Ready to supercharge your AI agents?

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

YQ Article Style Imitation · ethanyoq | DecimalAI

Marketingby ethanyoq

YQ Article Style Imitation

Use when asked to study any writer or author, imitate article style, directly mimic a living or historical writer's prose style when requested, revise an imitation draft, or adapt Chinese articles for WeChat or Xiaohongshu.

Never made a case worse

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

45%77%of test cases passed +32 pts

Without skill10 of 22

With skill17 of 22

7 fixed10 passed either way5 still failing0 broke

Measured on gemini-3.6-flash8/7/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI want to draft a commentary piece in the style of a prominent columnist using their encyclopedia profile page, a short news mention about them, and a third-party interview where they were questioned. Should we proceed directly to drafting the style analysis?

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 ethanyoq-yq-article-style-imitation
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("ethanyoq-yq-article-style-imitation")
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 ethanyoq-yq-article-style-imitation

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/ethanyoq-yq-article-style-imitation/SKILL.md https://app.decimal.ai/s/ethanyoq-yq-article-style-imitation/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/ethanyoq-yq-article-style-imitation/SKILL.md

This gets SKILL.md only. The skill's 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/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/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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("ethanyoq-yq-article-style-imitation")
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/ethanyoq-yq-article-style-imitation/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/ethanyoq-yq-article-style-imitation/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 6 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 ethanyoq-yq-article-style-imitation

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/ethanyoq-yq-article-style-imitation/SKILL.md https://app.decimal.ai/s/ethanyoq-yq-article-style-imitation/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/ethanyoq-yq-article-style-imitation/SKILL.md

This gets SKILL.md only. The skill's 6 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/ethanyoq-yq-article-style-imitation/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/ethanyoq-yq-article-style-imitation.json

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/7/2026
Source: ethanyoq/skill-hub ↗
License: MIT

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

YQ Article Style Imitation

Core Principle

Build a reusable article-writing skill, not a project agent. The skill's job is:

collect reference writing,
deconstruct the writer's expression DNA,
draft or repair an imitation article,
adapt the repaired draft for WeChat or Xiaohongshu.

Do not let evidence-register language, risk-gate language, or workflow labels leak into the article. Do not draft from vibe memory, author profiles, interviews about the author, book pages, encyclopedia pages, or generic genre labels. Do not treat search results as sources. A result becomes a source only after the page is opened, readable text is available, and the usable text is saved or otherwise recorded in the run.

When the user explicitly requests direct style imitation, use direct imitation mode for any named writer or author. The target can be living, historical, Chinese, non-Chinese, professional, literary, journalistic, online-native, or self-provided. Chai Jing, Mao Ni, and He Caitou are examples, not limits.

Borrowing from the Nuwa-style distillation pattern, treat the task as "distill how this writer writes," not "repeat what this writer said." Extract the writer's observable expression DNA: narrative mechanics, tonal temperature, paragraph rhythm, sentence functions, question movement, evidence handling, judgment timing, image system, humor or restraint, and ending shape.

Do not downgrade direct imitation into generic "mechanism transfer" unless the user asks for mechanism transfer. The boundaries below prevent plagiarism, false attribution, and process leakage; they are not a ban on direct style imitation.

If older project artifacts conflict with this skill, treat only those lower-priority artifacts as stale. Current system, developer, platform, legal, and user instructions always take precedence; this skill must never reclassify a higher-priority rule as stale. Within those boundaries, direct imitation is allowed when the user explicitly requests it.

Required Workflow

Source fetch log: search, open, and record candidate pages before they enter the corpus. Mark inaccessible, 404, login-blocked, snippet-only, or off-target pages as rejected.
Reference corpus: collect title, author, URL/source, date, source role, source grade, access status, text availability, local text path, authorship evidence, accepted use, and selection reason. Keep URLs in the corpus only.
Author-source validity gate: before style teardown, prove that each primary style source is readable text written by the target writer. If there are not enough author-written primary sources, stop and report the source gap instead of drafting.
Style-source / fact-source separation: style sources do not need to match the article topic. Fact sources must support the topic's claims. Do not reject a valid target-writer text because it is about a different topic.
Expression-DNA teardown: analyze opening, scene density, paragraph rhythm, sentence functions, question movement, image system, humor/restraint, evidence handling, judgment timing, ending, and taboo patterns. Every style claim must cite valid primary source IDs and the local text used.
Evidence ledger: collect facts, sources, uncertainty, and verification paths. Keep links and formal labels here.
Mode selection gate: default to essay, commentary, reflective narrative, or other form implied by the reference sources. Use documentary reportage or pseudo-documentary/literary reportage only when the user asks for it or provides interview/case material.
Evidence-to-prose translation: turn evidence into natural narrative sentences before drafting.
Imitation draft: write in the requested reference style. If the user named a writer and asked to imitate, directly imitate that writer's style, including for living writers. Use new facts and new wording.
Point-of-view continuity gate: keep the article inside the subject's world; do not switch into "how to write/investigate this article" meta-commentary.
Imitation repair gate: check the draft for source leakage, AI/report language, fake interviews, meta-writing leakage, style decay, and weak ending.
Platform pattern check: before WeChat/Xiaohongshu adaptation, read references/platform-patterns.md and identify what evidence level supports the platform rules being used.
Platform adaptation: only after the imitation draft passes the repair gate and platform pattern check, adapt to WeChat and/or Xiaohongshu.
Independent review swarm: before release, spawn independent reviewer agents. The drafting agent cannot approve its own source quality, style fidelity, or publication readiness.
Final release audit: run the review artifact validator. If any independent reviewer returns REVISE or BLOCK, stop, repair the run package, and repeat the relevant review.

Independent Review Swarm

Use Nuwa's review pattern: Python scripts catch mechanical failures; independent agents catch judgment failures. Do not replace reviewer agents with the drafting agent's own checklist.

Before publishing or platform adaptation, create reviews/ inside the run directory and ask independent agents to write separate review files. Give each reviewer only the run package and the criteria below, not the drafting conversation. If subagent tooling is unavailable, run separate zero-context review passes and save their outputs in the same files.

Required reviewers:

Reviewer	Output file	Review focus	Must inspect
Source auditor	`reviews/01-source-audit.md`	Whether accepted style sources are author-written, readable, substantial, and correctly graded	`source-fetch-log.md`, `style-reference-corpus.md`, `raw-sources/`
Style auditor	`reviews/02-style-audit.md`	Whether the teardown actually supports the draft, and whether the draft decays into generic reportage, AI language, or platform copy	`style-mechanism-breakdown.md`, `imitation-draft.md`, accepted raw sources
Fact auditor	`reviews/03-fact-audit.md`	Whether factual claims in the draft are supported, overclaimed, or missing uncertainty	`evidence-ledger.md`, `imitation-draft.md`
Platform auditor	`reviews/04-platform-audit.md`	Required only when WeChat/Xiaohongshu drafts exist; checks platform adaptation against sourced platform patterns rather than generic memory	`references/platform-patterns.md`, platform drafts, platform notes

Each review file must include:

reviewer_role: one of source-auditor, style-auditor, fact-auditor, platform-auditor
verdict: PASS, REVISE, or BLOCK
checked_files: concrete files inspected
critical_findings: concrete issues or none
required_changes: exact changes required before release, or none
independence_note: confirm this was a separate review pass, not approval by the drafting agent

Reviewer standards:

PASS: no blocking issue; minor notes may remain.
REVISE: article can be repaired without rebuilding the corpus.
BLOCK: source corpus, teardown, evidence base, or platform basis is invalid; drafting must stop until the upstream package is fixed.

The main agent must summarize reviewer disagreements and resolve them by evidence, not by majority vote. One BLOCK is enough to stop release.

Author-Source Validity Gate

Direct imitation requires primary style sources. A primary style source is a complete or substantial text written by the target writer: article, essay, column, book excerpt, novel chapter, speech transcript authored by the writer, or an authorized/reposted text with a clear byline and provenance.

These may support background only, never style imitation:

encyclopedia pages, author profiles, book pages, bibliography pages;
news reports about the writer;
interviews where the writer is the subject but not the author;
reviews, summaries, biographies, introductions, or platform metadata;
short quotes detached from the surrounding article.

For each target writer, collect at least two primary style sources before drafting unless the user explicitly approves a smaller corpus. If no valid primary style source is available, stop with a source-gap note. Do not fill the gap with "reportage style," "novel style," or memory of the writer.

Reposts can be valid style sources. Do not reject a page merely because it is hosted by a third-party site such as a medical, media, blog, or archive site. Judge it by access, readable text, byline/provenance, and whether the text itself is substantial.

Use source grades:

A: first-party source, official archive, official account, or formal publication excerpt.
B: third-party repost with clear byline/provenance and readable substantial text.
C: search result, snippet-only page, unstable page, unclear byline, or incomplete text.
D: background-only page such as encyclopedia, author profile, book metadata, interview about the writer, review, or summary.

Only A and B can be accepted for style. C and D can never justify style teardown.

Corpus rows must include:

source_id
target_writer
role: primary-style-source or background-only
source_grade: A, B, C, or D
access_status: ok, blocked, 404, login-required, snippet-only, or equivalent
text_available: yes or no
local_text_path: path to the saved readable text used for teardown
title
byline / author
URL or local path
date if available
authorship evidence
accepted_for: style, background, fact, or rejected
why selected
what style behavior it can teach

If a source is reposted, state why the authorship is still credible. If authorship is unclear, mark it background-only.

Teardown Traceability Gate

Do not write generic teardown bullets such as "纪实观察向" or "长篇叙事向" unless each point is anchored to primary source IDs.

Every style observation must name:

the supported behavior;
the source IDs supporting it;
where it appears in the text: opening, transition, paragraph rhythm, evidence move, judgment timing, or ending;
one taboo: what not to copy or overdo.

If the teardown cannot point back to author-written texts, the imitation draft is not allowed.

Before drafting, run:

python "<skill>/scripts/validate_style_run.py" <run-directory> --target-writer <writer-name>

Fix any failures before writing the imitation draft. Then run the source auditor. Do not let the drafting agent certify its own corpus.

Form And Interview Mode

A writer's style is not synonymous with one genre. Many writers work across essays, columns, talks, interviews, fiction, newsletters, posts, book chapters, and reportage. Match the form implied by the selected primary sources and the user's request.

Default:

If the user asks only for "仿[某作家]文风", do not assume first-person reportage, fiction, commentary, or any other single genre.
Do not invent real interviews, real observed scenes, or first-person reporting claims.
Avoid lines like 我问他, 他说, 后来他告诉我, or 他对我说 unless they come from user-provided case notes, real interviews, or explicit pseudo-documentary mode.

Allowed when explicit:

If the user asks for 纪实, use real interview/case/source material only.
If the user asks for 伪纪实文学 or 伪纪实, a composite fictional scene is allowed, but do not imply it is a real interview or real reported event.
In pseudo-documentary mode, prefer third-person composite narration over fake first-person reporting.

Hard Boundaries For Published Drafts

Article drafts must not contain:

naked URLs, markdown links, or 来源: inline source labels;
workflow labels such as 已知事实, 候选假设, 验证路径, 风险门, 质量评分;
audit/report endings such as 这也是这篇文章目前能走到的边界;
generic AI phrases such as 根因, 写死, 清楚、可查、负责任, 在患者的经验里;
meta-writing or investigation-method commentary such as 所以，写..., 这篇文章, 本文, 如果要把它查清楚, 不能从...这个大词开始, 最危险的是;
fake interview/reportage signals such as 我问他, 后来他告诉我, or unsourced direct quotes when no interview/case source exists;
a final section named Safe Publication Notes, Quality Score, or similar process metadata.

Keep these in companion files, not the publishable article:

source URLs;
fact labels;
uncertainty notes;
medical/legal/compliance caveats;
quality scores;
publishing risk notes.

Evidence-To-Prose Rule

Evidence must enter the article as narration, not citation scaffolding.

Bad:

国家医保局说... 来源: https://...

Better:

后来我查到一段官方表述。它没有说医院不能再用原研药。它说的是，协议之外，医疗机构仍然可以选择非中选产品。

Bad:

已知事实是...

Better:

到这里，能确认的事情其实不多。政策不是一句话，医院也不是一个窗口。

Point-Of-View Continuity Rule

The publishable article must stay inside the article's object-level world: people, scenes, institutions, products, decisions, and consequences.

Do not switch into the writer's backstage view:

how to write this topic;
how to investigate this topic;
what this article can or cannot prove;
what a reporter should verify next.

Bad:

所以，写"消失的进口药"，最危险的不是提出疑问。

Better:

可那个站在窗口前的人，并不是在问一个品类。他问的是这一盒药，今天为什么不在这里。

Bad:

如果要把它查清楚，不能从"进口药"这个大词开始。

Better:

问题一旦落到这一盒药上，就变小了，也变清楚了：哪一个药名，哪一个厂牌，哪一个规格，哪一家医院，哪一天。

Verification paths belong in the evidence ledger. In the article, turn them into scene-bound questions a person in the story would naturally ask.

Imitation Repair Gate

Before platform adaptation, run:

python "<skill>/scripts/lint_article_style.py" <article-draft.md>

If it reports issues, revise the imitation draft first. Do not proceed to WeChat/Xiaohongshu adaptation until the draft is clean or each issue is explicitly justified.

Then manually check:

Does the first half and second half sound like the same writer?
Did policy/data paragraphs remain narrative?
Is the ending earned by the scene, not pasted from a report?
Does the article hide its scaffolding?
Does every paragraph stay inside the subject's world rather than explaining the author's writing or investigation method?

After this self-check, run the style auditor and fact auditor. The self-check is only a preparation step; it is not release approval.

For final release, run:

python "<skill>/scripts/review_style_run.py" <run-directory>

If platform drafts are included, require platform review:

python "<skill>/scripts/review_style_run.py" <run-directory> --require-platform-review

This script only validates that independent review artifacts exist and that no REVISE or BLOCK verdict remains. It cannot judge literary quality by itself; the independent reviewer agents do that work.

Platform Adaptation

Read references/platform-patterns.md and references/platform-adaptation.md only after the imitation draft passes the repair gate.

If current platform examples or accessible source material are insufficient, state the source gap in the platform draft notes instead of inventing platform rules.

Default:

WeChat: deeper, complete, restrained, credibility-first.
Xiaohongshu: shorter, visual, scenario-led, still not traffic-style.

References

references/style-workflow.md: detailed collection, teardown, drafting, and repair workflow.
references/platform-patterns.md: evidence-backed platform differences and source caveats.
references/platform-adaptation.md: WeChat and Xiaohongshu conversion rules.
scripts/validate_style_run.py: mechanical check for separate output files, source access fields, local source text, valid primary author-written sources, source-ID traceability, and fake interview signals.
scripts/lint_article_style.py: mechanical scan for URLs and AI/report-language leakage.
scripts/review_style_run.py: mechanical check that independent source, style, fact, and optional platform reviews exist, use explicit verdicts, and contain no unresolved release blockers.

About this skill

Automatic

Writing & Editing pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ethanyoq / skill-hub

skills/08-writing-marketing/yq-article-style-imitation/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 6 files · scripts

Illustrative Want to see what ethanyoq/yq-article-style-imitation 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

YQ Article Style Imitation

Core Principle

Required Workflow

Independent Review Swarm

Author-Source Validity Gate

Teardown Traceability Gate

Form And Interview Mode

Hard Boundaries For Published Drafts

Evidence-To-Prose Rule

Point-Of-View Continuity Rule

Imitation Repair Gate

Platform Adaptation

References

SkillSafety

Source

Related skills

More in the registry