Ready to supercharge your AI agents?

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

STRING Database · FreedomIntelligence | DecimalAI

Scienceby FreedomIntelligence

STRING Database

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.

SkillScore

SkillScore45/100

Test results 45

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

0%45%of test cases passed +45 pts

Without skill0 of 22

With skill10 of 22

10 fixed0 passed either way12 still failing0 broke

Measured on gemini-3.6-flash7/26/2026v119 comparable

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 string-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("string-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 string-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/string-database/SKILL.md https://app.decimal.ai/s/string-database/SKILL.md

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 2 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 string-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("string-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/string-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/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-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/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/string-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 2 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 string-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("string-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/string-database/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/string-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 2 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 string-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/string-database/SKILL.md https://app.decimal.ai/s/string-database/SKILL.md

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 2 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/string-database/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 2 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

STRING Database

Overview

STRING is a comprehensive database of known and predicted protein-protein interactions covering 59M proteins and 20B+ interactions across 5000+ organisms. Query interaction networks, perform functional enrichment, discover partners via REST API for systems biology and pathway analysis.

When to Use This Skill

This skill should be used when:

Retrieving protein-protein interaction networks for single or multiple proteins
Performing functional enrichment analysis (GO, KEGG, Pfam) on protein lists
Discovering interaction partners and expanding protein networks
Testing if proteins form significantly enriched functional modules
Generating network visualizations with evidence-based coloring
Analyzing homology and protein family relationships
Conducting cross-species protein interaction comparisons
Identifying hub proteins and network connectivity patterns

Quick Start

The skill provides:

Python helper functions (scripts/string_api.py) for all STRING REST API operations
Comprehensive reference documentation (references/string_reference.md) with detailed API specifications

When users request STRING data, determine which operation is needed and use the appropriate function from scripts/string_api.py.

Core Operations

1. Identifier Mapping (`string_map_ids`)

Convert gene names, protein names, and external IDs to STRING identifiers.

When to use: Starting any STRING analysis, validating protein names, finding canonical identifiers.

Usage:

from scripts.string_api import string_map_ids

# Map single protein
result = string_map_ids('TP53', species=9606)

# Map multiple proteins
result = string_map_ids(['TP53', 'BRCA1', 'EGFR', 'MDM2'], species=9606)

# Map with multiple matches per query
result = string_map_ids('p53', species=9606, limit=5)

Parameters:

species: NCBI taxon ID (9606 = human, 10090 = mouse, 7227 = fly)
limit: Number of matches per identifier (default: 1)
echo_query: Include query term in output (default: 1)

Best practice: Always map identifiers first for faster subsequent queries.

2. Network Retrieval (`string_network`)

Get protein-protein interaction network data in tabular format.

When to use: Building interaction networks, analyzing connectivity, retrieving interaction evidence.

Usage:

from scripts.string_api import string_network

# Get network for single protein
network = string_network('9606.ENSP00000269305', species=9606)

# Get network with multiple proteins
proteins = ['9606.ENSP00000269305', '9606.ENSP00000275493']
network = string_network(proteins, required_score=700)

# Expand network with additional interactors
network = string_network('TP53', species=9606, add_nodes=10, required_score=400)

# Physical interactions only
network = string_network('TP53', species=9606, network_type='physical')

Parameters:

required_score: Confidence threshold (0-1000)
- 150: low confidence (exploratory)
- 400: medium confidence (default, standard analysis)
- 700: high confidence (conservative)
- 900: highest confidence (very stringent)
network_type: 'functional' (all evidence, default) or 'physical' (direct binding only)
add_nodes: Add N most connected proteins (0-10)

Output columns: Interaction pairs, confidence scores, and individual evidence scores (neighborhood, fusion, coexpression, experimental, database, text-mining).

3. Network Visualization (`string_network_image`)

Generate network visualization as PNG image.

When to use: Creating figures, visual exploration, presentations.

Usage:

from scripts.string_api import string_network_image

# Get network image
proteins = ['TP53', 'MDM2', 'ATM', 'CHEK2', 'BRCA1']
img_data = string_network_image(proteins, species=9606, required_score=700)

# Save image
with open('network.png', 'wb') as f:
    f.write(img_data)

# Evidence-colored network
img = string_network_image(proteins, species=9606, network_flavor='evidence')

# Confidence-based visualization
img = string_network_image(proteins, species=9606, network_flavor='confidence')

# Actions network (activation/inhibition)
img = string_network_image(proteins, species=9606, network_flavor='actions')

Network flavors:

'evidence': Colored lines show evidence types (default)
'confidence': Line thickness represents confidence
'actions': Shows activating/inhibiting relationships

4. Interaction Partners (`string_interaction_partners`)

Find all proteins that interact with given protein(s).

When to use: Discovering novel interactions, finding hub proteins, expanding networks.

Usage:

from scripts.string_api import string_interaction_partners

# Get top 10 interactors of TP53
partners = string_interaction_partners('TP53', species=9606, limit=10)

# Get high-confidence interactors
partners = string_interaction_partners('TP53', species=9606,
                                      limit=20, required_score=700)

# Find interactors for multiple proteins
partners = string_interaction_partners(['TP53', 'MDM2'],
                                      species=9606, limit=15)

Parameters:

limit: Maximum number of partners to return (default: 10)
required_score: Confidence threshold (0-1000)

Use cases:

Hub protein identification
Network expansion from seed proteins
Discovering indirect connections

5. Functional Enrichment (`string_enrichment`)

Perform enrichment analysis across Gene Ontology, KEGG pathways, Pfam domains, and more.

When to use: Interpreting protein lists, pathway analysis, functional characterization, understanding biological processes.

Usage:

from scripts.string_enrichment import string_enrichment

# Enrichment for a protein list
proteins = ['TP53', 'MDM2', 'ATM', 'CHEK2', 'BRCA1', 'ATR', 'TP73']
enrichment = string_enrichment(proteins, species=9606)

# Parse results to find significant terms
import pandas as pd
df = pd.read_csv(io.StringIO(enrichment), sep='\t')
significant = df[df['fdr'] < 0.05]

Enrichment categories:

Gene Ontology: Biological Process, Molecular Function, Cellular Component
KEGG Pathways: Metabolic and signaling pathways
Pfam: Protein domains
InterPro: Protein families and domains
SMART: Domain architecture
UniProt Keywords: Curated functional keywords

Output columns:

category: Annotation database (e.g., "KEGG Pathways", "GO Biological Process")
term: Term identifier
description: Human-readable term description
number_of_genes: Input proteins with this annotation
p_value: Uncorrected enrichment p-value
fdr: False discovery rate (corrected p-value)

Statistical method: Fisher's exact test with Benjamini-Hochberg FDR correction.

Interpretation: FDR < 0.05 indicates statistically significant enrichment.

6. PPI Enrichment (`string_ppi_enrichment`)

Test if a protein network has significantly more interactions than expected by chance.

When to use: Validating if proteins form functional module, testing network connectivity.

Usage:

from scripts.string_api import string_ppi_enrichment
import json

# Test network connectivity
proteins = ['TP53', 'MDM2', 'ATM', 'CHEK2', 'BRCA1']
result = string_ppi_enrichment(proteins, species=9606, required_score=400)

# Parse JSON result
data = json.loads(result)
print(f"Observed edges: {data['number_of_edges']}")
print(f"Expected edges: {data['expected_number_of_edges']}")
print(f"P-value: {data['p_value']}")

Output fields:

number_of_nodes: Proteins in network
number_of_edges: Observed interactions
expected_number_of_edges: Expected in random network
p_value: Statistical significance

Interpretation:

p-value < 0.05: Network is significantly enriched (proteins likely form functional module)
p-value ≥ 0.05: No significant enrichment (proteins may be unrelated)

7. Homology Scores (`string_homology`)

Retrieve protein similarity and homology information.

When to use: Identifying protein families, paralog analysis, cross-species comparisons.

Usage:

from scripts.string_api import string_homology

# Get homology between proteins
proteins = ['TP53', 'TP63', 'TP73']  # p53 family
homology = string_homology(proteins, species=9606)

Use cases:

Protein family identification
Paralog discovery
Evolutionary analysis

8. Version Information (`string_version`)

Get current STRING database version.

When to use: Ensuring reproducibility, documenting methods.

Usage:

from scripts.string_api import string_version

version = string_version()
print(f"STRING version: {version}")

Common Analysis Workflows

Workflow 1: Protein List Analysis (Standard Workflow)

Use case: Analyze a list of proteins from experiment (e.g., differential expression, proteomics).

from scripts.string_api import (string_map_ids, string_network,
                                string_enrichment, string_ppi_enrichment,
                                string_network_image)

# Step 1: Map gene names to STRING IDs
gene_list = ['TP53', 'BRCA1', 'ATM', 'CHEK2', 'MDM2', 'ATR', 'BRCA2']
mapping = string_map_ids(gene_list, species=9606)

# Step 2: Get interaction network
network = string_network(gene_list, species=9606, required_score=400)

# Step 3: Test if network is enriched
ppi_result = string_ppi_enrichment(gene_list, species=9606)

# Step 4: Perform functional enrichment
enrichment = string_enrichment(gene_list, species=9606)

# Step 5: Generate network visualization
img = string_network_image(gene_list, species=9606,
                          network_flavor='evidence', required_score=400)
with open('protein_network.png', 'wb') as f:
    f.write(img)

# Step 6: Parse and interpret results

Workflow 2: Single Protein Investigation

Use case: Deep dive into one protein's interactions and partners.

from scripts.string_api import (string_map_ids, string_interaction_partners,
                                string_network_image)

# Step 1: Map protein name
protein = 'TP53'
mapping = string_map_ids(protein, species=9606)

# Step 2: Get all interaction partners
partners = string_interaction_partners(protein, species=9606,
                                      limit=20, required_score=700)

# Step 3: Visualize expanded network
img = string_network_image(protein, species=9606, add_nodes=15,
                          network_flavor='confidence', required_score=700)
with open('tp53_network.png', 'wb') as f:
    f.write(img)

Workflow 3: Pathway-Centric Analysis

Use case: Identify and visualize proteins in a specific biological pathway.

from scripts.string_api import string_enrichment, string_network

# Step 1: Start with known pathway proteins
dna_repair_proteins = ['TP53', 'ATM', 'ATR', 'CHEK1', 'CHEK2',
                       'BRCA1', 'BRCA2', 'RAD51', 'XRCC1']

# Step 2: Get network
network = string_network(dna_repair_proteins, species=9606,
                        required_score=700, add_nodes=5)

# Step 3: Enrichment to confirm pathway annotation
enrichment = string_enrichment(dna_repair_proteins, species=9606)

# Step 4: Parse enrichment for DNA repair pathways
import pandas as pd
import io
df = pd.read_csv(io.StringIO(enrichment), sep='\t')
dna_repair = df[df['description'].str.contains('DNA repair', case=False)]

Workflow 4: Cross-Species Analysis

Use case: Compare protein interactions across different organisms.

from scripts.string_api import string_network

# Human network
human_network = string_network('TP53', species=9606, required_score=700)

# Mouse network
mouse_network = string_network('Trp53', species=10090, required_score=700)

# Yeast network (if ortholog exists)
yeast_network = string_network('gene_name', species=4932, required_score=700)

Workflow 5: Network Expansion and Discovery

Use case: Start with seed proteins and discover connected functional modules.

from scripts.string_api import (string_interaction_partners, string_network,
                                string_enrichment)

# Step 1: Start with seed protein(s)
seed_proteins = ['TP53']

# Step 2: Get first-degree interactors
partners = string_interaction_partners(seed_proteins, species=9606,
                                      limit=30, required_score=700)

# Step 3: Parse partners to get protein list
import pandas as pd
import io
df = pd.read_csv(io.StringIO(partners), sep='\t')
all_proteins = list(set(df['preferredName_A'].tolist() +
                       df['preferredName_B'].tolist()))

# Step 4: Perform enrichment on expanded network
enrichment = string_enrichment(all_proteins[:50], species=9606)

# Step 5: Filter for interesting functional modules
enrichment_df = pd.read_csv(io.StringIO(enrichment), sep='\t')
modules = enrichment_df[enrichment_df['fdr'] < 0.001]

Common Species

When specifying species, use NCBI taxon IDs:

Organism	Common Name	Taxon ID
Homo sapiens	Human	9606
Mus musculus	Mouse	10090
Rattus norvegicus	Rat	10116
Drosophila melanogaster	Fruit fly	7227
Caenorhabditis elegans	C. elegans	6239
Saccharomyces cerevisiae	Yeast	4932
Arabidopsis thaliana	Thale cress	3702
Escherichia coli	E. coli	511145
Danio rerio	Zebrafish	7955

Full list available at: https://string-db.org/cgi/input?input_page_active_form=organisms

Understanding Confidence Scores

STRING provides combined confidence scores (0-1000) integrating multiple evidence types:

Evidence Channels

Neighborhood (nscore): Conserved genomic neighborhood across species
Fusion (fscore): Gene fusion events
Phylogenetic Profile (pscore): Co-occurrence patterns across species
Coexpression (ascore): Correlated RNA expression
Experimental (escore): Biochemical and genetic experiments
Database (dscore): Curated pathway and complex databases
Text-mining (tscore): Literature co-occurrence and NLP extraction

Recommended Thresholds

Choose threshold based on analysis goals:

150 (low confidence): Exploratory analysis, hypothesis generation
400 (medium confidence): Standard analysis, balanced sensitivity/specificity
700 (high confidence): Conservative analysis, high-confidence interactions
900 (highest confidence): Very stringent, experimental evidence preferred

Trade-offs:

Lower thresholds: More interactions (higher recall, more false positives)
Higher thresholds: Fewer interactions (higher precision, more false negatives)

Network Types

Functional Networks (Default)

Includes all evidence types (experimental, computational, text-mining). Represents proteins that are functionally associated, even without direct physical binding.

When to use:

Pathway analysis
Functional enrichment studies
Systems biology
Most general analyses

Physical Networks

Only includes evidence for direct physical binding (experimental data and database annotations for physical interactions).

When to use:

Structural biology studies
Protein complex analysis
Direct binding validation
When physical contact is required

API Best Practices

Always map identifiers first: Use string_map_ids() before other operations for faster queries
Use STRING IDs when possible: Use format 9606.ENSP00000269305 instead of gene names
Specify species for networks >10 proteins: Required for accurate results
Respect rate limits: Wait 1 second between API calls
Use versioned URLs for reproducibility: Available in reference documentation
Handle errors gracefully: Check for "Error:" prefix in returned strings
Choose appropriate confidence thresholds: Match threshold to analysis goals

Detailed Reference

For comprehensive API documentation, complete parameter lists, output formats, and advanced usage, refer to references/string_reference.md. This includes:

Complete API endpoint specifications
All supported output formats (TSV, JSON, XML, PSI-MI)
Advanced features (bulk upload, values/ranks enrichment)
Error handling and troubleshooting
Integration with other tools (Cytoscape, R, Python libraries)
Data license and citation information

Troubleshooting

No proteins found:

Verify species parameter matches identifiers
Try mapping identifiers first with string_map_ids()
Check for typos in protein names

Empty network results:

Lower confidence threshold (required_score)
Check if proteins actually interact
Verify species is correct

Timeout or slow queries:

Reduce number of input proteins
Use STRING IDs instead of gene names
Split large queries into batches

"Species required" error:

Add species parameter for networks with >10 proteins
Always include species for consistency

Results look unexpected:

Check STRING version with string_version()
Verify network_type is appropriate (functional vs physical)
Review confidence threshold selection

Additional Resources

For proteome-scale analysis or complete species network upload:

Visit https://string-db.org
Use "Upload proteome" feature
STRING will generate complete interaction network and predict functions

For bulk downloads of complete datasets:

Download page: https://string-db.org/cgi/download
Includes complete interaction files, protein annotations, and pathway mappings

Data License

STRING data is freely available under Creative Commons BY 4.0 license:

Free for academic and commercial use
Attribution required when publishing
Cite latest STRING publication

Citation

When using STRING in publications, cite the most recent publication from: https://string-db.org/cgi/about

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/string-database/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1Bundled 2 files · scripts

Illustrative Want to see what string-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

STRING Database

Overview

When to Use This Skill

Quick Start

Core Operations

1. Identifier Mapping (string_map_ids)

2. Network Retrieval (string_network)

3. Network Visualization (string_network_image)

4. Interaction Partners (string_interaction_partners)

5. Functional Enrichment (string_enrichment)

6. PPI Enrichment (string_ppi_enrichment)

7. Homology Scores (string_homology)

8. Version Information (string_version)

Common Analysis Workflows

Workflow 1: Protein List Analysis (Standard Workflow)

Workflow 2: Single Protein Investigation

Workflow 3: Pathway-Centric Analysis

Workflow 4: Cross-Species Analysis

Workflow 5: Network Expansion and Discovery

Common Species

Understanding Confidence Scores

Evidence Channels

Recommended Thresholds

Network Types

Functional Networks (Default)

Physical Networks

API Best Practices

Detailed Reference

Troubleshooting

Additional Resources

Data License

Citation

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry

1. Identifier Mapping (`string_map_ids`)

2. Network Retrieval (`string_network`)

3. Network Visualization (`string_network_image`)

4. Interaction Partners (`string_interaction_partners`)

5. Functional Enrichment (`string_enrichment`)

6. PPI Enrichment (`string_ppi_enrichment`)

7. Homology Scores (`string_homology`)

8. Version Information (`string_version`)