Ready to supercharge your AI agents?

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

Get Started Free →

Product Safety Surveillance (multi-product, openFDA) · mims-harvard | DecimalAI

Scienceby mims-harvard

Product Safety Surveillance (multi-product, openFDA)

Retrieve and interpret post-market safety records across **every FDA-regulated

Maintained

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

3 of 22 cases passed every check with the skill.

Measured on gemini-3.6-flash7/29/2026v1 · latest is v23 comparable

Lift withheld: 3 comparable cases; this report requires 8.

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; 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 tooluniverse-product-safety-surveillance
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("tooluniverse-product-safety-surveillance")
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 tooluniverse-product-safety-surveillance

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/tooluniverse-product-safety-surveillance/SKILL.md https://app.decimal.ai/s/tooluniverse-product-safety-surveillance/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/tooluniverse-product-safety-surveillance/SKILL.md

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

Other ways to add it

Claude Code docs

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

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

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

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

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

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

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

Other ways to add it

Claude Agent SDK docs

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

Install

pip install "decimalai[openai-agents]"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

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

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

Other ways to add it

OpenAI Agents docs

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

Install

pip install "decimalai[openai]"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

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

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

Other ways to add it

OpenAI SDK docs

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

Install

pip install "decimalai[anthropic]"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

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

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

Other ways to add it

Anthropic docs

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

Install

pip install "decimalai[google-genai]"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/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/tooluniverse-product-safety-surveillance/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

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

Other ways to add it

Gemini API docs

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

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

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

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

Other ways to add it

LangChain docs

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

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

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

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

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

Other ways to add it

CrewAI docs

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

Install

pip install "decimalai[adk]"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

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

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

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

Other ways to add it

Google ADK docs

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

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

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

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

Other ways to add it

Pydantic AI docs

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

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

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

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

Other ways to add it

Deep Agents docs

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

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

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

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

Other ways to add it

Microsoft Agent Framework docs

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

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add tooluniverse-product-safety-surveillance

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("tooluniverse-product-safety-surveillance")
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/tooluniverse-product-safety-surveillance/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

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

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

Other ways to add it

Strands docs

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

pip install "decimalai>=0.15"
decimalai skills add tooluniverse-product-safety-surveillance

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/tooluniverse-product-safety-surveillance/SKILL.md https://app.decimal.ai/s/tooluniverse-product-safety-surveillance/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-product-safety-surveillance/SKILL.md

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

Other ways to add it

Cursor and other editors docs

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

Get the file

curl -fsSL https://app.decimal.ai/s/tooluniverse-product-safety-surveillance/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/tooluniverse-product-safety-surveillance.json

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

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2 (v1 tested 7/29/2026)
Source: mims-harvard/ToolUniverse ↗
License: Apache-2.0

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

Product Safety Surveillance (multi-product, openFDA)

Retrieve and interpret post-market safety records across every FDA-regulated product class except drug-AE signal mining: medical devices, food / dietary supplements / cosmetics, veterinary drugs, and drug supply (shortages), plus cross-product enforcement/recall reports.

KEY PRINCIPLES

Decide the product class first. Device? Food/supplement/cosmetic? Vet drug? Drug shortage? Recall? The class picks the tool.
Build a valid Lucene query. openFDA uses field-scoped field:value terms; combine with a space-separated AND. Phrases and special characters need care (see Query Grammar).
Retrieve, then interpret. These are spontaneous/voluntary reports. Report the records and their fields; never assert causation or rates.
Cite every record with the tool name, the openFDA endpoint, the query used, and the total hit count from meta.results.total.
Stay in scope. If the request is drug-AE signal detection (PRR/ROR/IC), STOP and point to tooluniverse-pharmacovigilance / tooluniverse-adverse-event-detection.

When to Use vs When NOT to Use

USE for:

Device adverse events (MAUDE): "adverse events / malfunctions / deaths for [device]"
Device recalls & enforcement: "device recalls for [firm]", "Class I device recalls"
Device clearance context: "510(k) clearances for [device type]"
Food / dietary-supplement / cosmetic adverse events (CAERS): "supplement reactions", "cosmetic adverse events for [brand]"
Food recalls/enforcement: "food recall for listeria / undeclared allergen"
Veterinary drug adverse events: "adverse events for [drug] in dogs"
Drug shortages: "is [drug] in shortage", "injectables on current shortage"
Drug recalls/enforcement: "drug recalls for contamination"

DO NOT USE for (point elsewhere):

Drug adverse-event SIGNAL detection / disproportionality (PRR, ROR, IC) → tooluniverse-pharmacovigilance or tooluniverse-adverse-event-detection
Drug-AE association strength scoring, demographic risk stratification of drug AEs → same two skills
Drug efficacy, mechanism, pharmacogenomics → other tooluniverse-* skills

This skill retrieves and interprets multi-product safety records. It does not compute drug-AE signal statistics.

Tool Map (which tool for which question)

Product class	Question	Tool	openFDA endpoint
Device	Adverse events / malfunctions / deaths (MAUDE)	`OpenFDA_search_device_adverse_events`	`/device/event.json`
Device	Recalls	`OpenFDA_search_device_recalls`	`/device/recall.json`
Device	Enforcement / recall reports	`OpenFDA_search_device_enforcement`	`/device/enforcement.json`
Device	510(k) clearances (context)	`OpenFDA_search_device_510k`	`/device/510k.json`
Device	Unique Device Identifier (UDI) lookup	`OpenFDADevice_search_udi`	--
Device	US regulatory class (1/2/3)	`OpenFDADevice_get_classification`	--
Device	Premarket Approval (PMA, Class 3 devices)	`OpenFDADevice_search_pma`	--
Food/supplement/cosmetic	Adverse events (CAERS)	`OpenFDA_search_food_adverse_events`	`/food/event.json`
Food	Enforcement / recall reports	`OpenFDA_search_food_enforcement`	`/food/enforcement.json`
Veterinary	Animal drug adverse events	`OpenFDA_search_animalvet_adverse_events`	`/animalandveterinary/event.json`
Drug supply	Shortages	`OpenFDA_search_drug_shortages`	`/drug/shortages.json`
Drug	Enforcement / recall reports	`OpenFDA_search_drug_enforcement`	`/drug/enforcement.json`
Drug	Adverse events (raw FAERS records)	`OpenFDA_search_drug_events`	`/drug/event.json`
Drug	Labels	`OpenFDA_search_drug_labels`	`/drug/label.json`

All tools take a Lucene search string plus optional limit and skip. All are keyless and verified live.

Note: OpenFDADevice_search_recalls/_search_adverse_events/_search_510k return the same underlying openFDA data as OpenFDA_search_device_recalls/_device_adverse_events/_device_510k above (two independently-added wrappers over the same endpoints) — either works, no need to call both. Use whichever is already in your loaded toolset; the OpenFDADevice_* family additionally has the three UDI/classification/PMA tools with no equivalent in the other family.

openFDA Query Grammar (CRITICAL — read before querying)

Field-scoped term: field:value (e.g. event_type:Death, status:Current).
Nested fields use dot paths: device.generic_name:pacemaker, products.industry_name:Cosmetics, animal.species:Dog, reaction.veddra_term_name:Vomiting, drug.active_ingredients.name:carprofen.
Combine terms with a SPACE-separated AND (verified working): device.generic_name:pacemaker AND event_type:Death.
- Do NOT use +AND+ — the +-joined boolean form errors through these tools. Use a literal space around AND.
Multi-word values: join with + only for adjacency within a single field value (e.g. device.generic_name:infusion+pump). This is matched as tokens, not an exact phrase.
Avoid raw special characters ((, ), /, leading +) inside values — they break the query. Pick a simpler token (e.g. products.industry_name:Dietary instead of the full Dietary Conventional Foods/Meal Replacements).
Dates are strings: device AE/MAUDE use YYYYMMDD (e.g. date_received); recalls/enforcement use YYYY-MM-DD (e.g. event_date_initiated, recall_initiation_date).
Result envelope: every successful call returns {status:"success", data:{meta:{results:{total, skip, limit}}, results:[...]}}. Read the hit count from data.meta.results.total.
Counts/aggregations: native openFDA supports &count=<field>; these TU wrappers center on search. To rank terms, retrieve a batch (e.g. limit:100) and tally the field yourself in Python.

Interpretation Tables (raw openFDA field → meaning)

Medical devices — MAUDE adverse events (`/device/event.json`)

Field	Meaning
`event_type`	`Death`, `Injury`, `Malfunction`, or `No answer provided`. Death/Injury = patient harm; Malfunction = device failure without (reported) harm.
`device[].generic_name` / `device[].brand_name`	Device category / trade name.
`device[].manufacturer_d_name`	Device manufacturer.
`patient[]`	Patient-level outcome data (may be sparse).
`mdr_text[].text`	Narrative; `text_type_code` distinguishes event description vs manufacturer narrative.
`report_number`	MAUDE report id. Duplicate / follow-up reports of the same event are common — do not count reports as distinct events.
`date_received`	`YYYYMMDD` FDA received date.

Medical devices — recalls (`/device/recall.json`)

Field	Meaning
`product_description`	What was recalled.
`recalling_firm`	Firm issuing the recall.
`recall_status`	e.g. `Open`, `Terminated`. Terminated = FDA closed the action.
`product_code`	FDA device product code.
`k_numbers[]`	Associated 510(k) clearance numbers.
`root_cause_description`	FDA root-cause category (e.g. `Labeling design`).
`event_date_initiated`	`YYYY-MM-DD` recall start.

Enforcement reports (device / drug / food `/.../enforcement.json`)

Field	Meaning
`classification`	Recall severity: `Class I` (serious/fatal hazard), `Class II` (temporary/reversible), `Class III` (unlikely to cause harm).
`status`	`Ongoing` / `Terminated` / `Completed`.
`reason_for_recall`	Why recalled.
`product_description`	Recalled product.
`recalling_firm`	Firm.

Food / supplement / cosmetic — CAERS adverse events (`/food/event.json`)

Field	Meaning
`reactions[]`	MedDRA reaction terms (British spelling, e.g. `Diarrhoea`, `Nausea`).
`outcomes[]`	e.g. `Hospitalization`, `Life Threatening`, `Disability`, `Death`, `Other Serious or Important Medical Event`, `Visited an ER`.
`products[].industry_name`	Product category (`Cosmetics`, `Dietary Conventional Foods/Meal Replacements`, `Milk/Butter/Dried Milk Prod`, …).
`products[].role`	`SUSPECT` (implicated) vs `CONCOMITANT` (also consumed).
`products[].name_brand`	Brand name.
`consumer`	`age`, `gender` of the consumer (often sparse).

Veterinary — animal drug adverse events (`/animalandveterinary/event.json`)

Field	Meaning
`animal.species`	`Dog`, `Cat`, `Horse`, …
`animal.gender`	Animal sex.
`number_of_animals_affected`	Count in the report.
`reaction[].veddra_term_name`	VeDDRA clinical sign (e.g. `Vomiting`, `Diarrhoea`).
`drug[].brand_name` / `drug[].active_ingredients[].name`	Implicated product / active.
`drug[].used_according_to_label` / `off_label_use`	Label vs off-label use.

Drug shortages (`/drug/shortages.json`)

Field	Meaning
`status`	`Current` or `Resolved`.
`availability`	e.g. `Unavailable`, `Limited`.
`generic_name`	Drug in shortage.
`shortage_reason`	e.g. `Delay in shipping of the drug`, `Demand increase for the drug`.
`dosage_form`	e.g. `Injection`, `Tablet`.
`therapeutic_category[]`	Clinical category.
`company_name`	Manufacturer.
`update_type` / `initial_posting_date` / `update_date`	Posting metadata.

Workflow

Classify the product from the request (device / food-supplement-cosmetic / vet / drug shortage / recall).
Pick the tool from the Tool Map.
Build the Lucene query following Query Grammar (single field for a first pass; add AND for combinations). Keep values simple; avoid special characters.
Run it and read data.meta.results.total and data.results[].
Interpret the fields with the table above. For severity: device event_type:Death; enforcement classification:Class I; CAERS outcomes:Death/Hospitalization; shortage status:Current.
Summarize and cite. Report counts, key fields, the query used, and the LIMITATIONS caveat. To rank terms, pull limit:100 and tally in Python (no count aggregation in these wrappers).
If out of scope (drug-AE signal/PRR/ROR), stop and route to the pharmacovigilance skills.

Worked Examples (verified live)

Example 1 — Device deaths for a device type (MAUDE)

"Are there any reported deaths in adverse-event reports for pacemakers?"

OpenFDA_search_device_adverse_events {"search":"device.generic_name:pacemaker AND event_type:Death","limit":1}

Real output (abbrev): status:success, meta.results.total = 16619; first record event_type = Death, device.generic_name = DEFIBRILLATOR/PACEMAKER. Interpretation: 16,619 MAUDE reports match a pacemaker device with a Death event type. These are spontaneous reports — duplicates likely, and "Death" means a death was reported in temporal association, not that the device caused it.

Example 2 — Device recalls for a firm

"What device recalls has Medtronic Navigation issued?"

OpenFDA_search_device_recalls {"search":"recalling_firm:Medtronic","limit":1}

Real output (abbrev): total = 1896; first record recall_status = Terminated, product_code = HAW, root_cause_description = Labeling design, k_numbers = ["K990214"], event_date_initiated = 2011-01-20, product_description = a tactile probe for spine surgery. Interpretation: 1,896 recall records match firms containing "Medtronic". recall_status: Terminated means FDA has closed this action; the root cause was a labeling-design issue.

Example 3 — Drug shortage lookup for an injectable

"Is ketorolac injection in shortage right now?"

OpenFDA_search_drug_shortages {"search":"dosage_form:Injection AND status:Current","limit":1}

Real output (abbrev): total = 799; first record generic_name = Ketorolac Tromethamine Injection, status = Current, shortage_reason = Delay in shipping of the drug, availability = Unavailable, company_name = Fresenius Kabi USA, LLC. Interpretation: 799 current shortage records are injectables; ketorolac tromethamine injection is currently in shortage (status Current, availability Unavailable) due to a shipping delay.

Example 4 — Supplement / cosmetic CAERS reactions

"Are there CAERS adverse-event reports implicating cosmetics?"

OpenFDA_search_food_adverse_events {"search":"products.industry_name:Cosmetics","limit":1}

Real output (abbrev): total = 52214; first record products[].industry_name = Cosmetics, products[].role = SUSPECT, outcomes = ["Hospitalization","Other Serious or Important Medical Event"]. Interpretation: 52,214 CAERS reports name a cosmetic product as SUSPECT. CAERS is voluntary; a SUSPECT role reflects the reporter's attribution, not a verified causal link.

Example 5 — Veterinary adverse events for a drug in a species

"What adverse events are reported for carprofen in dogs?"

OpenFDA_search_animalvet_adverse_events {"search":"drug.active_ingredients.name:carprofen AND animal.species:Dog","limit":1}

Real output (abbrev): total = 46469; first record animal.species = Dog, reaction[].veddra_term_name includes Leucocytosis NOS, Neutrophilia, Depression, Elevated alanine aminotransferase (ALT). Interpretation: 46,469 veterinary reports match carprofen-containing products in dogs. VeDDRA terms describe reported clinical signs; counts reflect reporting, not incidence.

Limitations (state these in every report)

Spontaneous / voluntary reports. MAUDE (device), CAERS (food/supplement/cosmetic), FAERS (drug), and the animal/vet system are passive surveillance. Reports are unverified and a report is not a confirmed causal event.
No causation, no denominator. Counts (meta.results.total) are report counts, not incidence or rates. There is no exposure denominator, so you cannot compute risk.
Reporting bias. Serious events, new products, recalls, and media/regulatory attention drive reporting spikes (Weber effect). High counts may reflect usage volume or attention, not hazard.
Duplicate reports. MAUDE in particular contains follow-up/duplicate reports of the same event; do not treat report counts as event counts.
CAERS voluntary & sparse. Consumer/age/gender fields are often missing; SUSPECT role is reporter attribution.
This skill does not compute signal statistics (PRR/ROR/IC). For drug-AE disproportionality use tooluniverse-pharmacovigilance / tooluniverse-adverse-event-detection.
Data currency: each response carries a meta.last_updated date; openFDA lags real-world events.

See references/openfda_fields.md for the full per-endpoint field reference and additional query examples.

References

openFDA: https://open.fda.gov
MAUDE (device adverse events): https://www.fda.gov/medical-devices/mandatory-reporting-requirements-manufacturers-importers-and-device-user-facilities
Device recalls / 510(k): https://www.fda.gov/medical-devices
CAERS (food/supplement/cosmetic): https://www.fda.gov/food/compliance-enforcement/cfsan-adverse-event-reporting-system-caers
Drug shortages: https://www.fda.gov/drugs/drug-shortages
Recall classifications: https://www.fda.gov/safety/industry-guidance-recalls

About this skill

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Clinical / Healthcare pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/22/2026

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

mims-harvard / ToolUniverse

skills/tooluniverse-product-safety-surveillance/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 9/22/2026Version v2Bundled 1 file

Illustrative Want to see what tooluniverse-product-safety-surveillance 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.

mims-harvard/tooluniverse-product-safety-surveillancePost-market safety surveillance and recall/adverse-event RETRIEVAL across the full spectrum of FDA-regulated products that are NOT covered by the drug-AE signal skills: medical devices, food / dietary supplements / cosmetics, veterinary drugs, and drug supply (shortages). Orchestrates openFDA endpoints (MAUDE device adverse events + device recalls + 510(k), CAERS food/supplement/ cosmetic adverse events, veterinary adverse events, drug shortages, and cross-product enforcement/recall reports). USNear-identical description+27 pts pass-rate 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?

Safety

What it changes

Track record

Use this skill

Product Safety Surveillance (multi-product, openFDA)

When to Use vs When NOT to Use

Tool Map (which tool for which question)

openFDA Query Grammar (CRITICAL — read before querying)

Interpretation Tables (raw openFDA field → meaning)

Medical devices — MAUDE adverse events (/device/event.json)

Medical devices — recalls (/device/recall.json)

Enforcement reports (device / drug / food /.../enforcement.json)

Food / supplement / cosmetic — CAERS adverse events (/food/event.json)

Veterinary — animal drug adverse events (/animalandveterinary/event.json)

Drug shortages (/drug/shortages.json)

Workflow

Worked Examples (verified live)

Example 1 — Device deaths for a device type (MAUDE)

Example 2 — Device recalls for a firm

Example 3 — Drug shortage lookup for an injectable

Example 4 — Supplement / cosmetic CAERS reactions

Example 5 — Veterinary adverse events for a drug in a species

Limitations (state these in every report)

References

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry

Medical devices — MAUDE adverse events (`/device/event.json`)

Medical devices — recalls (`/device/recall.json`)

Enforcement reports (device / drug / food `/.../enforcement.json`)

Food / supplement / cosmetic — CAERS adverse events (`/food/event.json`)

Veterinary — animal drug adverse events (`/animalandveterinary/event.json`)

Drug shortages (`/drug/shortages.json`)