Ready to supercharge your AI agents?

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

Get Started Free →

LINE Official Account Manager · leoyeai | DecimalAI

Sales & Supportby leoyeai

LINE Official Account Manager

Operate LINE Official Account Manager (chat.line.biz) via browser automation.

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

23%77%of test cases passed +55 pts

Without skill5 of 22

With skill17 of 22

13 fixed4 passed either way4 still failing1 broke

Measured on gemini-3.6-flash8/8/2026v118 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI need to attach a private note regarding customer preferences to a LINE OA conversation. Where are these notes entered, and what is the maximum character limit per note?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-line-oa
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("leoyeai-line-oa")
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 leoyeai-line-oa

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/leoyeai-line-oa/SKILL.md https://app.decimal.ai/s/leoyeai-line-oa/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-line-oa/SKILL.md

This gets SKILL.md only. The skill's 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/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/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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("leoyeai-line-oa")
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/leoyeai-line-oa/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-line-oa/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 6 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 leoyeai-line-oa

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/leoyeai-line-oa/SKILL.md https://app.decimal.ai/s/leoyeai-line-oa/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-line-oa/SKILL.md

This gets SKILL.md only. The skill's 6 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/leoyeai-line-oa/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-line-oa.json

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-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

SKILL.md

LINE Official Account Manager

⚠️ CRITICAL: Always use profile:"openclaw" (isolated browser) for all browser actions. Never use Chrome relay. Keep the same targetId across operations to avoid losing the tab.

⚠️ CONTEXT Management:

Snapshot results are large. Do NOT repeat them in thinking.
Extract needed info and process immediately. Do not re-describe the entire snapshot.
Preferred approach: Use snapshot refs:"aria" compact:true to find element refs, then act + click/type with ref.
Avoid: Hard-coded evaluate with textContent.includes() — unreliable due to DOM timing and structure variations.

⚠️ AUTO-LOGIN SCRIPTS:

auto-login.mjs is a reference implementation (not directly executable by agents)
login-flow.md is the agent-executable version (use this for automation)
Why separate? Agents use browser tool calls, not Node module imports

Configuration

Before first use, check if config.json exists:

read file_path:"skills/line-oa/config.json"

⚠️ PATH RULE: Always use workspace-relative paths starting from skills/line-oa/. Never use ../ or absolute paths starting with /.

If missing, help the user run the following command to start the setup wizard:

cd skills/line-oa
node scripts/setup.js

Enter LINE OA Manager

This is the first step for all operations below.

Check and start browser service:
```
browser action:"status"
```
If "running": false, start the browser service:
```
browser action:"start" profile:"openclaw"
```
Wait 2-3 seconds for the service to initialize.
Read config to get chatUrl:
```
read file_path:"skills/line-oa/config.json"
```
Extract chatUrl from the JSON (e.g., https://chat.line.biz/U1234567890abcdef1234567890abcdef/).

Open browser:

browser action:"open" profile:"openclaw" targetUrl:"<chatUrl>"

Capture targetId and url from response.

Wait for page load:

browser action:"act" profile:"openclaw" targetId:"<targetId>" request:{"kind":"wait","timeMs":2000}

Check current URL:

browser action:"act" profile:"openclaw" targetId:"<targetId>" request:{"kind":"evaluate","fn":"function(){return window.location.href;}"}

Key result: If the current URL matches chatUrl, you have successfully logged in! Go to step 5, else proceed to troubleshooting.

Troubleshooting

If you see the login page (the URL redirects to account.line.biz), use these automation scripts:

a. Click LINE Account button:

read file_path:"skills/line-oa/scripts/click-line-account.js"

Execute the script directly:

browser action:"act" profile:"openclaw" targetId:"<targetId>" request:{"kind":"evaluate","fn":"<script_content>"}

Wait 2 seconds.

b. Click Login button:

read file_path:"skills/line-oa/scripts/click-login.js"

Execute the script directly:

browser action:"act" profile:"openclaw" targetId:"<targetId>" request:{"kind":"evaluate","fn":"<script_content>"}

Wait 3 seconds.

c. Reload chatUrl:

browser action:"navigate" profile:"openclaw" targetId:"<targetId>" targetUrl:"<chatUrl>"

Wait 2 seconds, then take snapshot to verify left-side chat list is visible.

After Check

Proceed with the user's other requests.
Clean Up Browser Tabs:

a. Open a blank tab:
```
browser action:"open" profile:"openclaw" targetUrl:"about:blank"
```
b. Get all tabs:
```
browser action:"tabs" profile:"openclaw"
```
c. Close all tabs except the newest one (about:blank):
```
browser action:"close" profile:"openclaw" targetId:"<your_targetId>"
```
Important: Always clean up tabs after all operations to prevent resource accumulation. The blank tab keeps the browser service running for faster next use.

Quick Check (for cron / automated checks)

Complete flow: login → list chats → report. Follow these steps exactly.

Read config: read file_path:"skills/line-oa/config.json" → get chatUrl
Open browser: browser action:"open" profile:"openclaw" targetUrl:<chatUrl> → get targetId
Wait: browser action:"act" profile:"openclaw" targetId:<targetId> request:{"kind":"wait","timeMs":3000}
Check URL: browser action:"act" profile:"openclaw" targetId:<targetId> request:{"kind":"evaluate","fn":"function(){return window.location.href;}"}
- If URL contains account.line.biz → go to Troubleshooting section below to login, then come back
- If URL contains chat.line.biz → continue

Run this one-liner script as-is, do not modify:

browser action:"act" profile:"openclaw" targetId:<targetId> request:{"kind":"evaluate","fn":"(function(){var r=document.querySelectorAll('.list-group-item-chat');return Array.from(r).map(function(e){var h=e.querySelector('h6');var p=e.querySelector('.text-muted.small');var pt=p?p.textContent.trim():'';var ms=e.querySelectorAll('.text-muted');var t='';for(var i=0;i<ms.length;i++){var v=ms[i].textContent.trim();if(v&&v.length<20&&v!==pt)t=v;}var d=e.querySelector('span.badge.badge-pin');var u=!!d&&getComputedStyle(d).display!=='none';return{name:h?h.textContent.trim():'',time:t,lastMsg:pt.substring(0,100),unread:u};}).filter(function(i){return i.name;});})()"}

⚠️ CHECKPOINT: Did you actually call the browser tool above? If you only thought about it but didn't call it, STOP and call it NOW. You MUST see a tool result before continuing.

Report: take the first 5 items, format each as: <name> (<time>) <lastMsg> [未讀] or [已讀] based on unread field. If empty array, say "目前沒有聊天記錄".
Clean up: open about:blank, list all tabs, close everything except about:blank.

Check LINE Messages

Extracts all chats from the left-side chat list with unread status. Does NOT require clicking into each chat.

Prerequisites: You must be logged in and on the chat list page (see Login section Step 5 for verification).

Steps

Read the script content:

read file_path:"skills/line-oa/scripts/list-chats.js"

Run the script via browser evaluate:

Pass the script content directly as the fn parameter:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"evaluate","fn":"<script_content>"}

The script returns a JSON array of all chat items with structure:
```
[{ name: string, time: string, lastMsg: string, unread: boolean }]
```
- name: customer display name
- time: timestamp (e.g., "21:32", "Yesterday", "Friday")
- lastMsg: last message preview (~100 chars)
- unread: true if green dot present, false otherwise

Get URLs for unread chats (optional but recommended for faster follow-up):

For each unread chat, click into it to get the direct URL, then return to list:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"evaluate","fn":"function(){const items=document.querySelectorAll('.list-group-item-chat');const target=Array.from(items).find(el=>{const h6=el.querySelector('h6');return h6&&h6.textContent.includes('<customer_name>');});if(target){const link=target.querySelector('a.d-flex');if(link){link.click();return {clicked:true};}return {linkNotFound:true};}return {itemNotFound:true};}"}

Wait 500ms, then get the URL:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"evaluate","fn":"function(){return window.location.href;}"}

Navigate back to list:

browser action:"navigate" profile:"openclaw" targetId:"<your_targetId>" targetUrl:"<chatUrl>"

Wait 1 second before processing next unread chat.

Result: Store the chat URL (e.g., https://chat.line.biz/U1234567890abcdef1234567890abcdef/chat/U803dc04f...) alongside the chat info for faster access later.

How to Report Results

If unread: true exists: List each unread chat with name, time, preview, and URL (if obtained)
If no unread: Say "No unread messages at this time"

Notes

Unread indicator: span.badge.badge-pin inside each chat list item (green dot)
Limitation: lastMsg shows the last message in the thread, which may be an auto-response rather than the customer's original message
Chat URLs: Getting URLs requires clicking each chat. Do this for unread chats to enable faster replies later.
To read full messages: See "View Specific Messages" section below

View Specific Messages

Opens any chat (read or unread) and displays its messages. Works for viewing message history, checking context, or preparing to reply.

Prerequisites: You must be logged in and on the chat list page. You should know the customer name (from list-chats.js or user request).

Steps

Find and click the chat item to open messages:

Use evaluate to find the chat item by name (more reliable than snapshot for dynamic chat list):

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"evaluate","fn":"function(){const items=document.querySelectorAll('.list-group-item-chat');const target=Array.from(items).find(el=>{const h6=el.querySelector('h6');return h6&&h6.textContent.includes('<customer_name>');});if(target){const link=target.querySelector('a.d-flex');if(link){link.click();return {clicked:true};}return {linkNotFound:true};}return {itemNotFound:true};}"}

Replace <customer_name> with the actual customer name.

Wait for messages panel to load:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"wait","timeMs":2000}

Take a screenshot to view the messages:
```
browser action:"screenshot" profile:"openclaw" targetId:"<your_targetId>"
```
The screenshot will show:
- Recent messages in the chat (right panel)
- Customer info and tags (far right panel)
- Auto-response status banner (if active)
Optional: Read recent messages programmatically

If you need structured message data instead of a screenshot, read and run this script:
```
read file_path:"skills/line-oa/scripts/read-messages.js"
```
Execute:
```
browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"evaluate","fn":"<script_content>"}
```
Returns an array of recent messages with:
- time: timestamp
- text: message content
- isCustomer: true if from customer, false if from you
- hasImage: true if message contains an image

Navigation Tips

To scroll to earlier messages:

The messages panel auto-scrolls to the bottom by default

To see earlier history, use:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"evaluate","fn":"function(){const panel=document.querySelector('.conversation-panel, .messages-container, [class*=\"chat-container\"]');if(panel){panel.scrollTo({top:0,behavior:'smooth'});return {scrolled:true};}return {error:'Messages panel not found'};}"}

Wait 1 second after scrolling, then take another screenshot

Common issues:

If messages don't load: increase wait time to 3000ms
If customer name has special characters: use partial match (e.g., "John" instead of "John ⭐️")
If click fails: the chat might not be visible in the current scroll position of the left panel

Handling Images

When you see images in the screenshot or hasImage: true in message data:

Find and download the image:

function(){
  const allPhotoImgs = Array.from(document.querySelectorAll('img[alt="Photo"]'));
  const targetImg = allPhotoImgs.find(img => {
    const parent = img.closest('.chat');
    return parent && !parent.classList.contains('chat-reverse') && parent.innerText.includes('<time>');
  });
  
  if (!targetImg) return {error: 'Image not found'};
  
  const parent = targetImg.closest('.chat');
  const downloadLink = Array.from(parent.querySelectorAll('a')).find(a => a.textContent.trim() === 'Download');
  
  if (downloadLink) {
    downloadLink.click();
    return {clicked: true};
  }
  return {error: 'Download link not found'};
}

Replace <time> with the message timestamp (e.g., "09:11").

Wait and locate downloaded file:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"wait","timeMs":2000}

exec command:"ls -t ~/Downloads/line_oa_chat_*.jpg 2>/dev/null | head -1"

Send to user:

message action:"send" target:"<user>" filePath:"<path>" message:"Customer sent this image"

Note: Downloaded images are named line_oa_chat_YYMMDD_HHMMSS.jpg

Reply to a Message

⚡ Fast Path: If you already have the chat URL from a previous "Check LINE Messages" operation, skip steps 1-2 and go directly to step 3:

browser action:"navigate" profile:"openclaw" targetId:"<your_targetId>" targetUrl:"<chat_url>"

Wait 2 seconds, then proceed to step 3.

Standard Path (when you don't have the chat URL):

Take a snapshot to find the chat item:

browser action:"snapshot" profile:"openclaw" targetId:"<your_targetId>" refs:"aria"

Click a chat item link in the left panel (e.g., ref:"e68"):

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"click","ref":"e68"}

If the input box is locked (auto-response mode), click the manual chat toggle button in the top banner to unlock it.
Take another snapshot to find the input box and send button.

Click the text input box (e.g., ref:"e509"):

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"click","ref":"e509"}

Type the reply message:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"type","ref":"e509","text":"Hello! I'm Emma, happy to help you!"}

Click the green Send button (e.g., ref:"e522") or press Enter:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"click","ref":"e522"}

Manage Notes

Each chat has a Notes panel on the right side. Notes are internal-only (not visible to customers). Max 300 characters per note.

Add a note

Open the conversation.
Click the + button next to the Notes heading in the right panel.
Type content in the textarea.
Click Save.

Edit a note

Find the note in the right panel.
Click the pencil icon at the note's bottom-right corner.
Modify the textarea content.
Click Save.

Delete a note

Click the trash icon at the note's bottom-right corner.
A confirmation dialog appears — click Delete to confirm.

Manage Tags

Tags are shown in the right panel below the user's name. They are predefined labels for categorizing chats.

Add a tag

Open the conversation.
Click the Add tags link (or the pencil icon next to existing tags) in the right panel.
The Edit tags modal opens, showing an input field and all available tags.
Click a tag from the "All tags" list to select it (it moves to the input field).
Click Save.

Remove a tag

Open the Edit tags modal (same as above).
Click the × next to the tag in the input field to deselect it.
Click Save.

Switch Account

LINE OA Manager can manage multiple official accounts. Switch between them using the account dropdown in the top-left corner.

Take a snapshot to find the account selector:

browser action:"snapshot" profile:"openclaw" targetId:"<your_targetId>" refs:"aria"

Click the account combobox (shows current account name):

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"click","ref":"e11"}

Wait for the dropdown menu to appear:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"wait","timeMs":1000}

Take another snapshot to see available accounts in the listbox:
```
browser action:"snapshot" profile:"openclaw" targetId:"<your_targetId>" refs:"aria"
```
The snapshot will show a list of accounts you have access to. Look for generic items in the listbox (each account will have a name and "Administrator" or role label).

Click the desired account item (e.g., ref:"e589"):

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"click","ref":"e589"}

Wait for the page to load the new account's chat list:

browser action:"act" profile:"openclaw" targetId:"<your_targetId>" request:{"kind":"wait","timeMs":2000}

Notes

LINE periodically expires sessions; re-login required when that happens
Session is usually active for several hours if the browser remains open

When it activates

Automatically, when a task matches. Use when asked to check LINE messages, reply to LINE customers, or manage LINE OA chat interface.

About this skill

Automatic

Support pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/line-oa/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 6 files · scripts

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

LINE Official Account Manager

Configuration

Enter LINE OA Manager

Troubleshooting

After Check

Quick Check (for cron / automated checks)

Check LINE Messages

Steps

How to Report Results

Notes

View Specific Messages

Steps

Navigation Tips

Handling Images

Reply to a Message

Manage Notes

Add a note

Edit a note

Delete a note

Manage Tags

Add a tag

Remove a tag

Switch Account

Notes

When it activates

SkillSafety

Source

Related skills

More in the registry