Ready to supercharge your AI agents?

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

PubChem Database · FreedomIntelligence | DecimalAI

Scienceby FreedomIntelligence

PubChem Database

Query PubChem via PUG-REST API/PubChemPy (110M+ compounds). Search by name/CID/SMILES, retrieve properties, similarity/substructure searches, bioactivity, for cheminformatics.

Never made a case worse

SkillScore

SkillScore9/100

Test results 9

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

5%9%of test cases passed +5 pts

Without skill1 of 22

With skill2 of 22

1 fixed1 passed either way20 still failing0 broke

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

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 pubchem-database
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("pubchem-database")
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 pubchem-database

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/pubchem-database/SKILL.md https://app.decimal.ai/s/pubchem-database/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/pubchem-database/SKILL.md

This gets SKILL.md only. The skill's 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/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/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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("pubchem-database")
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/pubchem-database/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/pubchem-database/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 3 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 pubchem-database

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/pubchem-database/SKILL.md https://app.decimal.ai/s/pubchem-database/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/pubchem-database/SKILL.md

This gets SKILL.md only. The skill's 3 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/pubchem-database/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/pubchem-database.json

This gets SKILL.md only. The skill's 3 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/26/2026
Source: FreedomIntelligence/OpenClaw-Medical-Skills ↗
License: Not recorded

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

PubChem Database

Overview

PubChem is the world's largest freely available chemical database with 110M+ compounds and 270M+ bioactivities. Query chemical structures by name, CID, or SMILES, retrieve molecular properties, perform similarity and substructure searches, access bioactivity data using PUG-REST API and PubChemPy.

When to Use This Skill

This skill should be used when:

Searching for chemical compounds by name, structure (SMILES/InChI), or molecular formula
Retrieving molecular properties (MW, LogP, TPSA, hydrogen bonding descriptors)
Performing similarity searches to find structurally related compounds
Conducting substructure searches for specific chemical motifs
Accessing bioactivity data from screening assays
Converting between chemical identifier formats (CID, SMILES, InChI)
Batch processing multiple compounds for drug-likeness screening or property analysis

Core Capabilities

1. Chemical Structure Search

Search for compounds using multiple identifier types:

By Chemical Name:

import pubchempy as pcp
compounds = pcp.get_compounds('aspirin', 'name')
compound = compounds[0]

By CID (Compound ID):

compound = pcp.Compound.from_cid(2244)  # Aspirin

By SMILES:

compound = pcp.get_compounds('CC(=O)OC1=CC=CC=C1C(=O)O', 'smiles')[0]

By InChI:

compound = pcp.get_compounds('InChI=1S/C9H8O4/...', 'inchi')[0]

By Molecular Formula:

compounds = pcp.get_compounds('C9H8O4', 'formula')
# Returns all compounds matching this formula

2. Property Retrieval

Retrieve molecular properties for compounds using either high-level or low-level approaches:

Using PubChemPy (Recommended):

import pubchempy as pcp

# Get compound object with all properties
compound = pcp.get_compounds('caffeine', 'name')[0]

# Access individual properties
molecular_formula = compound.molecular_formula
molecular_weight = compound.molecular_weight
iupac_name = compound.iupac_name
smiles = compound.canonical_smiles
inchi = compound.inchi
xlogp = compound.xlogp  # Partition coefficient
tpsa = compound.tpsa    # Topological polar surface area

Get Specific Properties:

# Request only specific properties
properties = pcp.get_properties(
    ['MolecularFormula', 'MolecularWeight', 'CanonicalSMILES', 'XLogP'],
    'aspirin',
    'name'
)
# Returns list of dictionaries

Batch Property Retrieval:

import pandas as pd

compound_names = ['aspirin', 'ibuprofen', 'paracetamol']
all_properties = []

for name in compound_names:
    props = pcp.get_properties(
        ['MolecularFormula', 'MolecularWeight', 'XLogP'],
        name,
        'name'
    )
    all_properties.extend(props)

df = pd.DataFrame(all_properties)

Available Properties: MolecularFormula, MolecularWeight, CanonicalSMILES, IsomericSMILES, InChI, InChIKey, IUPACName, XLogP, TPSA, HBondDonorCount, HBondAcceptorCount, RotatableBondCount, Complexity, Charge, and many more (see references/api_reference.md for complete list).

3. Similarity Search

Find structurally similar compounds using Tanimoto similarity:

import pubchempy as pcp

# Start with a query compound
query_compound = pcp.get_compounds('gefitinib', 'name')[0]
query_smiles = query_compound.canonical_smiles

# Perform similarity search
similar_compounds = pcp.get_compounds(
    query_smiles,
    'smiles',
    searchtype='similarity',
    Threshold=85,  # Similarity threshold (0-100)
    MaxRecords=50
)

# Process results
for compound in similar_compounds[:10]:
    print(f"CID {compound.cid}: {compound.iupac_name}")
    print(f"  MW: {compound.molecular_weight}")

Note: Similarity searches are asynchronous for large queries and may take 15-30 seconds to complete. PubChemPy handles the asynchronous pattern automatically.

4. Substructure Search

Find compounds containing a specific structural motif:

import pubchempy as pcp

# Search for compounds containing pyridine ring
pyridine_smiles = 'c1ccncc1'

matches = pcp.get_compounds(
    pyridine_smiles,
    'smiles',
    searchtype='substructure',
    MaxRecords=100
)

print(f"Found {len(matches)} compounds containing pyridine")

Common Substructures:

Benzene ring: c1ccccc1
Pyridine: c1ccncc1
Phenol: c1ccc(O)cc1
Carboxylic acid: C(=O)O

5. Format Conversion

Convert between different chemical structure formats:

import pubchempy as pcp

compound = pcp.get_compounds('aspirin', 'name')[0]

# Convert to different formats
smiles = compound.canonical_smiles
inchi = compound.inchi
inchikey = compound.inchikey
cid = compound.cid

# Download structure files
pcp.download('SDF', 'aspirin', 'name', 'aspirin.sdf', overwrite=True)
pcp.download('JSON', '2244', 'cid', 'aspirin.json', overwrite=True)

6. Structure Visualization

Generate 2D structure images:

import pubchempy as pcp

# Download compound structure as PNG
pcp.download('PNG', 'caffeine', 'name', 'caffeine.png', overwrite=True)

# Using direct URL (via requests)
import requests

cid = 2244  # Aspirin
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/PNG?image_size=large"
response = requests.get(url)

with open('structure.png', 'wb') as f:
    f.write(response.content)

7. Synonym Retrieval

Get all known names and synonyms for a compound:

import pubchempy as pcp

synonyms_data = pcp.get_synonyms('aspirin', 'name')

if synonyms_data:
    cid = synonyms_data[0]['CID']
    synonyms = synonyms_data[0]['Synonym']

    print(f"CID {cid} has {len(synonyms)} synonyms:")
    for syn in synonyms[:10]:  # First 10
        print(f"  - {syn}")

8. Bioactivity Data Access

Retrieve biological activity data from assays:

import requests
import json

# Get bioassay summary for a compound
cid = 2244  # Aspirin
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/assaysummary/JSON"

response = requests.get(url)
if response.status_code == 200:
    data = response.json()
    # Process bioassay information
    table = data.get('Table', {})
    rows = table.get('Row', [])
    print(f"Found {len(rows)} bioassay records")

For more complex bioactivity queries, use the scripts/bioactivity_query.py helper script which provides:

Bioassay summaries with activity outcome filtering
Assay target identification
Search for compounds by biological target
Active compound lists for specific assays

9. Comprehensive Compound Annotations

Access detailed compound information through PUG-View:

import requests

cid = 2244
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON"

response = requests.get(url)
if response.status_code == 200:
    annotations = response.json()
    # Contains extensive data including:
    # - Chemical and Physical Properties
    # - Drug and Medication Information
    # - Pharmacology and Biochemistry
    # - Safety and Hazards
    # - Toxicity
    # - Literature references
    # - Patents

Get Specific Section:

# Get only drug information
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON?heading=Drug and Medication Information"

Installation Requirements

Install PubChemPy for Python-based access:

uv pip install pubchempy

For direct API access and bioactivity queries:

uv pip install requests

Optional for data analysis:

uv pip install pandas

Helper Scripts

This skill includes Python scripts for common PubChem tasks:

scripts/compound_search.py

Provides utility functions for searching and retrieving compound information:

Key Functions:

search_by_name(name, max_results=10): Search compounds by name
search_by_smiles(smiles): Search by SMILES string
get_compound_by_cid(cid): Retrieve compound by CID
get_compound_properties(identifier, namespace, properties): Get specific properties
similarity_search(smiles, threshold, max_records): Perform similarity search
substructure_search(smiles, max_records): Perform substructure search
get_synonyms(identifier, namespace): Get all synonyms
batch_search(identifiers, namespace, properties): Batch search multiple compounds
download_structure(identifier, namespace, format, filename): Download structures
print_compound_info(compound): Print formatted compound information

Usage:

from scripts.compound_search import search_by_name, get_compound_properties

# Search for a compound
compounds = search_by_name('ibuprofen')

# Get specific properties
props = get_compound_properties('aspirin', 'name', ['MolecularWeight', 'XLogP'])

scripts/bioactivity_query.py

Provides functions for retrieving biological activity data:

Key Functions:

get_bioassay_summary(cid): Get bioassay summary for compound
get_compound_bioactivities(cid, activity_outcome): Get filtered bioactivities
get_assay_description(aid): Get detailed assay information
get_assay_targets(aid): Get biological targets for assay
search_assays_by_target(target_name, max_results): Find assays by target
get_active_compounds_in_assay(aid, max_results): Get active compounds
get_compound_annotations(cid, section): Get PUG-View annotations
summarize_bioactivities(cid): Generate bioactivity summary statistics
find_compounds_by_bioactivity(target, threshold, max_compounds): Find compounds by target

Usage:

from scripts.bioactivity_query import get_bioassay_summary, summarize_bioactivities

# Get bioactivity summary
summary = summarize_bioactivities(2244)  # Aspirin
print(f"Total assays: {summary['total_assays']}")
print(f"Active: {summary['active']}, Inactive: {summary['inactive']}")

API Rate Limits and Best Practices

Rate Limits:

Maximum 5 requests per second
Maximum 400 requests per minute
Maximum 300 seconds running time per minute

Best Practices:

Use CIDs for repeated queries: CIDs are more efficient than names or structures
Cache results locally: Store frequently accessed data
Batch requests: Combine multiple queries when possible
Implement delays: Add 0.2-0.3 second delays between requests
Handle errors gracefully: Check for HTTP errors and missing data
Use PubChemPy: Higher-level abstraction handles many edge cases
Leverage asynchronous pattern: For large similarity/substructure searches
Specify MaxRecords: Limit results to avoid timeouts

Error Handling:

from pubchempy import BadRequestError, NotFoundError, TimeoutError

try:
    compound = pcp.get_compounds('query', 'name')[0]
except NotFoundError:
    print("Compound not found")
except BadRequestError:
    print("Invalid request format")
except TimeoutError:
    print("Request timed out - try reducing scope")
except IndexError:
    print("No results returned")

Common Workflows

Workflow 1: Chemical Identifier Conversion Pipeline

Convert between different chemical identifiers:

import pubchempy as pcp

# Start with any identifier type
compound = pcp.get_compounds('caffeine', 'name')[0]

# Extract all identifier formats
identifiers = {
    'CID': compound.cid,
    'Name': compound.iupac_name,
    'SMILES': compound.canonical_smiles,
    'InChI': compound.inchi,
    'InChIKey': compound.inchikey,
    'Formula': compound.molecular_formula
}

Workflow 2: Drug-Like Property Screening

Screen compounds using Lipinski's Rule of Five:

import pubchempy as pcp

def check_drug_likeness(compound_name):
    compound = pcp.get_compounds(compound_name, 'name')[0]

    # Lipinski's Rule of Five
    rules = {
        'MW <= 500': compound.molecular_weight <= 500,
        'LogP <= 5': compound.xlogp <= 5 if compound.xlogp else None,
        'HBD <= 5': compound.h_bond_donor_count <= 5,
        'HBA <= 10': compound.h_bond_acceptor_count <= 10
    }

    violations = sum(1 for v in rules.values() if v is False)
    return rules, violations

rules, violations = check_drug_likeness('aspirin')
print(f"Lipinski violations: {violations}")

Workflow 3: Finding Similar Drug Candidates

Identify structurally similar compounds to a known drug:

import pubchempy as pcp

# Start with known drug
reference_drug = pcp.get_compounds('imatinib', 'name')[0]
reference_smiles = reference_drug.canonical_smiles

# Find similar compounds
similar = pcp.get_compounds(
    reference_smiles,
    'smiles',
    searchtype='similarity',
    Threshold=85,
    MaxRecords=20
)

# Filter by drug-like properties
candidates = []
for comp in similar:
    if comp.molecular_weight and 200 <= comp.molecular_weight <= 600:
        if comp.xlogp and -1 <= comp.xlogp <= 5:
            candidates.append(comp)

print(f"Found {len(candidates)} drug-like candidates")

Workflow 4: Batch Compound Property Comparison

Compare properties across multiple compounds:

import pubchempy as pcp
import pandas as pd

compound_list = ['aspirin', 'ibuprofen', 'naproxen', 'celecoxib']

properties_list = []
for name in compound_list:
    try:
        compound = pcp.get_compounds(name, 'name')[0]
        properties_list.append({
            'Name': name,
            'CID': compound.cid,
            'Formula': compound.molecular_formula,
            'MW': compound.molecular_weight,
            'LogP': compound.xlogp,
            'TPSA': compound.tpsa,
            'HBD': compound.h_bond_donor_count,
            'HBA': compound.h_bond_acceptor_count
        })
    except Exception as e:
        print(f"Error processing {name}: {e}")

df = pd.DataFrame(properties_list)
print(df.to_string(index=False))

Workflow 5: Substructure-Based Virtual Screening

Screen for compounds containing specific pharmacophores:

import pubchempy as pcp

# Define pharmacophore (e.g., sulfonamide group)
pharmacophore_smiles = 'S(=O)(=O)N'

# Search for compounds containing this substructure
hits = pcp.get_compounds(
    pharmacophore_smiles,
    'smiles',
    searchtype='substructure',
    MaxRecords=100
)

# Further filter by properties
filtered_hits = [
    comp for comp in hits
    if comp.molecular_weight and comp.molecular_weight < 500
]

print(f"Found {len(filtered_hits)} compounds with desired substructure")

Reference Documentation

For detailed API documentation, including complete property lists, URL patterns, advanced query options, and more examples, consult references/api_reference.md. This comprehensive reference includes:

Complete PUG-REST API endpoint documentation
Full list of available molecular properties
Asynchronous request handling patterns
PubChemPy API reference
PUG-View API for annotations
Common workflows and use cases
Links to official PubChem documentation

Troubleshooting

Compound Not Found:

Try alternative names or synonyms
Use CID if known
Check spelling and chemical name format

Timeout Errors:

Reduce MaxRecords parameter
Add delays between requests
Use CIDs instead of names for faster queries

Empty Property Values:

Not all properties are available for all compounds
Check if property exists before accessing: if compound.xlogp:
Some properties only available for certain compound types

Rate Limit Exceeded:

Implement delays (0.2-0.3 seconds) between requests
Use batch operations where possible
Consider caching results locally

Similarity/Substructure Search Hangs:

These are asynchronous operations that may take 15-30 seconds
PubChemPy handles polling automatically
Reduce MaxRecords if timing out

Additional Resources

PubChem Home: https://pubchem.ncbi.nlm.nih.gov/
PUG-REST Documentation: https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest
PUG-REST Tutorial: https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest-tutorial
PubChemPy Documentation: https://pubchempy.readthedocs.io/
PubChemPy GitHub: https://github.com/mcs07/PubChemPy

About this skill

Automatic

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

FreedomIntelligence / OpenClaw-Medical-Skills

skills/pubchem-database/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1Bundled 3 files · scripts

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

Other skills for the same job

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

PubChem Database

Overview

When to Use This Skill

Core Capabilities

1. Chemical Structure Search

2. Property Retrieval

3. Similarity Search

4. Substructure Search

5. Format Conversion

6. Structure Visualization

7. Synonym Retrieval

8. Bioactivity Data Access

9. Comprehensive Compound Annotations

Installation Requirements

Helper Scripts

scripts/compound_search.py

scripts/bioactivity_query.py

API Rate Limits and Best Practices

Common Workflows

Workflow 1: Chemical Identifier Conversion Pipeline

Workflow 2: Drug-Like Property Screening

Workflow 3: Finding Similar Drug Candidates

Workflow 4: Batch Compound Property Comparison

Workflow 5: Substructure-Based Virtual Screening

Reference Documentation

Troubleshooting

Additional Resources

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry