Ready to supercharge your AI agents?

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

nmpa-drug-registry-lookup · 中国药品权威 Registry · ethanyoq | DecimalAI

Researchby ethanyoq

nmpa-drug-registry-lookup · 中国药品权威 Registry

中国药品权威数据库查询 — NMPA(国家药监局) + CDE(药品审评中心) + DrugBank(英文名/ATC) + PubChem(化学结构) 多源融合,提供(通用名 ↔ 商品名 ↔ 英文名 ↔ 适应症 ↔ NMPA 批文号 ↔ 上市日期)精确映射。Make sure to use this skill whenever the user mentions 药品名 / 通用名 / 商品名 / NMPA / 国药准字 / 药监局 / CDE / drug brand name / generic name / drug registry / pharmaceutical lookup / drug verification / 药物核验 / 商品名对应 / drug cross-check / drug authority lookup. 在任何 medical / market-sizing / clinical / disease-research 报告生成阶段,**所有药品提及必须先调 lookup_drug() 验证**,严禁 LLM 凭训练记忆拼凑通用名↔商品名↔英文名

Never made a case worse

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%77%of test cases passed +59 pts

Without skill4 of 22

With skill17 of 22

13 fixed4 passed either way5 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhen an English drug name maps to multiple legacy Chinese phonetic translations in historic literature, which title takes precedent in the verified record?

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 ethanyoq-nmpa-drug-registry-lookup
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("ethanyoq-nmpa-drug-registry-lookup")
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 ethanyoq-nmpa-drug-registry-lookup

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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md https://app.decimal.ai/s/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

This gets SKILL.md only. The skill's 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/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/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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("ethanyoq-nmpa-drug-registry-lookup")
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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/ethanyoq-nmpa-drug-registry-lookup/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 10 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 ethanyoq-nmpa-drug-registry-lookup

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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md https://app.decimal.ai/s/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

This gets SKILL.md only. The skill's 10 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/ethanyoq-nmpa-drug-registry-lookup/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/ethanyoq-nmpa-drug-registry-lookup.json

This gets SKILL.md only. The skill's 10 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: ethanyoq/skill-hub ↗
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

nmpa-drug-registry-lookup · 中国药品权威 Registry

一句话定义

中国市场所有报告里的药品提及,都从此 skill 拿权威记录(NMPA + CDE + DrugBank + PubChem 多源融合);LLM 不允许凭记忆改写药品名。

Iron Law(违反此条 = 报告作废)

任何写入报告的药品名(通用名 / 商品名 / 英文名),必须通过 lookup_drug() 验证。

LLM 不允许凭训练记忆拼凑通用名↔商品名↔英文名对应关系 — 因为:

药企会更换商品名(如同一通用名在不同厂家有多个商品名)
新药持续上市,LLM 训练截止日期之后的数据完全不可信
中国市场命名经常与全球市场不同(如:Lorlatinib 中国商品名"博瑞纳",国外"Lorbrena")
一个药名错位 = 整份报告地基塌方(治疗推荐错 / GRADE 错 / LP 错 / 市场份额测算错)

唯一允许的姿势:

from nmpa_drug_registry_lookup.scripts.registry import lookup_drug, UnverifiedDrugError

rec = lookup_drug("洛拉替尼")
if rec is None:
    raise UnverifiedDrugError("洛拉替尼 not in NMPA registry — refuse to write to report")

# 报告里写药名时,通用名和商品名都从 record 取,不要手输
generic_zh = rec.generic_name_zh   # "洛拉替尼"
generic_en = rec.generic_name_en   # "Lorlatinib"
brand_zh   = rec.brand_names_zh[0] # "博瑞纳"

绝不允许:

# 错误!LLM 凭记忆
report_html += "<p>洛拉替尼(商品名:赛可瑞)...</p>"   # 赛可瑞实际是克唑替尼!
report_html += "<p>布加替尼(商品名:博瑞纳)...</p>"   # 博瑞纳实际是洛拉替尼!

何时调用

任何报告生成阶段(market-sizing / 治疗方案 / 决策树 / 市场份额测算)涉及具体药品名
用户问"X 药的通用名是什么?"、"Y 药什么时候在中国上市?"、"Z 药 NMPA 批文号是多少?"
medical-evidence-grading / disease-market-sizing-orchestration 调用方需要药名锚定
报告生成完毕,跑 cross_check_drug_mentions() 全文扫描,catch LLM 偷偷凭记忆改写的药名

何时不调用

文献检索本身(给 PubMed query 时)— 不需要,query 自由文本即可
询问药物机制 / 靶点(用 pubtator-entity-search 抓基因/通路)
询问临床试验状态(用 clinical-trials-v2)

与其他 skill 的协作关系

                        ┌─ pubmed-eutils(召回主力)
召回层 ───┬─────────────┤
          │             └─ europepmc-search
          │
          │             ┌─ cn-clinical-guidelines-fetch(指南权威)
权威层 ───┼─────────────┤
          │             └─ ★ nmpa-drug-registry-lookup(本 skill · 药品权威)
          │
          ▼
报告生成层 ───  所有药品名引用 → lookup_drug() / cross_check_drug_mentions()

调用顺序:

orchestration 解析疾病 → fetch_chinese_guidelines() 拿指南治疗推荐表
用指南里提到的药品 → lookup_drugs_batch() 建立本疾病 drug_registry.json
报告生成时所有药品名引用从 drug_registry.json 取(LLM 禁止改写)
报告草稿出来 → cross_check_drug_mentions(html) 全文扫描,critical 严重性 → raise

核心函数签名

from dataclasses import dataclass
from pathlib import Path

@dataclass(frozen=True)
class DrugRecord:
    """中国药品权威记录。frozen 防止 LLM 修改。"""
    generic_name_zh: str         # 通用名(中文,首选 NMPA 命名)
    generic_name_en: str         # 通用名(英文,DrugBank/INN)
    brand_names_zh: tuple[str, ...]    # 商品名列表(中国市场,可能多个生产厂家)
    brand_names_en: tuple[str, ...]    # 商品名列表(全球)
    nmpa_approval_no: str        # NMPA 批准文号(如 国药准字 H20180123 / 进 J20180012)
    first_approval_date_cn: str  # 中国首次上市日期 ISO yyyy-mm-dd
    indications_cn: tuple[str, ...]    # 适应症(中文)
    atc_code: str                # ATC 分类(如 L01ED05 = 抗肿瘤 ALK 抑制剂)
    target: str                  # 靶点(对靶向药,如 "ALK")
    drug_class: str              # 类别(如 "三代 ALK-TKI")
    sources: tuple[str, ...]     # 来源 URL,可追溯


class UnverifiedDrugError(Exception):
    """lookup 失败时调用方应 raise — 拒绝写入报告。"""


def lookup_drug(
    name: str,                   # 任意名称(通用/商品/英文,模糊匹配)
    market: str = "CN",
    cache_dir: Path | None = None,
) -> DrugRecord | None:
    """单药查询。匹配优先级:
    1. 已知 fallback dict 精确命中(NMPA 网站抓不到时的兜底)
    2. NMPA 精确通用名
    3. NMPA 商品名
    4. DrugBank generic_name
    5. PubChem 化学名 fallback

    None = 该药不在权威数据库 → 调用方必须 raise UnverifiedDrugError。
    """


def lookup_drugs_batch(
    names: list[str],
    market: str = "CN",
    cache_dir: Path | None = None,
) -> dict[str, DrugRecord | None]:
    """批量查询。返回 {name: DrugRecord or None}。"""


def cross_check_drug_mentions(
    text: str,                   # 报告 HTML / Markdown 草稿
    market: str = "CN",
    cache_dir: Path | None = None,
) -> dict:
    """扫描文本里所有疑似药品名,逐个 lookup,返回错误清单。

    Returns:
        {
            "ok": bool,
            "verified_drugs": [...],       # 命中权威数据库的药名
            "unverified_drugs": [...],     # 在数据库找不到 → 必须修
            "name_mismatches": [           # 通用名/商品名混用错位(critical)
                {"text_uses": "赛可瑞", "claimed_as": "洛拉替尼",
                 "actual_generic": "克唑替尼", "evidence_source": "NMPA"},
                ...
            ],
            "violation_severity": "none" | "warning" | "critical",
        }

    严重性规则:
    - 任何 name_mismatches 非空 → critical(LLM 把 A 药写成 B 药商品名)
    - 仅 unverified_drugs 非空 → warning(可能是新药 / 仿制名)
    - 全部 verified → none
    """

数据源(免费公开)

来源	提供	抓取方式
NMPA 国家药监局 (`nmpa.gov.cn`)	通用名 / 批文号 / 适应症 / 上市时间 (权威 I 级)	REST + WebFetch + bs4
CDE 药品审评中心 (`cde.org.cn`)	临床试验阶段 / 适应症详情	WebFetch
DrugBank(免费学术)	英文名 / ATC code / mechanism	API / scrape
PubChem(NIH)	化学结构 / IUPAC / 同义词	REST(`pug.ncbi.nlm.nih.gov/rest/pug`)
NCBI Gene	靶点基因(已通过 pubtator-entity-search 间接)	复用

fallback 兜底:NMPA 网站反爬严重时,scripts/_known_drugs_fallback.py 含一份手工核验的常用药字典,每条都有 NMPA 公开页 URL 引用作来源。

失败模式(8 条)

#	症状	原因	修复
1	lookup 返回 None	药品不在 NMPA(可能仿制名 / 进口未上市 / 拼写错)	让用户确认是否仍写入,标 unverified;不允许 LLM 凭记忆补
2	同一通用名多个商品名	多厂家(如阿仑膦酸钠)	brand_names_zh 列出全部,不要任选一个
3	通用名↔商品名错位(LLM 偷偷脑补)	LLM 训练截止后数据老化	`cross_check_drug_mentions` 全文扫描,critical 级 raise
4	NMPA 网站抓取失败(反爬)	nmpa.gov.cn 改版 / 验证码	降级:cache → fallback dict → 报错
5	同一英文名对应多个中文音译	早期未规范化	NMPA 通用名为唯一权威,其他作 alias
6	DrugBank 拒绝学术抓取	反爬升级	该字段标 None,不阻塞主流程(NMPA 字段是必需)
7	LLM 在 prompt 里"脑补"通用名	训练数据过时	任何 grade_evidence / LP 阶段都强制 lookup,不接受 LLM 直出
8	进口药批文号格式 vs 国产不同	NMPA 编号规则:H/J/Z/S 前缀	不要自行拆解,作为 opaque string 存储

跨平台

Python: 3.10+(用 PEP 604 X | None 类型注解)
依赖: httpx, beautifulsoup4, 可选 pypdf(适应症附件解析)
测试: python -m pytest(Windows 用 C:\Python3\python.exe -m pytest,不要用 python3 stub)
Windows GBK 终端兼容: 测试入口加 sys.stdout.reconfigure(encoding="utf-8")
Cache: JSON 文件 <cache_dir>/drug_registry.json,TTL 7 天;SQLite 是 future work
不联网测试: 测试用 tests/fixtures/nmpa_responses/*.html 预录制响应,绝不在 CI 里直连 NMPA

调用方典型用法

A. 单药 lookup

from nmpa_drug_registry_lookup.scripts.registry import lookup_drug, UnverifiedDrugError

rec = lookup_drug("洛拉替尼")
if rec is None:
    raise UnverifiedDrugError("洛拉替尼 not in NMPA registry — refuse to write to report")

print(rec.generic_name_en)    # "Lorlatinib"
print(rec.brand_names_zh)     # ("博瑞纳",)
print(rec.atc_code)           # "L01ED05"
print(rec.first_approval_date_cn)  # "2022-04-29"

B. 批量预热(orchestration 在 Step 0b 调)

from nmpa_drug_registry_lookup.scripts.registry import lookup_drugs_batch

key_drugs = ["克唑替尼", "阿来替尼", "塞瑞替尼", "恩沙替尼",
             "布加替尼", "洛拉替尼", "伊鲁阿克", "依奉阿克"]
results = lookup_drugs_batch(key_drugs)

missing = [d for d, r in results.items() if r is None]
if missing:
    raise UnverifiedDrugError(f"NMPA registry missing: {missing}")

# 写入 .cache/<slug>/drug_registry.json,后续报告生成阶段 LLM 必须从此取

C. 报告生成完毕全文扫描

from nmpa_drug_registry_lookup.scripts.registry import cross_check_drug_mentions

result = cross_check_drug_mentions(report_html)
if result["violation_severity"] == "critical":
    # LLM 把 A 药写成 B 药商品名 — 必须重生成
    raise OrchestrationError(f"drug name mismatches: {result['name_mismatches']}")
elif result["violation_severity"] == "warning":
    # 仅有 unverified(可能是新药)— §0 加红色警告
    add_section_zero_warning(result["unverified_drugs"])

引用与下游

上游: cn-clinical-guidelines-fetch(指南先告诉本 skill 该疾病有哪些药)
下游: disease-market-sizing-orchestration(在内容生成阶段强制锚定)、content-verification-layer(report-level cross-check 的事实审计层)
同层互补: pubtator-entity-search(基因靶点)、pubmed-eutils(文献召回)

参考文档:

references/nmpa-fetch-api.md — NMPA 网站结构 + 抓取策略
references/drugbank-integration.md — DrugBank 学术免费用法
references/failure-modes.md — 8 失败模式详解

About this skill

Automatic

Clinical / Healthcare pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ethanyoq / skill-hub

skills/06-data-search/nmpa-drug-registry-lookup/SKILL.md

View on GitHub ↗

License MITImported 10/24/2026Version v1Bundled 10 files · scripts

Illustrative Want to see what ethanyoq/nmpa-drug-registry-lookup would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

nmpa-drug-registry-lookup · 中国药品权威 Registry

一句话定义

Iron Law(违反此条 = 报告作废)

何时调用

何时不调用

与其他 skill 的协作关系

核心函数签名

数据源(免费公开)

失败模式(8 条)

跨平台

调用方典型用法

A. 单药 lookup

B. 批量预热(orchestration 在 Step 0b 调)

C. 报告生成完毕全文扫描

引用与下游

SkillSafety

Source

Related skills

More in the registry