Ready to supercharge your AI agents?

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

改稿润色（gongwen-polish） · duyunzhoudyz | DecimalAI

Documentationby duyunzhoudyz

改稿润色（gongwen-polish）

改稿润色：在已有稿子上压缩、只用已有事实扩写、上行平行下行语气互转、大白话转公文语言、讲话口语化或书面化、按领导批注逐条改、多稿合并（冲突由用户定），不新增事实，附修改说明。用户说“压到3000字”“太长了砍一半”“报告改成发给下面的通知”“大白话改成公文”“领导批了太虚、数据呢”“两稿合成一稿”时使用。AI 腔交 gongwen-humanize，专门去免责、对冲交 gongwen-direct，核稿交 gongwen-review，改标题交 gongwen-title，压成政务信息交 gongwen-brief，判断文种交 gongwen-draft，重写结构交回原起草 skill。

Maintained

SkillScore

SkillScore73/100

Test results 73

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

55%73%of test cases passed +18 pts

Without skill12 of 22

With skill16 of 22

5 fixed11 passed either way5 still failing1 broke

Measured on gemini-3.6-flash11/6/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task一份关于数字经济发展的公文初稿，请全面修改其中的AI腔调，去掉“值得注意的是”、“翻案句”和新八股词汇，保持其他结构不变。

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-polish
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-polish")
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-polish

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 13 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-polish

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-polish")
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-polish/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-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/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-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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-polish")
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-polish/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-polish/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 13 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-polish

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 13 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-polish/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 11/6/2026
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

改稿润色（gongwen-polish）

在用户已有的稿子上做七种修改：压缩、扩写、调语气、转译、口语化或书面化、按领导批注改稿、多稿合并。只动表达和取舍，不加事实：改后稿的每个数字、案例、表态都能在原稿或用户材料里找到；缺的标【待补】，几稿说法不一的列出来由用户定。每次交付都附修改说明。

适用范围

适用：已有一稿（哪怕是大白话、流水账），要按下表改。

任务	用户常说
压缩	压到3000字、太长了砍一半、按减负规定压一压、讲话控制在15分钟
扩写	太单薄了扩一扩、写到2000字
调语气（新文种和受文对象已定）	报告改成发给下面的通知、领导定了请示改成函发、下发的改成向上汇报的口气
转译	科室写的大白话改成公文、业务说法改得像公文
口语化或书面化	讲话稿改得好讲一点、把领导讲话录音整理稿改成书面材料
按批注改稿	领导批了“太虚”“数据呢”、按批注改、领导在 Word 里批了意见
多稿合并	两稿合成一稿、甲乙两个版本取长补短

不适用（转交）：

用户要的	转给
通篇去 AI 腔：“值得注意的是”、翻案句、新八股词	gongwen-humanize
专门去免责声明、对冲、平衡腔；同一份下行文“像在商量”，改成要求口气	gongwen-direct
全面核稿，查格式、标点、数字、提法	gongwen-review
重拟标题、小标题	gongwen-title
只有素材、记录、数据表，还没有稿子	起草 skill：总结汇报 gongwen-report，法定公文 gongwen-draft，讲话 gongwen-speech，党建 gongwen-party
判断该用什么文种（“这个请示是不是该用函”），或文种用错、行文规则有问题要改	gongwen-draft 模式二
要推倒结构重写：换文种后结构全变（如报告改实施方案、拆任务分工）、提纲重搭	原起草 skill；以上级文件为依据拆任务的交 gongwen-implement；本行业专用文书交已装的对应行业包
长材料压成政务信息、简报、新闻稿	gongwen-brief
拿原稿和领导改过的稿子，总结领导的改稿习惯	gongwen-profile
排成 Word	gongwen-format

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/.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（如“建议再去 AI 腔”）。

一稿兼有几种问题时，本 skill 只做第一张表中的任务。免责声明、AI 自述、对话引导语按红线三直接删除；其他 AI 腔、对冲语气、格式错误不顺手改，列入修改说明的“转交事项”。用户同时要求“顺便去 AI 味”的，先完成本 skill 的任务，再转交 gongwen-humanize。

开工检查

保密（references/_shared/guardrails.md 第一条）：
- docx 文件必须先提取文本检查密级，再做任何其他处理：有 Python 时运行 python scripts/secret_check.py <文件>（含页眉页脚），命中即停；没有 Python 时用 zipfile 解压 docx，读取 word/document.xml 和所有 word/header*.xml、word/footer*.xml，搜索"秘密""机密""绝密""★""内部资料""工作秘密""不得外传""内部使用"等字样，发现任意一个即停止——只读 document.xml 不算完成，密级标志常在页眉里。用了 python-docx 等库读正文的，还必须用 zipfile 单独检查所有 header 文件（正文读取不含页眉）。纯文本稿件同样先扫一遍再改。
- 稿子出现敏感信号（个人敏感信息，”内部””不公开””暂不对外”等字样，未公开的人事任免或财务数据）时，才在起草说明末尾提示一句：”提示：涉密材料请勿输入联网 AI。”普通稿件不提示，同一会话只说一次。
- 带密级标识，或标注”内部资料””工作秘密””不得外传””内部使用”的，立即停止，不改写、不复述原文，告诉用户涉密信息不得输入联网 AI 工具，并说明可继续的三种情形：改用单位内网部署、允许处理此类材料的模型；已删除相关内容；标识系误加或材料已公开（guardrails 第一条第2款）。正文中正常出现”保密工作”之类的词不算。
- 有身份证号、手机号、病案号、住院号、学号、银行卡号、家庭住址、患者或学生真实姓名的，提醒用户脱敏；改稿写成”张某””138****0000”。这是本 skill 唯一允许改动的事实。”保密提示”按位置和信息类型列出，不复述原值。
留底：Agent 环境下，用户贴的文字原样存为工作目录下的 公文/<YYYYMMDD>-<简短标题>/原稿.txt（多稿存 原稿-甲.txt、原稿-乙.txt，批注存 批注.txt）。用户给的文件不改动：.docx 运行 python scripts/polish_stat.py body 原文件.docx --out <上述目录>/原稿.txt 转成文字稿（有修订痕迹的按接受全部修订导出，在说明中写明）；正文后混有批注转述的，分开存。
单位画像：读 .gongwen/单位画像.md（没有再找 ~/.gongwen/，用户粘贴的按粘贴内容），同目录的 领导偏好卡.md、禁用词.md、文风参数.md 一并读取；偏好卡里的篇幅、用词、数据呈现偏好优先于本 skill 的默认做法。没有画像时按 references/_shared/profiles/roles.md 第九节“无画像降级”处理，单位类型从稿件判断。
定任务：按”适用范围”第一张表识别。可叠加几项（如”按批注改，再压到2000字”），按”合并 → 批注 → 调语气、转译、口语化或书面化 → 压缩或扩写”的顺序做，篇幅最后定。 4a. 原稿矛盾扫描：读完原稿后查以下四类内部矛盾，在起草说明”原稿矛盾”行汇总，改稿时一并处理：（1）数字与条数不一致，如”四项任务”而正文有五条；（2）时间跨度与期限描述不一致，如”一年左右”而起止日期明确为8个月；（3）同一指标两处说法不一，如”基本完成”与”全面完成”并存；（4）同一职能存在两个并列机构或制度，如同时写”联席会议制度”和”领导小组”却未说明关系，不擅自合并或删去其一，起草说明标注待核实。其余三类正文按最合理的一致写法处理，修改说明写明怎么处理的，请用户确认。
定角色模式：按 roles.md 第一节的顺序；本 skill 中的差异见“角色适配”。党建、组织、纪检材料和对外发布的材料叠加严谨模式。
提问：最多 3 个，只问下表缺项，放回复末尾，不阻塞改稿：首轮按下表默认值改出全文并写进“所作假设”，用户答复后在已交付稿上改（references/_shared/profiles/roles.md 第十节）。“直接改”或高效模式不问，待补、待核实只进起草说明。调语气缺发文主体、受文对象或文种又推断不出的，属核心事实缺失（第十节情形②）：首轮只出措辞对照建议，开头说明缺哪一项，末尾问清，不改全文。

任务	只问	不回答时的默认
压缩、扩写	目标字数或讲话时长	压缩：说"按减负规定""减负""按规定压"的，目标取原稿三分之二；给了具体数（"压到N字""砍一半"）的，以用户指定为准；说"该删的删""帮我精简""能删多少删多少""删掉空话套话"不给字数的，同样取三分之二；只说"太长了"的，取七成；扩写：不定目标，展开到素材用完为止
调语气	新的发文主体、受文对象和文种	不猜；只出措辞对照建议，不改全文；要判断用什么文种的，建议重新起草
按批注改稿	批注原话和对应位置	位置看不出的那条列为“未落实，请确认位置”
多稿合并	以哪一稿为底稿	最新的一稿；分不出新旧的，用结构最完整的一稿

守住两条底线（references/_shared/guardrails.md 第六条）：要求“改得查不出是 AI 写的”，或把正式文件改成便笺、“白头”规避发文管理的，说明原因，不按此办，其余照常改；对照检查、述职、心得体会、研讨发言、交流发言、谈心谈话记录要扩写而缺本人事例的，只在相应位置标【待补：本人具体事例】，不代拟，起草说明中给出填写指引（写本岗位做过的哪件事、学习后工作有什么改变）。党建个人材料素材不足、需先出提纲的，转 gongwen-party。
交接卡：网页环境用户贴了交接卡的，按卡上的单位画像、模式、任务、本站和已确认事项开工，卡上有的不再问（references/_shared/style/output-format.md 第四部分）。

工作流程

第一步　读稿，冻结事实

读到单独一行的【起草说明】为止。原稿起草说明中的待补、待核实事项继承下来。
判定文书类型（统一词表：总结、汇报材料、讲话稿、通知、报告、请示、函……）、行文方向、单位类型、当前字数。有 Python 时运行 python scripts/polish_stat.py count 原稿.txt；没有时按段估算，说明中写“字数为估算”。
列事实清单（供自己对照，不必输出）：
- 数字、日期、金额、百分数、发文字号、书名号和引号内的内容；
- 人名、职务、单位名、责任分工、完成时限；
- 状态和强度：已、正在、拟、将；必须、应当、要、可以、力争；
- 政治性提法、上级文件原文、领导原话（指稿中引用的上级领导讲话和他人原话，不含本次要口语化、书面化的讲话人本人的讲话）；
- 【待补】【待核实】标记。
改稿全程对照清单：清单内容只能原样保留，或在下列四种情形整句删去：压缩；合并（去重）；按删减类批注删去批注所指内容；调语气时删去新方向不适用的事项（如向上请求的事项）。删去的都写进“附：删去的数据”并写明理由。不能改值、不能升级状态、不能换说法。政治性提法、领导原话和含“要”“必须”“应当”等强度词的句子，只整句保留或整句删去，不做句内删改；其他句子可句内压缩（压缩第 4 条），清单项不动，改动列入说明。例外只有四种，都写进修改说明：
1. 脱敏替换；
2. 调语气时按 references/tone.md 对照表调整称谓和要求措辞；
3. 批注明确要求调语气强度的（如“语气太软”），按 references/_shared/style/defensive.md 第六部分调整“必须、要、可以”，写进批注落实对照表；
4. 讲话人本人的讲话稿、录音整理稿口语化或书面化时，可以改表达，观点、表态、要求和数据不变；提法句不改写（见口语化第 1 条）。
局部修改（按批注改、调语气）时，范围以外的原文逐字保留。
标题中的“（初稿）”“（征求意见稿）”等草稿标记，交付稿去掉，用户要求保留的除外。原稿内部矛盾（数字、时间、条数不一致）是第 4 条的例外，按开工检查 4a 处理。

第二步　按任务改

细则见参考资料，这里是每项必做的动作。Agent 环境改完先把正文写入原稿同目录的 正文.txt（已存在时加 -v2，此后各步都用这份），复核中的修改直接改这份文件。

压缩（细则 references/length.md 第一至五部分）

定目标：用户给的 > 偏好卡、画像 > 默认值（见开工检查第 6 条表）。讲话按时长乘每分钟约 200 字（画像另有语速的按画像）。“以内”“不超过”为上限口径，超 1 字也不行；改后低于上限七成的，复查是否删了必保内容，不为凑够七成加字。其余以目标±10%为准。
算账：删减量＝当前字数－目标。有 Python 时运行 python scripts/polish_stat.py count 原稿.txt --target 3000（上限口径加 --max），看各部分占比。改完对 正文.txt 再运行一次验证；超出目标 10% 以上的继续按第 3 条顺序删减；没有 Python 时人工逐段估算，写"约 N 字（估算）"，同样须达到目标 ±10% 再交付。
按铺垫 → 复述 → 空泛表态 → 重复举例的顺序删（各级认定见 references/length.md 第三部分），删完一级算一次字数，够了就停。空泛表态中，以下排比口号优先删除，不计入必保内容：无对象和数字支撑的"打好组合拳""形成大合唱""上下联动左右协同""齐抓共管""合力推进""形成合力""汇聚合力""凝聚共识"等；"全方位多维度""多举措多渠道""更加扎实""持续走深走实""抓铁有声踏石留印""驰而不息""久久为功"等力度修饰套话；不与具体事项绑定的"赋能""抓手""闭环""新生态""新机制""构建大格局"等空泛新八股词。
还不够，再做句内压缩：合并同类项、删修饰语、长句改短句（references/length.md 第四部分）；第一步第 4 条所列句子除外。
必保内容：事实和数据、措施、责任主体、时限、需要上级支持的事项、【待补】【待核实】。删到只剩必保内容仍超目标的，停止删减，照常交付：回复第一段说明现在多少字、超出多少，末尾请用户选：放宽目标；指定可删的部分；把某部分转为附件。不为达标删事实，不把估算字数说成已达标。

扩写（细则 references/length.md 第六部分）

只展开已有事实：把一句话的做法按材料展开成步骤；补上材料里有、原稿没写的时间、主体、数据和事项。
不加形势背景、重要意义、表态，不编案例、数据、成效，不从结果倒推过程（没有调研记录，不写“经过深入调研”）。
篇幅（references/_shared/guardrails.md 第四条第2款）：改前估算素材能支撑多少字。差距超过 30% 的，在回复第一段说明目标字数和素材可支撑的字数，附补料清单（补哪几样材料就能写足）；应有的板块保留，缺内容处最关键的标【待补：该补什么】（一般不超过 3 处），其余写进补料清单；只按“做法—过程—结果”展开已有事实，不注水，【待补】不计入字数。

调语气（行文方向互转）（对照表 references/tone.md 第一、二部分）

先定关系：新的发文主体、受文对象和文种由用户定。按 references/_shared/rules/doc-types.md 第六节决策表核对方向和文种是否匹配；不匹配的，说明并建议先重新判断文种，不自行改定。
改五处：称谓、开头语、请求或要求的措辞、期望语、结语；标题文种随之改。内容和事实不变。
新方向必需而原稿没有的要素标【待补】：改下行文缺完成时限、联系方式（责任单位按受文对象写“各××”；原稿已有报送安排的才写报送方式）；改请示缺请示事项、倾向性意见。不新拟任务和报送要求。
新方向不适用的事项整句删去：上行文中向上请求的事项在下行文中没有承受方，不改写成对下级的任务；删去的写进修改说明，建议另行请示。
分清谁来做：原稿中由下级执行的事项（“我局将督促各卫生院于……前完成”）改成对下级的要求（“各卫生院要于……前完成”）；本机关自己做的保留主体（“县卫生健康局将会同……开展督查”），不转给下级。
部门以自己名义面向下级党委、政府的（如县直部门发各乡镇人民政府），不写“必须”“务必”“要”之类的指令性要求（references/_shared/rules/jianfu.md JF-16），改用“请各乡镇……”的商洽口吻，或建议由县政府办公室行文，修改说明写明依据。
换文种后结构要整体重搭的（报告改实施方案、拆任务分工），只改语气，并建议重新起草。

转译（业务语言改公文语言）（词表 references/tone.md 第三部分）

逐句改：口语词换公文词；一句话写一件事；主语换成单位（我科、我院、公司）；按原稿顺序加层次序号，不调整结构。不得带宏大开头、空泛总括和段尾拔高。
业务术语、指标名称照用；首次出现的缩写能确定的写全称，拿不准的保留缩写并在“待核实”请用户核实。
不拔高：“还行”不改成“成效显著”，“差不多完成”不改成“全面完成”；带“大概”“差不多”“好像”的数字，正文写原数、约数保持约数，起草说明“待核实”请用户核实。
修改说明按“业务原话→公文表述”列典型几处。
- 例：“大概多了两百台”写“较上年增加约200台”，不写“同比增长显著”；需全年总量而原话没有的，写“全年完成手术【待补：全年手术台数】台”。

口语化或书面化（references/tone.md 第四部分）

讲话稿口语化：长句拆短，一句一般不超过 30 字；长定语拆开；加称谓和过渡语，前后呼应；精确数据保留，书面括注、顿号长串改成说得出口的句子。不加金句，不加引文。听众难懂的办学、政策提法（如“立德树人”）不改写成大白话：整句删去并写入说明，或整句保留、前后加过渡。
书面化（讲话录音整理稿、发言改成材料）：删口头禅、现场称呼、重复，补全句子，口语词换书面词，加层次序号。
讲话稿改完按每分钟约 200 字核算时长，写进说明。

按领导批注改稿（对照表 references/annotations.md）

收齐批注：原话和位置（references/annotations.md 第一部分）。Agent 环境下 docx 运行 python scripts/polish_stat.py comments 批注稿.docx 提取；有修订痕迹的，按开工检查第 2 条导出 原稿.txt（按改后的算），不接受某处修订的请用户先在 Word 中处理。读不出批注的，请用户逐条转述“位置｜原文片段｜批注原话”。
逐条按 references/annotations.md 第二部分对照表改；一条批注两个意思的（“太虚，数据呢”）拆成两项。
补事实类先在原稿和用户材料里找；找不到的标【待补：说明】，对照表状态写“待补材料”，说明里请用户提供。台账里与批注事项对应的问题可并入落实（措施写成“针对××问题”），对照表注明来源；措施动作、责任人、时限没有的标【待补】不自拟。
批注与红线冲突的（如“写成全市第一”而材料没有依据），按红线处理，在对照表中写明原因，请用户提供依据。
批注以外不顺手改；其他问题写进修改说明“批注以外的建议”。
出“批注落实对照表”，列为：序号｜位置｜批注原话｜落实方式｜状态（已落实、部分落实、待补材料、未落实请确认）。
偏好卡：从本轮批注归纳一至三条可能的偏好，写成“历次改稿记录”的一行，标“观察中”，按 references/annotations.md 第四部分处理（Agent 环境征得同意后追加到 .gongwen/领导偏好卡.md，网页环境交用户保存）。

多稿合并（references/merge.md）

编号定底稿：甲稿、乙稿……写明各稿来源；底稿按开工检查第 6 条表确定，结构以底稿为准。领导改过的稿子与原稿合并的，以领导稿为底稿，措辞以领导稿为准；原稿有、领导稿没有的数据和事项补回，注明“领导稿未保留，已补回，请确认”；领导稿删去的评价和表态不补回。
按部分对齐，同一事项取事实更全、表述更准的说法；两稿各有的事实都保留，去重。
冲突不替用户选，不平均、不相加：数字、口径、时限、措施不一致的，正文写底稿说法；状态、结论不一致的（如“基本完成”与“全面完成”），正文一律写较保守的说法。正文不标记，不把两种说法揉成第三种，两稿说法整理进“合并冲突清单”（序号｜位置｜各稿说法｜本稿处理｜请谁确认）；提法不一致的都不改，清单请用户对照最新原文。
出“合并说明”：部分｜采用｜理由；舍弃的句子也写理由。Agent 环境运行 python scripts/polish_stat.py trace 正文.txt 原稿-甲.txt 原稿-乙.txt，“未找到来源”的句子和小句逐条核对，属新增事实的删去或改为【待补】。

第三步　复核

事实比对（必做）：
- 有 Python 时运行 python scripts/fact_diff.py 原稿.txt 正文.txt --json（合并多稿时第一份写底稿，其余各稿用 --ref 原稿-乙.txt 追加，几稿加几个）。“改稿新增”每一项都必须是新增的【待补】或脱敏替换，否则恢复原稿写法。“原稿有而改稿没有”只允许第一步第 4 条的四种删除情形，逐项确认删的不是成效数据、责任、时限、需上级支持的事项（调语气删去的上行请求除外），并写进“附：删去的数据”；其他一律恢复。
- 用了补充材料的，另运行 python scripts/fact_diff.py 原稿.txt 正文.txt --ref 材料.txt --ledger（几份材料加几个 --ref），输出每一项同样只能是新增标记或脱敏替换。
- fact_diff 不比对人名、单位名、分工、时限和义务强度，对照第一步清单人工核一遍。
改动范围：运行 python scripts/polish_stat.py compare 原稿.txt 正文.txt。每处改动都对应本次任务（按批注改稿时对应某条批注），对应不上的恢复原文；“新增”段落和“多出的文字”只能是措辞调整、新增标记或脱敏替换，带新数字、荣誉、评价、排名的删去或改为【待补】。另运行 python scripts/change_guard.py 原稿.txt 正文.txt --json（要求结构不动的加 --keep-structure；合并多稿时只对底稿运行）：CHG-001（P0 事实变化）逐条恢复或在修改说明写明理由；CHG-004（结构变化）在结构不动时必须恢复；CHG-003（无规则依据的改动）按需列入说明供核对。
篇幅：上限口径运行 python scripts/polish_stat.py count 正文.txt --target <目标> --max，确认没超上限；其余去掉 --max，确认在±10% 以内（脚本判断下限时已扣除【待补】）。超出或不足的，继续改，或按压缩第 5 条、扩写第 3 条在回复第一段说明。
机检：python scripts/gongwen_lint.py 正文.txt --doc-type <文书类型> --json。本次改动带进来的问题必须改掉；原稿就有、不在本次任务内的（如发文字号格式）列入“转交事项”，建议再核稿。命中公文白名单的保留（references/_shared/style/ai-tone.md 第二部分）。疑似误报的（如“四、四季度安排”被报序号乱序），不改原标题，说明中写明位置和判断。
没有 Python 或脚本出错的，按 references/checklist.md 逐项人工核对（读不到时按本节和自检清单）：字数逐段估算（标题和【起草说明】之后不算），写“约N字（估算）”，上限口径按九成五控制；数字、日期、文号、书名号和引号内的内容、状态词、义务强度词逐项对照原稿和材料。在说明中写“未运行机检和事实比对，已人工逐段核对”。

第四步　交付

Agent 环境：正文已写入只含正文的 正文.txt 并在复核中改定，不另存起草说明。回复开头直接贴改后全文（篇幅差距说明、补料清单除外），其后写文件位置和起草说明，不写过程说明。
网页环境：依次输出改后正文、单独一行【起草说明】、说明内容。正文前只放篇幅差距说明（references/_shared/style/output-format.md 第三部分），不加引导语。路线还有下一站的，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，再粘贴交接卡和改后正文。
审稿模式只给修改建议时，按“角色适配”输出建议清单，不输出正文。

输出规范

正文、起草说明、交付位置按 references/_shared/style/output-format.md：正文纯文本，不用 Markdown，层次序数依次为一、（一）1.（1），正文只允许【待补：说明】一种提示。起草说明只在对话中，放在正文之后，不超过 5 行、每行一句，不写工具名和规则号，无内容的省略：

假设：任务、目标字数、底稿、单位类型。待补：一行汇总，写位置和要补什么。待核实：一行汇总。修改说明：一行，写“原稿约 N 字，改后约 M 字，共修改 K 处”，加改了什么、为什么改、事实核对结果，有转交事项的写要点。保密提示：有脱敏时写一行，按位置和信息类型列出，不复述原值。

教学模式另附写作要点。附表放在起草说明之后，标题为“附：删去的数据”（有删除时，逐项写理由）“附：批注落实对照表”“附：合并说明”“附：合并冲突清单”“附：领导偏好卡改稿记录（待保存）”“附：提法核对清单”；逐条的修改说明（教学、转译模式）也作附表，可用表格。

自检清单

有 Python 时运行第三步的 gongwen_lint、fact_diff、change_guard、compare、count；无法运行按第三步第 5 条人工核对。

角色适配

教学模式：首轮直接改出全文，不先交修改计划；修改思路（删哪几处、加哪几处、改哪五处措辞）写进写作要点；修改说明逐条列“原文｜改后｜理由”三栏，理由落到删减顺序、措辞对照表或规则条款；写作要点另写本稿最该学的三处。
高效模式：不提问直接改（调语气缺受文对象或文种的照问）；修改说明不展开，一行写改动类型，涉及规则的写依据条款；“删去的数据”逐项列入附表；可同时给两个篇幅（如3000字版和1500字版）；可一次处理多份稿件，逐份输出；回复末尾不另设“需要你确认”的问句。
转译模式：只问业务口径（统计时段、计量单位、指标名称）；术语、指标、口径一字不动；修改说明按“业务原话→公文表述”对照，理由用业务人员听得懂的话写。
审稿模式：用户只要意见、没让动稿子的（“先别动稿子”“看看哪些能删”），给一页纸：主要问题三至五条（每条一句话加依据）、建议删改的段落和预计改后字数（只给一个推荐值）、需要补的材料、转交事项（AI 腔的类型和位置，即使在拟删文字内也列出，建议再去 AI 腔）；不提问，需背景的标“待确认”；用户点名要改（如“压到3000字”）或说“那你改一版”的，首轮按高效模式出改后稿。
严谨模式：政治性提法、上级文件原文、领导原话一律不改写、不截断，压缩时只能整句保留或整句删去并在说明中列出；附提法核对清单（提法｜位置｜出处｜是否改动）。原稿已有提法不在正文逐处标记，出处栏写“未提供原文，请对照最新原文”；新增引用处也只在清单中标出。

单位差异

单位类型	改稿时特别注意
党政机关	下行文件压缩按减负规定上限，超限为 P1；提法最密，改前先圈出
基层	面向群众的稿子转大白话时写清时间、地点、要求、咨询电话；不向村（社区）转嫁责任
社区	对居民用服务和提醒的口气，不用命令口吻；居民信息一律脱敏
公立医院	指标名称照用原稿，不改成通俗说法；缩写首次写全称；患者信息脱敏
高校	校级与学院两级发文语气不同；学术材料保留学术用语；学生信息脱敏
中小学	致家长的稿子通俗、具体，写清需要家长配合的事
国有企业	经营数据、专业术语照用；商业秘密提醒脱敏；党委前置研究等程序表述不删

表中要“写清”的要素，原稿和材料没有的标【待补】，不自拟。医院、学校、国企内部材料不受减负规定字数条款直接约束，超限只作提示。详见 references/units.md。

参考资料

没有文件系统（网页版、内网提示词版）时，读不到的文件按本文和附录执行，不向用户索要。

文件	何时读取
`references/length.md`、`tone.md`、`annotations.md`、`merge.md`	第二步各任务（见各任务标题后的括注）
`references/checklist.md`、`references/units.md`	无法运行脚本时；定单位类型后
`references/_shared/guardrails.md`、`style/output-format.md`	开工前、与用户要求冲突时；交付、交接卡
`references/_shared/style/ai-tone.md`、`references/_shared/style/defensive.md`	判断哪些归 humanize、direct；调语气强度
`references/_shared/rules/` 下的 jianfu.md、doc-types.md、gbt15835.md、data-expression.md	定压缩目标、查 JF-16；核对文种和惯用语；数字写法、百分点
`references/_shared/profiles/roles.md`、`references/_shared/profiles/units/`	定角色模式和单位类型
`scripts/polish_stat.py`	count、compare、trace、comments、body
`scripts/fact_diff.py`、`scripts/change_guard.py`、`scripts/gongwen_lint.py`	第三步复核

About this skill

Automatic

Writing & Editing pack

SkillSafety

✓ 3 of 3 passed

Code scan14 of 15 checks clean

0 critical · 0 warning · 2 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

No issues (informational notes only).

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

duyunzhoudyz / gongwen-skills

skills/gongwen-polish/SKILL.md

View on GitHub ↗

License PolyForm-Noncommercial-1.0.0Imported 11/2/2026Version v1Bundled 13 files · scripts

Illustrative Want to see what duyunzhoudyz/gongwen-polish 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

改稿润色（gongwen-polish）

适用范围

开工检查

工作流程

第一步 读稿，冻结事实

第二步 按任务改

第三步 复核

第四步 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　读稿，冻结事实

第二步　按任务改

第三步　复核

第四步　交付