Ready to supercharge your AI agents?

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

Get Started Free →

VueUse Functions · antfu | DecimalAI

Frontendby antfu

VueUse Functions

Apply VueUse composables where appropriate to build concise, maintainable Vue.js / Nuxt features.

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

50%50%of checks passed 0 pts

Without skill50%

With skill50%

4 fixed16 passed either way1 still failing2 broke

Measured on gemini-3.6-flash8/2/2026v2

Track record

Agent runs: 3; 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 vueuse-functions
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("vueuse-functions")
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 vueuse-functions

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/vueuse-functions/SKILL.md https://app.decimal.ai/s/vueuse-functions/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/vueuse-functions/SKILL.md

This gets SKILL.md only. The skill's 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/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/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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("vueuse-functions")
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/vueuse-functions/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/vueuse-functions/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 265 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 vueuse-functions

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/vueuse-functions/SKILL.md https://app.decimal.ai/s/vueuse-functions/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/vueuse-functions/SKILL.md

This gets SKILL.md only. The skill's 265 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/vueuse-functions/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/vueuse-functions.json

This gets SKILL.md only. The skill's 265 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2, tested 8/2/2026
Source: antfu/skills ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

references/

SKILL.md

VueUse Functions

This skill is a decision-and-implementation guide for VueUse composables in Vue.js / Nuxt projects. It maps requirements to the most suitable VueUse function, applies the correct usage pattern, and prefers composable-based solutions over bespoke code to keep implementations concise, maintainable, and performant.

When to Apply

Apply this skill whenever assisting user development work in Vue.js / Nuxt.
Always check first whether a VueUse function can implement the requirement.
Prefer VueUse composables over custom code to improve readability, maintainability, and performance.
Map requirements to the most appropriate VueUse function and follow the function’s invocation rule.
Please refer to the Invocation field in the below functions table. For example:
- AUTO: Use automatically when applicable.
- EXTERNAL: Use only if the user already installed the required external dependency; otherwise reconsider, and ask to install only if truly needed.
- EXPLICIT_ONLY: Use only when explicitly requested by the user.
NOTE User instructions in the prompt or AGENTS.md may override a function’s default Invocation rule.

Functions

All functions listed below are part of the VueUse library, each section categorizes functions based on their functionality.

IMPORTANT: Each function entry includes a short Description and a detailed Reference. When using any function, always consult the corresponding document in ./references for Usage details and Type Declarations.

State

Function	Description	Invocation
`createGlobalState`	Keep states in the global scope to be reusable across Vue instances	AUTO
`createInjectionState`	Create global state that can be injected into components	AUTO
`createSharedComposable`	Make a composable function usable with multiple Vue instances	AUTO
`injectLocal`	Extended `inject` with ability to call `provideLocal` to provide the value in the same component	AUTO
`provideLocal`	Extended `provide` with ability to call `injectLocal` to obtain the value in the same component	AUTO
`useAsyncState`	Reactive async state	AUTO
`useDebouncedRefHistory`	Shorthand for `useRefHistory` with debounced filter	AUTO
`useLastChanged`	Records the timestamp of the last change	AUTO
`useLocalStorage`	Reactive LocalStorage	AUTO
`useManualRefHistory`	Manually track the change history of a ref when the user calls `commit()`	AUTO
`useRefHistory`	Track the change history of a ref	AUTO
`useSessionStorage`	Reactive SessionStorage	AUTO
`useStorage`	Create a reactive ref that can be used to access & modify LocalStorage or SessionStorage	AUTO
`useStorageAsync`	Reactive Storage with async support	AUTO
`useThrottledRefHistory`	Shorthand for `useRefHistory` with throttled filter	AUTO

Elements

Function	Description	Invocation
`useActiveElement`	Reactive `document.activeElement`	AUTO
`useDocumentVisibility`	Reactively track `document.visibilityState`	AUTO
`useDraggable`	Make elements draggable	AUTO
`useDropZone`	Create a zone where files can be dropped	AUTO
`useElementBounding`	Reactive bounding box of an HTML element	AUTO
`useElementSize`	Reactive size of an HTML element	AUTO
`useElementVisibility`	Tracks the visibility of an element within the viewport	AUTO
`useIntersectionObserver`	Detects changes to a target element's visibility	AUTO
`useMouseInElement`	Reactive mouse position related to an element	AUTO
`useMutationObserver`	Watch for changes being made to the DOM tree	AUTO
`useParentElement`	Get parent element of the given element	AUTO
`useResizeObserver`	Reports changes to the dimensions of an Element's content or the border-box	AUTO
`useWindowFocus`	Reactively track window focus with `window.onfocus` and `window.onblur` events	AUTO
`useWindowScroll`	Reactive window scroll	AUTO
`useWindowSize`	Reactive window size	AUTO

Browser

Function	Description	Invocation
`useBluetooth`	Reactive Web Bluetooth API	AUTO
`useBreakpoints`	Reactive viewport breakpoints	AUTO
`useBroadcastChannel`	Reactive BroadcastChannel API	AUTO
`useBrowserLocation`	Reactive browser location	AUTO
`useClipboard`	Reactive Clipboard API	AUTO
`useClipboardItems`	Reactive Clipboard API	AUTO
`useColorMode`	Reactive color mode (dark / light / customs) with auto data persistence	AUTO
`useCssSupports`	SSR compatible and reactive `CSS.supports`	AUTO
`useCssVar`	Manipulate CSS variables	AUTO
`useDark`	Reactive dark mode with auto data persistence	AUTO
`useEventListener`	Use EventListener with ease	AUTO
`useEyeDropper`	Reactive EyeDropper API	AUTO
`useFavicon`	Reactive favicon	AUTO
`useFileDialog`	Open file dialog with ease	AUTO
`useFileSystemAccess`	Create and read and write local files with FileSystemAccessAPI	AUTO
`useFullscreen`	Reactive Fullscreen API	AUTO
`useGamepad`	Provides reactive bindings for the Gamepad API	AUTO
`useImage`	Reactive load an image in the browser	AUTO
`useMediaControls`	Reactive media controls for both `audio` and `video` elements	AUTO
`useMediaQuery`	Reactive Media Query	AUTO
`useMemory`	Reactive Memory Info	AUTO
`useObjectUrl`	Reactive URL representing an object	AUTO
`usePerformanceObserver`	Observe performance metrics	AUTO
`usePermission`	Reactive Permissions API	AUTO
`usePreferredColorScheme`	Reactive prefers-color-scheme media query	AUTO
`usePreferredContrast`	Reactive prefers-contrast media query	AUTO
`usePreferredDark`	Reactive dark theme preference	AUTO
`usePreferredLanguages`	Reactive Navigator Languages	AUTO
`usePreferredReducedMotion`	Reactive prefers-reduced-motion media query	AUTO
`usePreferredReducedTransparency`	Reactive prefers-reduced-transparency media query	AUTO
`useScreenOrientation`	Reactive Screen Orientation API	AUTO
`useScreenSafeArea`	Reactive `env(safe-area-inset-*)`	AUTO
`useScriptTag`	Creates a script tag	AUTO
`useShare`	Reactive Web Share API	AUTO
`useSSRWidth`	Used to set a global viewport width which will be used when rendering SSR components that rely on the viewport width like `useMediaQuery` or `useBreakpoints`	AUTO
`useStyleTag`	Inject reactive `style` element in head	AUTO
`useTextareaAutosize`	Automatically update the height of a textarea depending on the content	AUTO
`useTextDirection`	Reactive dir of the element's text	AUTO
`useTitle`	Reactive document title	AUTO
`useUrlSearchParams`	Reactive URLSearchParams	AUTO
`useVibrate`	Reactive Vibration API	AUTO
`useWakeLock`	Reactive Screen Wake Lock API	AUTO
`useWebNotification`	Reactive Notification	AUTO
`useWebWorker`	Simple Web Workers registration and communication	AUTO
`useWebWorkerFn`	Run expensive functions without blocking the UI	AUTO

Sensors

Function	Description	Invocation
`onClickOutside`	Listen for clicks outside of an element	AUTO
`onElementRemoval`	Fires when the element or any element containing it is removed from the DOM	AUTO
`onKeyStroke`	Listen for keyboard keystrokes	AUTO
`onLongPress`	Listen for a long press on an element	AUTO
`onStartTyping`	Fires when users start typing on non-editable elements	AUTO
`useBattery`	Reactive Battery Status API	AUTO
`useDeviceMotion`	Reactive DeviceMotionEvent	AUTO
`useDeviceOrientation`	Reactive DeviceOrientationEvent	AUTO
`useDevicePixelRatio`	Reactively track `window.devicePixelRatio`	AUTO
`useDevicesList`	Reactive enumerateDevices listing available input/output devices	AUTO
`useDisplayMedia`	Reactive `mediaDevices.getDisplayMedia` streaming	AUTO
`useElementByPoint`	Reactive element by point	AUTO
`useElementHover`	Reactive element's hover state	AUTO
`useFocus`	Reactive utility to track or set the focus state of a DOM element	AUTO
`useFocusWithin`	Reactive utility to track if an element or one of its descendants has focus	AUTO
`useFps`	Reactive FPS (frames per second)	AUTO
`useGeolocation`	Reactive Geolocation API	AUTO
`useIdle`	Tracks whether the user is being inactive	AUTO
`useInfiniteScroll`	Infinite scrolling of the element	AUTO
`useKeyModifier`	Reactive Modifier State	AUTO
`useMagicKeys`	Reactive keys pressed state	AUTO
`useMouse`	Reactive mouse position	AUTO
`useMousePressed`	Reactive mouse pressing state	AUTO
`useNavigatorLanguage`	Reactive navigator.language	AUTO
`useNetwork`	Reactive Network status	AUTO
`useOnline`	Reactive online state	AUTO
`usePageLeave`	Reactive state to show whether the mouse leaves the page	AUTO
`useParallax`	Create parallax effect easily	AUTO
`usePointer`	Reactive pointer state	AUTO
`usePointerLock`	Reactive pointer lock	AUTO
`usePointerSwipe`	Reactive swipe detection based on PointerEvents	AUTO
`useScroll`	Reactive scroll position and state	AUTO
`useScrollLock`	Lock scrolling of the element	AUTO
`useSpeechRecognition`	Reactive SpeechRecognition	AUTO
`useSpeechSynthesis`	Reactive SpeechSynthesis	AUTO
`useSwipe`	Reactive swipe detection based on `TouchEvents`	AUTO
`useTextSelection`	Reactively track user text selection based on `Window.getSelection`	AUTO
`useUserMedia`	Reactive `mediaDevices.getUserMedia` streaming	AUTO

Network

Function	Description	Invocation
`useEventSource`	An EventSource or Server-Sent-Events instance opens a persistent connection to an HTTP server	AUTO
`useFetch`	Reactive Fetch API provides the ability to abort requests	AUTO
`useWebSocket`	Reactive WebSocket client	AUTO

Animation

Function	Description	Invocation
`useAnimate`	Reactive Web Animations API	AUTO
`useInterval`	Reactive counter that increases on every interval	AUTO
`useIntervalFn`	Wrapper for `setInterval` with controls	AUTO
`useNow`	Reactive current Date instance	AUTO
`useRafFn`	Call function on every `requestAnimationFrame`	AUTO
`useTimeout`	Reactive value that becomes `true` after a given time	AUTO
`useTimeoutFn`	Wrapper for `setTimeout` with controls	AUTO
`useTimestamp`	Reactive current timestamp	AUTO
`useTransition`	Transition between values	AUTO

Component

Function	Description	Invocation
`computedInject`	Combine `computed` and `inject`	AUTO
`createReusableTemplate`	Define and reuse template inside the component scope	AUTO
`createTemplatePromise`	Template as Promise	AUTO
`templateRef`	Shorthand for binding ref to template element	AUTO
`tryOnBeforeMount`	Safe `onBeforeMount`	AUTO
`tryOnBeforeUnmount`	Safe `onBeforeUnmount`	AUTO
`tryOnMounted`	Safe `onMounted`	AUTO
`tryOnScopeDispose`	Safe `onScopeDispose`	AUTO
`tryOnUnmounted`	Safe `onUnmounted`	AUTO
`unrefElement`	Retrieves the underlying DOM element from a Vue ref or component instance	AUTO
`useCurrentElement`	Get the DOM element of current component as a ref	AUTO
`useMounted`	Mounted state in ref	AUTO
`useTemplateRefsList`	Shorthand for binding refs to template elements and components inside `v-for`	AUTO
`useVirtualList`	Create virtual lists with ease	AUTO
`useVModel`	Shorthand for v-model binding	AUTO
`useVModels`	Shorthand for props v-model binding	AUTO

Watch

Function	Description	Invocation
`until`	Promised one-time watch for changes	AUTO
`watchArray`	Watch for an array with additions and removals	AUTO
`watchAtMost`	`watch` with the number of times triggered	AUTO
`watchDebounced`	Debounced watch	AUTO
`watchDeep`	Shorthand for watching value with `{deep: true}`	AUTO
`watchIgnorable`	Ignorable watch	AUTO
`watchImmediate`	Shorthand for watching value with `{immediate: true}`	AUTO
`watchOnce`	Shorthand for watching value with `{ once: true }`	AUTO
`watchPausable`	Pausable watch	AUTO
`watchThrottled`	Throttled watch	AUTO
`watchTriggerable`	Watch that can be triggered manually	AUTO
`watchWithFilter`	`watch` with additional EventFilter control	AUTO
`whenever`	Shorthand for watching value to be truthy	AUTO

Reactivity

Function	Description	Invocation
`computedAsync`	Computed for async functions	AUTO
`computedEager`	Eager computed without lazy evaluation	AUTO
`computedWithControl`	Explicitly define the dependencies of computed	AUTO
`createRef`	Returns a `deepRef` or `shallowRef` depending on the `deep` param	AUTO
`extendRef`	Add extra attributes to Ref	AUTO
`reactify`	Converts plain functions into reactive functions	AUTO
`reactifyObject`	Apply `reactify` to an object	AUTO
`reactiveComputed`	Computed reactive object	AUTO
`reactiveOmit`	Reactively omit fields from a reactive object	AUTO
`reactivePick`	Reactively pick fields from a reactive object	AUTO
`refAutoReset`	A ref which will be reset to the default value after some time	AUTO
`refDebounced`	Debounce execution of a ref value	AUTO
`refDefault`	Apply default value to a ref	AUTO
`refManualReset`	Create a ref with manual reset functionality	AUTO
`refThrottled`	Throttle changing of a ref value	AUTO
`refWithControl`	Fine-grained controls over ref and its reactivity	AUTO
`syncRef`	Two-way refs synchronization	AUTO
`syncRefs`	Keep target refs in sync with a source ref	AUTO
`toReactive`	Converts ref to reactive	AUTO
`toRef`	Normalize value/ref/getter to `ref` or `computed`	EXPLICIT_ONLY
`toRefs`	Extended `toRefs` that also accepts refs of an object	AUTO

Array

Function	Description	Invocation
`useArrayDifference`	Reactive get array difference of two arrays	AUTO
`useArrayEvery`	Reactive `Array.every`	AUTO
`useArrayFilter`	Reactive `Array.filter`	AUTO
`useArrayFind`	Reactive `Array.find`	AUTO
`useArrayFindIndex`	Reactive `Array.findIndex`	AUTO
`useArrayFindLast`	Reactive `Array.findLast`	AUTO
`useArrayIncludes`	Reactive `Array.includes`	AUTO
`useArrayJoin`	Reactive `Array.join`	AUTO
`useArrayMap`	Reactive `Array.map`	AUTO
`useArrayReduce`	Reactive `Array.reduce`	AUTO
`useArraySome`	Reactive `Array.some`	AUTO
`useArrayUnique`	Reactive unique array	AUTO
`useSorted`	Reactive sort array	AUTO

Time

Function	Description	Invocation
`useCountdown`	Reactive countdown timer in seconds	AUTO
`useDateFormat`	Get the formatted date according to the string of tokens passed in	AUTO
`useTimeAgo`	Reactive time ago	AUTO
`useTimeAgoIntl`	Reactive time ago with i18n supported	AUTO

Utilities

Function	Description	Invocation
`createDisposableDirective`	Utility for authoring disposable directives	AUTO
`createEventHook`	Utility for creating event hooks	AUTO
`createUnrefFn`	Make a plain function accepting ref and raw values as arguments	AUTO
`get`	Shorthand for accessing `ref.value`	EXPLICIT_ONLY
`isDefined`	Non-nullish checking type guard for Ref	AUTO
`makeDestructurable`	Make isomorphic destructurable for object and array at the same time	AUTO
`set`	Shorthand for `ref.value = x`	EXPLICIT_ONLY
`useAsyncQueue`	Executes each asynchronous task sequentially and passes the current task result to the next task	AUTO
`useBase64`	Reactive base64 transforming	AUTO
`useCached`	Cache a ref with a custom comparator	AUTO
`useCloned`	Reactive clone of a ref	AUTO
`useConfirmDialog`	Creates event hooks to support modals and confirmation dialog chains	AUTO
`useCounter`	Basic counter with utility functions	AUTO
`useCycleList`	Cycle through a list of items	AUTO
`useDebounceFn`	Debounce execution of a function	AUTO
`useEventBus`	A basic event bus	AUTO
`useMemoize`	Cache results of functions depending on arguments and keep it reactive	AUTO
`useOffsetPagination`	Reactive offset pagination	AUTO
`usePrevious`	Holds the previous value of a ref	AUTO
`useStepper`	Provides helpers for building a multi-step wizard interface	AUTO
`useSupported`	SSR compatibility `isSupported`	AUTO
`useThrottleFn`	Throttle execution of a function	AUTO
`useTimeoutPoll`	Use timeout to poll something	AUTO
`useToggle`	A boolean switcher with utility functions	AUTO
`useToNumber`	Reactively convert a string ref to number	AUTO
`useToString`	Reactively convert a ref to string	AUTO

@Electron

Function	Description	Invocation
`useIpcRenderer`	Provides ipcRenderer and all of its APIs with Vue reactivity	EXTERNAL
`useIpcRendererInvoke`	Reactive ipcRenderer.invoke API result	EXTERNAL
`useIpcRendererOn`	Use ipcRenderer.on with ease and ipcRenderer.removeListener automatically on unmounted	EXTERNAL
`useZoomFactor`	Reactive WebFrame zoom factor	EXTERNAL
`useZoomLevel`	Reactive WebFrame zoom level	EXTERNAL

@Firebase

Function	Description	Invocation
`useAuth`	Reactive Firebase Auth binding	EXTERNAL
`useFirestore`	Reactive Firestore binding	EXTERNAL
`useRTDB`	Reactive Firebase Realtime Database binding	EXTERNAL

@Head

Function	Description	Invocation
`createHead`	Create the head manager instance.	EXTERNAL
`useHead`	Update head meta tags reactively.	EXTERNAL

@Integrations

Function	Description	Invocation
`useAsyncValidator`	Wrapper for `async-validator`	EXTERNAL
`useAxios`	Wrapper for `axios`	EXTERNAL
`useChangeCase`	Reactive wrapper for `change-case`	EXTERNAL
`useCookies`	Wrapper for `universal-cookie`	EXTERNAL
`useDrauu`	Reactive instance for drauu	EXTERNAL
`useFocusTrap`	Reactive wrapper for `focus-trap`	EXTERNAL
`useFuse`	Easily implement fuzzy search using a composable with Fuse.js	EXTERNAL
`useIDBKeyval`	Wrapper for `idb-keyval`	EXTERNAL
`useJwt`	Wrapper for `jwt-decode`	EXTERNAL
`useNProgress`	Reactive wrapper for `nprogress`	EXTERNAL
`useQRCode`	Wrapper for `qrcode`	EXTERNAL
`useSortable`	Wrapper for `sortable`	EXTERNAL

@Math

Function	Description	Invocation
`createGenericProjection`	Generic version of `createProjection`	EXTERNAL
`createProjection`	Reactive numeric projection from one domain to another	EXTERNAL
`logicAnd`	`AND` condition for refs	EXTERNAL
`logicNot`	`NOT` condition for ref	EXTERNAL
`logicOr`	`OR` conditions for refs	EXTERNAL
`useAbs`	Reactive `Math.abs`	EXTERNAL
`useAverage`	Get the average of an array reactively	EXTERNAL
`useCeil`	Reactive `Math.ceil`	EXTERNAL
`useClamp`	Reactively clamp a value between two other values	EXTERNAL
`useFloor`	Reactive `Math.floor`	EXTERNAL
`useMath`	Reactive `Math` methods	EXTERNAL
`useMax`	Reactive `Math.max`	EXTERNAL
`useMin`	Reactive `Math.min`	EXTERNAL
`usePrecision`	Reactively set the precision of a number	EXTERNAL
`useProjection`	Reactive numeric projection from one domain to another	EXTERNAL
`useRound`	Reactive `Math.round`	EXTERNAL
`useSum`	Get the sum of an array reactively	EXTERNAL
`useTrunc`	Reactive `Math.trunc`	EXTERNAL

@Motion

Function	Description	Invocation
`useElementStyle`	Sync a reactive object to a target element CSS styling	EXTERNAL
`useElementTransform`	Sync a reactive object to a target element CSS transform.	EXTERNAL
`useMotion`	Putting your components in motion.	EXTERNAL
`useMotionProperties`	Access Motion Properties for a target element.	EXTERNAL
`useMotionVariants`	Handle the Variants state and selection.	EXTERNAL
`useSpring`	Spring animations.	EXTERNAL

@Router

Function	Description	Invocation
`useRouteHash`	Shorthand for a reactive `route.hash`	EXTERNAL
`useRouteParams`	Shorthand for a reactive `route.params`	EXTERNAL
`useRouteQuery`	Shorthand for a reactive `route.query`	EXTERNAL

@RxJS

Function	Description	Invocation
`from`	Wrappers around RxJS's `from()` and `fromEvent()` to allow them to accept `ref`s	EXTERNAL
`toObserver`	Sugar function to convert a `ref` into an RxJS Observer	EXTERNAL
`useExtractedObservable`	Use an RxJS `Observable` as extracted from one or more composables	EXTERNAL
`useObservable`	Use an RxJS `Observable`	EXTERNAL
`useSubject`	Bind an RxJS `Subject` to a `ref` and propagate value changes both ways	EXTERNAL
`useSubscription`	Use an RxJS `Subscription` without worrying about unsubscribing from it or creating memory leaks	EXTERNAL
`watchExtractedObservable`	Watch the values of an RxJS `Observable` as extracted from one or more composables	EXTERNAL

@SchemaOrg

Function	Description	Invocation
`createSchemaOrg`	Create the schema.org manager instance.	EXTERNAL
`useSchemaOrg`	Update schema.org reactively.	EXTERNAL

@Sound

Function	Description	Invocation
`useSound`	Play sound effects reactively.	EXTERNAL

About this skill

Automatic

Frontend / UI pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/22/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

antfu / skills

skills/vueuse-functions/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v2Bundled 265 files

Illustrative Want to see what vueuse-functions 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.

vueuse/vueuse-functionsApply VueUse composables where appropriate to build concise, maintainable Vue.js / Nuxt features.Near-identical description+13 pts pass-rate lift

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

Safety

What it changes

Track record

Use this skill

VueUse Functions

When to Apply

Functions

State

Elements

Browser

Sensors

Network

Animation

Component

Watch

Reactivity

Array

Time

Utilities

@Electron

@Firebase

@Head

@Integrations

@Math

@Motion

@Router

@RxJS

@SchemaOrg

@Sound

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry