Ready to supercharge your AI agents?

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

上级文件转化（gongwen-implement） · duyunzhoudyz | DecimalAI

Documentationby duyunzhoudyz

上级文件转化（gongwen-implement）

把上级来文转化为本单位的落实材料：提取上级文件要点，做任务分解表（任务、牵头、配合、时限、成果形式、对应上级条款），起草实施方案、贯彻落实方案，按任务表写贯彻落实情况报告，整理学习传达要点；逐条对标对表查漏项，检测照抄上级原文，倒排时限，提示层层加码。用户说省里发了通知要出实施方案、把文件里的任务拆一拆、对标对表、方案跟上级文件太像、报送贯彻落实情况、传达会议精神时使用。只转发不拆任务交 gongwen-draft，自主制定的方案交 gongwen-report，巡视审计整改交 gongwen-rectify；装有行业包时，本行业专用文书交对应行业包。

Maintained

SkillScore

SkillScore73/100

Test results 73

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%73%of test cases passed +41 pts

Without skill7 of 22

With skill16 of 22

10 fixed6 passed either way5 still failing1 broke

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

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task上级发来了《关于开展消防安全大检查的通知》，我们单位不需要拆解任务，只需要发一个简短的转发通知给下级单位执行，请帮我起草这篇转发通知。

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-implement
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-implement")
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-implement

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 14 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-implement

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-implement")
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-implement/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-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/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-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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-implement")
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-implement/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-implement/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 14 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-implement

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 14 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-implement/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 14 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

上级文件转化（gongwen-implement）

上级来文后，本单位要限期拿出实施方案，事后还要报落实情况。本 skill 把上级文件逐条落到任务分解表，或写明不涉及的理由；任务写本单位措施，用户给的优先，缺的按上级要求和文种常规写出可执行措施，时限、负责人等须用户定的标【待补】；本单位时限早于上级时限；不擅自提高标准，不向下层层要材料。

适用范围

适用：上级文件要点提取；任务分解表（可转 Excel）；以上级文件为依据的实施方案、贯彻落实方案、工作方案、实施意见；按任务表逐项报进展的贯彻落实情况报告；学习传达要点；对已写好的方案或落实情况报告做对标对表检查；把照抄上级的初稿改成本单位方案。
不适用（转交）：

用户要的	转给
只转发上级文件、不拆任务的转发通知；印发方案用的印发通知；会议通知	gongwen-draft
没有上级文件依据、本单位自主制定的方案、计划、工作要点	gongwen-report
巡视巡察、审计、督查反馈问题的整改方案、台账和报告；按检查清单逐项自查	gongwen-rectify
本人的学习心得、研讨发言，党课	gongwen-party
领导在部署会、传达会上的讲话	gongwen-speech
会议议定事项的督办清单	gongwen-minutes
压缩篇幅、调语气；标题；全面核稿；排版	gongwen-polish；gongwen-title；gongwen-review；gongwen-format
装有行业包时的行业专用文书：中小学课后服务方案（有上级通知的也算）、国企改革任务台账和改革进展报告等	gongwen-k12、gongwen-soe 等对应行业包；没装的按本表其他行或本 skill 流程处理

开工时判定不归本 skill 的，不出要点表、任务表和方案，告诉用户该怎么办、为什么，用描述性说法，不写 skill 名。能调用其他 skill 的环境直接调用；目标 skill 未安装或在网页环境的，按 references/_shared/style/output-format.md 第四部分转交：给交接卡、“新开对话粘贴 dist/prompts/<skill 名>.md 继续”的说明和安装命令。

开工检查

保密，按 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。
- 材料出现敏感信号时才在起草说明末尾附一句“提示：涉密材料请勿输入联网 AI。”（回复开头不放），同一会话只说一次。
- 读文件前先看版头文尾。有密级标识，或标注“内部资料”“工作秘密”“不得外传”“内部使用”的，按第2款立即停止，不摘录、不复述，告诉用户改用单位内网部署的模型，或提供已公开版本、删去相关内容后再发；用户说明属于第2款所列情形后再继续。
- 只标“此件不公开”等公开属性、没有上述标识的，照常处理，保密提示后加一句“该文件标注不公开，请确认其中不含工作秘密和内部敏感信息”。
- 上级文件的联系人姓名和手机号不抄进任何产出，牵头、配合写单位或科室。用户材料中患者、学生、群众的个人信息提醒脱敏（机关干部姓名照写），产出改用“张某”“138****0000”，保密提示写明已替换。
单位画像：依次找 .gongwen/单位画像.md、~/.gongwen/单位画像.md 或对话开头贴的画像，领导偏好卡、禁用词一并读取；再读 references/_shared/profiles/units/ 下对应文件和 references/units.md。没有画像的按 references/_shared/profiles/roles.md 第九节。
收齐材料，只问缺的，问题不超过3个，放回复末尾，不阻塞起草：
- 上级文件原文（必需）。用户只说了文件名的，请用户粘贴原文或主要条款。拿不到原文、也说不出上级要求的，不凭记忆补写上级文件内容，只交方案框架、空白要点表和材料清单（references/structures.md 第五部分），并告知用户：能口述上级主要要求的，可先按口述起草（references/structures.md 第五部分第3条）。
- 本单位情况：职责分工（谁牵头）、现有基础和数据、拟采取的具体措施、领导已明确的意见。
- 时限：上级规定的完成和报送时间取自原文；问用户本单位是否已定时限。缺本单位情况不阻止起草，措施按上级要求和文种常规写出，须用户定的要素标【待补】。用户说“直接写”的不再问。
定产品（可组合）：说“出个方案”的，交要点表、任务分解表和方案三件；“报落实情况”走模式二；“传达精神”走模式三；拿已写好的方案或落实情况报告挑问题的走模式四；拿照抄初稿改成本单位方案的，按“照抄初稿改写”。
定角色模式：按 references/_shared/profiles/roles.md 第一节的顺序确定；没有画像、用户话里也没有识别信号的，按教学模式。学习传达要点、党委（党组）文件和党建任务的落实方案，叠加严谨模式。
以下要求说明原因、不照办，其余照常（references/_shared/guardrails.md 第二条第 3 款、第六条）：只想“改得看不出是照抄”而不给本地措施的，不做同义替换降重；要编“特色做法”“亮点成效”的；要把正式文件改成便笺或“白头”规避发文管理的。
用户贴了交接卡的，按卡开工，卡上有的不再问（references/_shared/style/output-format.md 第四部分）。

六条红线在本 skill 的落点

一、保密见开工检查第1条，交接卡和 上级文件.txt 不带联系人信息。二、上级文件内容只取原文；本单位数据、分工、时限只来自用户、画像和原文分工（时限可经用户同意倒排），缺的标【待补】，存疑的列入“待核实”；措施缺的按上级要求和文种常规写出，责任主体只用材料已有的单位、部门。三、表格放在【起草说明】之后。四、不复述背景、意义、指导思想，不照搬上位文件，不层层要材料（references/_shared/rules/jianfu.md 第2、3、12条）。五、任务注明对应上级条款。六、不编特色做法和成效，不为降重做同义替换。

工作流程（方案）

本文和 references/ 中的示例均为虚构，数量、单位、日期不得用于实际起草。

第一步　拆上级文件，出要点表

通读正文和附件，附件里的任务清单、指标表往往才是真正的任务。
登记文件信息：发文机关、标题、文号、成文日期、主送，只抄原文，缺的写【待补】。
给每一条编号，用原文自己的层次号，如“二（三）”“附件1第4项”；原文没有序号的按段编“第5段”。
一条一行，归入七类：目标指标、重点任务、时限节点、责任分工、报送要求、工作要求（含“不得”“严禁”）、保障措施。一条里有两类内容的拆成两行。
定本单位关系：主办、协办、不涉及、待确认。依据顺序为原文分工、用户说明、画像职责；判断不了的写“待确认”，不猜；“不涉及”写理由。
要点栏压缩原文：保留主体、动作、对象、数字、时限，以及“原则上”“力争”“确保”“全覆盖”这类定标准的词；删修饰和号召。

表格式、判定细则和压缩示例见 references/mapping.md 第一部分。

第二步　任务分解表与对标对表核对

序号	任务（本单位措施）	牵头单位	配合单位	完成时限	成果形式	对应上级条款
1	对全市1386台住宅电梯逐台检查维保记录和安全保护装置	市市场监管局	市住房城乡建设局	7月3日前	检查问题清单	二（一）

要点表中“主办”“协办”的每一条至少对应一行任务；一行可对应几条，条款号写全。
任务栏：主体换成本单位，动作和对象取自上级条款，再接用户给的本地措施（对象、范围、数量、方式）。本地措施缺的，按上级要求和常规写出可执行措施，不夹带新数字、项目名；台数、地点等须用户提供的接【待补：缺什么】；不把上级原句搬进任务栏。
一项任务只写一个牵头单位，配合可以多个。按属地分头落实的，牵头可写“各街道办事处”，另写一个统筹单位。用户和画像都没说的写【待补：牵头单位】，不按机构名称猜分工；用户只列了部门名称没说职责的，请用户确认分工放在回复末尾问题的第一条；配合、统筹单位同样只取自用户、画像或原文。
完成时限按 references/deadline-burden.md 第一部分：用户给了的照用，核对是否早于上级时限；“下周五”按今天推算为具体日期；“月底前”等期限照原话写。用户没给的，写【待补：完成时限，须早于上级要求的×月×日】，倒排建议放进时限倒排表；用户说过“时间你倒排”“日期你定”的，直接写倒排日期，依据写进起草说明“假设”。有倒排时限或倒排建议的，都附“附：时限倒排表”。
成果形式写看得见的东西：制度文件、问题清单、项目清单、系统上线、验收结论。上级原文有要求的照用，没有的不新增台账、照片、学习笔记之类的留痕。
用户自加的、上级文件没有的任务，对应条款栏写“本单位自定”，第四步做加码检查。
对标对表核对：要点表每一条都要有结论，只有三种：已对应（写任务序号或方案段落）、不涉及（写理由）、漏项。漏项补一行任务，措施按常规写出，须用户定的标【待补】。报送要求、工作要求、禁止性规定最容易漏：报送要求对应到“形成落实情况报告”一类任务，禁止性规定对应到方案的工作要求。核对表列为“附：对标对表核对表”（references/mapping.md 第三部分）。
有 Python 环境时，把表存为 任务分解表.md，运行 python scripts/md2xlsx.py 任务分解表.md 任务分解表.xlsx --title "某某重点任务分解表"；没生成 xlsx 的，告诉用户把表格复制到 Excel 整理。

首轮交付按 references/_shared/profiles/roles.md 第十节，各模式相同：要点表、任务分解表、方案正文和起草说明一次交付，须用户定的牵头单位、时限等标【待补】（正文一般不超过 3 处），问题放回复末尾。只在三种情形停下，并在回复开头说明属于哪一种：没有上级原文、用户也说不出上级要求（交框架，见开工检查第3条）；用户明确要求先看要点表或任务表；材料涉密（开工检查第1条）。

第三步　起草方案

结构和写法见 references/structures.md 第一部分。

标题写“发文单位＋事项＋实施方案”，如“某市住宅电梯安全隐患专项整治行动实施方案”。不把上级文件全称套进标题，避免“关于贯彻落实《关于……的通知》的实施方案”。
开头一句写依据和目的：“为贯彻落实《……》（某政办发〔2026〕37号），结合我市实际，制定本方案。”一般不另写形势背景、重要意义，确需交代的一段以内且不空泛，不复述上级的指导思想和总体要求。
工作目标：上级有指标的，照录数值，或写用户提供的本地分解数；不高于上级标准。用户要求高于上级的照写，列入加码提示。没有的写【待补：目标值】。
重点任务按任务分解表组织，每项写“小标题＋措施＋（牵头单位：……；配合单位：……；完成时限：……）”，缺的项不在括注里写占位，小标题写“动作＋对象”。
- 正：（二）评估老旧住宅电梯。各区6月19日前完成214台老旧住宅电梯安全评估，对未装应急救援装置的当场下达整改通知。（数量、时限取自用户材料）
实施步骤：上级分阶段的，本单位每阶段截止日期早于上级对应阶段。
工作要求两三条：上级的禁止性规定在这里落实；只写有主体、有动作的安排，不写“高度重视”“加强领导”一类空表态。向下报送要求只写一次：何时、报给谁、报什么，不超出上级要求。
正文末尾写“附件：重点任务分解表”，表另交。
篇幅：部署专项工作或具体任务的，一般不超过4000字（references/_shared/rules/jianfu.md 第三部分）；工具约定一般2000～3500字，任务分解表另计。用户指定字数的，按 references/_shared/guardrails.md 第四条第2款；未指定的，不凑字数。
措辞：部署用“要”“于×月×日前完成”，不用“建议”“尽量”“适时”（references/_shared/style/defensive.md 第五部分）；避开 AI 腔（references/_shared/style/ai-tone.md）。

第四步　照抄检测、加码检查、时限核对

照抄检测。有 Python 环境时，先按第五步第3条建交付目录，写入 上级文件.txt（docx 可直接用）和 正文.txt，运行 python scripts/overlap_check.py 正文.txt 上级文件.txt --json（字段见 references/localize.md 第四部分）：
- 总重合率超过30%的，以及高重合段落（本段一半以上与上级相同），逐段处理：用户给了本地措施的，改写为本地措施；没给的，按上级要求和常规写出本单位可执行措施（用本单位主体、对象，不沿用上级原句），删掉照抄的展开。
- 不做同义替换：换了词，内容还是上级的。
- 高重合段落是标题行或只含指标、行动名称的，核实后保留并在检测结果中写明（见 references/localize.md 第一部分）。
- 改完重跑，直到总重合率不超过30%、高重合段落都已处理或注明保留；前后两次结果写进“附：重合检测结果”。
- 不能运行脚本的，按 references/localize.md 第三部分人工比对，说明写“未运行重合检测，已人工逐段比对”。
加码检查：任务分解表逐行与上级条款比八项：标准、时限、范围、频次、材料报送、考核问责、转嫁责任、配套文件。超出上级要求的列入“附：加码风险提示”，写明本稿写法、上级要求、依据和建议。用户坚持要写的照写，提示保留。细则见 references/deadline-burden.md 第二部分。
时限核对：每个本单位时限都早于上级对应时限；预留只按汇总、审核、报送的实际需要，不层层大幅提前。
漏项复查：对标对表核对表中没有未处理的“漏项”。

第五步　自检与交付

机检：有 Python 时运行 python scripts/gongwen_lint.py 正文.txt --doc-type 实施方案 --json。工作方案传“实施方案”，贯彻落实方案传“贯彻落实方案”，落实情况报告传“报告”，学习传达要点传“其他”。P0 必改，P1 逐条判断；【待补】报的 P2 保留。ELM 要素缺失的，能确定的补写，不能确定的标【待补】；EVD 强评价缺数据的，补用户材料中的数据或改用不带强评价的写法，不得编造数据。无法运行时按 references/checklist.md 人工检查（读不到的按本文自检清单），起草说明写“未运行机检，已按人工清单检查”。
过一遍本文“自检清单”；篇幅、层次、开头结语可参照 references/_shared/style/baseline.md 中该文种的典型参数（非硬规则；用户指定篇幅时以用户为准）。
能写文件的，按 references/_shared/style/output-format.md 第三部分建 公文/<YYYYMMDD>-<简短标题>/（第四步已建的沿用），写入 上级文件.txt、要点表.md、任务分解表.md（和 xlsx）、正文.txt（只含正文）。上级文件.txt 写入前删去联系人和手机号所在的行，多份写成 上级文件-甲.txt、上级文件-乙.txt；一次出几份的，写成 正文-实施方案.txt、正文-落实情况报告.txt 等。对话中报文件位置、一段话概述、重合率，再给【起草说明】和附表，不贴全文。
网页环境（读不到文件系统才按本条，与上一条不同时做）：依次输出正文、【起草说明】、附表；开头直接交付正文，不加引导语。附表名称前加“附：”，按产品取用，顺序为任务分解表、对标对表核对表、上级要求差异表、时限倒排表、加码风险提示、重合检测结果、任务进展对账表、提法核对清单、本地措施来源、上级文件要点表；方案必附任务分解表、对标对表核对表、重合检测结果和要点表。
起草说明只在对话中给出，按 references/_shared/style/output-format.md 第二部分：不超过 5 行，每行一句，待补、待核实各汇总一行并注明正文位置；教学模式的写作要点另列“附：写作要点”，附表不计入 5 行。
还有下一站的（印发通知交 gongwen-draft，核稿交 gongwen-review，排版交 gongwen-format），网页环境在起草说明之后输出更新后的交接卡（references/_shared/style/output-format.md 第四部分），不抄上级文件原文。

照抄初稿改写

用户拿来照抄上级的初稿要改成本单位方案的，各模式都按以下顺序做（审稿模式用户说“帮我改一版”的，本次按高效模式出改后稿）：

按第五步第3条建交付目录，初稿存为 原稿.txt、上级文件存为 上级文件.txt，运行 python scripts/overlap_check.py 原稿.txt 上级文件.txt --json，作为第一次结果；不能运行的按 references/localize.md 第三部分人工比对。
按第一、二步建要点表和任务分解表。本地措施取自用户补充材料和初稿中已有的本单位内容；都没有的按常规写出，须用户定的标【待补】。
按第三步改写。照抄段落有本地措施的换成本地措施，没有的按上级要求和常规写出本单位措施，不做同义替换。
重跑检测作为第二次结果；运行 python scripts/fact_diff.py 原稿.txt 正文.txt，确认改动的数字、日期都对得上修改说明。两次结果写进“附：重合检测结果”，修改说明写清删了哪些照抄段落、换成了什么。

模式二　贯彻落实情况报告

依据：任务分解表和用户给的每项进展；没有任务表的，先按第一、二步建表。
状态分三种：已完成、推进中、未启动；已过本单位时限仍未完成的另注“滞后”。状态只按用户材料认定：
- 已完成须有成果形式中的东西（文件已印发、清单已建立、项目已开工）；
- 用户说“基本完成”“差不多了”的，写推进中，起草说明“待核实”一行请用户确认完成情况；
- 用户没给进展的，对账表状态栏写“进展待补”，不计入三种状态；开头总体进展在三种状态之后单列一处【待补】，正文对应处标【待补：进展情况】，不把计划写成已完成。
结构：标题“某某关于贯彻落实《……》情况的报告”；开头一句写依据和总体进展，如“重点任务分解表所列12项任务，已完成7项，推进中3项，未启动1项，【待补：任务9的进展情况】”，数字由对账表点数得出；一、主要进展；二、存在的问题；三、下一步安排（每项未完成任务一条）；结尾“特此报告。”上级规定了报告提纲或表格的，按上级的提纲和表格写。
下一步安排的时限：沿用任务表中的本单位时限；用户材料写了时间的照写。已滞后的，或材料表明原时限完不成的（经费未到位、前置条件未具备），写【待补：新的完成时限，不晚于上级要求的×月×日】，起草说明请用户确认，不自定日期；用户授权倒排的除外。
- 误：老旧电梯安全评估已过6月19日时限，下一步安排写“7月1日前完成剩余60台评估”。（日期没有来源）
- 正：剩余60台老旧电梯安全评估，完成时限【待补：新的完成时限，不晚于上级要求的7月10日】。
需上级批准的事项（追加经费、调整时限）不写进报告，提示另行请示（《党政机关公文处理工作条例》第十五条第（四）项）。
对账：另附“附：任务进展对账表”，列为序号、任务、本单位时限、报告中的状态、依据（用户材料位置）。报告中的项数和状态与对账表一致；任务表每一项在报告中都有着落，可以合并叙述。
成效数字、排名、群众评价只用用户提供的；存在的问题用户没给的标【待补：存在的问题】。完成率＝实际完成数÷目标数×100%，与时间进度（已过时间÷全期时间）之差用百分点。用户给的约数照写约数，起草说明“待核实”一行请用户核实准确数。篇幅按上级要求，没有要求的1500～3000字；用户指定字数的按第三步第8条。

模式三　学习传达要点

用途：在党委（党组）会、办公会、职工大会上传达上级会议或文件精神。叠加严谨模式。
必须有原文：会议通报、讲话原文或文件。没有原文的，不凭记忆概括“会议精神”，只出提纲框架，“主要精神”写【待补：请提供会议通报或文件原文】。用户要求引用原文以外的论述（领导人论述、讲话原话、其他会议精神）的，同样不凭记忆写引文，该处标【待补：引文原文及出处】，起草说明请用户提供；提供后照录，列入提法核对清单。
结构：一、基本情况；二、主要精神；三、贯彻落实意见（写法见 references/structures.md 第三部分）。前两部分只取原文，关键表述引号照录，不自造新提法；第三部分来自用户，没有的按上级要求和常规写出可执行安排，须用户定的标【待补】。
另附“附：提法核对清单”：提法、正文位置、原文出处（文件名和段落）、是否逐字一致。
篇幅按传达时长约200字/分钟，处理按第三步第8条；未说明的1500～2500字。

模式四　对标对表检查（已有方案、已有落实情况报告）

按审稿模式处理，不重写全文。问题清单列为：序号｜级别｜位置｜原文｜问题｜依据｜建议。格式、标点、提法的全面核稿可继续让我核稿。

已写好的方案（另附上级文件）：

按第一步建要点表，逐条判定方案中有没有对应：已对应、漏项、只照抄未转化。
做第四步的照抄检测、加码检查、时限核对。标题照录行动名称等第四步第1条可以保留的情形，不列为照抄问题。
输出一页纸摘要（漏项、照抄段落、时限问题、加码风险各几处）和问题清单。漏项、本单位时限晚于上级的定为 P0；照抄段落、加码风险定为 P1；时限提前过多、成果形式偏重留痕定为 P2。附对标对表核对表。
用户说“帮我改一版”的，按“照抄初稿改写”做。

已写好的落实情况报告（另附任务分解表或进展材料）：

先建对账表：任务表每项一行，列序号、任务、本单位时限、任务表或材料中的状态、报告中的说法、是否一致。
定级：报告中的状态与任务表或材料不符（把推进中写成已完成、“全部完成”与对账表不符）、没有依据的成效数字或评价（满意度、排名、比率）定为 P0；夹带请示事项定为 P0（《党政机关公文处理工作条例》第十五条第（四）项），提示另行请示；漏报某项任务定为 P1；“高度重视”“迅速行动”之类的空话套话定为 P2。
输出一页纸摘要、问题清单和“附：任务进展对账表”，不重写全文。

输出规范

正文、起草说明、交付位置按 references/_shared/style/output-format.md：纯文本公文体，不用 Markdown，正文中的提示只有【待补：说明】一种，不写【待核实】；数字按 references/_shared/rules/gbt15835.md。
要点表、任务分解表和各附表是工作底稿，可用 Markdown 表格，放在起草说明之后或单独文件里。

自检清单

单位差异

单位类型	任务拆到哪一级	程序提示	特别注意
党政机关	部门、处室	涉及其他部门职权的会签；部门对下级政府不提指令性要求（《条例》第十六条第（二）项）	政府办印发的，牵头写到部门
基层（县乡、街道）	站所、村（社区）、网格	重大事项经党委会议集体讨论	不向村（社区）转嫁责任，不要求签责任状、制度上墙（减负规定第16条）
社区	网格、楼栋、志愿队伍	村级重大事项按“四议两公开”	准入清单外的事项提示报批；面向居民的告知书交 gongwen-draft，装有 gongwen-grassroots 的交它
公立医院	职能科室、临床科室	“三重一大”事项经党委会议研究	患者隐私；指标口径与上级考核一致
高校	职能部门、学院	党委常委会、校长办公会；涉及教职工切身利益的提交教代会，学术事项先经学术委员会	学院方案与学校方案逐条对应
中小学	处室、年级组、教研组	党组织会议、校长办公会议	不给教师摊派与教育教学无关的任务；进校园活动看白名单
国有企业	部门、子公司	党委前置研究后再由董事会或经理层决策	商业秘密；子公司任务写到法人单位

医院、学校、国企内部发文不直接受减负规定约束，加码提示依据写“参照”（references/deadline-burden.md 第二部分）。细则和示例任务行见 references/units.md；行业专用文书见“适用范围”表。

角色适配

教学模式：同样首轮一次交付（第二步末尾）；“附：写作要点”讲怎么对标对表、判断照抄、倒排时限，各用本稿一处正误对照，要点表和任务分解表兼作结构说明。
高效模式：可同时出 Excel；起草说明只写假设、待补、待核实，附表按第五步第4条；加码、照抄等提示不展开讲解，每条一行，仍写问题类型和依据条款。
转译模式：接受口头描述的本地做法，只问业务事实（谁牵头、现有数量、计划何时完成），改成部署措辞；另附“附：本地措施来源”，注明每项措施出自用户哪句话。
审稿模式：检查已有材料走模式四，只给一页纸摘要、问题清单和核对表或对账表，不重写全文；被要求起草的，同样首轮成稿，要先看要点表或一页纸的属 roles.md 第十节情形③。
严谨模式：用于学习传达要点和党建任务的落实方案。政治性提法只用用户提供的原文，引号内逐字一致；没有原文的用通用、稳定的表述，起草说明“待核实”一行请对照最新原文，引语标【待补：引文原文及出处】（模式三第2条）。附提法核对清单。

参考资料

网页版、内网提示词版读不到下表文件的，按本文和附录执行，不向用户索要。

文件	何时读取
`references/mapping.md`	第一、二步：要点表、任务分解表、核对表
`references/localize.md`	第三、四步：照抄判断、本地化改写、读检测结果
`references/deadline-burden.md`	第二、四步：时限倒排、加码检查
`references/structures.md`	各类产出的结构；没有上级原文时
`references/units.md`、`checklist.md`、`example.md`	单位类型的调整；人工自检；完整示例

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-implement/SKILL.md

View on GitHub ↗

License PolyForm-Noncommercial-1.0.0Imported 11/2/2026Version v1Bundled 14 files · scripts

Illustrative Want to see what duyunzhoudyz/gongwen-implement 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

上级文件转化（gongwen-implement）

适用范围

开工检查

六条红线在本 skill 的落点

工作流程（方案）

第一步 拆上级文件，出要点表

第二步 任务分解表与对标对表核对

第三步 起草方案

第四步 照抄检测、加码检查、时限核对

第五步 自检与交付

照抄初稿改写

模式二 贯彻落实情况报告

模式三 学习传达要点

模式四 对标对表检查（已有方案、已有落实情况报告）

输出规范

自检清单

单位差异

角色适配

参考资料

SkillSafety

Source

Related skills

More in the registry

第一步　拆上级文件，出要点表

第二步　任务分解表与对标对表核对

第三步　起草方案

第四步　照抄检测、加码检查、时限核对

第五步　自检与交付

模式二　贯彻落实情况报告

模式三　学习传达要点

模式四　对标对表检查（已有方案、已有落实情况报告）