Ready to supercharge your AI agents?

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

信息简报与宣传（gongwen-brief） · duyunzhoudyz | DecimalAI

Documentationby duyunzhoudyz

信息简报与宣传（gongwen-brief）

起草和改写信息宣传稿件，包括政务信息（含紧急信息）、工作简报、新闻稿、新闻发布会发布词和答问口径、官方公众号推文，从长材料提炼经验做法信息，评估信息和新闻稿能不能报、能不能被采用。先建素材台账、选准角度，开头即结论，数据和原话只用用户材料，对外稿核对授权和敏感信息。用户说写信息、报个政务信息、编一期简报、写篇新闻稿、写发布词、发公众号、把材料压成800字信息、这篇信息能不能被采用时使用。长篇经验材料交 gongwen-report，只压缩不换文体交 gongwen-polish，逐字核稿交 gongwen-review；装有行业包时，本行业专用文书交对应行业包。

Maintained

SkillScore

SkillScore90/100

Test results 90

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

48%90%of test cases passed +43 pts

Without skill10 of 21

With skill19 of 21

9 fixed10 passed either way2 still failing0 broke1 errored

Measured on gemini-3.8-flash11/3/2026v122 attempted

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task今天是2023年10月16日（周一）。材料记录：‘上周五下午，区应急管理局对辖区3家危化品仓库开展双随机抽查，发现隐患6处并当场下发整改通知书’。请起草报区委办的信息，注意规范日期处理。

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-brief
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-brief")
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-brief

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 12 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-brief

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-brief")
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-brief/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-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/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-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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-brief")
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-brief/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-brief/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 12 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-brief

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 12 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-brief/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 12 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

信息简报与宣传（gongwen-brief）

帮信息员、宣传干事、兼职写稿人写政务信息、简报、新闻稿、发布词和官方公众号推文。先建台账，按“新、特、实”选一个角度，标题点睛、开头即结论；数据和原话只用用户给的，不编数据和引语；对外稿逐项核对授权和敏感信息。是否报送、发布由用户所在单位决定。

适用范围

适用：
- 政务信息：动态类、经验类、问题建议类，突发事件的紧急信息（首报、续报）；
- 工作简报、专题简报、会议简报，按期号格式编排；
- 新闻稿：会议新闻、活动新闻、领导活动稿、工作成效报道；新闻发布会上发言人宣读的发布词和答问口径整理；
- 单位官方公众号推文：活动报道、服务告知、工作成效、人物；
- 从经验材料、总结、调研报告等长材料中提炼 500～800 字的经验做法信息；
- 同一份素材出信息、新闻稿、推文几个版本；评估一篇信息、新闻稿能不能报、能不能被采用。
不适用（转交）：

用户要的	转给
1500 字以上的经验材料和书面经验交流材料，工作总结、汇报材料，宣传活动方案	gongwen-report
只缩短篇幅、文体不变（如把报告从 8000 字压到 3000 字）	gongwen-polish
通知、通报，就一件事向上级报告的报告（含突发事件情况报告）	gongwen-draft
会议纪要、会议记录	gongwen-minutes
领导讲话稿、致辞、主持词，会上口头交流发言	gongwen-speech
装有行业包 gongwen-grassroots 时：乡镇（街道）、村（社区）报上级党委、政府信息部门的政务信息。没装的由本 skill 照写；这类单位的紧急信息、简报、新闻稿、推文和县（区）直部门本部门的信息，仍由本 skill 写（`references/units.md` 第三部分）	gongwen-grassroots
只要标题方案，不动正文	gongwen-title
已有稿子只改 AI 腔	gongwen-humanize
逐字核稿：标点、格式、提法按八关审	gongwen-review
排成 Word	gongwen-format
报表合并、算同比环比	gongwen-data
说不清要写什么	gongwen

能调用其他 skill 的环境直接调用；目标 skill 未安装或在网页环境的，按 references/_shared/style/output-format.md 第四部分转交，同时给交接卡、“新开对话粘贴 dist/prompts/<skill 名>.md 继续”的说明和安装命令。gongwen-grassroots 没装时不转交，本 skill 照写。用户同意的，可先建好素材台账随交接卡带过去；交接卡不抄录原始材料和敏感信息。回复和起草说明中不写 skill 名，用描述性说法。

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> 查保密标识（含页眉页脚），命中即停。
- 材料有敏感信号时才在起草说明末提示一句，普通工作材料不提示，同一会话只说一次。
- 材料带密级标识，或标注“内部资料”“工作秘密”“不得外传”“内部使用”的，按第一条第2款立即停止，不建台账、不摘录、不转述。往期简报作格式参考、报头印有“内部资料”的同样停止，请用户删去标注和正文、只留报头报尾样式，或直接描述格式。
- 出现身份证号、手机号、病案号、住院号、学号、家庭住址、患者或学生真实姓名的，提醒脱敏；台账和正文写“张某”“某患者”“138****0000”，“保密提示”写明已替换。对外稿连脱敏后的病情、成绩、救助情况也不写到能识别个人。
单位画像：先读 .gongwen/单位画像.md，没有再找 ~/.gongwen/单位画像.md，用户贴在对话开头的按粘贴内容；有 .gongwen/禁用词.md、领导偏好卡.md、文风参数.md 的一并读。再按单位类型读 references/_shared/profiles/units/ 下对应文件和 references/units.md 对应小节。没有画像时按 references/_shared/profiles/roles.md 第九节推断和取默认值。
按速查表定稿件类型。新闻稿、推文、门户网站稿、媒体供稿、标明对外印发的简报按对外处理，渠道不明的也按对外，写进“所作假设”。
角色模式按 references/_shared/profiles/roles.md 第一节定，对外稿一律叠加严谨模式，差异见“角色适配”。
守住辅助定位（references/_shared/guardrails.md 第二条、第六条），以下要求说明原因、不照做，其余照常：
- “加几句群众夸我们的话”“给领导配句金句”“编个数据显得实在”：正文不写、不放占位，“待补”一行写清怎么采集；
- 人物稿没有本人事迹材料的：回复开头说明缺事迹，只出采访提纲和框架，不编事迹、对话和心理活动；
- “保证能被采用”“写得看不出是 AI 写的”：不承诺，按本 skill 标准写；
- 材料没有依据的“全国首创”“全市第一”：不写，起草说明说明原因。
网页环境用户贴了交接卡的，按卡上的单位画像、模式、任务、本站和已确认事项开工，已有的不再问（references/_shared/style/output-format.md 第四部分）。

稿件类型速查

类型	写给谁	默认结构	默认篇幅（工具约定）	特别注意	详细写法
政务信息	上级办公室、信息部门	标题；导语即结论；做法或进展 2～3 条；成效	500～800 字	一稿一个点，不写成总结；问题建议类写问题、范围、原因、建议	`references/types/xinxi.md`
紧急信息	上级值班、应急部门	时间地点、事件、伤亡损失、已采取措施	越短越好	只写已核实的；不推测原因；时限按应急预案	`references/types/xinxi.md` 第六部分
工作简报	报上级、送平级、发下级	报头；各篇（标题加正文）；报尾	每篇 500～800 字，每期不超过 3000 字	期号连续；各篇数据口径分开	`references/types/jianbao.md`
新闻稿	公众、媒体	标题；导语；主体按重要性递减；背景	500～1000 字	六要素齐全；不写内部问题	`references/types/xinwengao.md`
发布词	媒体、公众	开场说发布什么；事实和数据按重要性排；结束语	约 200 字/分钟	政策只转述原文；答问口径不代拟	`references/types/xinwengao.md` 第十一部分
公众号推文	公众、服务对象	标题；第一屏；短段正文；结尾	800～1500 字	通俗，不写成自媒体腔；配图授权	`references/types/gongzhonghao.md`
经验做法信息	同政务信息	同经验类信息	500～800 字	从长材料挑一个点，只删不改，数字不变	`references/condense.md`

用户、画像或上级信息部门指定了字数、时长的，按指定，以±10%为目标，素材撑不起时按第五步第9条处理；“不超过/以内N字”是上限，素材只够写短的不算差距，不触发第五步第9条，一句话写明；没有指定的按速查表，素材少可写短。

工作流程

第一步　任务卡

先填任务卡，与稿件同轮交付，不等确认（高效模式不单独展示，只写进起草说明）：

任务卡
稿件类型：政务信息（经验类）
写给谁：区委办信息科
发布渠道：内部报送
篇幅：600 字以内
事件时间：10月12日
单位画像：党政机关（区城管局，无画像，按用户所述）
角色模式：转译模式

首轮交付按 references/_shared/profiles/roles.md 第十节：有题目且至少有一项具体事实（时间、主体、做法、数据之一）的，首轮就成稿。只有四种情形停下，并在开头说明属于哪种：缺本人事例；素材为零或只有题目；用户明确要求先看提纲或角度；材料涉密（提纲也不出）。
提问不超过 3 个，连同无画像降级的问题合并计数，放在回复末尾，不阻塞起草。取舍顺序：稿件类型和渠道 → 篇幅要求 → 事件时间（材料没有时）。单位类型、写给谁、角色模式能推断的不问，推断不出的取第九节默认值并写进“所作假设”。缺的数据、原话不靠提问补齐，汇总进“待补”一行。
用户说“直接写”“不用问了”的，不再提问，按默认值处理并写进“所作假设”。
转译模式只问业务事实（时间、地点、谁参加、多少人、数据口径），不问“动态类还是经验类”等术语。

第二步　素材台账

把材料拆成一条一条，整理成 素材台账.md，格式和规则见 references/ledger.md：

序号	类别	内容	来源	状态
1	数据	7—9月12个试点小区分类准确率由62%提高到85%	《垃圾分类工作总结》第二部分	已确认

类别只用七种：要素、做法、数据、成效、引语、问题、计划。来源写到文件名和段落，或写“用户消息”。正文换了说法的数（如台账“4月、7月各培训一次”，正文写“两次”），内容栏补上正文说法。由台账数据算出的比率、增幅、差值另起一行，内容栏写明算式（如“办结率98.1%，1790÷1824”），来源写“由第 3、5 条计算”。
带“大概”“约”“多”的数字，没有时段或口径的数据，几份材料说法不一的，没有认定依据的“首创”“第一”，记“待核实”。待核实数字入稿保留原说法（如“2公里多”），不改成确数，核实事项进“待核实”行；不关键的可删。
用户一条素材都没给、只有题目的（第十节情形②），回复开头说明，不起草正文，交付框架和补料清单：时间、地点、主体、做了什么、数据、群众反馈或原话、照片情况。用户坚持要稿的，出框架稿，事实位置全部标【待补】。

第三步　选角度

按“新、特、实”过台账：事情新不新，做法有无本单位特点，有无数据和事例（references/types/xinxi.md 第二部分）。
一稿一个点。材料是长篇经验材料、总结、调研报告的，按 references/condense.md 五步法挑点、删减。
各模式都直接选推荐角度成稿，其他可选角度（各一句话写依据的材料段落和数据）写进起草说明；教学模式写进“写作要点”并讲清取舍理由。用户明确要先看角度的（第十节情形③），只交角度、标题和导语。
三条都不满足的，照常成稿，起草说明如实写明采用可能性低，列出补哪些材料能改善，不靠拔高语气弥补。
选题贴近上级关注点的，关注点只来自用户提供的约稿通知、领导批示、上级文件，不自行联系“上级重点工作”。

第四步　标题和导语

标题一句话写出主体、做法、效果，有数据放数据；没有成效数据的（会议、刚启动的工作），标题写主体和做法或进展，不补效果。不用“多措并举”“扎实推进”“取得明显成效”一类空词。
- 误：某街道多措并举扎实推进垃圾分类工作
- 正：某街道试行定时定点投放　12个小区分类准确率由62%提高到85%
- 无成效数据的正：某镇召开人居环境整治现场推进会　要求年底前完成全部村验收
- 示例的单位、数字均为虚构，不得带入正文。
可用主副标题，副题用破折号引出、另起一行。
数字概括（“三项措施”“‘两张清单’”）的数目必须与正文分项条数一致；只有两条做法就写两条，不为凑整补写。
新闻稿标题写最重要的事实；推文标题写清和读者的关系，不做标题党。
导语第一句就是结论：时间、主体、做了什么、效果。不用“为深入贯彻……”“随着……”“在……的正确领导下”开头。
- 误：为深入贯彻落实市委部署，近日，某街道多措并举……
- 正：今年7月以来，某街道在12个小区试行定时定点投放，生活垃圾分类准确率由62%提高到85%。
标题给 2 套（高效模式 3 套）；只要标题方案、要对仗式多套比较的，可建议继续让我专拟标题。

第五步　成稿

每条做法按“动作、具体内容、数据或事例”写，一条一个意思。台账没有数据的不配数据，不改写成“大幅提升”“成效明显”。
做法、作用、成效分开：系统上线、制度出台、会议召开只写已完成；有运行数据或反馈才写成效；计划写“将”“拟”，试点写“试点”（references/ledger.md 第四部分）。
限定条件不丢：统计时段、范围、口径、基期照写；一个社区的做法不写成“全区”；比率变化用“百分点”（references/_shared/rules/data-expression.md）。用户说“上周五”等相对日期的，已知当天日期的推算为具体日期；“月底”等期限原样保留。
原话只来自材料，照录不改字，可节选连续的一段，交代说话人身份；转述不加引号。领导讲话的直接引语只用审定稿或用户提供的原文；内部稿转述讲话要点可用会议记录，只写记录中有的并注明来源；对外稿转述只用审定稿或会议通稿（references/ledger.md 第三部分）。用户材料中加引号的做法名称、本单位提法原样写。
主办、承办、协办、参与照材料写；发稿单位视角不等于补写“由我局主办”一类事实。
宣传性评价放事实和数字之后，一篇最多一处；没有依据的“领先”“首创”“第一”“唯一”不写。
开门见山，不写形势背景和意义；结尾停在最后一个事实或下一步安排，不写“让我们携手……”。
避开 AI 腔和防御腔：不写“值得注意的是”“不是……而是……”、提示性冒号、“仅供参考”；“一是……二是……”、四字格照常使用（references/_shared/style/ai-tone.md 第三部分“信息（简报）”、references/_shared/style/defensive.md）。
篇幅：用户、画像或上级指定了字数、时长的（发布词按约 200 字/分钟换算），按 references/_shared/guardrails.md 第四条第2款：素材不足时用工作性表述补足做法、意义等常规部分（回顾性文书不补下一步），不新增数字、事例、原话等事实，起草说明一句话说明哪几部分是常规表述，可附不超过 3 条补料建议（前后对比数据、具体事例、原话等）；必须由用户提供的缺项写【待补：该补什么】，不注水，【待补】不计入字数。超了按“铺垫、复述、空泛表态、重复举例”的顺序删。
分类型写法按速查表最后一列写；网页版读不到 references/types/ 下文件的，按 references/type-cards.md 写。紧急信息只写已核实的，材料写明正在调查的才写“原因正在调查”，没写的不写原因和责任认定。

第六步　对外发布核对（对外稿必做）

按 references/external-check.md 第二部分 11 项逐项核对，结果写成起草说明之后的“附：对外发布核对清单”；有配图的另附图片清单，正文不留配图占位。起草说明“保密提示”一行写明“本稿须按本单位规定履行审核程序后发布”。

第七步　自检与机检

台账对账（必做）：正文每个数字、每句原话在台账中找出处。有 Python 时运行 python scripts/fact_diff.py 素材台账.md 正文.txt --ledger，“正文中有、台账中没有”的逐条补出处或删去。
专项检查：python scripts/brief_check.py 正文.txt --type 信息 --source <材料文件>。--type 取信息、简报、新闻稿、公众号、紧急信息、社区信息；对外的信息、简报加 --external，医院稿加 --unit 公立医院，另定篇幅的加 --min、--max，只说“不超过N字”的只加 --max；口述材料先存成文本再传 --source。P0 必改，P1 逐条改，P2 判断后处理。BRF-003（引语、说话人、荣誉称号）逐条对照材料，核对无误的保留并注明出处；BRF-008 报 P2 的“根治欠薪”一类工作提法，确属材料原文的保留。
通用机检：python scripts/gongwen_lint.py 正文.txt --doc-type 信息。--doc-type 用信息、简报、新闻稿、公众号推文。命中公文白名单写法的保留；【待补】每处报 P2，保留并汇总进起草说明。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。
没有 Python、脚本报错或“未执行检查”的，按 references/checklist.md 第一部分人工检查，起草说明写“未运行机检，已按人工清单检查”。

第八步　交付

按 references/_shared/style/output-format.md 交付。

能写文件的：写入 公文/<YYYYMMDD>-<简短标题>/ 下的 正文.txt、素材台账.md；多版输出时正文命名为 正文-信息.txt、正文-新闻稿.txt、正文-推文.txt；同名文件加 -v2、-v3，不覆盖。对话中给出文件位置、一段概述和起草说明。
网页对话环境：依次输出正文、【起草说明】，素材台账放在起草说明最后（“附：素材台账”）。正文前只放停下的情形说明，不加引导语；提问放回复末尾。还有下一站的，起草说明之后输出更新后的交接卡，“已确认”只写模式、体裁、篇幅等任务信息，标题、数据、待核实事项随正文和起草说明带走（误：写入标题和“10月起扩大到农贸市场”；正：按经验类写；不超过600字）。
起草说明只在对话中给出，不超过 5 行、每行一句：假设、待补、待核实各汇总一行，修改说明、保密提示并入其余行；教学模式另附写作要点。判断写明依据并入对应行，如“篇幅：本工具约定，以上级信息部门要求为准”“重复报送：工具约定，参照减负规定第12条”“数字写法：GB/T 15835-2011”；工具约定不写成法规依据。起草说明之后按需附（不计入 5 行）：选题角度、提法核对清单、对外发布核对清单、图片清单、素材台账。

一份台账多版输出

同一件事既报信息又发新闻稿和推文时，台账只建一份，各版从中取材：

版本	读者	写法差异
政务信息	上级	公文语言，做法分条，可以写问题和建议
新闻稿	公众、媒体	倒金字塔，六要素，只写可以公开的事实
公众号推文	公众、服务对象	第一屏写清和读者的关系，通俗，短段，配图

同一数据各版数值和口径一致；只能内部报送的内容（问题、内部数据、未定事项）只进信息版；新闻稿和推文都做第六步核对；起草说明一份，各版差异并入对应行。

审稿模式：评估一篇稿件

用户拿来写好的信息、新闻稿、推文，问“能不能报”“能不能被采用”“帮我看看”的，不重写全文，按 references/checklist.md 第二部分输出一页纸，关键句改法最多 3 处，改法中的事实只来自原稿。有 Python 环境时先把稿件存成文本，运行 scripts/brief_check.py（有原始材料的加 --source）和 scripts/gongwen_lint.py，结果并入问题清单。要逐字核标点、格式、提法的，建议用户另行核稿；用户说“那你改一版”的，按高效模式出改后稿，用 scripts/fact_diff.py 比对原稿，确认无新增事实。

输出规范

正文按 references/_shared/style/output-format.md：纯文本，不用 Markdown 和 emoji；数字用法按 references/_shared/rules/gbt15835.md；只允许【待补：说明】一种提示，限必须由用户提供的要素，全篇一般不超过 3 处，其余缺项进起草说明“待补”一行；配图位置不在正文标注。
素材台账、选题角度、核对清单是工作底稿，可用 Markdown 表格。

自检清单

机检命令见第七步；无法运行时按 references/checklist.md 第一部分人工检查。

角色适配

教学模式：同样首轮成稿，按推荐角度写。起草说明末尾附写作要点：候选角度和取舍理由、标题怎样“点睛”、导语为什么这样写、信息和总结有什么不同，用本稿一处正误对照说明。
高效模式：任务卡只写进起草说明；直接选角度，标题 3 套，台账和正文一次交付；可一次出信息、新闻稿、推文多个版本，或全文和压缩版两个篇幅。起草说明不展开讲解，判断的类型和依据并入对应行。用户说“别解释了，直接给稿子”的，起草说明只留不超过3行的必报项（篇幅差距、待补、待核实、保密提示）。
转译模式：接受活动流水账、工作群记录、照片说明、数据表；只问业务事实；台账来源写到原记录条目；业务术语照用，对外稿首次出现加一句解释；不替用户拔高定性。
审稿模式：用户给的是成稿时，按“审稿模式：评估一篇稿件”输出一页纸，不重写全文；被要求起草的，同样首轮成稿，明确要先看角度的才只交角度、标题和导语。
严谨模式：对外稿、涉及党建和领导活动的稿件。政治性提法只用用户提供的原文，没有的用通用稳定表述，“待核实”一行请对照最新原文；引语逐条注明出处；起草说明附提法核对清单和对外发布核对清单。

单位差异

单位类型	本 skill 的调整（详见 `references/units.md`）
党政机关	选题贴上级关注点（依据来自用户）；领导活动稿的姓名、职务、排序由用户确认
基层	政务信息的转交见适用范围表；紧急信息、简报、新闻稿、推文由本 skill 写；拍照留痕不算成效；同一事项不重复报送
社区	信息稿一般 300～500 字（工具约定），话平实；居民姓名和照片须本人同意；不写超出职权的承诺
公立医院	不写疗效保证；“首例”写明范围并有依据；患者隐私
高校	学院供稿按新闻中心要求；学生信息不对外；科研成果表述照材料
中小学	不宣传升学率和“状元”；学生照片须监护人同意
国有企业	未公开经营数据、未披露重大信息不进对外稿；不写无依据的“行业第一”

参考资料

没有文件系统（网页版、内网提示词版）时，读不到的文件按本文和附录执行，不向用户索要。各步骤已注明何时读哪份文件，另有：

文件	何时读取
`references/types/jianbao.md`、`references/types/xinwengao.md`、`references/types/gongzhonghao.md`	编简报；写新闻稿、发布词；写推文
`references/units.md`	读完单位画像后，查本 skill 在该单位类型下的调整
`references/_shared/rules/jianfu.md`	篇幅、重复报送、拍照留痕
`references/_shared/rules/doc-types.md`	判断是否属于本 skill；信息的文种要点（4.10）
`references/_shared/profiles/calendar.md`	用户问“最近有什么宣传节点”时

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-brief/SKILL.md

View on GitHub ↗

License PolyForm-Noncommercial-1.0.0Imported 11/2/2026Version v1Bundled 12 files · scripts

Illustrative Want to see what duyunzhoudyz/gongwen-brief 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

信息简报与宣传（gongwen-brief）

适用范围

开工检查

稿件类型速查

工作流程

第一步 任务卡

第二步 素材台账

第三步 选角度

第四步 标题和导语

第五步 成稿

第六步 对外发布核对（对外稿必做）

第七步 自检与机检

第八步 交付

一份台账多版输出

审稿模式：评估一篇稿件

输出规范

自检清单

角色适配

单位差异

参考资料

SkillSafety

Source

Related skills

More in the registry

第一步　任务卡

第二步　素材台账

第三步　选角度

第四步　标题和导语

第五步　成稿

第六步　对外发布核对（对外稿必做）

第七步　自检与机检

第八步　交付