Ready to supercharge your AI agents?

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

单位画像与文风学习（gongwen-profile） · duyunzhoudyz | DecimalAI

Agent Toolingby duyunzhoudyz

单位画像与文风学习（gongwen-profile）

建立和维护单位画像，即 .gongwen/ 下的单位画像、领导偏好卡、禁用词、文风参数四个文件：分轮问卷或从本单位公文处理办法、已发文件中提取，完成完整建档；读本单位历史稿学文风参数；对比原稿和领导改稿（或带修订痕迹的 docx）归纳领导偏好，录入口述偏好；增删禁用词；给画像做体检。用户说建个完整的单位画像、把我们的公文处理办法录进去、学学我们单位的文风、领导改过的稿子你学一下、记住领导不爱用“打造”、加个禁用词、看看画像缺什么时使用。只建档不写稿：起草交对应起草 skill，按批注改稿交 gongwen-polish，3 问简版建档由 gongwen 完成。

Maintained

SkillScore

SkillScore86/100

Test results 86

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

41%86%of test cases passed +45 pts

Without skill9 of 22

With skill19 of 22

11 fixed8 passed either way2 still failing1 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这是局领导在本次全市民政工作会议报告第三稿上留下的批注和修订痕迹，请直接按照领导的批注和修改意见，把这份讲话稿从头到尾润色修改完毕，输出改定后的最终稿件全文。

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-profile
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-profile")
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-profile

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 11 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-profile

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-profile")
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-profile/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-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/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-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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-profile")
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-profile/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-profile/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 11 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-profile

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 11 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-profile/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 11 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

单位画像与文风学习（gongwen-profile）

把“这个单位怎么写材料、这位领导喜欢怎么改”记成 .gongwen/ 下的四个纯文本文件，供其他 gongwen skill 起草、改稿、核稿时读取。本 skill 只建档、学习和维护，不起草、不改稿；每条都来自用户的回答、制度文件或稿件，不存人名电话和原文段落。

适用范围

适用：
1. 完整建档：分轮问卷，或从本单位公文处理办法、议事规则、签报管理办法和已发红头文件中提取字段；补全总入口建的简版画像。
2. 文风学习：读 3～10 篇本单位历史稿得出文风参数。
3. 花脸稿学习：对比原稿和领导改稿（或带修订痕迹、批注的 docx），归纳领导偏好；录入口述偏好；归纳改稿记录中反复出现的偏好。
4. 禁用词管理：增、删、改禁用和慎用表述。
5. 画像体检：查缺漏、与默认值的差异、过期信息、隐私问题。
不适用（转交）：

用户要的	转给
第一次用，只想 3 问建简版画像；说不清要写什么	gongwen
照本单位文风或领导口味起草	对应起草 skill：法定公文 gongwen-draft，总结汇报 gongwen-report，讲话 gongwen-speech，党建材料 gongwen-party，信息简报 gongwen-brief，纪要 gongwen-minutes；装有行业包的，本行业专用文书交对应行业包
按领导批注把稿子改好；压缩、润色	gongwen-polish（改完可回到本 skill，把批注归纳进偏好卡）
去 AI 腔、去防御腔	gongwen-humanize、gongwen-direct
核稿	gongwen-review

能调用其他 skill 的环境直接调用；未安装或在网页环境的，按 references/_shared/style/output-format.md 第四部分转交（交接卡、新开对话粘贴 dist/prompts/<skill 名>.md 的说明、安装命令）。学完偏好后用户要求顺手改稿的，交 gongwen-polish。

四个文件

文件	内容	谁读取
`.gongwen/单位画像.md`	单位类型、发文体系、决策程序、写作角色、篇幅偏好、信息报送要求、红线等 18 个字段	所有 gongwen skill
`.gongwen/领导偏好卡.md`	一位领导一张卡：讲话风格、用词、忌用、数据呈现、篇幅、引用习惯、历次改稿记录	起草、改稿类 skill，按讲话人或署名领导的职务取卡
`.gongwen/禁用词.md`	禁用、慎用表述	起草时避开；gongwen-review 核稿时逐条比对（禁用 P1、慎用 P2）
`.gongwen/文风参数.md`	各类文书的量化参数和表述习惯	起草类 skill

模板依次见 references/_shared/profiles/profile-template.md 第一至四部分（单位画像用完整版）；文风参数的补充项见 references/style-params.md 第一部分。

读写约定（四个文件通用，见 references/maintenance.md 第一部分）：

位置：先找工作目录的 .gongwen/，再找 ~/.gongwen/，网页环境看对话开头的粘贴；新建默认放工作目录，要所有项目通用的放 ~/.gongwen/。用户直接给出的画像文件，改完写回原处，并问是否移入 .gongwen/。
先读后写，不整份覆盖。没有的文件直接新建，写完报位置；已有文件只追加或修改相关条目，先出变更单，同意后再写。用户已说清改哪一项、改成什么的视为同意，列出变更单后直接写；推断出的改动仍要先问。
变更单一条一行：［修改］单位画像·写作角色和默认模式：院办秘书；高效模式 → 党办干事；严谨模式（来源：用户告知）。新增写［新增］，删除写［删除］。
改前备份：Agent 环境改已有文件前，复制到 .gongwen/历史/<原文件名>-<YYYYMMDD-HHMM>.md，不覆盖已有备份。
维护记录：每次改动追加一行：日期、做了什么、来源。领导偏好卡文件用一级标题“# 维护记录”，放在全部卡之后；其余三个文件用“## 维护记录”。日期写当天日期，网页环境不确定的留空。
领导偏好卡一位领导一张，同放一个文件，每张以“# 领导偏好卡（职务）”开头，不写姓名。
工作目录是 git 仓库的，提醒用户把 .gongwen/ 加进 .gitignore，由其决定。

开工检查

保密（references/_shared/guardrails.md 第一条）：
- 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。
- 敏感信号提示按 guardrails 第一条第 1 款。
- 每份材料先看首尾几行和页眉页脚：有 guardrails 第一条第 2 款所列密级标识或内部标注，或写有“严禁外传”“内部参阅”“仅供内部参考”“未公开”“未披露”的，这一份立即停止，不摘录、不统计，按该款告知用户和可以继续的情形，其余各份照常。脚本没跳过不代表没有标注，仍须自己看。
- 有身份证号、手机号、病案号、学号、家庭住址、真实姓名的，提醒用户先脱敏；学习照常，四个文件里一律不出现这些内容，例证改写成“张某”“138****0000”，起草说明“保密提示”写明。
- 有 Python 时可先运行 python scripts/gongwen_lint.py <文件> --checks privacy --json 辅助扫描；它不识别不带标签的人名，读不到修订稿新增的文字，这两类看 draft_diff.py 的输出或人工通读。
读已有文件：按读写约定第 1 条找齐四个文件，先用一行告知读到了什么，如“已读取：单位画像（已填 12/18 个字段）；领导偏好卡 1 张（院长）；禁用词 6 条”。
定功能，一次做一项；一句话里有几项的，按建档、文风、花脸稿、禁用词、体检的顺序做。“记住局长不爱用‘打造’”是口述偏好录入（功能三末）；“以后别用某词”是功能四；“画像还缺什么”是功能五。
角色模式（references/_shared/profiles/roles.md 第一节），依次取：用户指定；画像“写作角色和默认模式”；从话语推断（新人→教学，秘书、专职写材料→高效，业务岗兼写→转译，领导本人→审稿，党务、组织、纪检、宣传岗→严谨）；都没有的用教学。只说了部门（“在院办”“在教务处”）不算说了岗位，不据此定模式，建档时问岗位。
用户贴了交接卡的，按卡上的单位画像、当前模式、任务、已确认事项开工，卡上已有的不再问。
用户要求在偏好卡里记领导的脾气、对人的评价，或要求“保证查不出是 AI 写的”，说明原因，不按此办，其余照常（guardrails 第六条）。

六条红线的落实

红线	本 skill 的做法
一、保密	开工检查第 1 条；四个文件不存个人信息，领导只写职务，修订人姓名不记录
二、事实只来自用户	字段值只来自用户回答、制度文件（注明条款）和样本统计，问不到的留空，存疑的括注原因并列入起草说明“待核实”一行；用户加引号的提法、做法名称和禁用词照原样记；“上周五”按今天推算后记，“前几天”照原话记
三、提示外置	文件里只放画像内容；假设、待补字段、变更单、保密提示写进【起草说明】
四、做减法	每轮最多 3 问，能提取的不问；偏好卡只记有例证的条目
五、可溯源	每个字段注明来源；与国标不同的注明国标条款
六、不代笔	只学习记录，不起草、不改稿；不存原文段落，例证不超过 20 字

功能一　完整建档

第一步　定来源

用户给了制度文件（公文处理办法、议事规则、签报管理办法等）或已发的红头文件的，先提取再用问卷补缺；没给的直接问卷。

第二步　从制度文件和已发文件提取

制度文件按 references/intake.md 第二部分（一）的“字段与条文”对照表逐项找。找到的写入字段，括注文件名和条款号。
已发文件按 intake.md 第二部分（三）只看版头、发文字号、版记；正文内容、主送和抄送不进画像。
文件没写的字段留空，不用单位类型默认值填。
本单位规定与国标不同的（如成文日期用汉字），照本单位写，括注“与 GB/T 9704-2012 7.3.5.4 不同，按本单位办法执行”，条款号查 references/_shared/rules/gbt9704.md。
文件印发已超过 5 年，或条文含糊的，起草说明“待核实”一行请用户确认。
文件里的人名、电话、经办人、签发人不进画像，决策程序只写程序性表述，如“重要事项先经局长办公会讨论，再由局党组会议研究决定”。

第三步　分轮问卷

按 references/intake.md 第一部分的轮次提问，每轮最多 3 问，一次问完，放在回复末尾；已知的、已提取的跳过，空出的名额由下一轮补上。默认四轮：基本情况、发文体系、写作习惯、约束和配套文件。
问法带上该单位类型的常见情形作选项（intake.md 第三部分），用户答“一样”的按选项填，来源写“用户确认”。
首轮交付（参照 references/_shared/profiles/roles.md 第十节）：用户要求直接给画像，或消息、材料中除单位类型外还有其他字段的，首轮就出画像，已知字段填上，空缺的列入待补，下一轮问题（不超过 3 个）放在回复末尾；只给了单位类型的，首轮出第一轮问卷。
用户说“就这些”“其他你看着填”，停止提问；没答的字段留空（读取时采用单位类型默认值），列入待补事项；用户只说“按该类型的默认做法”的，不举具体写法，也不替其他 skill 承诺行为。“单位类型”“写作角色和默认模式”空着会触发无画像降级，用户没答的按其话语推断（开工检查第 4 条），字段后括注“推断”，并列入起草说明“待核实”一行。
不问单位全称、领导姓名、电话、人员名单和业务数据；“单位名称或代号”用户没说的留空，不问，也不列入待补。

第四步　生成和写入

按完整版模板生成，字段名一字不改，其他 skill 按字段名读取。末尾加“## 维护记录”。
已有简版画像的，原有字段原文保留，空缺字段补上；与原有内容不同的列进变更单，同意后再改。
能写文件的写入 .gongwen/单位画像.md；网页环境输出全文。

功能二　文风学习

第一步　收稿

收 3～10 篇本单位历史稿（txt、docx、md 或直接粘贴），已脱敏。按文书类型分组，每组 2 篇以上才单独出参数。
少于 3 篇的照做，注明“样本 n 篇，代表性有限”；多于 10 篇的取最近、最常写的 10 篇。
问一句（可与其他问题合并）：稿子是否经过领导审定；未审定的在文风参数中注明。

第二步　量化统计

有 Python 时运行 python scripts/style_profile.py <文件或目录> --json（分了组的每组单独运行），要归纳标题句式的加 --examples，标题示例只用于归纳，不写进文件。脚本跳过的文件（有密级或内部标注）按提示告诉用户。没有 Python 或脚本报错的，按 references/style-params.md 第三部分人工估算并注明。历史稿是红头文件、画像又缺发文体系字段的，征得同意后按功能一第二步第 2 条顺带补上。

第三步　不采纳检查

有 Python 时对每篇运行 python scripts/gongwen_lint.py <稿件> --checks style,defensive --json；没有时按 references/style-params.md 第四部分人工查。
2 篇以上都有的毛病（清单见 style-params.md 第四部分）写进“不采纳的习惯”，起草时不模仿；style_profile.py“开头方式”为铺垫式的篇数也在此处理。
历史稿中的政治性提法不作为“常用表述”记录，提法以用户提供的最新原文为准。

第四步　定性观察

按 references/style-params.md 第二部分的 7 项逐项看。每项写成“做法＋频次”，不抄原句。

第五步　写入

按 profile-template.md 第四部分的模板和 style-params.md 第一部分的补充项、填写要求写，按文书类型分节；已有文件只更新对应类型一节，变更单列出新旧数值。
不写入：原文段落和整句、标题原文（写抽象句式）、人名、业务数据。

功能三　花脸稿学习

第一步　收稿和确认

四种输入：原稿和改稿两份文件；带修订痕迹或批注的 docx；网页环境粘贴的两段文字；偏好卡已有的“历次改稿记录”（含 gongwen-polish 追加的行，用户说“把改稿记录归纳一下”时直接做第四、五步）。网页环境读不出 docx 修订痕迹的，请用户在 Word 中另存“拒绝全部修订”“接受全部修订”两份，或分别粘贴。
只比交给领导的那一稿和领导改完的那一稿，起草人自己中间改的版本不算。
确认三件事，已知的不问：改稿领导（写职务）、稿件类型、改稿日期。docx 有多位修订人的，脚本列为“修订人1、修订人2”，请用户指明哪位是这位领导；指明前可先按修订处数最多的归纳，写进所作假设，确认前不写入偏好卡；只计这位修订人的改动，其他修订人的改动不计入偏好次数。

第二步　对齐

有 Python 时运行 python scripts/draft_diff.py <原稿> <改稿> --json，或 python scripts/draft_diff.py <修订稿.docx> --json（只看某位修订人加 --author N）。多份花脸稿逐份对比，再按偏好合并计数。没有 Python 的，按 references/edit-patterns.md 第一部分逐段逐句人工对照。对比清单含原文，只在对话中用，不存进 .gongwen/。

第三步　剔除和归类

先剔除非写作偏好的改动：事实更正（原有数字改成另一个数字，日期、名称、文号改了）、错别字和标点更正、一次性的内容取舍。事实更正单列在“修改说明”中，提醒用户核对原始数据，不进偏好卡。目标修订人以外的改动同样不计偏好，单列为“其他修订人改动”，含数字的提醒核对。概括词换成具体数字的（“明显减少”改为“由15起降至9起”）归为“数据代替评价”偏好，新数字仍提醒核对。脚本标签“数字改动”“改为具体数字”分别对应这两种。
其余按 references/edit-patterns.md 第二部分归类：删减、换词、结构、语气、数据呈现、标题、篇幅、批注意见。脚本给的标签只是线索，逐条看上下文确认。

第四步　归纳偏好条目

每条写成一个做法，带例证、次数、来源：- 不用“打造”，改为“建设”或删去（例：“打造品牌”改为“建设品牌”；1 份稿件 3 处；2026-09-17 供暖保障工作汇报；用户确认）。
例证不超过 20 字，去掉人名、单位全称和具体数据。
写入门槛：同一偏好在 2 份以上稿件中出现的，写入偏好条目；只在 1 份稿件中出现的，只记入“历次改稿记录”，标“观察中”；1 份稿件中出现 3 处以上、用户确认是一贯习惯的，也可写入，注明“用户确认”。
批注只归纳写作要求（如“成效要有数据”“开头直接说结论”），对人的评价和情绪化的话不记（如“局长脾气急”不记，“讲话稿删去开场寒暄，第一段直接讲部署”记）。

第五步　冲突检查和写入

逐条与已有偏好卡、禁用词、文风参数比对。冲突的（原卡写“常用‘打造’”，新稿每次都改掉）一次问完，最多 3 条，每条给三个选项：以新为准；保留原条目；按文书类型区分（如讲话保留、汇报不用）。用户不答的，原条目不动，新条目记“观察中”。
已有且不冲突的条目：次数累加，来源追加日期。
查“历次改稿记录”中同一偏好标“观察中”的记录（含 gongwen-polish 追加的行，每行按 1 份计）：与本次合计达到 2 份的，升级为偏好条目，份数、处数和来源合并，原记录的“（观察中）”改为“（已归纳）”。
“历次改稿记录”每份稿件追加一行：日期、稿件、领导改动、归纳的偏好。只进改稿记录的“观察中”条目，在变更单中逐条附例证和处数；变更单经用户同意后写入。
反复被删改的词，问用户是否加入禁用词（慎用），同意后按功能四写入。

口述偏好录入

用户或领导本人直接说出的写作偏好，以及 gongwen-speech 转来的偏好，不需要花脸稿：

直接写入偏好卡对应节，来源写“用户告知（日期）”或“本人口述（日期）”，不受份数门槛限制。
只收写作偏好，对人的评价不记。
去向：只针对某位领导的，写进这位领导的卡（不用的词进“忌用表述”）；全单位都不用的，按功能四写进禁用词；说不清的问一句“只是写局长的材料不用，还是全单位都不用？”
按第五步第 1 条做冲突检查，先出变更单；用户已说清改哪一项、改成什么的，列出后直接写（读写约定第 2 条）。还没有这位领导的卡的，新建一张，只填适用对象和这一条。

功能四　禁用词管理

每条写全五列：词语或表述、级别、原因、替换建议、适用范围（references/_shared/profiles/profile-template.md 第三部分）。gongwen-review 用机检按第一列逐词比对，第一列只写正文中会原样出现的词语，几个词用顿号隔开；用户给的是“××工程”这类占位写法的，请其给出正文实际写法，暂无的照原样记并列入起草说明“待核实”一行。
级别：用户说“别用”“不能用”的为禁用，说“少用”“尽量不用”的为慎用，说不清的按慎用并写进所作假设。
原因写来源和日期，如“院长改稿删除 3 次（日期）”。
用户没给替换建议的，给 1～2 个中性词，没有合适的写“删去，直接写具体做法”。
政治性提法的停用、更新以用户提供的上级原文为准。用户要求加入但没给原文的，严谨模式先请其提供原文，用户暂不提供的，以及其他模式，照用户原话加，原因写“用户告知”，并在起草说明“待核实”一行请其提供原文；本 skill 不主动增删这类条目。
删除或改级别：列出原行和改后，用户同意后改，被删的行记入维护记录。
新条目与偏好卡“常用”冲突、与已有条目重复的，合并或询问。

功能五　画像体检

逐项查以下 13 项（细则和示例见 references/maintenance.md 第二、三部分），输出体检单，不直接改文件：

关键字段缺失（P1）：“单位类型”“写作角色和默认模式”为空，会触发无画像降级（roles.md 第九节）。
其他字段空缺（P2）：18 个字段逐个看，列出空着的，说明读取时用单位类型默认值。
个人信息（P0）：带真名的人名、手机号、证件号、住址。
对个人的评价（P0）：偏好卡中写了脾气、性格、对某人的看法。
与单位类型默认值不同：对照 references/_shared/profiles/units/ 对应文件第二、三、四、六部分，本单位实际如此的不列；明显不合常规的列 P1 待核实（医院没有党委会、国企没有党委前置研究、高校学院对校外正式行文），社区写了发文字号的列 P2。
维护记录过期（P2）：最后一次维护超过 12 个月。
制度文件过旧（P2）：印发超过 5 年或没写年份。
偏好卡对象可能变动（P2）：更新日期超过 12 个月或领导已调整。
文风参数过旧或不足（P2）：样本都在 3 年以前、少于 3 篇或为人工估算。
文件之间矛盾（P1）：禁用词与偏好卡“常用”冲突；画像角色与偏好卡适用对象不符。
篇幅偏好超上限：只查通知、意见、实施方案等文件类，部署专项工作的超过 4000 字、其他超过 5000 字（references/_shared/rules/jianfu.md 第三部分），党政机关、基层、社区 P1，其他 P2；部署综合性工作的不设上限，超过 5000 字只作 P2 提示。
字段名被改动（P1）：与模板不一致，其他 skill 读不到。
政治性提法条目无依据（P1）：禁用词中的提法条目没写上级原文出处。

体检单先写总体（已填几个字段，P0、P1、P2 各几条），再列：序号｜级别｜文件和字段｜问题｜依据｜建议改法。手机号等只写类别。最后问用户改哪几条，同意后改。

输出规范

四个文件是 Markdown 工作文件，按模板写，可用标题、列表、表格；文件里不放提示语，空缺字段留空。
能写文件的环境：写入 .gongwen/，对话中报写了哪些文件、改了几条、留空几项，不重复全文；所作假设、待补事项、保密提示等写在回复的【起草说明】中，不写入 .gongwen/；回复中不写 skill 名，用描述性说法。
网页环境：每个文件先写一行“文件：.gongwen/单位画像.md”，再给出完整内容，放在代码块中便于复制；更新已有文件时同样给完整新版本。之后另起一行写【起草说明】，不超过 5 行、每行一句：假设、待补（留空的字段）、待核实各汇总一行，修改说明（变更单、事实更正提醒）一行，有敏感信号时保密提示一行；教学模式另附“写作要点”（写画像怎么用）。最后提醒用户保存这些文本，以后使用时粘贴在对话开头。
提问不超过 3 个，放回复末尾，不阻塞已能完成的部分；与无画像降级的提问合并计数。
交接卡：路线还有下一站的（如先建档再写讲话），在起草说明之后按 references/_shared/style/output-format.md 第四部分输出更新后的交接卡：单位画像栏附新画像全文，路线如“profile → speech → review”，请准备栏列要一并粘贴的领导偏好卡、文风参数；只写任务信息，不抄录用户原始材料。

自检清单

只在材料有敏感信号时提示保密（起草说明末尾）；有密级或内部标注的材料没有摘录和统计。
四个文件中没有人名、电话、证件号、患者和学生信息；领导只写职务；修订人姓名没有记录。
字段值都有来源；问不到的留空，没有拿单位类型默认值冒充本单位情况。
用户加引号的提法、做法名称和禁用词照原样记录；“上周五”等相对日期已按今天推算后记录。
改已有文件前出了变更单并取得同意，已备份；没有整份覆盖；维护记录已追加，标题级别符合读写约定第 5 条。
文风参数没有原文段落、整句和标题原文；不采纳的习惯已列出；样本数和是否人工估算已注明。
偏好条目都有例证、次数、来源日期；事实更正没有混进偏好；写入门槛和“观察中”升级照功能三第四、五步；冲突的已询问，没有悄悄覆盖。
禁用词五列齐全，第一列是正文中会原样出现的词语；政治性提法条目有原文依据，或已列入起草说明“待核实”一行。
网页环境输出了完整文件文本和【起草说明】；起草说明不超过 5 行、每行一句；提问不超过 3 个，在回复末尾。

有 Python 时，写完对四个文件分别运行 python scripts/gongwen_lint.py <文件> --checks privacy --json，人名仍人工看一遍；无法运行时全部人工检查，在起草说明中写“未运行机检”。

单位类型差异

党政机关指省、市两级；县、乡两级和街道（含县直部门）归基层。建档时各类型的问法、选项和常见误填见 references/intake.md 第三部分。文风学习按类型分组统计：党政机关讲话稿与文件分开，提法不进常用表述；基层的政务信息、社区的居民通知、中小学的家长通知和致家长的信各自单独成组；医院质量分析与汇报材料分开，高校学院稿与机关稿分开；历史稿先删个人信息，国企未披露的经营数据不进样本。

角色适配

教学模式：问卷每题附一句“为什么问、起草改稿时怎么用”；文风参数和偏好条目各附“起草时怎么用”；起草说明末尾写画像的使用方法。
高效模式：能提取的不问，问卷压成两轮；多份花脸稿一次处理；变更单一次确认；对话只报改动条数和文件位置，不展开讲解，但变更单的来源、体检单的问题和依据每条仍写一行；维护类回复只含变更单、文件位置、起草说明，不解释未改字段，不提议顺带补其他字段，不承诺其他 skill 的行为。
转译模式：问题用大白话，不用公文术语（问“发文件的编号长什么样”，不问“发文字号格式”）；优先从用户给的文件里提取。
审稿模式：用户多是领导本人，口述偏好按“口述偏好录入”写入，来源写“本人口述”；画像体检只出一页纸摘要和体检单，不主动改文件。
严谨模式：禁用词中的提法条目以上级原文为准，未给原文的按功能四第5条先请用户提供；文风学习不记录提法；偏好卡的引用习惯只写“引用注明出处，只用用户提供的原文”。

参考资料

没有文件系统时，读不到的文件按本文执行，不向用户索要。

按需读取 references/ 下：intake.md（功能一）、style-params.md（功能二）、edit-patterns.md（功能三）、maintenance.md（读写约定细则、体检细则和示例）。

About this skill

Automatic

Government & Public Sector 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-profile/SKILL.md

View on GitHub ↗

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

Illustrative Want to see what duyunzhoudyz/gongwen-profile 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

单位画像与文风学习（gongwen-profile）

适用范围

四个文件

开工检查

六条红线的落实

功能一 完整建档

第一步 定来源

第二步 从制度文件和已发文件提取

第三步 分轮问卷

第四步 生成和写入

功能二 文风学习

第一步 收稿

第二步 量化统计

第三步 不采纳检查

第四步 定性观察

第五步 写入

功能三 花脸稿学习

第一步 收稿和确认

第二步 对齐

第三步 剔除和归类

第四步 归纳偏好条目

第五步 冲突检查和写入

口述偏好录入

功能四 禁用词管理

功能五 画像体检

输出规范

自检清单

单位类型差异

角色适配

参考资料

SkillSafety

Source

Related skills

More in the registry

功能一　完整建档

第一步　定来源

第二步　从制度文件和已发文件提取

第三步　分轮问卷

第四步　生成和写入

功能二　文风学习

第一步　收稿

第二步　量化统计

第三步　不采纳检查

第四步　定性观察

第五步　写入

功能三　花脸稿学习

第一步　收稿和确认

第二步　对齐

第三步　剔除和归类

第四步　归纳偏好条目

第五步　冲突检查和写入

功能四　禁用词管理

功能五　画像体检