Ready to supercharge your AI agents?

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

去防御性写作（gongwen-direct） · duyunzhoudyz | DecimalAI

Documentationby duyunzhoudyz

去防御性写作（gongwen-direct）

去掉公文稿里的防御性写作：删免责声明和套话提醒，清理“可能”“在一定程度上”等对冲语气和平衡腔，把部署性文件里的“建议”“可以考虑”改成分层的要求措辞，点明模糊主体，让请示有倾向性意见、批复明确表态、把报告里夹带的请示事项拿出来，风险提示保留。用户说“去掉仅供参考”“这通知像在跟下级商量，改成要求口气”“说话太软不硬气”“批复模棱两可”“请示没写倾向性意见”“把对冲语气去掉”时使用。AI 句式交 gongwen-humanize；全面核稿和格式、标点、数字交 gongwen-review；压缩、扩写交 gongwen-polish；从零起草交对应起草 skill，行业专用文书交对应行业包。

Maintained

SkillScore

SkillScore68/100

Test results 68

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

23%68%of test cases passed +45 pts

Without skill5 of 22

With skill15 of 22

10 fixed5 passed either way7 still failing0 broke

Measured on gemini-3.8-flash11/3/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task请去除以下通知中的防御腔，并输出符合规范的公文文本： **关于开展节水行动的通知** *各科室*： - 建议各部门可以考虑关紧水龙头。 - 以上措施仅供参考。

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-direct
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-direct")
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-direct

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 8 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-direct

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-direct")
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-direct/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-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/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-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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-direct")
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-direct/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-direct/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 8 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-direct

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 8 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-direct/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 8 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

去防御性写作（gongwen-direct）

AI 写的公文常给自己留后路：结尾挂“仅供参考”，部署写成“建议各单位可以考虑”，请示不说倾向，批复不说同意还是不同意。本 skill 把这些话改成态度明确、措辞分层的公文表述，同时守住两条底线：必要的谨慎不删，用户没定的事不替用户定。

两种角色

行为规则：共享规则 references/_shared/style/defensive.md 已同步进本项目所有 skill，各 skill 起草时自行遵守，不需要调用本 skill。改稿时以它为准则。
独立改稿：用户拿来已有稿件（多为 AI 生成）要求去掉防御腔时，按本文件流程处理，操作细节查改写指南 references/rewrite-guide.md。

适用范围

适用：对已有稿件清理七类问题：免责声明和套话提醒、对冲语气、平衡腔、部署性文件里的建议式措辞、模糊主体、空泛表态、AI 式过度提问和元话术。请示补齐态度要素、批复明确表态、报告剥离请示事项，也归本 skill。
不适用：
- “值得注意的是”“不是……而是……”、破折号过密、赋能闭环等新八股词、译文腔：转 gongwen-humanize。
- 格式、标点、数字错误，提法风险，送签前的全面核稿：转 gongwen-review。
- 按目标字数压缩或扩写、改换行文方向（如把报告改成下发的通知）：转 gongwen-polish。
- 没有原稿、要从零写：法定公文转 gongwen-draft，讲话稿转 gongwen-speech，总结、汇报、方案转 gongwen-report，其他按文种转对应起草 skill；装有行业包时，本行业专用文书交对应行业包。
- 排成 Word：转 gongwen-format。
转交：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 第四部分给出交接卡、“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。
一篇稿子既有 AI 腔又有防御腔：本 skill 只改防御腔，在起草说明里写明 AI 腔的位置和处数，建议再去 AI 腔。两个 skill 都不动事实，先后顺序不限。

开工检查

保密：按红线文件 references/_shared/guardrails.md 第一条执行，具体做法见第一步。
- 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（没有则查 ~/.gongwen/单位画像.md），取单位类型和默认模式；都不存在时按“无画像降级”处理（references/_shared/profiles/roles.md 第九节）。.gongwen/禁用词.md 存在时一并读取。
角色模式：按 references/_shared/profiles/roles.md 第一节确定，差异见本文件“角色适配”。
原稿：本 skill 只改用户给的稿子。用户只有需求没有稿子的，转对应起草 skill（见“适用范围”），不在这里写。
首轮交付和提问：原稿在手就首轮交改后稿，拿不准的按默认处理，写进起草说明“所作假设”；提问不超过 3 个，放在回复末尾，用户答复后在已交付的稿子上改（roles.md 第十节）。只有原稿涉密、审稿模式只列问题时不出改后稿。用户说“直接改”“不用问了”的，不再提问。用户贴了交接卡的（网页和 Agent 环境都一样），按卡上的画像、模式、任务和已确认事项开工，卡上已有的不再问（references/_shared/style/output-format.md 第四部分）。
辅助不代笔（红线第六条）：只改措辞，表态、承诺、方案选择留给用户；不以“规避 AI 检测”为改稿目标；用户要求把正式文件改成“温馨提示”、便笺等以规避发文管理的，说明不能协助。

工作流程

第一步　保密检查

稿件出现敏感信号（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。”普通工作稿件不提示，同一会话只说一次。
通读原稿。带有密级标识（“秘密★”“机密★”“绝密★”，或版头标注的密级和保密期限），或标注了“内部资料”“工作秘密”“不得外传”“内部使用”等字样的，立即停止（正文中正常出现“保密工作”“涉密人员管理”之类的词语不算）：不改稿，不复述原稿内容，告诉用户涉密信息不得输入联网 AI 工具，建议改用内网模型，或删除涉密内容后再发。
出现身份证号、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；改后正文一律换成“张某”“138****0000”等写法，起草说明保密提示一行列出替换位置。
有 Python 时，可加跑 --checks privacy 辅助扫描，以人工判断为准。

第二步　确定文书类型和行文对象

按文种确定性要求 references/certainty-by-doctype.md 第八部分判断文书类型，名称用统一词表：决定、通告、意见、通知、通报、报告、请示、批复、函、纪要、签报、总结、计划、工作要点、汇报材料、调研报告、经验材料、述职报告、实施方案、讲话稿、信息、其他。
同时确定对象：隶属下级、不相隶属单位、上级、群众。对象决定“建议”改成“要”还是“请”。
判断不出的，先按“其他”处理改稿，写进起草说明“所作假设”；在回复末尾与其他问题合并问一次，用户说“直接改”的不问。

第三步　诊断

有 Python 时：

原稿是粘贴文本的，先存为 公文/<YYYYMMDD>-<简短标题>/原稿.txt（同名已存在时加 -v2，不覆盖）。用户给的是文件（包括上一站产出的 正文.txt）时，直接以该文件为原稿，不另存、不改动它。
运行：python scripts/gongwen_lint.py <原稿文件> --doc-type <文书类型> --checks defensive,residue --json
不传 --doc-type 时，引擎按标题推断，推断不出按“其他”；为避免误判（如请示、报告里正当的“建议”被 DEF-015、DEF-021 误报），调用时一律传 --doc-type。
读 JSON 的 issues：P0 必改；P1 按改写指南 references/rewrite-guide.md 对应部分判断后改；P2 逐条人工判断。命中“哪些不删”（rewrite-guide 第九部分）的不改，记入“保留项”。
输出中 char_count 为 0，或提示“尚在开发”“未执行检查”的，视为机检没有运行。

没有 Python 或机检没有运行时：按改写指南第十一部分速查表逐类检索，起草说明写“未运行机检，按速查表人工诊断”。机检跑过的，也要按速查表中标“人工”的几行补查，如“本方案仅供参考”“仅供领导参考”“不够全面”，这类变体说法规则不一定覆盖。

无论是否机检，再按文种确定性要求 references/certainty-by-doctype.md 核对文种要素：请示有没有请求事项、倾向性意见、规范结语；批复有没有表态；报告有没有夹带请示；部署事项有没有责任主体和时限。

第四步　分类改写

总规则：

只动措辞。数字、日期、金额、人名、单位名、文号、书名号和引号内的文字、政治性提法、上级文件原文一律不动。原稿只写星期几、“下周”“月底”的，照原话保留，不推算具体日期。
删多于加。改后正文字数不超过原稿（新增的【待补】除外），不新增段落、措施、罚则。用户另给了字数或时长目标的，不为凑字数扩写，也不为达标删事实；改后与目标差距超过 30% 的（【待补】不计入字数），在回复第一段说明，篇幅调整转 gongwen-polish（references/_shared/guardrails.md 第四条第2款）。
不替用户拿主意。倾向性意见、同意与否、是否对外承诺、是否允许例外，原稿没有的标【待补】。
不把不确定说成确定。删对冲词前先看有没有事实支撑：有的直接陈述；没有的，缺统计数据处标【待补】，其余保留原稿的限定写法，原说法和核实事项写进起草说明“待核实”一行。
先查保留清单再动手。
原稿已有的强制措施和罚则不删不改。例如“一律移交公安机关予以拘留”：有没有法律依据、发文机关有没有权限，不归本 skill 判断。列入起草说明的转交事项，写明位置和原文，建议再核稿，按法规关核查法律依据和发文权限。
例句和条款不照搬。改写指南和文种要求里的例句（含其中的数字、日期、单位名、文号）只示意改法，不得带入用户稿件；起草说明里引用的条款，只用本 skill 资料已列出的，查不到条号的只写规则名，不凭记忆写条款号。

类别	默认改法	不改的情形
免责声明、套话提醒	整句删；声明“数据均为示例”的，对应数字换成【待补】	汇报结尾“不妥之处，请批评指正”；征求意见复函“以上意见供参考”
对冲语气	有事实的直接陈述；预期成效改“力争”；没依据的缺数据处标【待补】，其余保留原写法并在起草说明“待核实”一行说明；叠用的只留一个	风险提示、安全提示；问题查摆“一定程度上存在”；调查中、初步统计等真实不确定
平衡腔	请示写倾向，缺则【待补】；部署文件删去权衡句，直接提要求	“既要……又要……”分述两项要求；纪要如实记录讨论；调研报告的利弊分析
建议式部署	对隶属下级改“要”，可选动作改“可”；对不相隶属单位、下级政府、群众改“请”	请示、报告、签报、函、调研报告里的“建议”；有例外的“原则上”
模糊主体	原稿或材料点了名的换成具体单位；分派任务找不到主体的标【待补：责任单位】	主送“各有关单位”；泛指的“会同有关部门”
空泛表态	批复、答复态度不明的标【待补：同意/不同意】；“适时”“择机”顶替时限的标【待补：完成时限】	单独的“高度重视”；套话堆砌转 gongwen-humanize
过度提问、元话术	正文首尾的引导语、征询、客套整句删；正文中向读者发问的改成要求	讲话稿中的设问

各文种的确定性要求如下，完整版在文种确定性要求 references/certainty-by-doctype.md 中：

请示：请求事项具体，有本单位倾向性意见，结尾“妥否，请批示”或“当否，请批示”。缺倾向性意见的写【待补：本单位倾向性意见】，不替用户编。
批复：明确同意或不同意。态度不明的写【待补：同意/不同意】。
通知、意见、决定等部署性文件：按“必须、应当、要、可以”分层，不用“建议”“可以考虑”。“必须”“严禁”不因改稿新增。“原则上”在确有例外时是正当用法，保留。
报告：只陈述事实。夹带的请求语句连同金额移入起草说明，结语改“特此报告。”，建议另行请示（可继续让我起草请示）。
讲话稿：语气可以更有力；用户没确认的承诺只改到“力争”，起草说明列出请用户确认。

单位差异见 references/unit-adjust.md（网页版见“单位差异”一节），改“建议”前先看对象是不是群众、是不是不相隶属单位。

改过头同样是错：把“要”全换成“必须”，删了“可能”把预测写成承诺，添加原稿没有的罚则，替用户选方案，删掉风险提示（rewrite-guide 第十部分）。

第五步　事实核对

有 Python 时：

改后正文存为同目录 正文.txt（同名已存在时加 -v2、-v3，不覆盖原稿），运行：python scripts/fact_diff.py <原稿文件> <改后正文文件> --json
“原稿有而改稿没有”：每一项都要在起草说明里有去向（移入起草说明、示例数据换成待补、脱敏替换）。删掉的套话句里重复出现的数量（如“三种模式各有优劣”中的“三种”），只要正文其他位置仍保留该事实，在修改说明注明即可。说不清去向的，恢复原文。
“改稿新增”：只允许是新增的【待补】。其他新增的数字、日期、单位名一律删掉。
对改后正文再跑一遍第三步的机检命令：P0 清零；剩下的 P1、P2 要么改掉，要么在修改说明写明保留理由。复检只计 defensive、residue 两类；若另跑全量机检，AI 类（AI-xxx）命中属转交事项，不要求清零。

没有 Python，或脚本输出“尚在开发”时，人工核对：把原稿中的数字、日期、金额、百分数、文号、人名、单位名、书名号和引号内容逐项列出，在改稿中逐项对照；起草说明写“未运行事实比对脚本，已人工核对”。

事实比对只能证明改稿没有改动原稿，证明不了原稿本身属实。原稿由 AI 生成、用户又没说明数据来源的，在起草说明“待核实”一行提示一次：“原稿中的数字、案例、文件名称请对照原始材料确认，本次改稿未核实其真伪。”

第六步　输出

按“输出规范”交付改后正文和起草说明。审稿模式例外，见“角色适配”。

输出规范

遵守输出格式规范 references/_shared/style/output-format.md：

先给改后正文：纯文本公文体，不用 Markdown，正文前不加“以下是……”。原稿带 Markdown 符号的，去掉符号，内容不动。
正文后单独一行写【起草说明】，只在对话中，不超过 5 行、每行一句，不写工具名和规则号，没有内容的省略：
- 假设：文书类型、行文对象、单位类型的推断依据。
- 待补：一行汇总，写位置和要补的内容，例如“第二段：本单位倾向新建还是改扩建，及理由”。
- 待核实：一行汇总，写位置、原稿说法、建议对照的材料。
- 修改说明：一行，按七类汇总改了几处、典型改法（教学、高效、转译模式见“角色适配”）。
- 保密提示：有脱敏替换时写。教学模式另附写作要点，逐条的修改说明（原文、改后、理由）作附表。“保留项”（没删的谨慎表述及理由）、“移出项”（从正文移出的请求事项、示例数据原文）、“需确认”（自选动作、原则上、讲话承诺）、“转交事项”（发现的 AI 句式、格式标点问题，以及原稿已有的强制措施和罚则，只列不改，建议再去 AI 腔、再核稿）有则作附表，放在起草说明之后。
Agent 工具环境（网页对话环境不运行脚本、不写文件，按人工核对，起草说明注明“未运行机检”）：在 公文/<YYYYMMDD>-<简短标题>/ 下写 原稿.txt（用户粘贴时）、只含正文的 正文.txt，同名文件已存在时加 -v2、-v3，不覆盖。对话开头直接贴改后全文，其后写文件位置并给出起草说明，不写过程说明。
网页对话环境：依次输出正文、【起草说明】、说明内容。
交接卡：用户贴了交接卡、路线还有下一站的（如 gongwen-humanize），网页和 Agent 环境都在起草说明之后输出更新后的交接卡，本站改为下一站，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。
审稿模式只列问题、不改稿时，Agent 工具环境把一页纸摘要和问题清单写入同目录 文风问题清单.md。

自检清单

复检命令同第三步（对 正文.txt 运行）；不能运行时按速查表人工检查，起草说明写明“未运行机检”。

角色适配

教学模式：首轮就交改后稿，不先讲课。修改说明逐条列“原文、改后、理由”三栏，理由写到类别和依据，如“部署性文件对下级用‘建议’，要求不明确”；保留项也讲清为什么留。起草说明末尾“写作要点”写 2～3 条这类文书的确定性要求，如请示为什么要有倾向性意见（《党政机关公文处理工作条例》第十五条）。
高效模式：直接给改后全文；修改说明压成一行，按类别计数，如“‘建议’改‘要’7 处”，不展开讲解；待补、待核实、需确认事项照列，不省略。多篇稿件逐篇处理、逐篇输出。
转译模式：稿子多出自业务人员或按业务人员口述生成。诊断、工程安全、数据口径等专业判断中的谨慎原样保留，不替业务人员把专业结论说死。判断顺序：先看有无数据或事实支撑，有则删对冲词直述；属专业结论且业务人员未确认的，只留一个限定词，在“需确认”里提问，不写死；修改说明按“原话、公文表述”对照，少用术语；需要补的只问业务事实，如“自查截止是哪天”“这项由哪个科室牵头”。
审稿模式：不重写全文。先给一页纸摘要（防御腔总体情况、最影响效力的 3～5 处），再给分级问题清单，每条写位置、原文、类别、建议改法、依据，P0 在前。用户说“改一版”时，按高效模式出改后稿。
严谨模式：政治性提法、上级文件原文和引语中的限定词（“原则上”“一般”“逐步”）一律不动；对外发布、报上级党组织的材料，“预计”“初步”不改成定论，承诺从严；引文未注明出处的，起草说明“待核实”一行请用户对照原文出处；改动触及提法的，在起草说明逐条标出，请用户确认。

单位差异

单位类型	去防御时的调整
党政机关	部门对下级人民政府不提指令性要求，“建议”改“请”；上级原文中的限定词不动
基层	给村（社区）的任务点明主体和时限；不转嫁执法责任；面向群众不加强制措施，原稿已有的列入转交事项
社区	对居民用“请”，保持提醒口吻；不新增处罚、追责类后果，原稿已有的列入转交事项；防汛防疫提示的“可能”全留
公立医院	诊疗风险、用药、院感提示中的“可能”保留；疗效表述不改成保证
高校	学术判断中有依据的限定保留；学院对学校的签报、请示中的“建议”保留
中小学	对家长用“请”；不出现给家长布置作业的要求；讲话不承诺升学结果
国有企业	经营预测的“预计”“力争”保留；“建议董事会审议”属上行建议，保留

参考资料

文件	何时读取
`references/_shared/guardrails.md`	开工前；与流程冲突时以它为准
`references/_shared/style/defensive.md`	判断某种写法算不算防御腔；措辞层级表
`references/rewrite-guide.md`	第四步逐类改写；没有机检时用第十一部分速查表
`references/certainty-by-doctype.md`	第二步定文种；第四步核对请示、批复、部署文件、报告、讲话稿的确定性要求
`references/unit-adjust.md`	单位类型不是党政机关，或对象是群众、家长、居民时
`references/_shared/style/output-format.md`	第六步输出；转交和交接卡
`references/_shared/style/ai-tone.md`	判断某个问题属于 AI 腔（转 gongwen-humanize）还是防御腔
`references/_shared/profiles/roles.md`	确定角色模式；无画像降级
`references/_shared/rules/doc-types.md`	文种结构、惯用语、易混文种
`references/_shared/rules/tiaoli.md`	行文规则条款（请示、报告、对下级政府行文）
`scripts/gongwen_lint.py`	第三步诊断、第五步复检
`scripts/fact_diff.py`	第五步事实核对

About this skill

Automatic

Writing & Editing pack

SkillSafety

✓ 3 of 3 passed

Code scan14 of 15 checks clean

0 critical · 0 warning · 1 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-direct/SKILL.md

View on GitHub ↗

License PolyForm-Noncommercial-1.0.0Imported 11/2/2026Version v1Bundled 8 files · scripts

Illustrative Want to see what duyunzhoudyz/gongwen-direct 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

去防御性写作（gongwen-direct）

两种角色

适用范围

开工检查

工作流程

第一步 保密检查

第二步 确定文书类型和行文对象

第三步 诊断

第四步 分类改写

第五步 事实核对

第六步 输出

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　保密检查

第二步　确定文书类型和行文对象

第三步　诊断

第四步　分类改写

第五步　事实核对

第六步　输出