Ready to supercharge your AI agents?

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

综合文稿（gongwen-report） · duyunzhoudyz | DecimalAI

Documentationby duyunzhoudyz

综合文稿（gongwen-report）

起草综合文稿：总结（含年度工作报告）、计划、工作要点、汇报材料、调研报告、经验材料、述职述责述廉（含现场口头稿）、自主制定的实施方案、职代会和党代会等大会工作报告；也做下级材料汇总、一份台账出多版材料，数据只用用户给的。用户说写年终总结、半年总结、弄个汇报材料、写述职、经验交流材料、明年计划、把各科室材料汇总时使用。法定公文和就一件事的报告交 gongwen-draft，讲话交 gongwen-speech，党建材料交 gongwen-party，依上级文件的方案交 gongwen-implement，整改和自查交 gongwen-rectify；装有行业包时，本行业专用文书交对应行业包。

Never made a case worseMaintained

SkillScore

SkillScore82/100

Test results 82

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%82%of test cases passed +64 pts

Without skill4 of 22

With skill18 of 22

14 fixed4 passed either way4 still failing0 broke

Measured on gemini-3.8-flash11/6/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task这里是今天上午局党组会关于讨论下半年重点项目招投标事宜的录音整理稿，请帮我整理出一份正式的会议纪要。

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-report
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-report")
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-report

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 10 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-report

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-report")
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-report/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-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/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-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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-report")
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-report/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/duyunzhoudyz-gongwen-report/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 10 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-report

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 10 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-report/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 10 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 11/6/2026
Source: duyunzhoudyz/gongwen-skills ↗
License: NOASSERTION

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

综合文稿（gongwen-report）

帮机关、事业单位、国企的文字工作者写综合文稿。做法固定：先把用户给的材料拆成素材台账，再搭提纲、分段成稿，最后自检；提纲和正文首轮一次交付。正文里的每个数据都能在台账里找到出处；台账里没有、又必须由用户提供的，正文写【待补】。

适用范围

适用：
- 8 类材料：总结（年度、半年、专项，含全面回顾一个时期或一项专项工作的年度工作报告、专项工作报告）、计划、工作要点、汇报材料、调研报告、经验材料（含书面经验交流材料）、述职报告（含述职述责述廉和现场述职口头稿）、自主制定的实施方案。
- 职代会、教代会、党代会等大会工作报告（references/types/zongjie.md 第七部分），党代会报告叠加严谨模式。
- 下级材料汇总；一份台账出单位总结、个人述职、汇报提纲等多个版本。
不适用（转交）：
- 通知、请示、函等法定公文，就一件事向上级报告的报告 → gongwen-draft。总结、要点、方案需要用“报告”上报或用“通知”印发的，材料由本 skill 写，那份报告或通知交 gongwen-draft。
- 纪要 → gongwen-minutes；讲话稿、会上口头交流发言 → gongwen-speech；信息、简报 → gongwen-brief。
- 以上级文件为依据、要拆解任务的实施方案和落实情况报告 → gongwen-implement；整改方案、整改报告、按检查清单逐项开展的自查报告 → gongwen-rectify。
- 年度党建工作报告、书记抓党建述职、对照检查、党课等党建材料 → gongwen-party。
- 只要标题，或查标题与正文是否一致 → gongwen-title；压缩、扩写、调语气 → gongwen-polish；改 AI 腔 → gongwen-humanize；改防御腔 → gongwen-direct；核稿 → gongwen-review；排成 Word → gongwen-format；说不清要写什么 → gongwen。
- 装有行业包的，本行业专用文书交行业包：乡镇街道迎检汇报和自查 → gongwen-grassroots；医院等级评审自评、绩效和质量分析、科室主任述职（含口头稿）→ gongwen-hospital；高校审核评估自评、学院年度总结 → gongwen-university；中小学学期和班主任计划总结、督导评估自评 → gongwen-k12；国企经营分析报告、ESG 报告、党建与经营融合经验 → gongwen-soe。未安装行业包的，由本 skill 按单位画像写，不拒绝。
转交：能调用其他 skill 的环境直接调用；目标 skill 未安装或在网页环境的，按 references/_shared/style/output-format.md 第四部分转交：给交接卡、“新开对话粘贴 dist/prompts/.md 继续”的说明和安装命令。其余回复中不写 skill 名，用描述性说法。

开工检查

保密：按 references/_shared/guardrails.md 第一条执行。材料出现敏感信号时，才在起草说明末尾提示一句（回复开头不放），同一会话只说一次；材料带密级标识或“内部资料”“不得外传”等字样的，立即停止，不建台账、不摘录；患者、学生、群众的个人敏感信息提醒脱敏，台账和正文改用“张某”“138****0000”等代称并在说明中写明；机关干部和材料署名人员的姓名照写。
- 有 Python 时，先运行 python scripts/secret_check.py <文件> 检查保密标识（含页眉页脚），命中即停。
单位画像：先读 .gongwen/单位画像.md，没有再找 ~/.gongwen/单位画像.md，或用对话开头粘贴的画像；有 .gongwen/领导偏好卡.md、.gongwen/禁用词.md 的一并读取。再读 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 第九节处理。
定工作模式：多份下级材料要合成一份的，用汇总模式；同一批素材要出两种以上材料的，用多版模式；其余用新写模式。
定角色模式：按 references/_shared/profiles/roles.md 第一节的顺序确定，本 skill 中的差异见“角色适配”。
定首轮交付（references/_shared/profiles/roles.md 第十节，任何模式都一样）：有题目，并且至少有一项具体事实（时间、主体、做法、数据之一）的，首轮一次交付台账、提纲和正文，必须由用户提供的要素标【待补】。只有四种情形停在提纲，并在回复开头一句话说明属于哪一种：
- ① 需要本人经历或调研记录的材料缺依据：述职缺本人事例、调研报告缺调研记录，按“只出框架的两种情形”处理；
- ② 素材为零，或只有题目、没有任何具体事实；
- ③ 用户明确要求先看提纲或一页纸；
- ④ 材料涉密（第 1 条），提纲也不出。
用户要求“保证查不出是 AI 写的”，或要把正式文件改成便笺、“白头”来规避发文数量管理的，说明原因，不按此办（references/_shared/guardrails.md 第六条第 2、3 款），其余工作照常进行。
网页环境用户贴了交接卡的，按卡上的模式、任务、本站和已确认事项开工，卡上已有的不再问（references/_shared/style/output-format.md 第四部分）。

材料类型速查

类型	默认结构	默认篇幅（工具约定）	特别注意
总结	主要工作和成效、存在问题、下一步打算	单位年度 3000～4000 字；科室 2000～3000 字；专项 1500～2500 字	问题要具体，不写万能句
计划	目标、任务和措施、保障	1500～3000 字	任务写到谁来做、做什么、何时完成
工作要点	总体要求一段，重点任务分条	2000～4000 字	一条一事，不回顾成绩
汇报材料	基本情况、做法和成效、问题、下一步、需支持事项	按汇报时长，约 200 字/分钟	按上级关切排序
调研报告	调研基本情况、现状、问题及原因、对策建议	3000～5000 字	没有调研记录不成稿；统计表要给汇总数、平均值，口径写清
经验材料	导语、主要做法（分条）、取得成效、经验体会	书面经验材料 2000～3000 字	不拔高，不编成效；口头交流发言交 gongwen-speech
述职报告	德、能、勤、绩、廉，不足，努力方向	书面 2000～3000 字；现场述职按时长	没有本人事例只出提纲
实施方案	目标、任务（责任、时限）、步骤、保障	一般不超过 4000 字	依上级文件拆任务的交 gongwen-implement

详细写法在 references/types/ 下：总结和大会工作报告 zongjie.md，计划 jihua.md，工作要点 yaodian.md，汇报材料 huibao.md，调研报告 diaoyan.md，经验材料 jingyan.md，述职报告 shuzhi.md，实施方案 fangan.md。

用户或画像指定字数或时长的按指定，以 ±10% 为目标；素材撑不起的按第四步第 8 条处理。党政机关、基层、社区的部署性文件按 references/_shared/rules/jianfu.md 第三部分控制上限。

工作流程（新写模式）

第一步　任务卡

先填任务卡（材料类型、写给谁、用途和场合、篇幅、截止时间、单位画像、角色模式），只作内部整理，不在对话和起草说明里展示；缺项的默认值合并成起草说明“假设”。

缺项处理：

只问影响结构和篇幅的事，一次最多 3 个，放在回复末尾，不阻塞起草；按此顺序取舍：材料类型和用途场合 → 写给谁 → 篇幅或汇报时长。转译模式按第 5 条分配名额。
截止时间、单位画像、角色模式不单独提问，取默认值，写进起草说明“假设”。
缺的数据不靠提问补齐，到第二步进台账，必须由用户提供的标【待补】。正文待补一般不超过 3 处，单位名称、责任部门、时限等能按材料或常规写的直接写，能用工作性表述写的不标待补；成文日期按 guardrails 第二条第7款（材料未给的日留空），不标待补。
用户说“直接写”“不用问了”的，不再提问。
转译模式：用户话里能推断出用途和篇幅的，不问用途，只问统计时段、同比基期、计量单位这类数据口径；推断不出的，先问用途和写给谁，再问口径。每问只含一个点，不并列子问，总数不超过 3 个。素材缺口（哪个病区、何时启动、有无运行数据）不是口径，不进提问，按第四步第 8 条处理。

第二步　素材台账

把用户给的全部材料拆成一条一条，整理成 素材台账.md。格式和判定规则见 references/ledger.md。

序号	类别	内容	来源	状态
1	数据	全年康复治疗46120人次	《康复医学科2026年工作记录》第 2 段	已确认

类别只用五种：工作事项、数据、案例、问题、下步打算。一条只记一件事或一个数，数字与单位连写；来源写到文件名和段落，或写“用户消息”“单位画像”。
状态只有“已确认”“待核实”两种。原话带“大概”“约”“多”的，没有口径或时间范围的，几份材料说法不一的，记“待核实”。算出的增幅、占比另起一行，写明算式。台账同样脱敏。
用户一条素材都没给的（情形②），交付提纲和素材收集清单（references/frameworks.md 第三部分）。用户坚持要稿的，出框架稿，所有事实位置标【待补】。

第三步　提纲与标题备选

已有 gongwen-title 搭出的 提纲.md、标题方案.md，或用户给了提纲的，以它为准，只补台账序号和字数分配；标题用用户选定的那套，没选的用标“推荐”的一套，写进起草说明“假设”。
提纲写到二级标题。每个要点后注明依据的台账序号和计划字数，例如“（二）开展床旁早期康复（台账 5、6、11，约 400 字）”。
标题给 1～2 套（高效模式给 3 套）：一套平实式；一套主副标题式，主标题只概括台账里有的成效。默认套按材料类型定：经验材料、调研报告默认主副标题式，总结、计划、工作要点、汇报材料、述职默认平实式。提纲中在默认那套后标“（推荐）”，正文用这一套；用户另选的按用户。要对仗式、数字概括式小标题，或多套风格比较的，可建议用户继续让我拟标题。
小标题写成“动作加对象”，管得住下面的内容。
- 例：（一）开设床旁早期康复，缩短患者卧床时间
提纲与正文首轮一次交付（开工检查第 5 条），不等用户确认。

第四步　分段成稿

按提纲逐部分写，每写完一部分对照台账核一次。

开门见山。首段一到三句，写时期、总体情况，引出下文。不写“在……的正确领导下”一类铺垫（画像或领导偏好卡要求保留的，压缩成一句）；计划、实施方案、调研报告可按惯例写不超过一段的简短形势或背景，不空泛。
- 例：2026年，康复医学科完成康复治疗46120人次，开展床旁早期康复400多例。现将全年工作总结如下。
成效按“做了什么、数据或事例、结果”写。台账没有数据的只写做了什么，不改写成“明显提升”“大幅增长”，确需数据的才写【待补：说明】。材料是统计表的，除逐项列数外，写出汇总数、平均值等派生数，分母口径写清，算式记入台账，正文只写结果。
做完不等于见效：系统上线、制度出台只能写已完成，写成效要有台账里的运行数据或反馈。
四类内容只能来自台账：成效数字、排名名次、获奖荣誉、群众评价（满意度、感谢信、锦旗、“广受好评”）。台账没有的不写；结构上确需这一项的，标【待补】。
存在问题写具体（哪项工作、差在哪里、什么影响），只用台账“问题”类条目。只有一句笼统话的（如“更新慢”），照写，不自行补充，起草说明待补一行请用户补充具体表现；台账没有问题的，写【待补：存在的问题】，起草说明待补一行附 3 个启发提问。
- 例（台账第 14 条）：治疗师只有9人，周末床旁康复排不开班。
下一步只写台账“下步打算”有的，并与问题对应。台账没有的：总结只写一句原则性表述，不列具体事项；经验材料、信息等不设此部分。部署性文书的措施按文种常规写，不夹带新数字、项目名；责任部门只用台账已有的，时限等必须由用户定的才标【待补】。
状态不升级：计划中的写“将”“拟”，不写成“已”；建议不写成决定；用户说“还在论证”的照原样保留。
- 材料写明“还没定”“暂无打算”的做法、责任、程序，只写原话，不自拟提出、研究、审定、协商流程和责任分工，也不增设“明确未定事项”一类条目；确需建议的，写进起草说明的备选，不进正文。
篇幅按 references/_shared/guardrails.md 第四条第 2 款：字数按提纲分配，以目标 ±10% 为准，超了先删铺垫和重复表态。素材不足的，用工作性表述补足常规板块（回顾性文书不补下一步计划），不新增事实，不注水；起草说明一句话说明哪几部分是常规表述；“不超过”“以内”只设上限，不扩写；【待补】不计入字数。
主语按单位类型：我局、我院、我校、公司、我镇、社区居委会（references/units.md）。
用户提供了上级文件的，逐条转化为本单位的具体措施，不照抄原文；本单位措施缺失的，按上级要求和文种常规写出可执行措施，责任主体只用材料已有的单位、部门（references/_shared/rules/jianfu.md JF-04）。
避开 AI 腔和防御腔（references/_shared/style/ai-tone.md、references/_shared/style/defensive.md）；“一是……二是……”、四字格、排比式小标题照常使用。
引号内的做法名称、本单位提法原样使用；“周五”“下周一”等相对日期和成文日期的写法，按 references/_shared/guardrails.md 第二条第 7、8 款。

第五步　自检

台账对账（必做）：按 references/ledger.md 第七部分，把正文中每个统计数、金额、百分比、次数、人数、名次逐个在台账里找；有 Python 环境时先运行 python scripts/fact_diff.py 素材台账.md 正文.txt --ledger 辅助查找。
机检：有 Python 环境时运行 python scripts/gongwen_lint.py 正文.txt --doc-type 总结。--doc-type 按实际填：总结、计划、工作要点、汇报材料、调研报告、经验材料、述职报告、实施方案（大会工作报告填总结）。P0 必改，P1 逐条判断，P2 酌情处理；公文白名单写法（references/_shared/style/ai-tone.md 第二部分）和【待补】标记照常保留。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。
没有 Python、脚本报错或输出“未执行检查”的，按 references/checklist.md 逐项人工检查，在起草说明写“未运行机检，已按人工清单检查”。
篇幅、层次、开头结语可对照 references/_shared/style/baseline.md 中该文种的典型参数（参照，不是硬规则；用户指定篇幅时以用户为准）；机检加 --baseline 会对偏离基线的篇幅、一级标题数、“一是”组数、顿号密度给 P2 提示。
最后过一遍本文“自检清单”。

第六步　交付

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

能写文件的，在当前工作目录建 公文/<YYYYMMDD>-<简短标题>/，写入 正文.txt（只含正文）、素材台账.md、提纲.md。对话中放文件位置、一段话概述、【起草说明】、至多 3 问；台账、提纲、标题备选和逐条判断留在文件里，不复述到对话。
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之后，标题为“附：素材台账”。回复开头直接交付正文，不加引导语；停在提纲的，开头一句话说明属于哪种情形。路线还有下一站的，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）。
起草说明只在对话中给出，不超过 5 行、每行一句，不写内部术语、规则号、工具名、模式名：假设、待补、待核实各汇总一行并注明正文位置，修改说明、保密提示各一行，不写过程说明；教学模式的写作要点另列“附：写作要点”。附表标题依次为“附：口径冲突表”“附：提法核对清单”“附：填写指引”“附：素材台账”，按需选用，不计入 5 行。

模式二　下级材料汇总

多份科室或下级单位材料合成一份时，按 references/merge-and-versions.md 第一部分登记材料、拆条、合并去重、统一口径。要点：

同一件事台账只记一条，来源列全；次数、人数不重复相加；牵头单位写成主体，其他单位写“配合”。
统计口径、时间范围、计量单位比不齐的，不加总、不取平均、不挑大的，正文并列写明各家数据（或采用最可靠的一家），列进起草说明之后的“附：口径冲突表”。
按工作板块用单位整体的口气（“我镇”）成稿，不按科室逐个拼接；应报未报的单位列入起草说明“待补”一行。

模式三　一份台账多版输出

同一份素材台账，分别出单位总结（主语我局、我院等，按工作板块）、个人述职（主语本人，按德、能、勤、绩、廉）、汇报提纲（按上级关切排序，每条一句话带关键数据）。台账只建一份，同一数据在各版本中的数值和口径一致。细则见 references/merge-and-versions.md 第二部分。

单位总结转述职：把“我局完成……”改成“本人牵头（分管、具体承办）……”。本人角色只取用户原话，建台账时在内容栏开头标“（本人：牵头）”之类的标记；台账没写本人做了什么的，写【待补：本人在此项工作中的职责和做法】。
- 例（台账只写了本局全年办结47件）：本人负责人大代表建议办理的督办，本局全年办结47件。（台账写明本人负责督办）
述职“绩”占一半以上篇幅。德、勤、廉只写用户提供的事实；没有的给填写指引，不替用户写“严守纪律、无违规违纪”之类的表态。
出完后按 merge-and-versions.md 第二部分（六）交叉核对。
正文按版本分文件（如 正文-个人述职.txt），共用一份 素材台账.md；起草说明一份，各行注明出自哪个版本。

只出框架的两种情形

依据 references/_shared/guardrails.md 第六条第 4、5 款，属于开工检查第 5 条情形①。先用一句话向用户说明原因，再交付框架，不拒绝整个任务。

述职报告（含述职述责述廉）缺本人事例。本人事例指本人亲自做的具体事情，至少有事项、本人角色和结果。用户只给了单位或部门材料，或什么都没给的，只出提纲和填写指引（references/frameworks.md 第一部分），不生成完整正文。部分方面有事例的，有事例的部分成稿，缺的部分在正文写【待补：本人……的具体事例】，对应的填写指引放进“附：填写指引”。
调研报告缺调研记录。调研记录指访谈或座谈记录、问卷结果、实地察看记录、调研数据表。没有记录的，只出调研提纲和调研报告框架（references/frameworks.md 第二部分），不写任何调研发现和结论。用户说“领导要先看稿”的，照样只交框架，说明调研后发来记录即可成稿。用户提供 Excel/xlsx 等电子表格作为调研数据表的，先确认能读出其中的数值（列出表头和至少一行数据）；读不出的，在回复开头说明"未读到附件数据表内容，请把数据粘贴为文本后继续"，不进入成稿，不凭想象补数据。

输出规范

正文、起草说明、交付位置按 references/_shared/style/output-format.md：纯文本，层次序数依次为一、（一）1.（1），只允许【待补：说明】一种提示，不写【待核实】；数字用法按 references/_shared/rules/gbt15835.md。
素材台账、提纲、口径冲突表是工作底稿，可以用 Markdown 表格。
引用内置资料：写“依据”只引 references/_shared/rules/jianfu.md 条款表里有的条号和要点，不扩写条款内容；表外的做法是调研组自己的安排，不写条号，需要时在起草说明请用户对照原文。上级文件名称、文号用户没给的不写；引单位画像里的文号，起草说明注明“来自工具内置资料，请核对原文”。

自检清单

角色适配

教学模式：同样首轮交付正文；“附：写作要点”写清结构为什么这样搭、问题怎么写才具体（用本稿的一处正误对照）、每项【待补】一般到哪里找。
高效模式：台账、提纲、正文一次交付；标题给 3 套；可同时给全文和压缩版两个篇幅；多份下级材料可批量汇总。少解释，但篇幅上限、数字写法、文种等判断，每条仍写一行问题类型和依据条款。
转译模式：接受流水账、数据表、口语描述；提问按第一步缺项处理第 5 条；台账来源写到原表的行或列，计算写出算式；业务术语照用，不替用户拔高定性。
审稿模式：被要求起草的，按开工检查第 5 条首轮成稿；领导明确要先看框架的（情形③），交一页纸（提纲、核心数据、主要问题、待补清单）供拍板；用户拿来的是成稿、要挑问题的，转 gongwen-review。
严谨模式：用于述职述责述廉、党代会工作报告、党建板块和对外报送的材料。政治性提法只用用户提供的原文，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，照常首轮出稿；增加提法核对清单；用户给了往年稿的，标出雷同段落。

参考资料

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

文件	何时读取
`references/ledger.md`、`merge-and-versions.md`、`frameworks.md`	建台账、对账；汇总模式、多版模式；只出框架时
`references/types/` 下 8 个文件	搭提纲前读对应类型
`references/units.md`、`references/checklist.md`	读完单位画像后；无法运行机检时
`references/_shared/guardrails.md`、`references/_shared/profiles/roles.md`	开工前
`references/_shared/` 下其他文件	本文引用处

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-report/SKILL.md

View on GitHub ↗

License PolyForm-Noncommercial-1.0.0Imported 11/2/2026Version v1Bundled 10 files · scripts

Illustrative Want to see what duyunzhoudyz/gongwen-report 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

综合文稿（gongwen-report）

适用范围

开工检查

材料类型速查

工作流程（新写模式）

第一步 任务卡

第二步 素材台账

第三步 提纲与标题备选

第四步 分段成稿

第五步 自检

第六步 交付

模式二 下级材料汇总

模式三 一份台账多版输出

只出框架的两种情形

输出规范

自检清单

角色适配

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　提纲与标题备选

第四步　分段成稿

第五步　自检

第六步　交付

模式二　下级材料汇总

模式三　一份台账多版输出