Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →多源文献聚合检索：PubMed + PMC + 预印本（bioRxiv / medRxiv / ChemRxiv / Research Square）+ NCBI Bookshelf + 专利 一次调用，自动 PMID/PMCID/DOI 三级去重。用于医学 RAG 知识库广召回、全文 OA 链接发现、资助信息检索。返回完整元数据（OA 链接、citations、grants）。定位：广召回 · 多源 · RAG 友好。与 pubmed-eutils 互补 —— 本 skill 做"撒网"式多源聚合，后者做单源精准 + Clinical Queries。不做：单源精准检索（→ pubmed-eutils）、全文 XML 抽取（→ bioc-fulltext-fetch）、实体识别（→ pubtator-entity-search）、证据分级（→ medical-evidence-grading）。
SkillScore91/100
Test results 91
3/3 safety checks passed
23%91%of test cases passed +68 pts
Passed 20 of 22 test cases with the skill, and 5 of 22 without it.
15 fixed5 passed either way2 still failing0 broke
This benchmark measured an earlier version of the skill.
One test task在未配置任何 YAML 配置文件或环境变量 EUROPEPMC_EMAIL 的情况下，运行文献搜索客户端时会使用什么默认 email 标识？系统在首次请求前会给出怎样的行为反馈？
Adds every file the skill has, pinned so you can update it. No account needed.
pip install "decimalai>=0.15"
decimalai skills add ethanyoq-europepmc-search
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")claude --plugin-dir "$(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.
/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai/decimalai:install ethanyoq-europepmc-searchThe plugin needs python3 and curl on your machine.
No Python or account. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/ethanyoq-europepmc-search/SKILL.md https://app.decimal.ai/s/ethanyoq-europepmc-search/SKILL.md.claude/skills/ethanyoq-europepmc-search/SKILL.mdThis gets SKILL.md only. The skill's 3 other files are not included.
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.
pip install "decimalai[claude-agent-sdk]"
decimalai skills add ethanyoq-europepmc-searchimport 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.
pip install "decimalai[claude-agent-sdk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
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.
pip install "decimalai[openai-agents]"
decimalai skills add ethanyoq-europepmc-searchfrom 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.
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.
pip install "decimalai[openai-agents]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
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.
pip install "decimalai[openai]"
decimalai skills add ethanyoq-europepmc-searchimport 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.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.
pip install "decimalai[openai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/ethanyoq-europepmc-search/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].messageThis gets SKILL.md only. The skill's 3 other files are not included.
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.
pip install "decimalai[anthropic]"
decimalai skills add ethanyoq-europepmc-searchimport 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()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.
pip install "decimalai[anthropic]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
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.
pip install "decimalai[google-genai]"
decimalai skills add ethanyoq-europepmc-searchfrom 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)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.
pip install "decimalai[google-genai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
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.
pip install "decimalai[langchain]" langchain-openai
decimalai skills add ethanyoq-europepmc-searchfrom 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!"}]})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.
pip install "decimalai[langchain]" langchain-openaifrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add ethanyoq-europepmc-searchimport 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.
pip install "decimalai>=0.16" "crewai>=1.15.27"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom 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 3 other files are not included.
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.
pip install "decimalai[adk]"
decimalai skills add ethanyoq-europepmc-searchfrom 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.
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.
pip install "decimalai[adk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
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.
pip install "decimalai[pydantic-ai]"
decimalai skills add ethanyoq-europepmc-searchfrom 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.
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.
pip install "decimalai[pydantic-ai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" deepagents
decimalai skills add ethanyoq-europepmc-searchimport 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.
pip install "decimalai>=0.16" deepagentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
Its own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" agent-framework
decimalai skills add ethanyoq-europepmc-searchimport 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.
pip install "decimalai>=0.16" agent-frameworkfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
Strands' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" strands-agents
decimalai skills add ethanyoq-europepmc-searchfrom 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.
pip install "decimalai>=0.16" strands-agentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("ethanyoq-europepmc-search")
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.
.agents/skills/ethanyoq-europepmc-search/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/ethanyoq-europepmc-search/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 3 other files are not included.
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 ethanyoq-europepmc-searchNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/ethanyoq-europepmc-search/SKILL.md https://app.decimal.ai/s/ethanyoq-europepmc-search/SKILL.md.agents/skills/ethanyoq-europepmc-search/SKILL.mdThis gets SKILL.md only. The skill's 3 other files are not included.
Give its text to your model as instructions. No account or package needed.
This gets SKILL.md only. The skill's 3 other files are not included.
Raw files: /s/ethanyoq-europepmc-search/SKILL.md · /s/ethanyoq-europepmc-search.json
Fetch the file and give its text to your model as instructions. No account or package needed.
curl -fsSL https://app.decimal.ai/s/ethanyoq-europepmc-search/SKILL.mdcurl -fsSL https://app.decimal.ai/s/ethanyoq-europepmc-search.jsonThis gets SKILL.md only. The skill's 3 other files are not included.
You don't need a DecimalAI account.
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.
Europe PMC RESTful Web Service 的薄封装。一次请求 = 多源召回:PubMed(MED)、PubMed Central(PMC)、AGRICOLA(AGR)、CABI(CBA)、预印本(PPR,涵盖 bioRxiv/medRxiv/ChemRxiv/arXiv 生命科学子集/Research Square/SSRN/Preprints.org)、专利(PAT)、NCBI Bookshelf(NBK)、ETHOS 论文集等。
跨平台 Python(Windows / macOS / Linux 均可),无需 Anaconda 锁定环境。
| 场景 | 用本 skill | 应改用 |
|---|---|---|
| RAG 知识库构建,需"撒网"式广召回 | ✅ | — |
| 同时要 PubMed + 预印本 | ✅ | — |
| 拿 DOI 反查全文 OA 链接 | ✅ | — |
| 找特定基金(NIH/NSFC/Wellcome)资助的研究 | ✅(grant_id) | — |
| 只要 PubMed 官方源 + Clinical Queries | ❌ | pubmed-eutils |
| 抽取已知 PMCID 的全文 XML / 段落 | ❌ | bioc-fulltext-fetch |
| 临床试验注册号检索 | ❌ | clinical-trials-v2 |
| 实体(基因/疾病/化合物)关联 | ❌ | pubtator-entity-search |
| 给文献排 GRADE 等级 | ❌ | medical-evidence-grading |
| 报告 Appendix C 终态参考文献 | ❌ | evidence-appendix-sync |
与 pubmed-eutils 的差异化(必读):
pubmed-eutils 精准复核 → bioc-fulltext-fetch 取 OA 全文 → pubtator-entity-search 实体抽取 → medical-evidence-grading 分级 → evidence-appendix-sync 写入报告Europe PMC RESTful 是完全开放 API,无需 API key,但服务条款要求传 email 联系方式。
配置加载顺序(高到低):
.config/europepmc.local.yaml~/.config/europepmc.yamlEUROPEPMC_EMAIL[email protected] 并打印 ⚠️ 警告# ~/.config/europepmc.yaml
email: [email protected]
default_page_size: 100
default_result_type: core # lite | core | idlist
default_format: json
timeout_seconds: 30
max_retries: 3
基础 URL:https://www.ebi.ac.uk/europepmc/webservices/rest/
| 端点 | 用途 |
|---|---|
search | 通用检索(本 skill 主力) |
article/{source}/{id} | 单篇详情 |
{source}/{id}/fullTextXML | 全文 XML(仅 OA PMC 子集) |
{source}/{id}/references | 参考文献 |
{source}/{id}/citations | 被引列表 |
{source}/{id}/supplementaryFiles | 补充材料 |
grant/search | 资助检索 |
search_articlesfrom typing import Literal
def search_articles(
query: str,
source_filter: list[str] | None = None,
max_results: int = 200,
sort: Literal["date", "cited"] | None = None,
) -> list[dict]:
"""通用多源检索,自动 cursorMark 分页拉满到 max_results。"""
source_filter:["MED","PMC","PPR"] 限定来源;None = 全部。详细来源代码见 references/source-filters.mdpmid / pmcid / doi / title / authors / journal / pub_year / abstract / source / is_preprint / preprint_server / has_full_text / oa_status / cited_by_count 等(完整 schema 见 §11)get_article_detailsdef get_article_details(identifier: str) -> dict:
"""单篇完整元数据。identifier 自动识别:
- 纯数字 → PMID(查 MED)
- PMC 前缀 → PMCID(查 PMC)
- 10. 开头 → DOI(用 query=DOI:"..." 反查)
- PPR 前缀 → 预印本 ID(查 PPR)
"""
get_full_text_linksdef get_full_text_links(pmid_or_pmcid: str) -> dict[str, str | list[str] | None]:
"""返回所有可用全文链接,按类型分类:
{
"oa_xml": "...", # OA 子集才有
"oa_pdf": "...",
"publisher_html": "...",
"subscription": [...], # SUBSCRIPTION 类型
"text_mining": [...], # TM 类型
"preprint_server": "..." # 仅预印本
}"""
search_with_grantsdef search_with_grants(
query: str,
grant_id: str | None = None,
funder: str | None = None,
) -> list[dict]:
"""资助检索。Europe PMC 有专门的 GRANT_ID / FUNDER 字段。
例:search_with_grants(query="cancer", grant_id="R01-CA123456")
search_with_grants(query="cardiology", funder="Wellcome Trust")
"""
find_similar_articlesdef find_similar_articles(pmid_or_pmcid: str, limit: int = 20) -> list[dict]:
"""调用 Europe PMC 内置 'Similar Articles' 算法(MeSH + 文本相似度)。
比 PubMed elink neighbor 召回略广,适合 RAG 邻域扩展。"""
| 用户 prompt 示例 | 应否触发本 skill |
|---|---|
| "找血液 IFI 相关的 PubMed + PMC + 预印本聚合检索" | ✅ 触发 |
| "给我所有支持论文的全文链接,包括 OA 状态" | ✅ 触发(get_full_text_links) |
| "查特定 NIH grant R01CA255621 资助的肿瘤研究" | ✅ 触发(search_with_grants) |
| "我做 RAG 知识库,需要广撒网召回 1000 条" | ✅ 触发 |
| "DOI 10.1038/... 反查全文链接" | ✅ 触发(get_article_details + get_full_text_links) |
| "我只要 PubMed 官方源的高精准查询 + Clinical Queries 过滤" | ❌ 改用 pubmed-eutils |
| "查 PMC 文章 PMC10987654 的全文段落" | 部分:本 skill get_full_text_links 给链接 → 全文取用交 bioc-fulltext-fetch |
| "给 200 篇文献排 GRADE 等级" | ❌ 改用 medical-evidence-grading(可链式接本 skill 输出) |
| "找 NCT12345678 临床试验招募信息" | ❌ 改用 clinical-trials-v2 |
最常用字段速查(完整 cheatsheet 见 references/query-syntax.md):
| 字段 | 示例 |
|---|---|
TITLE / TITLE_ABS | TITLE_ABS:"acute myeloid leukemia" |
AUTH | AUTH:"Smith J" |
JOURNAL | JOURNAL:"Nature" |
PUB_YEAR | PUB_YEAR:[2020 TO 2024] |
PUB_TYPE | PUB_TYPE:"Review" |
SRC | SRC:MED / SRC:PPR |
HAS_FT / OPEN_ACCESS | HAS_FT:Y AND OPEN_ACCESS:Y |
MESH | MESH:"Hematologic Neoplasms" |
GRANT_ID / FUNDER | GRANT_ID:"R01CA12345" |
DOI | DOI:"10.1038/s41586-020-2196-x" |
⚠️ 字段名 必须大写,title:foo 会被当成普通短语。
同一篇文章常在 MED + PMC + PPR 同时出现。去重规则按优先级:
superseded_by_pmid: <发表版 PMID>,下游 medical-evidence-grading 据此自动丢弃。每条 PPR 结果显式标注:
{
"source": "PPR",
"is_preprint": True,
"preprint_server": "bioRxiv", # 或 medRxiv / ChemRxiv / Research Square / SSRN
"preprint_doi": "10.1101/2024.03.15.123456",
"posted_date": "2024-03-15",
"version": 2
}
下游 medical-evidence-grading 看到 is_preprint=True 自动降权(GRADE 中作为 "very low" 起点)。本 skill 自身不做证据分级,只如实标注。
| ID | 故障 | 现象 | 处理 / 抛出 |
|---|---|---|---|
| F1 | API 速率限制(429) | HTTP 429 + Retry-After | 指数退避 2^n + jitter,最多 max_retries=3;仍失败抛 EuropePMCRateLimitError |
| F2 | 多源去重失败 | 同 DOI/PMID 出现多条未合并 | 走 _dedupe_three_tier() 强制去重;若三级 ID 都缺,按 (title 前 80 字 + first_author + pub_year) MD5 哈希再合并;无法合并则保留并标 dedup_warning=True |
| F3 | 预印本未标记 | 结果里 source=="PPR" 但 is_preprint=False | 检测到 source==PPR 强制设 is_preprint=True,补 preprint_server 字段(从 publisher 字段映射);写 WARN log |
| F4 | cursorMark 分页失败 | nextCursorMark 与上次相同但 hitCount 未取完 / 连续两次空响应 | 第一种正常终止;第二种抛 EuropePMCPaginationError,附最后一次 cursor 值便于断点续抓。详见 references/cursormark-pagination.md |
| F5 | email 未配置警告 | 配置链 4 级全空 | 退化用 [email protected],首次请求前打印 ⚠️ WARN,提示用户配置 ~/.config/europepmc.yaml |
| F6 | 查询语法错误 | HTTP 400 + errMsg | 抛 EuropePMCQueryError(errMsg),不静默吞;常见原因:字段名小写、引号未配对、AND/OR 未大写 |
| F7 | 命中为 0 | HTTP 200 + hitCount=0 | 返回空列表 + WARN"无命中,建议放宽 query / 移除 source_filter / 检查字段大小写" |
| F8 | 服务端 5xx / 超时 | HTTP 5xx 或 requests.Timeout | 指数退避重试 max_retries 次;仍失败抛 EuropePMCServerError |
| F9 | 结果超 max_results | hitCount > max_results | 截断并在返回 dict 顶层设 truncated=True,附 last_cursor_mark 便于续抓 |
致命错误一律抛异常,不静默吞(遵循 coding-style.md 错误处理原则)。
pageSize=1000cursorMark(从 * 起),不要用 page= 偏移分页(>1000 条时官方不保证一致性)references/cursormark-pagination.md每篇文章返回的标准 schema(本 skill 是契约源 — bioc-fulltext-fetch / pubtator-entity-search / medical-evidence-grading / evidence-appendix-sync 都按此消费):
{
"primary_id": "PMID:38123456" | "PMCID:PMC10987654" | "DOI:10.xxx/...",
"all_ids": {"pmid": str|None, "pmcid": str|None, "doi": str|None, "ppr_id": str|None},
"title": str,
"authors": [{"full_name": str, "affiliation": str|None, "orcid": str|None}],
"journal": {"name": str, "iso_abbr": str|None, "issn": str|None},
"pub_year": int,
"pub_date": "YYYY-MM-DD",
"abstract": str|None,
"mesh_terms": list[str],
"keywords": list[str],
"source": "MED" | "PMC" | "PPR" | "AGR" | "CBA" | "PAT" | "NBK",
"sources_merged": list[str], # 去重前出现的所有源
"is_preprint": bool,
"preprint_server": str|None,
"preprint_doi": str|None,
"version": int|None,
"superseded_by_pmid": str|None,
"has_full_text": bool,
"oa_status": "OA" | "SUBSCRIPTION" | "UNKNOWN",
"full_text_links": {"oa_xml": str|None, "oa_pdf": str|None, "publisher_html": str|None},
"cited_by_count": int,
"grants": [{"grant_id": str, "agency": str, "country": str|None}],
"fetched_at": "ISO-8601 UTC",
"europepmc_url": "https://europepmc.org/article/MED/38123456"
}
字段缺失用 None,不省略 key(下游解构稳定性)。
[用户问题]
│
├─→ europepmc-search ← 本 skill (广召回 200~1000 条 + 多源去重)
│ │
│ ├─→ pubmed-eutils ← 拿 PMID 子集精准复核 + Clinical Queries
│ │ │
│ │ └─→ bioc-fulltext-fetch ← OA PMC 全文 XML
│ │ │
│ │ └─→ pubtator-entity-search ← 实体识别
│ │ │
│ │ └─→ medical-evidence-grading ← GRADE 分级
│ │ (依据 is_preprint 自动降权)
│ │ │
│ │ └─→ evidence-appendix-sync ← 终下游(写 Appendix C)
│ │
│ └─→ medical-evidence-grading 也可直接消费本 skill 输出(跳过精准复核)
│
└─→ clinical-trials-v2 / aact-bulk-trials ← 试验注册号另走专线
from europepmc_search import EuropePMCClient
cli = EuropePMCClient() # 自动加载 ~/.config/europepmc.yaml
# 1) 广召回:急性髓系白血病近 5 年 PubMed + 预印本
hits = cli.search_articles(
query='(TITLE:"acute myeloid leukemia" OR ABSTRACT:"AML") AND PUB_YEAR:[2020 TO 2025]',
source_filter=["MED", "PPR"],
max_results=500,
sort="date",
)
print(f"去重后 {len(hits)} 条,预印本 {sum(h['is_preprint'] for h in hits)} 条")
# 2) DOI 反查全文链接
links = cli.get_full_text_links("10.1056/NEJMoa2024850")
# 3) NIH R01 资助的 CAR-T 研究
ft = cli.search_with_grants(query="CAR-T", grant_id="R01CA255621")
# 4) 邻域扩展(RAG)
similar = cli.find_similar_articles("38123456", limit=30)
| 文件 | 内容 |
|---|---|
references/query-syntax.md | 完整字段表 + 布尔/通配/邻近搜索 + 5 个常用查询配方 + 排序参数 |
references/source-filters.md | 全部 SRC 来源代码 + 量级 + 预印本子源(bioRxiv/medRxiv/...) + 选择策略 |
references/cursormark-pagination.md | cursorMark 流程伪代码 + 终止条件 + 退避策略 + 5 个常见坑 |
Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.