.md - Complete template for Quality Manual with all required sections
procedures/CAPA-procedure-template.md - Example CAPA procedure following best practices
procedures/document-control-procedure-template.md - Example document control procedure

Quick Reference

The 31 Required Documented Procedures

Risk Management (4.1.5)
Software Validation (4.1.6)
Control of Documents (4.2.4)
Control of Records (4.2.5)
Internal Communication (5.5.3)
Management Review (5.6.1)
Human Resources/Competence (6.2)
Infrastructure Maintenance (6.3) - when applicable
Contamination Control (6.4.2) - when applicable
Customer Communication (7.2.3)
Design and Development (7.3.1-10) - when applicable
Purchasing (7.4.1)
Verification of Purchased Product (7.4.3)
Production Control (7.5.1)
Product Cleanliness (7.5.2) - when applicable
Installation (7.5.3) - when applicable
Servicing (7.5.4) - when applicable
Process Validation (7.5.6) - when applicable
Sterilization Validation (7.5.7) - when applicable
Product Identification (7.5.8)
Traceability (7.5.9)
Customer Property (7.5.10) - when applicable
Preservation of Product (7.5.11)
Control of M&M Equipment (7.6)
Feedback (8.2.1)
Complaint Handling (8.2.2)
Regulatory Reporting (8.2.3)
Internal Audit (8.2.4)
Process Monitoring (8.2.5)
Product Monitoring (8.2.6)
Control of Nonconforming Product (8.3)
Corrective Action (8.5.2)
Preventive Action (8.5.3)

(Note: Traditional count is "31 procedures" though list shows more because some are conditional)

Key Regulatory Requirements

FDA (United States):

21 CFR Part 820 (now QMSR) - harmonized with ISO 13485 as of Feb 2026
Device classification determines requirements
Establishment registration and device listing required

EU (European Union):

MDR 2017/745 (Medical Devices Regulation)
IVDR 2017/746 (In Vitro Diagnostic Regulation)
Technical documentation requirements
CE marking requirements

Canada:

Canadian Medical Devices Regulations (SOR/98-282)
Device classification system
Medical Device Establishment License (MDEL)

Other Regions:

Australia TGA, Japan PMDA, China NMPA, etc.
Often require or recognize ISO 13485 certification

Document Retention

Minimum retention: Lifetime of medical device as defined by organization

Typical retention periods:

Design documents: Life of device + 5-10 years
Manufacturing records: Life of device
Complaint records: Life of device + 5-10 years
CAPA records: 5-10 years minimum
Calibration records: Retention period of equipment + 1 calibration cycle

Always comply with applicable regulatory requirements which may specify longer periods.

Getting Started

First-time users should:

Read references/iso-13485-requirements.md to understand the standard
If you have existing documentation, run gap analysis script
Create Quality Manual using template and guide
Develop procedures in priority order
Use comprehensive checklist for final validation

For specific tasks:

Creating Quality Manual → See Section 4 and use quality-manual-guide.md
Creating CAPA procedure → See Section 4 and use CAPA template
Gap analysis → See Section 1 and 5
Understanding requirements → See Section 2

Need help? Start by describing your situation: what stage you're at, what you have, and what you need to create.

When it activates

Automatically, when a task matches. Use when users need help with ISO 13485 QMS documentation, including (1) conducting gap analysis of existing documentation, (2) creating Quality Manuals, (3) developing required procedures and work instructions, (4) preparing Medical Device Files, (5) understanding ISO 13485 requirements, or (6) identifying missing documentation for medical device certification. Also use when

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 — 7/30/2026

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

FreedomIntelligence / OpenClaw-Medical-Skills

skills/iso-13485-certification/SKILL.md

View on GitHub ↗

License MIT licenseImported 8/1/2026Version v1Bundled 5 files · scripts

Illustrative Want to see what iso-13485-certification would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

ISO 13485 Certification Documentation Assistant

Overview

Core Workflow

1. Assess Current State (Gap Analysis)

2. Understand Requirements (Reference Consultation)

3. Create Documentation (Template-Based Generation)

4. Develop Specific Documents

Creating a Quality Manual

Creating Procedures (SOPs)

Creating Medical Device Files (MDF)

5. Conduct Comprehensive Gap Analysis

Common Scenarios

Scenario 1: Starting from Scratch

Scenario 2: Gap Analysis for Existing QMS

Scenario 3: Creating Specific Document

Scenario 4: Updating for Regulatory Changes

Scenario 5: Preparing for Certification Audit

Best Practices

Document Development

Exclusions

Common Mistakes to Avoid

Resources

scripts/

references/

assets/templates/

Quick Reference

The 31 Required Documented Procedures

Key Regulatory Requirements

Document Retention

Getting Started

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry