Ready to supercharge your AI agents?

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

Head of Regulatory Affairs · alirezarezvani | DecimalAI

Legalby alirezarezvani

Head of Regulatory Affairs

Senior Regulatory Affairs Manager for HealthTech and MedTech companies. Prepares FDA 510(k), De Novo, and PMA submission packages; analyzes regulatory pathways for new medical devices; drafts responses to FDA deficiency letters and Notified Body queries; develops CE marking technical documentation under EU MDR 2017/745; coordinates multi-market approval strategies across FDA, EU, Health Canada, PMDA, and NMPA; and maintains regulatory intelligence on evolving standards.

Never made a case worse

SkillScore

SkillScore63/100

Test results 63

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

38%63%of test cases passed +25 pts

Without skill9 of 24

With skill15 of 24

6 fixed9 passed either way9 still failing0 broke

Measured on gemini-3.6-flash8/10/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe want to check current submission milestones across US, EU, and Canadian filings using the regulatory tracking utility script. What exact command-line command runs the tracker status report, and what key columns are printed?

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 alirezarezvani-regulatory-affairs-head
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("alirezarezvani-regulatory-affairs-head")
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 alirezarezvani-regulatory-affairs-head

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/alirezarezvani-regulatory-affairs-head/SKILL.md https://app.decimal.ai/s/alirezarezvani-regulatory-affairs-head/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/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/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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("alirezarezvani-regulatory-affairs-head")
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/alirezarezvani-regulatory-affairs-head/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/alirezarezvani-regulatory-affairs-head/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 alirezarezvani-regulatory-affairs-head

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/alirezarezvani-regulatory-affairs-head/SKILL.md https://app.decimal.ai/s/alirezarezvani-regulatory-affairs-head/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/alirezarezvani-regulatory-affairs-head/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/alirezarezvani-regulatory-affairs-head/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/alirezarezvani-regulatory-affairs-head.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 8/10/2026
Source: alirezarezvani/claude-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

Head of Regulatory Affairs

Regulatory strategy development, submission management, and global market access for medical device organizations.

Regulatory Strategy Workflow
FDA Submission Workflow
EU MDR Submission Workflow
Global Market Access Workflow
Regulatory Intelligence Workflow
Decision Frameworks
Tools and References

Regulatory Strategy Workflow

Develop regulatory strategy aligned with business objectives and product characteristics.

Workflow: New Product Regulatory Strategy

Gather product information:
- Intended use and indications
- Device classification (risk level)
- Technology platform
- Target markets and timeline
Identify applicable regulations per target market:
- FDA (US): 21 CFR Part 820, 510(k)/PMA/De Novo
- EU: MDR 2017/745, Notified Body requirements
- Other markets: Health Canada, PMDA, NMPA, TGA
Determine optimal regulatory pathway:
- Compare submission types (510(k) vs De Novo vs PMA)
- Assess predicate device availability
- Evaluate clinical evidence requirements
Develop regulatory timeline with milestones
Estimate resource requirements and budget
Identify regulatory risks and mitigation strategies
Obtain stakeholder alignment and approval
Validation: Strategy document approved; timeline accepted; resources allocated

Regulatory Pathway Selection Matrix

Factor	510(k)	De Novo	PMA
Predicate Available	Yes	No	N/A
Risk Level	Low-Moderate	Low-Moderate	High
Clinical Data	Usually not required	May be required	Required
Review Time	90 days (MDUFA)	150 days	180 days
User Fee	~$22K (2024)	~$135K	~$440K
Best For	Me-too devices	Novel low-risk	High-risk, novel

Regulatory Strategy Document Template

REGULATORY STRATEGY

Product: [Name]   Version: [X.X]   Date: [Date]

1. PRODUCT OVERVIEW
   Intended use: [One-sentence statement of intended patient population, body site, and clinical purpose]
   Device classification: [Class I / II / III]
   Technology: [Brief description, e.g., "AI-powered wound-imaging software, SaMD"]

2. TARGET MARKETS & TIMELINE
   | Market | Pathway        | Priority | Target Date |
   |--------|----------------|----------|-------------|
   | USA    | 510(k) / PMA   | 1        | Q1 20XX     |
   | EU     | Class [X] MDR  | 2        | Q2 20XX     |

3. REGULATORY PATHWAY RATIONALE
   FDA: [510(k) / De Novo / PMA] — Predicate: [K-number or "none"]
   EU:  Class [X] via [Annex IX / X / XI] — NB: [Name or TBD]
   Rationale: [2–3 sentences on key factors driving pathway choice]

4. CLINICAL EVIDENCE STRATEGY
   Requirements: [Summarize what each market needs, e.g., "510(k): bench + usability; EU Class IIb: PMCF study"]
   Approach: [Literature review / Prospective study / Combination]

5. RISKS AND MITIGATION
   | Risk                         | Prob | Impact | Mitigation                        |
   |------------------------------|------|--------|-----------------------------------|
   | Predicate delisted by FDA    | Low  | High   | Identify secondary predicate now  |
   | NB audit backlog             | Med  | Med    | Engage NB 6 months before target  |

6. RESOURCE REQUIREMENTS
   Budget: $[Amount]   Personnel: [FTEs]   External: [Consultants / CRO]

FDA Submission Workflow

Prepare and submit FDA regulatory applications.

Workflow: 510(k) Submission

Confirm 510(k) pathway suitability:
- Predicate device identified (note K-number, e.g., K213456)
- Substantial equivalence (SE) argument supportable on intended use and technological characteristics
- No new intended use or technology concerns triggering De Novo
Schedule and conduct Pre-Submission (Q-Sub) meeting if needed (see Pre-Sub Decision)
Compile submission package checklist:
- Cover letter with device name, product code, and predicate K-number
- Section 1: Administrative information (applicant, contact, 510(k) type)
- Section 2: Device description — include photos, dimensions, materials list
- Section 3: Intended use and indications for use
- Section 4: Substantial equivalence comparison table (see example below)
- Section 5: Performance testing — protocols, standards cited, pass/fail results
- Section 6: Biocompatibility summary (ISO 10993-1 risk assessment, if patient contact)
- Section 7: Software documentation (IEC 62304 level, cybersecurity per FDA guidance, if applicable)
- Section 8: Labeling — final draft IFU, device label
- Section 9: Summary and conclusion
Conduct internal review and quality check against FDA RTA checklist
Prepare eCopy per FDA format requirements (PDF bookmarked, eCopy cover page)
Submit via FDA ESG portal with user fee payment
Monitor MDUFA clock and respond to AI/RTA requests within deadlines
Validation: Submission accepted; MDUFA date received; tracking system updated

Substantial Equivalence Comparison Example

Characteristic	Predicate (K213456)	Subject Device	Same?	Notes
Intended use	Wound measurement	Wound measurement	✓	Identical
Technology	2D camera	2D + AI analysis	✗	New TC; address below
Energy type	Non-energized	Non-energized	✓
Patient contact	No	No	✓
SE conclusion	New TC does not raise new safety/effectiveness questions; bench data demonstrates equivalent accuracy (±2mm vs ±3mm predicate)

Workflow: PMA Submission

Confirm PMA pathway:
- Class III device or no suitable predicate
- Clinical data strategy defined
Complete IDE clinical study if required:
- IDE approval
- Clinical protocol execution
- Study report completion
Conduct Pre-Submission meeting
Compile PMA submission checklist:
- Volume I: Administrative, device description, manufacturing
- Volume II: Nonclinical studies (bench, animal, biocompatibility)
- Volume III: Clinical studies (IDE protocol, data, statistical analysis)
- Volume IV: Labeling
- Volume V: Manufacturing information, sterilization
Submit original PMA application
Address FDA questions and deficiencies
Prepare for FDA facility inspection
Validation: PMA approved; approval letter received; post-approval requirements documented

FDA Submission Timeline

Milestone	510(k)	De Novo	PMA
Pre-Sub Meeting	Day -90	Day -90	Day -120
Submission	Day 0	Day 0	Day 0
RTA Review	Day 15	Day 15	Day 45
Substantive Review	Days 15–90	Days 15–150	Days 45–180
Decision	Day 90	Day 150	Day 180

Common FDA Deficiencies and Prevention

Category	Common Issues	Prevention
Substantial Equivalence	Weak predicate comparison; no performance data	Build SE table with data column; cite recognized standards
Performance Testing	Incomplete protocols; missing worst-case rationale	Follow FDA-recognized standards; document worst-case justification
Biocompatibility	Missing endpoints; no ISO 10993-1 risk assessment	Complete ISO 10993-1 matrix before testing
Software	Inadequate hazard analysis; no cybersecurity bill of materials	IEC 62304 compliance + FDA cybersecurity guidance checklist
Labeling	Inconsistent claims vs. IFU; missing symbols standard	Cross-check label against IFU; cite ISO 15223-1 for symbols

See: references/fda-submission-guide.md

EU MDR Submission Workflow

Achieve CE marking under EU MDR 2017/745.

Workflow: MDR Technical Documentation

Confirm device classification per MDR Annex VIII
Select conformity assessment route based on class:
- Class I: Self-declaration
- Class IIa/IIb: Notified Body involvement
- Class III: Full NB assessment
Select and engage Notified Body (for Class IIa+) — see selection criteria below
Compile Technical Documentation per Annex II checklist:
- Annex II §1: Device description, intended purpose, UDI
- Annex II §2: Design and manufacturing information (drawings, BoM, process flows)
- Annex II §3: GSPR checklist — each requirement mapped to evidence (standard, test report, or justification)
- Annex II §4: Benefit-risk analysis and risk management file (ISO 14971)
- Annex II §5: Product verification and validation (test reports)
- Annex II §6: Post-market surveillance plan
- Annex XIV: Clinical evaluation report (CER) — literature, clinical data, equivalence justification
Establish and document QMS per ISO 13485
Submit application to Notified Body
Address NB questions and coordinate audit
Validation: CE certificate issued; Declaration of Conformity signed; EUDAMED registration complete

GSPR Checklist Row Example

GSPR Ref	Requirement	Standard / Guidance	Evidence Document	Status
Annex I §1	Safe design and manufacture	ISO 14971:2019	Risk Management File v2.1	Complete
Annex I §11.1	Devices with measuring function ±accuracy	EN ISO 15223-1	Performance Test Report PT-003	Complete
Annex I §17	Cybersecurity	MDCG 2019-16	Cybersecurity Assessment CS-001	In progress

Clinical Evidence Requirements by Class

Class	Clinical Requirement	Documentation
I	Clinical evaluation (CE)	CE report
IIa	CE with literature focus	CE report + PMCF plan
IIb	CE with clinical data	CE report + PMCF + clinical study (some)
III	CE with clinical investigation	CE report + PMCF + clinical investigation

Notified Body Selection Criteria

Scope: Designated for your specific device category
Capacity: Confirmed availability within target timeline
Experience: Track record with your technology type
Geography: Proximity for on-site audits
Cost: Fee structure transparency
Communication: Responsiveness and query turnaround

See: references/eu-mdr-submission-guide.md

Global Market Access Workflow

Coordinate regulatory approvals across international markets.

Workflow: Multi-Market Submission Strategy

Define target markets based on business priorities
Sequence markets for efficient evidence leverage:
- Phase 1: FDA + EU (reference markets)
- Phase 2: Recognition markets (Canada, Australia)
- Phase 3: Major markets (Japan, China)
- Phase 4: Emerging markets
Identify local requirements per market:
- Clinical data acceptability
- Local agent/representative needs
- Language and labeling requirements
Develop master technical file with localization plan
Establish in-country regulatory support
Execute parallel or sequential submissions
Track approvals and coordinate launches
Validation: All target market approvals obtained; registration database updated

Market Priority Matrix

Market	Size	Complexity	Recognition	Priority
USA	Large	High	N/A	1
EU	Large	High	N/A	1–2
Canada	Medium	Medium	MDSAP	2
Australia	Medium	Low	EU accepted	2
Japan	Large	High	Local clinical	3
China	Large	Very High	Local testing	3
Brazil	Medium	High	GMP inspection	3–4

Documentation Efficiency Strategy

Document Type	Single Source	Localization Required
Technical file core	Yes	Format adaptation
Risk management	Yes	None
Clinical data	Yes	Bridging assessment
QMS certificate	Yes (ISO 13485)	Market-specific audit
Labeling	Master label	Translation, local requirements
IFU	Master content	Translation, local symbols

See: references/global-regulatory-pathways.md

Regulatory Intelligence Workflow

Monitor and respond to regulatory changes affecting product portfolio.

Workflow: Regulatory Change Management

Monitor regulatory sources:
- FDA Federal Register, guidance documents
- EU Official Journal, MDCG guidance
- Notified Body communications
- Industry associations (AdvaMed, MedTech Europe)
Assess relevance to product portfolio
Evaluate impact:
- Timeline to compliance
- Resource requirements
- Product changes needed
Develop compliance action plan
Communicate to affected stakeholders
Implement required changes
Document compliance status
Validation: Compliance action plan approved; changes implemented on schedule

Regulatory Monitoring Sources

Source	Type	Frequency
FDA Federal Register	Regulations, guidance	Daily
FDA Device Database	510(k), PMA, recalls	Weekly
EU Official Journal	MDR/IVDR updates	Weekly
MDCG Guidance	EU implementation	As published
ISO/IEC	Standards updates	Quarterly
Notified Body	Audit findings, trends	Per interaction

Impact Assessment Template

REGULATORY CHANGE IMPACT ASSESSMENT

Change: [Description]   Source: [Regulation/Guidance]
Effective Date: [Date]  Assessment Date: [Date]  Assessed By: [Name]

AFFECTED PRODUCTS
| Product | Impact (H/M/L) | Action Required        | Due Date |
|---------|----------------|------------------------|----------|
| [Name]  | [H/M/L]        | [Specific action]      | [Date]   |

COMPLIANCE ACTIONS
1. [Action] — Owner: [Name] — Due: [Date]
2. [Action] — Owner: [Name] — Due: [Date]

RESOURCE REQUIREMENTS: Budget $[X]  |  Personnel [X] hrs

APPROVAL: Regulatory _____________ Date _______ / Management _____________ Date _______

Decision Frameworks

Pathway Selection and Classification Reference

FDA Pathway Selection

Is predicate device available?
            │
        Yes─┴─No
         │     │
         ▼     ▼
    Is device   Is risk level
    substantially  Low-Moderate?
    equivalent?       │
         │        Yes─┴─No
     Yes─┴─No      │     │
      │     │      ▼     ▼
      ▼     ▼   De Novo  PMA
    510(k)  Consider      required
           De Novo
           or PMA

EU MDR Classification

Is the device active?
        │
    Yes─┴─No
     │     │
     ▼     ▼
Is it an   Does it contact
implant?   the body?
  │            │
Yes─┴─No   Yes─┴─No
 │    │     │     │
 ▼    ▼     ▼     ▼
III  IIb  Check   Class I
         contact  (measuring/
         type     sterile if
         and      applicable)
         duration

Pre-Submission Meeting Decision

Factor	Schedule Pre-Sub	Skip Pre-Sub
Novel Technology	✓
New Intended Use	✓
Complex Testing	✓
Uncertain Predicate	✓
Clinical Data Needed	✓
Well-established		✓
Clear Predicate		✓
Standard Testing		✓

Regulatory Escalation Criteria

Situation	Escalation Level	Action
Submission rejection	VP Regulatory	Root cause analysis, strategy revision
Major deficiency	Director	Cross-functional response team
Timeline at risk	Management	Resource reallocation review
Regulatory change	VP Regulatory	Portfolio impact assessment
Safety signal	Executive	Immediate containment and reporting

Tools and References

Scripts

Tool	Purpose	Usage
regulatory_tracker.py	Track submission status and timelines	`python regulatory_tracker.py`

Regulatory Tracker Features:

Track multiple submissions across markets
Monitor status and target dates
Identify overdue submissions
Generate status reports

Example usage:

$ python regulatory_tracker.py --report status
Submission Status Report — 2024-11-01
┌──────────────────┬──────────┬────────────┬─────────────┬──────────┐
│ Product          │ Market   │ Type       │ Target Date │ Status   │
├──────────────────┼──────────┼────────────┼─────────────┼──────────┤
│ WoundScan Pro    │ USA      │ 510(k)     │ 2024-12-01  │ On Track │
│ WoundScan Pro    │ EU       │ MDR IIb    │ 2025-03-01  │ At Risk  │
│ CardioMonitor X1 │ Canada   │ Class II   │ 2025-01-15  │ On Track │
└──────────────────┴──────────┴────────────┴─────────────┴──────────┘
1 submission at risk: WoundScan Pro EU — NB engagement not confirmed.

References

Document	Content
fda-submission-guide.md	FDA pathways, requirements, review process
eu-mdr-submission-guide.md	MDR classification, technical documentation, clinical evidence
global-regulatory-pathways.md	Canada, Japan, China, Australia, Brazil requirements
iso-regulatory-requirements.md	ISO 13485, 14971, 10993, IEC 62304, 62366 requirements

Key Performance Indicators

KPI	Target	Calculation
First-time approval rate	>85%	(Approved without major deficiency / Total submitted) × 100
On-time submission	>90%	(Submitted by target date / Total submissions) × 100
Review cycle compliance	>95%	(Responses within deadline / Total requests) × 100
Regulatory hold time	<20%	(Days on hold / Total review days) × 100

Related Skills

Skill	Integration Point
mdr-745-specialist	Detailed EU MDR technical requirements
fda-consultant-specialist	FDA submission deep expertise
quality-manager-qms-iso13485	QMS for regulatory compliance
risk-management-specialist	ISO 14971 risk management

When it activates

Automatically, when a task matches. Use when users need to pl

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 v8 — 10/23/2026

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

alirezarezvani / claude-skills

.gemini/skills/regulatory-affairs-head/SKILL.md

View on GitHub ↗

License MITImported 11/7/2026Version v1Bundled 5 files · scripts

Illustrative Want to see what alirezarezvani/regulatory-affairs-head 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

Head of Regulatory Affairs

Table of Contents

Regulatory Strategy Workflow

Workflow: New Product Regulatory Strategy

Regulatory Pathway Selection Matrix

Regulatory Strategy Document Template

FDA Submission Workflow

Workflow: 510(k) Submission

Substantial Equivalence Comparison Example

Workflow: PMA Submission

FDA Submission Timeline

Common FDA Deficiencies and Prevention

EU MDR Submission Workflow

Workflow: MDR Technical Documentation

GSPR Checklist Row Example

Clinical Evidence Requirements by Class

Notified Body Selection Criteria

Global Market Access Workflow

Workflow: Multi-Market Submission Strategy

Market Priority Matrix

Documentation Efficiency Strategy

Regulatory Intelligence Workflow

Workflow: Regulatory Change Management

Regulatory Monitoring Sources

Impact Assessment Template

Decision Frameworks

Pathway Selection and Classification Reference

Pre-Submission Meeting Decision

Regulatory Escalation Criteria

Tools and References

Scripts

References

Key Performance Indicators

Related Skills

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry