Ready to supercharge your AI agents?

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

Get Started Free →

Feishu Literature Manager · leoyeai | DecimalAI

Researchby leoyeai

Feishu Literature Manager

Automated literature retrieval and Feishu Bitable management.

Never made a case worse

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

73%77%of test cases passed +5 pts

Without skill16 of 22

With skill17 of 22

1 fixed16 passed either way5 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v121 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskTo optimize insertion speed when adding 5 records to Feishu Bitable, how should the API tool calls be organized in the function calling interface?

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-feishu-literature-manager
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-feishu-literature-manager")
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-feishu-literature-manager

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-feishu-literature-manager/SKILL.md https://app.decimal.ai/s/leoyeai-feishu-literature-manager/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-feishu-literature-manager/SKILL.md

This gets SKILL.md only. The skill's 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/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-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/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-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager")
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-feishu-literature-manager/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-feishu-literature-manager/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 4 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-feishu-literature-manager

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-feishu-literature-manager/SKILL.md https://app.decimal.ai/s/leoyeai-feishu-literature-manager/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-feishu-literature-manager/SKILL.md

This gets SKILL.md only. The skill's 4 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-feishu-literature-manager/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-feishu-literature-manager.json

This gets SKILL.md only. The skill's 4 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

Feishu Literature Manager

Overview

This skill automates the complete workflow of creating a literature database in Feishu Bitable, from PubMed search to fully populated table with all required metadata including Chinese translations, impact factors, and formatted references.

Two Main Workflows:

Create New Database: Create a new Feishu Bitable from scratch
Supplement Existing Database: Add new papers to an existing table (avoiding duplicates)

Workflow Decision Tree

Workflow A: Create New Database

User provides: topic + number of papers
           ↓
1. Create Feishu Bitable
           ↓
2. Create all 17 required fields
           ↓
3. Search PubMed for papers
           ↓
4. Parse and validate results
           ↓
5. Extract complete metadata
           ↓
6. Translate titles and abstracts
           ↓
7. Add papers to table (PARALLEL CALLS)
           ↓
8. Set table permissions (full_access)
           ↓
9. Report completion

Workflow B: Supplement Existing Database ⭐ NEW

User provides: research topic + specific focus + table URL + number of papers
           ↓
1. Parse table URL to get app_token and table_id
           ↓
2. Get existing records to extract current PMIDs
           ↓
3. Search PubMed with focused keywords
           ↓
4. Filter out existing PMIDs (deduplication)
           ↓
5. Score and rank papers by relevance
           ↓
6. Select top N papers
           ↓
7. Fetch XML data for selected papers
           ↓
8. Parse metadata and translate
           ↓
9. Add papers to table (PARALLEL CALLS - 5-10 at a time)
           ↓
10. Report completion with summary

Batch Processing for Large Tasks

IMPORTANT: When retrieving more than 5 papers, process in batches!

Why Batch Processing is Necessary:

Token limitations - Large numbers of papers require extensive translation work
Quality assurance - Each batch ensures complete field information before proceeding
Better user experience - Users receive regular progress updates
Error recovery - Easier to resume if interrupted

Batch Processing Workflow:

User requests: topic + N papers (N > 5)
           ↓
Calculate batches: ceil(N / 5)
           ↓
For each batch (5 papers):
  1. Fetch PMIDs for this batch
  2. Retrieve XML data
  3. Parse metadata
  4. Translate titles and abstracts
  5. Add all 5 papers to table with COMPLETE fields
  6. Report batch completion
           ↓
Continue to next batch
           ↓
All batches complete → Report final status

Example: User requests 10 papers

Batch 1 (Papers 1-5):
  - Fetch PMIDs 1-5
  - Get XML data
  - Parse and translate
  - Add 5 papers with complete fields (including 摘要)
  - Report: "第一批完成，已添加5篇文献"

Batch 2 (Papers 6-10):
  - Fetch PMIDs 6-10
  - Get XML data
  - Parse and translate
  - Add 5 papers with complete fields (including 摘要)
  - Report: "第二批完成，已添加5篇文献"

Final Report: "任务全部完成！共添加10篇文献"

Critical Rules:

Never start a new batch until current batch is COMPLETE
- COMPLETE means ALL 17 fields filled, including 摘要（英文）and 摘要（中文）
- Report completion before starting next batch
Progress Reporting:
- After each batch: "第X批完成，已添加Y篇文献，剩余Z篇"
- Keep user informed of progress
Token Management:
- Monitor token usage
- If running low, inform user and continue in next conversation
- Save state (PMIDs retrieved, current batch) for resumption
Quality over Speed:
- Better to complete fewer papers with full information
- Than many papers with incomplete fields

⭐ PARALLEL API CALLS - BEST PRACTICE

CRITICAL: Always use parallel API calls when adding multiple papers!

Why Parallel Calls?

Sequential API calls are SLOW. Each call waits for response before next call. Parallel calls submit multiple requests simultaneously, dramatically improving efficiency.

How to Make Parallel Calls

In tool calls, submit MULTIPLE feishu_bitable_create_record calls in the SAME function_calls block:

// CORRECT: Parallel calls (5-10 papers at once)
<function_calls>
<invoke name="feishu_bitable_create_record">
<parameter name="app_token">xxx</parameter>
<parameter name="table_id">xxx</parameter>
<parameter name="fields">{paper 1 data}</parameter>
</invoke>
<invoke name="feishu_bitable_create_record">
<parameter name="app_token">xxx</parameter>
<parameter name="table_id">xxx</parameter>
<parameter name="fields">{paper 2 data}</parameter>
</invoke>
<invoke name="feishu_bitable_create_record">
<parameter name="app_token">xxx</parameter>
<parameter name="table_id">xxx</parameter>
<parameter name="fields">{paper 3 data}</parameter>
</invoke>
... (up to 10 calls at once)
</function_calls>

// WRONG: Sequential calls (SLOW!)
<function_calls>
<invoke name="feishu_bitable_create_record">...</invoke>
</function_calls>
// Wait for response...
<function_calls>
<invoke name="feishu_bitable_create_record">...</invoke>
</function_calls>
// Wait for response...

Recommended Batch Size

5-10 papers per parallel call - Optimal balance of speed and reliability
Maximum 10 papers - Avoid overwhelming the API

Example: Adding 10 Papers Efficiently

# Step 1: Prepare all paper data
papers_data = [prepare_paper_data(p) for p in papers[:10]]

# Step 2: Make parallel calls (submit all at once)
# All 10 feishu_bitable_create_record calls in same function_calls block
results = parallel_add_papers(papers_data)

# Step 3: Report results
print(f"Successfully added {len(results)} papers in one batch!")

⭐ SUPPLEMENTING EXISTING DATABASE - Step by Step

Overview

When user provides:

Research topic: e.g., "胃神经内分泌肿瘤"
Specific focus: e.g., "药物临床研究", "手术治疗", "诊断方法"
Table URL: Feishu Bitable link
Number of papers: How many to add

Step 1: Parse Table URL and Get Existing PMIDs

# Extract app_token from URL
# URL format: https://xxx.feishu.cn/base/APP_TOKEN?table=TABLE_ID
# Or: https://xxx.feishu.cn/wiki/xxx?table=TABLE_ID

# Get existing records
records = feishu_bitable_list_records(
    app_token=app_token,
    table_id=table_id,
    page_size=500  # Get all records
)

# Extract existing PMIDs
existing_pmids = set()
for record in records['records']:
    pmid = record['fields'].get('PMID')
    if pmid:
        existing_pmids.add(pmid)

print(f"Existing records: {len(records['records'])}, Unique PMIDs: {len(existing_pmids)}")

Step 2: Build Focused Search Query

# Combine research topic with specific focus
# Example: "胃神经内分泌肿瘤" + "药物临床研究"

# Search terms for different focuses:
FOCUS_KEYWORDS = {
    "药物临床研究": [
        "chemotherapy", "targeted therapy", "PRRT", "somatostatin analog",
        "everolimus", "sunitinib", "octreotide", "lanreotide", "immunotherapy",
        "PD-1", "PD-L1", "temozolomide", "capecitabine", "177Lu", "Lutetium",
        "clinical trial", "phase", "randomized", "treatment"
    ],
    "手术治疗": [
        "surgery", "resection", "gastrectomy", "endoscopic resection",
        "lymph node dissection", "surgical outcome"
    ],
    "诊断方法": [
        "diagnosis", "biomarker", "PET/CT", "endoscopy", "pathology",
        "immunohistochemistry", "molecular marker"
    ],
    "预后评估": [
        "prognosis", "survival", "outcome", "risk factor", "nomogram"
    ]
}

# Build search query
search_query = f"({topic}) AND ({' OR '.join(focus_keywords)})"

Step 3: Search PubMed and Filter

# Search PubMed
response = curl(f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term={search_query}&retmax=50&retmode=json&sort=pub_date")

new_pmids = [pmid for pmid in response['idlist'] if pmid not in existing_pmids]

print(f"Found {len(response['idlist'])} papers, {len(new_pmids)} are new")

Step 4: Score and Rank Papers by Relevance

# Fetch detailed info for new PMIDs
xml_data = curl(f"https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id={','.join(new_pmids)}&retmode=xml")

# Score each paper
def score_paper(paper, focus):
    score = 0
    title = paper['title'].lower()
    abstract = paper['abstract'].lower()[:500]
    
    # High relevance: keyword in title
    for kw in FOCUS_KEYWORDS.get(focus, []):
        if kw.lower() in title:
            score += 3
        if kw.lower() in abstract:
            score += 1
    
    # Neuroendocrine in title
    if 'neuroendocrine' in title or 'net' in title:
        score += 2
    
    # Clinical trial/phase in title
    if 'trial' in title or 'phase' in title:
        score += 2
    
    return score

# Sort by score
scored_papers = [(score_paper(p, focus), p) for p in papers]
scored_papers.sort(reverse=True, key=lambda x: x[0])

# Select top N
selected_papers = [p for score, p in scored_papers[:number_requested]]

Step 5: Add Papers with Parallel Calls

# Prepare all paper data
papers_data = [prepare_full_paper_data(p) for p in selected_papers]

# Make PARALLEL API calls (5-10 at a time)
# Submit all feishu_bitable_create_record calls in SAME function_calls block
results = parallel_add_papers(papers_data)

# Report results
print(f"✅ Added {len(results)} papers successfully!")

Core Capabilities

1. Table Field Structure (17 Required Fields)

Primary Field:

文献标题（中文） - Text (主字段, use Chinese title as primary field)

Basic Information:

文献题目（英文） - Text
文献题目（中文） - Text
发表年月 - DateTime (timestamp in milliseconds)
第一作者 - Text
第一作者单位 - Text
通讯作者 - Text
期刊名称 - Text

Abstracts:

摘要（英文） - Text (structured with BACKGROUND, METHODS, RESULTS, CONCLUSION)
摘要（中文） - Text (structured with 【背景】【目的】【方法】【结果】【结论】)

Identifiers:

PMID - Text
DOI - Text

Metadata:

免费全文链接 - URL (format: {"link": "URL", "text": "PMC免费全文"} or {"link": "DOI_URL", "text": "DOI链接"})
SCI分区 - Text (e.g., "JCR Q1", "JCR Q2", "中文核心期刊")
中科院分区 - Text (e.g., "医学1区", "医学2区", "中文核心期刊")
影响因子 - Number (MUST be numeric, not string!)
国标参考文献格式 - Text (GB/T 7714-2015 format)

2. Step-by-Step Workflow

Step 1: Create Feishu Bitable

# Use feishu_bitable_create_app
app = feishu_bitable_create_app(
    name="文献库标题",
    folder_token="optional_folder_token"
)
# Save app_token and default table_id from response

Step 2: Create Fields

# Use feishu_bitable_create_field for each of the 17 fields
# Field types: Text=1, Number=2, DateTime=5, URL=15
# Example:
feishu_bitable_create_field(
    app_token=app_token,
    table_id=table_id,
    field_name="文献题目（英文）",
    field_type=1  # Text
)

Step 3: Search PubMed

# Search PubMed using E-utilities API
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi?db=pubmed&term=SEARCH_TERM&retmax=NUMBER&retmode=json&sort=pub_date"

# Extract PMIDs from response
# Fetch detailed information for each PMID
curl -s "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=pubmed&id=PMID1,PMID2,...&retmode=xml"

Step 4: Parse PubMed XML

# Extract from XML:
# - Title (ArticleTitle)
# - Authors (LastName + ForeName initial)
# - First author affiliation
# - Corresponding author (last author or from affiliation)
# - Journal name
# - Publication date (Year, Month)
# - DOI
# - PMC ID (if available)
# - Volume, Issue, Pages
# - Abstract (all AbstractText elements with labels)

Step 5: Translate to Chinese

# Translate title to Chinese
# Translate abstract to Chinese with structured format:
# 【背景】... 【目的】... 【方法】... 【结果】... 【结论】...

Step 6: Get Journal Metadata

# Look up impact factor for journal
# Determine SCI partition (JCR Q1/Q2/Q3/Q4)
# Determine CAS partition (医学1区/2区/3区/4区)
# Use references/impact_factors.md for common journals

Step 7: Format Reference

# GB/T 7714-2015 format:
# Author1, Author2, Author3, et al. Title[J]. Journal Abbrev, Year, Volume(Issue): Pages. DOI: xxx.

# Example:
# Fazio N, La Salvia A. Immune Checkpoint Inhibitors in High-grade Gastroenteropancreatic Neuroendocrine Neoplasms[J]. Endocr Rev, 2026, 47(2): 178-190. DOI: 10.1210/endrev/bnaf037.

Step 8: Add to Feishu Table

# Use feishu_bitable_create_record
# IMPORTANT: 影响因子 must be numeric, not string!
# IMPORTANT: 免费全文链接 must be JSON format: {"link": "URL", "text": "text"}

record = feishu_bitable_create_record(
    app_token=app_token,
    table_id=table_id,
    fields={
        "PMID": pmid,
        "文献题目（英文）": english_title,
        "文献题目（中文）": chinese_title,
        "发表年月": timestamp_ms,  # DateTime as milliseconds
        "第一作者": first_author,
        "第一作者单位": first_affiliation,
        "通讯作者": corresponding_author,
        "期刊名称": journal,
        "摘要（英文）": english_abstract,
        "摘要（中文）": chinese_abstract,
        "DOI": doi,
        "免费全文链接": {"link": url, "text": text},
        "SCI分区": sci_partition,
        "中科院分区": cas_partition,
        "影响因子": impact_factor,  # Number, not string!
        "国标参考文献格式": reference,
        "文献标题（中文）": chinese_title  # Primary field (中文标题作为主字段)
    }
)

Step 9: Set Table Permissions

# Use feishu_perm to set full_access permission for the user
# This allows the user to fully manage the table (view, edit, manage permissions, delete)

feishu_perm(
    action="add",
    token=app_token,  # Use the Bitable's app_token
    type="bitable",
    member_type="openid",  # User's open_id
    member_id=user_open_id,  # User's open_id (e.g., "ou_xxx")
    perm="full_access"  # Full management permission
)

# Permission levels:
# - "view": View only
# - "edit": Can edit
# - "full_access": Full access (can manage permissions)

# Note: feishu_perm tool must be enabled in configuration:
# channels.feishu.tools.perm = true

3. User Reporting Requirements

Report after each step:

✅ Table Created: "已创建飞书多维表格，表格名称：[名称]，表格ID：[ID]"
✅ Fields Created: "已创建所有必填字段"
✅ PubMed Search: "已从PubMed检索到 [N] 篇文献"
✅ Deduplication: "去重后剩余 [N] 篇新文献"
✅ Metadata Extraction: "正在提取第 [X]/[N] 篇文献的详细信息..."
✅ Translation: "正在翻译中文标题和摘要..."
✅ Adding to Table: "正在添加第 [X]/[N] 篇文献到表格..."
✅ Permissions Set: "已为您设置表格管理权限"
✅ Completion: "✅ 任务完成！共添加 [N] 篇文献到表格中，表格现有 [M] 条记录，您拥有完全管理权限"

4. Common Pitfalls to Avoid

❌ WRONG:

String impact factor: "影响因子": "15.3"
Plain URL: "免费全文链接": "https://..."
Missing Chinese translation
Incomplete abstract (missing sections)

✅ CORRECT:

Numeric impact factor: "影响因子": 15.3
JSON URL: "免费全文链接": {"link": "https://...", "text": "PMC免费全文"}
Complete translations
Structured abstracts with all sections

5. Quality Checklist

Before adding each paper, verify:

All 17 fields are present
影响因子 is numeric
免费全文链接 is JSON format
发表年月 is timestamp in milliseconds
摘要（中文） has structured format
国标参考文献格式 follows GB/T 7714-2015
No duplicate PMIDs in table

6. Permission Management

IMPORTANT: Always set table permissions for the user after creating the table.

Configuration Required: The feishu_perm tool must be enabled in the OpenClaw configuration:

openclaw config set channels.feishu.tools.perm true
openclaw gateway restart  # Restart gateway to apply changes

Why It's Important:

Without proper permissions, users cannot fully manage tables they create
full_access permission allows users to:
- View and edit table content
- Manage permissions (add/remove collaborators)
- Delete the table
- Export and share the table

How to Get User's open_id: The user's open_id is available in the inbound context metadata:

{
  "sender_id": "ou_xxxxxxxxxxxx",
  "sender": "User Name"
}

Permission Levels:

view: Read-only access
edit: Can view and edit content
full_access: Full management access (recommended for table owners)

Resources

scripts/

pubmed_search.py - PubMed E-utilities API wrapper
parse_pubmed_xml.py - XML parsing utilities

references/

field_mapping.md - Complete field definitions and types
impact_factors.md - Common journal impact factors and partitions
reference_format.md - GB/T 7714-2015 formatting rules

When it activates

Automatically, when a task matches. Use when user requests to create a literature database, search PubMed for specific topics, or manage research papers in Feishu tables. Triggers on phrases like "create a literature table", "search papers and add to Feishu", "build a research database", "补充文献", "添加文献到表格", or "检索文献并建立表格". Supports complete workflow from topic definition to populated Feishu table with all required fields including Chinese translations, impact factors, an

About this skill

Automatic

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 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/feishu-literature-manager/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 4 files · scripts

Illustrative Want to see what leoyeai/feishu-literature-manager 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

Feishu Literature Manager

Overview

Workflow Decision Tree

Workflow A: Create New Database

Workflow B: Supplement Existing Database ⭐ NEW

Batch Processing for Large Tasks

⭐ PARALLEL API CALLS - BEST PRACTICE

Why Parallel Calls?

How to Make Parallel Calls

Recommended Batch Size

Example: Adding 10 Papers Efficiently

⭐ SUPPLEMENTING EXISTING DATABASE - Step by Step

Overview

Step 1: Parse Table URL and Get Existing PMIDs

Step 2: Build Focused Search Query

Step 3: Search PubMed and Filter

Step 4: Score and Rank Papers by Relevance

Step 5: Add Papers with Parallel Calls

Core Capabilities

1. Table Field Structure (17 Required Fields)

2. Step-by-Step Workflow

3. User Reporting Requirements

4. Common Pitfalls to Avoid

5. Quality Checklist

6. Permission Management

Resources

scripts/

references/

When it activates

SkillSafety

Source

Related skills

More in the registry