Ready to supercharge your AI agents?

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

乐享 MCP 服务 · LeoYeAI | DecimalAI

Documentationby LeoYeAI

乐享 MCP 服务

用于访问乐享知识库平台的专用 skill。当用户明确提到「乐享」「lexiang」「知识库」「知识」「文档」等关键词，或用户提供的链接 host 为 lexiangla.com，应优先调用本 skill。本 skill 支持：获取文档内容与元数据、搜索文档内容、查询知识库与目录结构、创建/编辑/移动文档、管理标签与评论、上传文件及维护附件等知识库操作能力。

Never made a case worse

SkillScore

SkillScore75/100

Test results 50 · Live runs 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

0%50%of test cases passed +50 pts

Without skill0 of 22

With skill11 of 22

11 fixed0 passed either way11 still failing0 broke

Measured on gemini-3.6-flash7/28/2026v120 comparable

Track record

Agent runs: 47; 2 in the last 30 days
Forks: 1

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 lexiang-knowledge-base
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("lexiang-knowledge-base")
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 lexiang-knowledge-base

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/lexiang-knowledge-base/SKILL.md https://app.decimal.ai/s/lexiang-knowledge-base/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/lexiang-knowledge-base/SKILL.md

This gets SKILL.md only. The skill's 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/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/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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("lexiang-knowledge-base")
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/lexiang-knowledge-base/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/lexiang-knowledge-base/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 16 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 lexiang-knowledge-base

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/lexiang-knowledge-base/SKILL.md https://app.decimal.ai/s/lexiang-knowledge-base/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/lexiang-knowledge-base/SKILL.md

This gets SKILL.md only. The skill's 16 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/lexiang-knowledge-base/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/lexiang-knowledge-base.json

This gets SKILL.md only. The skill's 16 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/28/2026
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

乐享 MCP 服务

触发场景：当用户明确提到「乐享」「lexiang」「知识」「文档」，或提供 lexiangla.com 链接，或给出 space_id、entry_id、team_id、/spaces/、/pages/ 等乐享标识时，应使用本服务。

优先级：处理乐享相关操作时，优先使用本 Skill 提供的能力，而非直接调用 MCP。本 Skill 封装了最佳实践和完整的使用说明。

需要调用 MCP 时，请以 MCP 服务端返回的最新的 schema 为准。

⛔ 必读（调用前必须理解）：

本服务直接暴露所有业务工具（如 team_list_teams、search_kb_search 等），可直接调用

调用前先确认工具参数定义，以 MCP 返回的 schema 为准

不确定参数时，使用 get_tool_schema(tool_name="xxx") 获取最新定义

🔑 AccessToken 生命周期管理

阶段 1：未配置 Token

当调用 MCP 连接失败或无认证信息时：

告知用户需要获取乐享 MCP 的 access_token
引导用户打开 https://lexiangla.com/mcp 获取配置信息
用户获取后，帮助完成 mcp.json 配置（参见「快速开始」）

阶段 2：Token 即将过期

当 MCP 返回正常结果但附带过期预警信息时：

先正常返回本次结果
在结果末尾附加提醒，引导用户续期：

⚠️ 您的乐享访问令牌即将过期。请打开以下链接自动续期（需已登录）：
https://lexiangla.com/mcp?action=renew&company_from={company_from}

阶段 3：Token 已过期（401 响应）

当 MCP 返回 401 未授权时：

不要反复重试
引导用户重新创建会话：

🔒 您的乐享访问令牌已过期。请打开以下链接创建新会话：
https://lexiangla.com/mcp?action=recreate&company_from={company_from}
创建后请将新的 access_token 提供给我进行更新。

租户隔离规则

company_from 和 access_token 必须属于同一租户，不同租户的 token 不能混用
OAuth 不支持跨租户授权
续期或重建 token 时，URL 中的 company_from 必须与当前配置一致
如果用户切换了企业/租户，必须重新获取对应租户的 token

📊 数据模型

核心概念

概念	说明
Team（团队）	顶级组织单元，一个团队下可以有多个知识库(Space)
Space（知识库）	知识的容器，属于某个团队，包含多个条目(Entry)，有 `root_entry_id` 作为根节点
Entry（条目）	知识库中的内容单元，可以是页面(page)、文件夹(folder)或文件(file)，支持树形结构(parent_id)
File（文件）	附件类型的条目，如 PDF、Word、图片等

层级关系

Team → Space → Entry（树形结构，root_entry_id 为根）
                  ├── page（页面）
                  ├── folder（文件夹）
                  └── file（文件）

URL 规则

域名固定为 https://lexiangla.com——即 {domain} = https://lexiangla.com

⛔ company_from 不是子域名，只能作为 URL 查询参数使用！

❌ 错误：https://km.lexiangla.com/pages/xxx（把 company_from 当子域名） ❌ 错误：https://abc.lexiangla.com/pages/xxx ✅ 正确：https://lexiangla.com/pages/xxx?company_from=km ✅ 正确：https://lexiangla.com/pages/xxx（无 company_from 时）

链接拼接规则：

https://lexiangla.com/pages/{entry_id}?company_from={company_from}

如果没有 company_from，直接使用 https://lexiangla.com/pages/{entry_id}（不加查询参数）。

company_from 获取方式（按优先级）：

MCP 连接 URL 中的 company_from 查询参数（如 mcp?company_from=km 中的 km）
环境变量 COMPANY_FROM
用户提供的 URL 中已有的 company_from 查询参数
如果均不可用，省略该参数

⛔ 严禁使用 mcp.lexiang-app.com 拼接任何用户可访问的链接！ 该域名仅用于 MCP 接口调用，不是用户访问地址。 ⛔ 严禁将 company_from 拼接为子域名！ company_from 只能作为 URL 查询参数（?company_from=xxx），不能拼成 https://{company_from}.lexiangla.com。

资源	URL 格式
团队首页	`{domain}/t/{team_id}/spaces`
知识库	`{domain}/spaces/{space_id}`
知识条目	`{domain}/pages/{entry_id}`

URL 解析规则

当用户提供链接时，从 URL 路径中提取 ID（忽略查询参数）：

URL 路径	提取方式
`/spaces/{space_id}`	取 `spaces/` 后面的部分作为 `space_id`
`/pages/{entry_id}`	取 `pages/` 后面的部分作为 `entry_id`
`/t/{team_id}/spaces`	取 `t/` 后面的部分作为 `team_id`

🛡️ 写入操作安全规则

核心原则：写入、修改、删除操作 必须基于用户明确提供的目标信息，禁止 Agent 自行选择或猜测目标。

🚫 绝对禁止

禁止遍历团队/知识库列表后自行选择写入目标
禁止根据名称"看起来合适"就决定写入
禁止在未确认时执行写入

✅ 允许写入的条件（满足之一即可）

条件	示例
用户提供了明确 URL	`"写到这里：https://lexiangla.com/spaces/xxx"`
用户提供了明确 ID	`"写入 space_id 为 xxx 的知识库"`
用户指定名称 + Agent 回显确认	Agent 搜到后展示详情，用户确认

写入操作涉及的工具

entry_create_entry、entry_import_content、entry_import_content_to_entry、block_update_block、block_update_blocks、block_create_block_descendant、block_delete_block、block_delete_block_children、block_move_blocks、entry_rename_entry、entry_move_entry、file_apply_upload、file_commit_upload、file_create_hyperlink

读取操作不受此限制

team_list_teams、team_describe_team、team_list_frequent_teams、space_list_spaces、space_describe_space、entry_list_children、block_list_block_children、search_kb_search、search_kb_embedding_search、space_list_recently_spaces、entry_list_latest_entries、entry_describe_ai_parse_content、file_describe_file、file_download_file 等只读操作可正常执行。

🔍 工具发现与调用

本服务直接暴露所有业务工具，可直接调用（如 team_list_teams()、search_kb_search(keyword="xxx")）。

同时提供以下辅助元工具，帮助发现和理解工具：

元工具	用途
`list_tool_categories`	列出所有工具分类及其工具列表
`search_tools`	按关键词或分类搜索工具
`get_tool_schema`	获取具体工具的完整参数定义

标准工作流

1. 直接调用已知工具：team_list_teams()、search_kb_search(keyword="xxx") 等
2. 不确定参数时：get_tool_schema(tool_name="xxx") → 获取参数定义
3. 不确定工具名时：search_tools(query="关键词") → 找到工具名

大多数常用工具已在本 Skill 中列出，可直接使用；遇到新工具或不确定的参数时，再用 get_tool_schema 查询。

🚀 快速开始

获取配置参数

访问：https://lexiangla.com/mcp

登录后获取：

company_from：你的企业标识
access_token：访问令牌（格式 lxmcp_xxx）

配置方式

方式1：自动配置（推荐）

请阅读 setup.md 中的步骤说明，按指引完成配置。

方式2：环境变量

export COMPANY_FROM="your_company"
export LEXIANG_TOKEN="lxmcp_YOUR_TOKEN_HERE"

方式3：直接修改 mcp.json

编辑 mcp.json，将 ${COMPANY_FROM} 和 ${LEXIANG_TOKEN} 替换为实际值。

mcp.json 配置模板

{
    "mcpServers": {
        "lexiang": {
            "enabled": true,
            "url": "https://mcp.lexiang-app.com/mcp?company_from=${COMPANY_FROM}",
            "transportType": "streamable-http",
            "headers": {
                "Authorization": "Bearer ${LEXIANG_TOKEN}"
            }
        }
    }
}

安装后验证

配置完成后，立即调用 whoami() 进行连通性检查并获取用户身份信息：

调用 whoami()
成功（返回用户信息）→ 向用户展示欢迎消息：

✅ 乐享 MCP 连接成功！

👤 当前用户：{用户姓名}
🏢 绑定乐享：{企业/租户名称}

🎉 配置已就绪，你现在可以这样使用乐享知识库：

💡 试试这样提问：
• "看看我最近访问的知识库有什么更新"
• "我要记录今天的工作内容，为我创建一个乐享文档并拟写一个模版"
• "搜索关于 XXX 的知识文档"
• "帮我总结一下这个知识库的内容：{知识库链接}"

根据 whoami 返回的实际字段灵活调整展示内容。

401 错误 → token 无效或已过期，引导用户重新获取（参见「AccessToken 生命周期管理」）
连接超时/其他错误 → 检查 mcp.json 配置是否正确

遇到问题？

问题	解决方案
连接无响应	确认 mcp.json 中 URL 包含 `company_from` 且格式正确
401 未授权	token 过期或租户不匹配，参见「AccessToken 生命周期管理」
参数报错	执行 `get_tool_schema(tool_name="xxx")` 获取最新参数定义

🎯 意图识别与澄清

明确使用本 Skill 的场景

关键词触发：用户提到「乐享」「lexiang」「知识库」「知识」「文档」
链接触发：用户提供的链接 host 为 lexiangla.com
上下文延续：用户之前已明确使用乐享，后续操作默认继续

🛡️ 写入安全提醒

❌ 禁止遍历团队/知识库列表后自行选择写入目标
✅ 用户提供了 URL / ID / 精确名称 + 确认后方可写入
✅ 写入目标不明确时（如"帮我写到乐享""执行吧"但未指定知识库），需要求用户提供具体写入位置
✅ 读取操作（搜索、浏览、查看）不受此限制

工具概述

本 MCP 服务提供以下工具，可直接调用。参数不确定时以 get_tool_schema 返回为准。

📚 知识库管理

entry_create_entry — 创建文档/文件夹
entry_import_content — 导入 Markdown/HTML 创建新文档（⚠️ 仅新建）
entry_import_content_to_entry — 导入内容到已有页面（支持覆盖/追加）
entry_list_latest_entries — 获取最近更新条目
entry_rename_entry — 重命名条目

📎 文件管理

file_apply_upload — 申请文件上传（返回 upload_url 和 session_id）
file_commit_upload — 确认上传完成

🧩 Block 操作

block_convert_content_to_blocks — Markdown/HTML 转 Block 结构
block_create_block_descendant — 创建 Block 结构
block_update_block — 单块更新
block_update_blocks — 批量更新
block_move_blocks — 移动 Block
block_delete_block_children — 删除子节点
block_delete_block — 删除指定 Block（含子孙）
block_describe_block — 获取单个 Block 详情
block_list_block_children — 读取 Block 内容

🔍 搜索与发现

search_kb_search — 关键词搜索
search_kb_embedding_search — 语义向量搜索
team_list_teams — 获取团队列表
team_describe_team — 获取团队详情
team_list_frequent_teams — 获取常用团队列表
space_list_spaces — 获取知识库列表
space_describe_space — 获取知识库详情（返回 root_entry_id）
space_list_recently_spaces — 获取最近访问知识库

📖 条目与结构浏览

entry_list_children — 浏览目录结构
entry_describe_entry — 获取条目元信息（不含正文）
entry_describe_ai_parse_content — 获取 AI 解析内容（含正文）
entry_list_parents — 获取父级路径（面包屑）

🔗 外部内容导入

file_create_hyperlink — 导入公众号文章等外部链接

内容搜索

关键词搜索 vs 语义搜索

工具	适用场景
`search_kb_search`	精确关键词匹配
`search_kb_embedding_search`	模糊查询、"记得大意但忘了标题"

建议：语义搜索召回后，再用 entry_describe_entry 或 entry_describe_ai_parse_content 精确读取。

搜索结果链接格式

根据返回的 target_type 拼接链接：

target_type	URL 格式
`kb_page`	`{domain}/pages/<target_id>`
`kb_file` / `kb_video`	`{domain}/teams/<team_id>/docs/<target_id>`

🔗 结果链接生成规则（通用）

适用于所有返回 entry_id 的操作，包括但不限于：entry_import_content、entry_create_entry、entry_import_content_to_entry、file_commit_upload、搜索结果等。

拼接规则

当操作成功返回了 entry_id（或 target_id），向用户展示访问链接时，使用上方「URL 规则」中定义的 {domain} 拼接：

{domain}/pages/{entry_id}

⛔ 禁止

禁止使用 mcp.lexiang-app.com 拼接用户访问链接
禁止使用 MCP 连接 URL（mcp.lexiang-app.com）的域名作为用户访问域名
禁止将 company_from 拼接为子域名（如 https://{company_from}.lexiangla.com 是错误的）
禁止编造或猜测域名，必须严格使用上方定义的 {domain}

📖 内容读取

工具	返回内容	用途
`entry_describe_entry`	条目元信息（ID、名称、类型等）	获取基本信息
`entry_describe_ai_parse_content`	条目正文内容	读取实际内容进行分析

常见操作流程

从知识库链接写入文档

⚠️ 仅在用户主动提供了知识库链接时执行。详见下方「常见使用场景 > 场景0」。

核心步骤：提取 space_id → space_describe_space 获取 root_entry_id → entry_import_content 写入 → 用 {domain}/pages/{entry_id} 拼接访问链接返回给用户。

微信公众号导入

当用户提供 mp.weixin.qq.com 链接且意图是"导入/收藏/保存到乐享"时，使用 file_create_hyperlink。

如果用户只是想阅读或总结内容，不要默认导入。

常见使用场景

场景0: 用户给了知识库链接，写入文档

用户："把报告写入乐享，链接是 https://lexiangla.com/spaces/16c4224607ea45ebacce6c15130a4957"

Step 1: 从 URL 提取 space_id = "16c4224607ea45ebacce6c15130a4957"
Step 2: call_tool("space_describe_space", {"space_id": "..."}) → 获取 root_entry_id
Step 3: call_tool("entry_import_content", {"space_id": "...", "parent_id": root_entry_id, "name": "报告", "content": "...", "content_type": "markdown"})
Step 4: 从返回结果取 entry_id，向用户展示访问链接：{domain}/pages/{entry_id}

要点：space_id 和 parent_id 要同时传；parent_id 用 root_entry_id 表示写入根目录；链接中 {domain} 见上方 URL 规则定义。

场景1: 创建文档

call_tool("entry_create_entry", {"name": "技术文档", "parent_entry_id": "abc123", "entry_type": "page"})

场景2: 导入 Markdown

call_tool("entry_import_content", {"parent_id": "folder123", "name": "技术文档", "content": "...", "content_type": "markdown"})

场景3: 创建结构化 Block 文档

call_tool("block_create_block_descendant", {
  "entry_id": "doc123",
  "descendant": [
    {"block_id": "h1", "block_type": "h1", "heading1": {"elements": [{"text_run": {"content": "项目文档"}}]}},
    {"block_id": "tip", "block_type": "callout", "callout": {"color": "#FFF3E0"}, "children": ["tip_p"]},
    {"block_id": "tip_p", "block_type": "p", "text": {"elements": [{"text_run": {"content": "重要提示内容"}}]}},
    {"block_id": "li1", "block_type": "bulleted_list", "bulleted": {"elements": [{"text_run": {"content": "功能一"}}]}}
  ],
  "children": ["h1", "tip", "li1"]
})

场景4: 上传文件（3 步）

Step 1: call_tool("file_apply_upload", {"parent_entry_id": "folder123", "name": "README.md", "size": 1024})
        → 返回 upload_url, session_id
Step 2: HTTP PUT upload_url（上传文件内容，非 MCP 调用）
Step 3: call_tool("file_commit_upload", {"session_id": "..."})

场景5: 读取 Block 内容

call_tool("block_list_block_children", {"entry_id": "abc123", "with_descendants": true})

场景6: 批量更新 Block

call_tool("block_update_blocks", {
  "entry_id": "abc123",
  "updates": {
    "actual_block_id": {
      "update_text_elements": {
        "elements": [{"text_run": {"content": "更新后的内容"}}]
      }
    }
  }
})

Block 结构核心规则

🍃 叶子节点（不能有 children）

标题块：h1, h2, h3, h4, h5
代码块：code
图片块：image
分割线：divider
图表块：mermaid, plantuml

📦 容器节点（必须指定 children）

提示框：callout
表格：table, table_cell
分栏布局：column_list, column
折叠块：toggle

详细说明：完整 Block 类型和字段定义见 references/block-schema.md。

⚠️ 核心注意事项

Block ID 映射：block_id 为客户端临时 ID，服务端返回实际 ID 映射
叶子节点限制：标题、代码块、图片等不支持 children 字段
容器节点要求：callout、table、column_list 等必须指定 children
文件上传大小：必须获取准确的文件大小（字节数）
_mcp_fields 优化：所有工具支持 _mcp_fields 参数选择返回字段，减少 token 消耗

更多细节：见 references/common-errors.md 和 references/markdown-import.md。

辅助资源

参考文档（references/ 目录）

文档	说明
`block-schema.md`	Block 类型完整说明
`mcp-examples.md`	复杂 Block 结构示例
`markdown-to-block.md`	Markdown 转 Block 指南
`block-update.md`	批量更新 Block 方法
`content-reorganize.md`	文档结构重组
`folder-sync.md`	文件夹同步方案
`markdown-import.md`	Markdown 导入详解
`common-errors.md`	常见错误排查
`skill-maintenance.md`	维护与反馈流程

辅助脚本（scripts/ 目录）

脚本	说明
`sync-folder.ts`	文件夹增量同步
`block-helper.ts`	Block 构建辅助工具
`mcp-validator.ts`	MCP 参数校验

❓ 问题与排查

遇到问题时，请先查阅 references/common-errors.md。

📮 维护与反馈

Issue 反馈流程和 Skill 自我进化机制见 references/skill-maintenance.md。

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

乐享 MCP 服务

🔑 AccessToken 生命周期管理

阶段 1：未配置 Token

阶段 2：Token 即将过期

阶段 3：Token 已过期（401 响应）

租户隔离规则

📊 数据模型

核心概念

层级关系

URL 规则

URL 解析规则

🛡️ 写入操作安全规则

🚫 绝对禁止

✅ 允许写入的条件（满足之一即可）

写入操作涉及的工具

读取操作不受此限制

🔍 工具发现与调用

标准工作流

🚀 快速开始

获取配置参数

配置方式

方式1：自动配置（推荐）

方式2：环境变量

方式3：直接修改 mcp.json

mcp.json 配置模板

安装后验证

遇到问题？

🎯 意图识别与澄清

明确使用本 Skill 的场景

🛡️ 写入安全提醒

工具概述

📚 知识库管理

📎 文件管理

🧩 Block 操作

🔍 搜索与发现

📖 条目与结构浏览

🔗 外部内容导入

内容搜索

关键词搜索 vs 语义搜索

搜索结果链接格式

🔗 结果链接生成规则（通用）

拼接规则

⛔ 禁止

📖 内容读取

常见操作流程

从知识库链接写入文档

微信公众号导入

常见使用场景

场景0: 用户给了知识库链接，写入文档

场景1: 创建文档

场景2: 导入 Markdown

场景3: 创建结构化 Block 文档

场景4: 上传文件（3 步）

场景5: 读取 Block 内容

场景6: 批量更新 Block

Block 结构核心规则

🍃 叶子节点（不能有 children）

📦 容器节点（必须指定 children）

⚠️ 核心注意事项

辅助资源

参考文档（references/ 目录）

辅助脚本（scripts/ 目录）

❓ 问题与排查

📮 维护与反馈

相关链接

SkillSafety

Source

Related skills

More in the registry