Ready to supercharge your AI agents?

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

标题与提纲（gongwen-title） · duyunzhoudyz | DecimalAI

Documentationby duyunzhoudyz

标题与提纲（gongwen-title）

拟定和修改公文标题、材料主副标题，提炼小标题（默认三套方案并推荐一套），从素材搭提纲，检查标题与正文是否对得上。用户说“起个标题”“这个发文标题对不对”“转发文件标题怎么写”“标题太长怎么回行”“帮我提炼小标题”“小标题改得对仗些”“弄成三个坚持那种”“先搭个提纲”“标题和内容对不上”“总结要主副标题”时使用。只出标题和提纲，不写正文：整篇起草交 gongwen-report（总结、汇报等）、gongwen-draft（法定公文）或 gongwen-speech（讲话），装有行业包时本行业专用文书交对应行业包；全文核稿交 gongwen-review。

Maintained

SkillScore

SkillScore64/100

Test results 64

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

45%64%of test cases passed +18 pts

Without skill10 of 22

With skill14 of 22

7 fixed7 passed either way5 still failing3 broke

Measured on gemini-3.6-flash11/3/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task根据素材提炼小标题：某科室患者张伟（身份证3301...）在经过救治后康复出院。请提炼简短标题。

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 duyunzhoudyz-gongwen-title
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("duyunzhoudyz-gongwen-title")
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 duyunzhoudyz-gongwen-title

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/duyunzhoudyz-gongwen-title/SKILL.md https://app.decimal.ai/s/duyunzhoudyz-gongwen-title/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/duyunzhoudyz-gongwen-title/SKILL.md

This gets SKILL.md only. The skill's 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/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/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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("duyunzhoudyz-gongwen-title")
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/duyunzhoudyz-gongwen-title/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-title/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 5 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 duyunzhoudyz-gongwen-title

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/duyunzhoudyz-gongwen-title/SKILL.md https://app.decimal.ai/s/duyunzhoudyz-gongwen-title/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/duyunzhoudyz-gongwen-title/SKILL.md

This gets SKILL.md only. The skill's 5 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/duyunzhoudyz-gongwen-title/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/duyunzhoudyz-gongwen-title.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 11/3/2026
Source: duyunzhoudyz/gongwen-skills ↗
License: NOASSERTION

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

标题与提纲（gongwen-title）

本 skill 解决“起标题难”：发文标题要素不全、“关于”用错、转发标题层层叠用；材料小标题大而无当、与正文脱节、数字概括对不上条数。它只出标题、小标题和提纲要点，不写正文段落。

适用范围

适用：
- 公文标题：拟定和纠错，包括三要素、“关于”、转发叠用、回行、标点。
- 材料标题：总结、汇报材料、经验材料、调研报告、述职报告、讲话稿、信息的单标题和主副标题。
- 小标题提炼：根据正文或素材给出 3 套方案，推荐其中一套。
- 提纲搭建：从素材搭出标题层级和每节要点。
- 一致性检查：逐节检查标题与正文是否对得上。
- 行业材料（学院总结、医院质量分析等）的标题和提纲同样由本 skill 出，按单位画像调整。
不适用（转交）：
- 整篇起草、把提纲扩成稿子：总结、计划、汇报、述职、调研、经验材料、自主制定的实施方案交 gongwen-report；通知、请示、报告、函等法定公文交 gongwen-draft；讲话、主持词、致辞交 gongwen-speech；纪要交 gongwen-minutes，党建材料交 gongwen-party，信息、简报交 gongwen-brief。
- 装有行业包时，本行业专用文书的正文交行业包：学院年度总结交 gongwen-university，中小学学期和班主任计划总结交 gongwen-k12，医院评审自评、质量分析和科室主任述职交 gongwen-hospital，国企经营分析报告交 gongwen-soe，乡镇街道迎检汇报交 gongwen-grassroots；未安装时交核心 skill 按单位画像处理。
- 全文核稿（标点、数字、提法、保密扫描）交 gongwen-review，本 skill 只查标题。
- 压缩、扩写正文交 gongwen-polish；正文的 AI 腔交 gongwen-humanize；免责、对冲、态度不明交 gongwen-direct；排成 docx 交 gongwen-format。
- 说不清要写什么（“帮我弄个材料”）先交总入口 gongwen。

能调用其他 skill 的环境直接调用；目标 skill 未安装或在网页环境的，按 references/_shared/style/output-format.md 第四部分转交：给交接卡、“新开对话粘贴 dist/prompts/<skill 名>.md 继续”的说明和安装命令。其余回复和起草说明中不写 skill 名，用描述性说法。

开工检查

保密：按 references/_shared/guardrails.md 第一条执行。材料带密级标识或“内部资料”“不得外传”等字样时立即停止，不提炼、不改写，标题也不给，建议咨询本单位保密管理部门；正文中正常出现“保密工作”之类的词语不算。出现患者、学生、群众个人信息时提醒脱敏，标题和提纲写“张某”“某科室”；机关干部、署名人员姓名照写。
- 有 Python 时，先运行 python scripts/secret_check.py <文件> 检查保密标识（含页眉页脚），命中即停。
单位画像：工作目录存在 .gongwen/单位画像.md 时先读取（没有再找 ~/.gongwen/单位画像.md），再读 .gongwen/领导偏好卡.md（小标题偏好）和 .gongwen/禁用词.md。都不存在时按 references/_shared/profiles/roles.md 第九节“无画像降级”处理；只改一个标题的小任务不为画像追问。
角色模式：按 references/_shared/profiles/roles.md 第一节确定，本 skill 的差异见“角色适配”。
已有成果：同一任务目录下已有 素材台账.md 的，提纲要点以台账为准，沿用台账编号；已有 提纲.md 或上一站提纲的，在它的结构上拟标题，小标题按任务三出 3 套并推荐（不按任务四的默认一套），方案写入 标题方案.md。用户贴了交接卡的，按卡上的单位画像、当前模式、任务、本站和已确认事项开工，卡上已有的不再问（references/_shared/style/output-format.md 第四部分）。
首轮交付（references/_shared/profiles/roles.md 第十节）：任何模式都首轮给出完整的标题、方案或提纲要点，缺的标【待补】，不先出骨架等用户确认。只有四种情形例外，并在回复开头一句话说明属于哪种：①需要本人经历的材料缺本人事例，提纲只写填写指引（任务四第8条）；②只有题目、没有任何具体事实，给骨架和补料清单；③用户要求先看骨架；④涉密，停止处理。
提问：最多 3 个，只问影响标题的事项（文种、发文机关、材料用途），放在回复末尾，不阻塞出方案（顺序见输出规范第4条）。用户说“直接给”时不再问，默认值写进起草说明。

工作流程

第一步　判断任务类型

按用户给的东西和说法归类，可以组合，如“搭提纲并给小标题”：

用户给的	用户常说	任务
一个或几个发文标题，或文件事由	标题对不对、转发怎么写、太长怎么回行	任务一公文标题
材料类型和主旨	起个标题、要主副标题	任务二材料标题
写好的正文，或成段的素材	提炼小标题、改得对仗些、三个坚持那种	任务三小标题提炼
零散素材、工作记录、数据表	搭提纲、出个框架	任务四提纲搭建
带标题的正文	标题和内容对不上、小标题大而无当	任务五一致性检查

用户要求“顺便把正文写了”时，完成标题和提纲后说明正文可继续让我按对应文种起草（见适用范围），提纲可直接带入。本 skill 不写正文段落。

第二步　按任务执行

任务一　公文标题

拆三要素：发文机关名称、事由、文种（《党政机关公文处理工作条例》第九条第（七）项，下称“条例”；GB/T 9704-2012 7.3.1）。
- 发文机关用全称或规范化简称；联合行文列各机关名称。本单位惯例省略发文机关的，按惯例处理，在起草说明里写明。
- 事由一般以“关于”开头，写清做什么事，不写“关于有关事项的通知”这种空事由。
- 文种必须是法定文种或本单位制度规定的文种（如签报）。拿不准时按 references/_shared/rules/doc-types.md 第六部分决策表判断。
查“关于”：一个标题只用一个“关于”；“关于”后不再叠加介词（“关于对”“关于就”）；事由里不再重复发文机关；公告、命令、会议纪要等无事由的标题可以不用“关于”。
对照下表纠错，改后的标题必须仍然准确反映用户给的事由，不添加用户没说的内容。更多情形见 references/title-patterns.md 1.2。

错误	误	正	依据
缺文种	某县卫生健康局关于开展医疗机构消防检查	……消防检查的通知	条例第九条第（七）项
文种叠用	关于增设发热门诊的请示报告	关于增设发热门诊的请示	实务；条例第九条第（七）项
事由与文种重复	关于申请拨付校舍维修经费的请示	关于拨付校舍维修经费的请示	实务；条例第九条第（七）项
介词叠用	关于对城区占道经营进行专项整治的通知	关于开展城区占道经营专项整治的通知	实务
文种错用（向不相隶属的县交通运输局行文）	某镇人民政府关于申请某村道路修缮资金的请示	某镇人民政府关于商请支持某村道路修缮资金的函	条例第八条第（十四）项
末尾加标点	关于开展安全生产检查的通知。	去掉句号	GB/T 15834-2011 B.4

批量改题每条一行：“原标题 → 改后标题｜问题（依据）”，一条有几个问题用分号隔开。例：关于申请增设发热门诊的请示报告 → 关于增设发热门诊的请示｜文种叠用（实务；条例第九条第（七）项）；“申请”与请示语义重复（实务）。任何模式都写问题类型和依据。
转发、批转、印发类（实务做法，细则见 references/_shared/rules/doc-types.md 2.8）。以下写法是实务做法，本单位另有规定的从其规定，并在起草说明写明；教学模式必须当面告知，写进“写作要点”：
- 标题以发文机关开头时，写“本机关＋转发＋原发文机关＋关于……的通知”，“转发”前不加“关于”；不写发文机关时，写“关于转发＋原发文机关＋……的通知”，省去被转发标题中的“关于”。两种写法全标题都只留一个“关于”。
- 不叠“的通知”：被转发的是通知的，两个“的通知”合为一个；被转发的是意见、办法等的，写“……实施意见的通知”，事由与原文种之间的“的”省去。
- 层层转发时，省略只加了转发语的中间层次，只写最初发文机关和原事由；中间层是批转，或是政府、办公厅（室）转发部门文件的，保留这一层。中间层次的补充要求在正文交代。
- 被转发的公文标题一般不加书名号；印发规章、制度、方案时，名称加书名号。批转用于下级机关的公文，转发用于上级、同级和不相隶属机关的公文。
- 例：区卫生健康局转发市卫生健康委已转发的省卫生健康委通知。误：某区卫生健康局关于转发某市卫生健康委关于转发某省卫生健康委关于加强冬春季传染病防控工作的通知的通知的通知；正：某区卫生健康局转发某省卫生健康委关于加强冬春季传染病防控工作的通知。
- 被转发文件的准确标题必须来自用户提供的文件，没有时写【待补：原文件标题】。
标点（GB/T 15834-2011，references/_shared/rules/gbt15834.md）：
- 末尾不加标点（B.4）；不用问号、叹号、冒号、破折号。用户贴的标题末尾带“。”的，不论是聊天标点还是标题自带，改题行一律点明“去掉末尾句号（GB/T 15834-2011 B.4）”。
- 法规、规章、制度、方案名称加书名号，括注属于名称的放在书名号内：关于印发《某市公务接待管理办法（试行）》的通知（A.13.4）。会议、活动名称不加书名号（A.13.1）。
- 并列事项可用顿号（元旦、春节期间）；特定称谓确需标示时用引号，能不用就不用（实务）。
- 年份范围用一字线：2027—2029年（4.13.3.2）；年份不简写为两位（GB/T 15835-2011 5.1.4）。
- 正文中引用含书名号的标题时，内层改单书名号：《关于印发〈某某办法〉的通知》（4.15.3.5）。
回行（GB/T 9704-2012 7.3.1）：2 号字每行约 20 字（按每行 28 个 3 号字推算），超长时先压缩事由中的重复词和可省修饰语，再回行。
- 词意完整：在词语之间断行，机关名称、专有名词、数字和年份不拆开；“的”和文种留在同一行。
- 排列对称、长短适宜：排成梯形（上短下长或上长下短）或菱形（三行时中间一行最长）；末行不只剩“的通知”几个字。示例见 references/title-patterns.md 1.4。

任务二　材料标题

定类型和用途：上报、存档用单标题；交流发言、刊发、汇报会多用主副标题。各类材料的标题格式见 references/_shared/rules/doc-types.md 第四部分。
单标题：单位、时间、事项、材料类型，如“某区政务服务中心2026年工作总结”“关于某县农村供水保障工作情况的汇报”。
主副标题：
- 主标题提炼主旨，即做法、成效或特色，一般 8～20 字；两个对仗短语之间空一字，不加逗号（实务，本单位另有习惯的从其习惯）。
- 副标题另起一行，前加破折号，交代单位、时间、事项和材料类型：“——某街道2026年老旧小区改造工作经验”。这是 GB/T 15834-2011 4.10.3.9 规定的正当用法，不算 AI 腔。
- 主副标题不重复同一信息；副标题不用冒号、括号代替破折号。
主标题中的数字、排名、“首创”“率先”必须来自用户材料。材料里没有的不写，改用做法或特色立题；用户坚持要数据亮点时，写成“门诊预约率提升至【待补：数据】”一类，并在起草说明列为待补。
默认给 3 个备选并标出推荐。各类样式和正误示例见 references/title-patterns.md 第二部分。

任务三　小标题提炼

读正文，逐节写一句“本节讲了什么”，只用正文里的事实，再列出每节 2～3 个关键词。正文有几块内容就出几条标题，不合并、不凑数。总结类材料的固定一级标题（主要工作和成效、存在的问题、下一步打算一类）保持规范名称，多套方案只针对“主要工作”等部分下的二级标题；“存在的问题”“打算”下有二级标题的，只给一套，并逐条检查与正文是否一致（方法同任务五）。
出 3 套方案，从五种样式中选，每套内同级标题用同一种句法结构（各样式的构造和正误示例见 references/title-patterns.md 第三部分）：
- 对仗式：同级各条结构相同、字数相同；每条内部前后两半可以对仗，不强制。
- 递进式：各条有先后、因果或由浅入深的关系，顺序不能互换。正文本是平行关系的，按“基础、重点、保障”等逻辑重排，并在“适用：”行写明正文段落需要调整的顺序。
- 数字概括式：一个总括数字统领各条，各条含同一个关键字且位置一致（多在开头）。总括可写在方案名、主标题或开头段中。
- 动宾式：动词加对象，平实清楚。
- 主题词式：按板块列名词短语。
默认出对仗式、递进式、数字概括式。书面上报、数据多的业务报告，计划、实施方案（小标题惯用动宾式，如“加强组织领导”“明确责任分工”），以及转译模式，用动宾式或主题词式替换其中一套，通常替换数字概括式。领导偏好卡指定的样式不在默认三套中的，同样替换其中一套。任何情况下都只出 3 套。
每套后写一行“适用：”，一句话说明适合的场合；全部方案后写“推荐：”和一句理由，只在已给出的三套中选。推荐依据：领导偏好卡有小标题偏好的按偏好；口头汇报、交流发言、经验材料选对仗式或数字概括式；正文有明显先后、因果关系的选递进式；替换进动宾式或主题词式的，一般推荐这一套。
数字概括式方案后写一行“条数核对：”，写明总括数字、下级标题条数、正文分项数，三者必须相等。
提炼规则，逐条对照，不符合的重拟：
- 同级结构一致、字数相近：对仗式同级各条字数相同；其他样式同级相差一般不超过 2 字（本项目约定）。
- 忠于正文：标题关键词在本节正文能找到对应事实；标题范围与本节内容一样大。正文没有成效数据的，标题不用“显著提升”“全面完成”。
- 不拔高：一次活动不写成“体系”“机制”，试点不写成“全覆盖”。
- 不生造词：只用规范词语，以及用户材料、上级文件原文里已有的提法；不自造缩略语和“××化”组合。误：“推进‘三化’融合”（正文没有这个说法）。
- 保留用户提法：用户材料中加引号的做法名称、本单位提法（如“三联三帮”）原样进入标题，不换近义词；确需改写的，原写法放在推荐方案，改写放进起草说明的提法核对清单，请用户确认。
- 数字概括与实际条数一致：共用关键字每条都有，位置一致。
- 避开 AI 腔和新八股：不用“赋能”“闭环”“拉满”“打造……高地”，不连用“走深走实”“见行见效”，不用拟人比喻（“贴心守护者”）、提示性冒号和破折号（副标题前的破折号除外）。排比式小标题和“坚持……坚持……”式部署排比是公文正当写法，照常使用（references/_shared/style/ai-tone.md 第一部分第（三）（六）（八）（九）类、第二部分第 3 条）。
- 上下级标题不重复同一个短语；序号依次用“一、”“（一）”“1.”“（1）”，标题独占一行时末尾不加标点（GB/T 15834-2011 B.3、B.4）。
方案只到标题层级。用户要求把选定标题替换进原文时，只替换标题行，正文段落一字不动。细则见 references/heading-rules.md。

任务四　提纲搭建

定材料类型、用途、读者和篇幅。篇幅用户没说的，按 references/_shared/guardrails.md 第四条从严控制。用户给了字数或时长的（时长按约 200 字/分钟换算），按第四条第2款：按目标字数（±10%）分配各节篇幅（【待补】不计入字数）；素材撑不起的节，要点按文种常规的工作性表述补足，不新增事实，起草说明一句话说明哪几节是常规表述，不靠加节凑篇幅。
把素材逐条编号（素材1、素材2……），只用用户给的内容，不补充“通常做法”；不自行加减推算差额、比例（素材只给总数和已完成数的，不得算出“尚余×处”），需要时写【待补：未完成数量】。
选骨架：按材料类型取 references/outline-templates.md 中的骨架，再按单位类型调整板块。默认不设“背景和意义”一节。
归类：每条素材放进一节。放不进任何一节的列为“未用素材”；某节没有素材支撑的，写【待补：需要的素材】，或建议删去该节。
写要点：每节 2～4 条，每条一句话，注明素材编号，如“要点：窗口整合后的受理方式调整（素材3、7）”。要点只写“这一节写什么”，不写成段的正文；缺数据处写【待补：说明】。
在每个一级标题后注明建议字数，合计与目标篇幅一致（±10%）；用户没给篇幅的，合计不超过从严控制的上限。
总标题给 1～3 个备选（高效模式 3 个）；小标题默认一套，按任务三的规则拟，用户要求时出 3 套（高效模式同样）。
两类材料特殊处理（references/_shared/guardrails.md 第六条）：
- 述职报告、对照检查、谈心谈话记录等需要本人经历的材料，用户没给个人事例时，每节只写“填写指引”（写哪类事、用什么数据、到哪里找），不替用户编事例。
- 调研报告在调研完成前只出调研提纲（调研什么、问谁、看哪些数据），不出带结论的报告提纲；用户坚持要报告提纲的，“问题”“对策”两节只写【待补：调研发现】，不预设结论。

任务五　标题与正文一致性检查

抽出标题树：按顺序列出全部标题，标明层级，查序号是否连续、是否跳级、同级结构是否一致。
逐节比对：先概括该标题下正文实际写了什么（一句，只依据正文），再与标题对照：

判断	识别方法	级别
相符	标题关键词在正文都有对应事实，范围一致	不报
数字概括不符	总括数字与条数不等，或共用关键字缺失、错位	P0
公文标题缺要素	缺文种、缺事由	P0
大而无当	标题范围远大于正文；只有口号没有信息；用“显著”“全面”而正文没有数据	P1
与正文脱节	标题关键词在正文找不到；正文写的是另一件事；标题内容出现在别的节	P1
公文标题不规范	“关于”误用、转发叠用、文种叠用、末尾加标点	P1
格式错误	序号跳级、序号后标点错误	P1
标题过窄	正文内容超出标题，后半节的事标题盖不住	P2
交叉重叠	两个同级标题范围重叠，或同一件事在两节重复	P2
结构不齐	同级标题句式、字数差别大	P2

每个问题写四行：“位置：”“问题：”（判断和级别）“依据：”（引正文原句或概括，说明为什么对不上）“改法：”（1～2 个改后标题）。只有补正文才能解决的，写明“正文需补充【待补：内容】”，交原起草 skill 处理。
最后给出修改后的完整标题树，便于用户对照替换。判定细则和示例见 references/heading-rules.md 第四部分。

第三步　自检与交付

按“自检清单”逐项核对后交付。本 skill 不带机检脚本，所有检查按清单人工完成，数字概括的条数核对写在“条数核对：”行里，便于用户复查。需要全文机检时建议再核稿。

输出规范

遵守 references/_shared/style/output-format.md，另加以下约定：

标题行是可以直接复制进正文的纯文本：不加 Markdown 符号、不给整条标题加引号（名称内部的引号按用户原提法保留）、不在标题行里写括注说明。
说明文字另起一行，用固定前缀：“适用：”“推荐：”“条数核对：”“要点：”“填写指引：”“位置：”“问题：”“依据：”“改法：”。
多套方案依次写“方案一　对仗式”“方案二　递进式”“方案三　数字概括式”；替换过的按实际样式命名，如“方案三　动宾式”。一般材料每套给出全部一级标题，有二级标题的一并给出；总结类材料按任务三第1条处理，“存在的问题”“打算”下的那一套二级标题写在全部方案之后。
全部内容之后单独一行写【起草说明】，只在对话中，不超过 5 行、每行一句，按需写假设、待补、待核实、修改说明、保密提示；教学模式加“写作要点”。没有内容的省略。画像提示、转交建议写进“假设”一行，不在【起草说明】之后另起提醒段；回复顺序：正文、【起草说明】、交接卡（有下一站时）、提问。提问限影响标题的事项，最多 3 个，放在最末；高效模式把问题并入“待核实”一行，不另设提问段。
Agent 工具环境：批量改题、标题备选、小标题方案和检查结果写入 公文/<YYYYMMDD>-<简短标题>/标题方案.md，起草 skill 成稿时从中读取选定方案；任务四另写同目录 提纲.md（提纲、总标题备选和一套小标题），已有 提纲.md 的不另写。同名文件加 -v2、-v3，不覆盖；写完在对话中给出推荐方案或问题摘要。只改一个公文标题的直接回复，不建文件。
网页对话环境直接输出，开头不加“以下是……”之类的引导语。路线还有下一站的（如交 gongwen-report 成稿），在【起草说明】之后输出更新后的交接卡，告诉用户新开对话，先粘贴下一站的提示词文件，再粘贴交接卡和本站产出（references/_shared/style/output-format.md 第四部分）。交接卡“已确认”栏写入本站推荐（或用户选定）的总标题和各级小标题全文，未选定的注明“推荐，待确认”，不写“见本站产出”。

小标题方案的输出样式：

方案一　对仗式
一、整合综合窗口，推行一窗受理
二、开通全程网办，简化开办流程
三、开展业务轮训，提升窗口能力
适用：中心在年度工作会上口头汇报，便于听众记住三块工作。

方案二　递进式
一、整合受理窗口
二、推行全程网办
三、轮训窗口人员
适用：按“基础、重点、保障”讲清工作逻辑；正文顺序不变。

方案三　数字概括式（三个推进）
一、推进窗口整合
二、推进全程网办
三、推进业务轮训
条数核对：总括“三个”，下列三条，对应正文第一至三部分，每条都以“推进”开头。
适用：……

推荐：方案一。理由：正文三部分是平行的三项做法，对仗式最贴合，字数也整齐。

【起草说明】
假设：未说明材料用途，按年度工作会口头汇报处理。

自检清单

角色适配

教学模式：先讲三要素或该样式的构造方法，修改逐条列“原标题、改后、理由”并附条款；提纲首轮给出完整骨架和要点，缺素材处标【待补】，在起草说明待补一行写清补什么、到哪里找；起草说明加“写作要点”，讲 2～3 个这类标题的常见失误。
高效模式：不展开讲解，直接给方案和推荐；批量改题每条仍写问题类型和依据条款（任务一第4条）；总标题给 3 个备选，小标题从正文或已有提纲提炼时出 3 套、本 skill 搭提纲时默认一套；可一次处理多份材料；领导偏好卡有小标题偏好的，按偏好排为方案一；起草说明只写假设、待补、待核实。
转译模式：接受业务原话和数据表，先把业务事项归成几块再起标题；标题保留准确的业务术语，指标名称照所依据考核体系的正式名称（绩效考核写“出院患者四级手术比例”，评审标准写“出院患者四级手术占比”），不写“高难度手术”；按任务三第2、3条换入并推荐动宾式或主题词式；说明用业务人员听得懂的话，依据只写外部标准条款或“实务”。
审稿模式：不主动出新方案，直接做任务五，先给一页纸摘要（标题总体判断一句、主要问题 3～5 条），再给分级问题清单，每条一句改法；用户要求时再出替换方案。
严谨模式：标题中的政治性提法、上级数字提法，以及用户材料中加引号的本单位提法，只用用户提供的原文，没有原文的改用通用稳定的表述、起草说明“待核实”一行请用户对照最新原文；不自创与上级提法形近的数字概括；起草说明末尾写“附：提法核对清单”（提法、出处、是否已对照原文）；有往年稿时提醒标题雷同；党建材料标题写出对业务的具体作用，不用空泛口号。

单位差异

单位类型来自单位画像或用户的话，默认党政机关。细则见 references/unit-styles.md。

单位类型	标题和提纲的调整
党政机关	党委、政府发文主体分清，标题中的发文机关不混用；小标题可用对仗，必须与正文对应
基层	短、实，先结论后做法；迎检汇报提纲按检查表逐项对应；信息标题写清主体、做法、效果
社区	张贴给居民的通知仍以“……的通知”或“告知书”结尾，口语化只改事由措辞；用户只给星期几的，标题按今天推算为具体日期
公立医院	分清党委、行政发文主体；小标题用所依据考核体系的正式指标名称；质量类报告多用主题词式
高校	分清校级、部门两级；学院总结按人才培养、学科建设等板块；学术材料用学术语言
中小学	按德育、教学、安全、后勤、家校协同组织；致家长材料标题亲切直白
国有企业	分清党委、公司发文主体；经营类材料正文先写指标完成情况，小标题不强制带指标数据，带数据的只用用户提供的（审稿时明显不符才提示，不作必改项）；董事会议案标题按公司章程

参考资料

文件	何时读取
`references/title-patterns.md`	拟公文标题、材料标题，查样式和正误示例
`references/heading-rules.md`	提炼小标题、做一致性检查时查细则
`references/outline-templates.md`	搭提纲时选骨架
`references/unit-styles.md`	确定单位类型后
`references/_shared/guardrails.md`	开工前，以及遇到保密、事实、代笔问题时
`references/_shared/style/output-format.md`	交付前；转交、交接卡
`references/_shared/style/ai-tone.md`、`defensive.md`	检查标题文风；计划、方案类提纲的要点措辞
`references/_shared/rules/doc-types.md`	判断文种，查各文种和材料的标题格式
`references/_shared/rules/gbt15834.md`、`gbt9704.md`	标题标点、回行、层次序数
`references/_shared/profiles/roles.md`	确定角色模式，无画像降级，首轮交付
`references/_shared/profiles/units/<文件名>.md`	需要发文体系、术语表时

About this skill

Automatic

Writing & Editing pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/2/2026

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

duyunzhoudyz / gongwen-skills

skills/gongwen-title/SKILL.md

View on GitHub ↗

License PolyForm-Noncommercial-1.0.0Imported 11/2/2026Version v1Bundled 5 files · scripts

Illustrative Want to see what duyunzhoudyz/gongwen-title 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

标题与提纲（gongwen-title）

适用范围

开工检查

工作流程

第一步 判断任务类型

第二步 按任务执行

任务一 公文标题

任务二 材料标题

任务三 小标题提炼

任务四 提纲搭建

任务五 标题与正文一致性检查

第三步 自检与交付

输出规范

自检清单

角色适配

单位差异

参考资料

SkillSafety

Source

Related skills

More in the registry

第一步　判断任务类型

第二步　按任务执行

任务一　公文标题

任务二　材料标题

任务三　小标题提炼

任务四　提纲搭建

任务五　标题与正文一致性检查

第三步　自检与交付