Ready to supercharge your AI agents?

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

公众号文章排版 Skill · isjiamu | DecimalAI

Documentationby isjiamu

公众号文章排版 Skill

微信公众号文章排版引擎，将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取，自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入（非 Markdown 先自动归一化），也支持"一键自动排版"（自动推断结构+选主题），还支持根据用户描述/参考图生成自定义主题组件库并保存本地复用。触发场景：(1) 用户提到"公众号排版""公众号文章""微信排版""gzh"，(2) 用户想把文章（md/docx/pdf/纯文本）转成公众号 HTML，(3) 用户说"自动排版""一键排版"公众号内容，(4) 用户想为公众号排版"生成新主题/自定义风格/按这张图做一套组件库"。不用于生成普通网页/落地页/PPT（用前端或 PPT 类 skill）。

Maintained

SkillScore

SkillScore52/100

Test results 52

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

22%52%of test cases passed +30 pts

Without skill5 of 23

With skill12 of 23

8 fixed4 passed either way10 still failing1 broke

Model 8/13/2026v1 · latest is v221 comparable

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.8-flash on 10/19/2026 did not produce a publishable comparison (graded differently). The snapshot above is the previously measured run.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhen running the WeChat official account HTML validation script after assembling the HTML section, what is the required condition regarding errors and punctuation warnings before final delivery?

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 isjiamu-gzh-design
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("isjiamu-gzh-design")
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 isjiamu-gzh-design

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/isjiamu-gzh-design/SKILL.md https://app.decimal.ai/s/isjiamu-gzh-design/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/isjiamu-gzh-design/SKILL.md

This gets SKILL.md only. The skill's 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/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/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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("isjiamu-gzh-design")
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/isjiamu-gzh-design/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/isjiamu-gzh-design/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 18 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 isjiamu-gzh-design

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/isjiamu-gzh-design/SKILL.md https://app.decimal.ai/s/isjiamu-gzh-design/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/isjiamu-gzh-design/SKILL.md

This gets SKILL.md only. The skill's 18 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/isjiamu-gzh-design/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/isjiamu-gzh-design.json

This gets SKILL.md only. The skill's 18 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2 (v1 tested 8/13/2026)
Source: isjiamu/gzh-design-skill ↗
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

公众号文章排版 Skill

把一篇 Markdown 文章转换为可直接复制粘贴进微信公众号编辑器、且粘贴后样式不丢失的 HTML。

核心资产是 references/ 下的主题组件库（每套一个主题：设计变量 + 各组件完整 HTML + 模板骨架 + 映射规则）外加 1 套通用增量库（代码块 / 图片·GIF / 小标签标题，所有主题共用）。主题清单以 references/theme-index.md 为单一来源。本 SKILL.md 只负责流程与决策，具体 HTML 代码一律从组件库取，不要凭记忆手写。

工作流

0. 输入与格式归一化

用户可能给：Markdown 文本或 .md 路径（直接进第 1 步）、.docx、.pdf、.txt/无标记纯文本、网页富文本。非 Markdown 输入必须先读 references/format-normalize.md 按其规则转成 Markdown 草稿并做结构确认（docx 用 scripts/extract_docx.py，PDF 用 Read 分页读取+清噪，纯文本按标题启发式推断结构）。什么都没给时，向用户索要。

用户说「直接排 / 自动排 / 一键 / 不用问」时进全自动模式：跳过结构确认与选主题提问，自动推断结构、按题材自选主题、排版校验，交付时附决策说明（章节结构、自拟标题、选题理由）。

1. 选主题（自动推荐制）

读 references/theme-index.md（主题信息的单一来源）。据文章题材主动推荐最契合的主题，再让用户一步确认——推荐但不擅自定死：

用户已在请求里指定主题 → 直接用，不问。
题材有明确契合 → 单问确认：「建议用 XX（理由），确认还是换一套？」选项给推荐项 + 1~2 个备选 + "看全部"。题材→主题契合参考 theme-index"适用场景"列：
- 教程 / 测评 / 清单 / 工具盘点 / 知识整理 / 方法论拆解（信息密度高）→ 摸鱼绿
- 深度分析 / 观点 / 力量感话题 → 红白色系
- 设计 / 科技评论 / 专业观点 / 高端品牌 → 石墨极简风
- 禅意 / 极简生活 / 深度随笔 → 留白禅意风
- 工具对比 / 创意评测（票据视觉隐喻）→ 摸鱼票据风
- 内刊手记 / 深度评测 / 案例复盘 → 橄榄手记
无明显倾向 → 默认首选 theme-index 第一行（摸鱼绿）作为推荐项放第一位，用 AskUserQuestion 让用户在几套里选（主题多于 4 套时先按气质分组问，再问该组下主题）。
全自动模式（用户明说「直接排 / 一键 / 不用问」）→ 不提问，自动选题材最契合主题或默认第一行，交付时说明选择理由。
用户对现有主题都不满意 / 想要新风格 → 走「自定义主题生成」流程（见下节），生成并登记后再回到本步选用。
theme-index 为空 → 停止排版，告知用户需要先添加主题风格（可走「自定义主题生成」）。

用户定下主题后，才进入该主题内部的组件匹配（第 3、4 步：判定文章类型 → 按该主题的配方表选组件组合）。

2. 读组件库（两份）

(1) 据 theme-index 中该主题的"组件库文件"列，Read 该主题专属组件库 references/theme-{标识}.md（含引言卡、章节标题、正文标记、签名等主题专属组件）。 (2) 同时 Read 通用增量库 references/common-components.md——代码块、图片/GIF、小标签标题这三类所有主题共用，套用当前主题主色即可。

后续生成完全依据这两份组件库，HTML 一律从中取、不要手写。

3. 解析 Markdown 结构

元素	识别规则
文章标题	`# 标题` 或 frontmatter `title`
开头引言	文章最开头的 `> 引用` 块
章节标题	`## 标题`
子章节	`### 标题`
加粗 / 高亮 / 下划线	`文字` / `==文字==` / `<u>文字</u>` 或 `++文字++`
引用段落	非开头的 `> 文字`
图片 / GIF	`![说明](URL)`、`![](xxx.gif)`（GIF 与图片同样处理）
代码 / 命令 / Prompt	``` 围栏代码块 ```、行内 `code`
分割线 / 列表	`---`、`***` / `- 项` 或 `1. 项`
表格	`\|` 分隔的 Markdown 表格（常来自 docx 转换）→ 优先用主题库的表格/卡片组件（主题库映射规则为准）

解析完结构后，判定文章类型（取主导类型，可复合）：教程/操作指南、盘点/工具清单、观点/深度分析、访谈/人物特稿、数据复盘/报告、生活/情感随笔、案例实战。判定依据：步骤和命令多→教程；并列条目多→盘点；引语和人物叙事多→访谈；数字和对比多→数据；论证推演多→观点。

4. 按配方选组件组合 → 装配 HTML

先查所选主题库的「文章类型 → 组件组合配方」表，按文章类型确定本篇的核心组件组合与点缀组件——不要拿到组件库就逐段随机选组件，配方保证同类文章的排版气质稳定。配方之外的元素再按主题库映射规则表补充。

然后依主题库的**"完整文章模板骨架"章节**装配，把每个 Markdown 元素替换为对应组件：

骨架顺序以主题库为准，不同主题骨架可能不同，不要套用其它主题的骨架。
行内标记按语义到所选组件库里找对应组件（组件编号各库不统一，一律以语义为准、不要套固定编号）：**加粗**→主色加粗；==高亮==→纯色浅底高亮；<u>文字</u> 或 ++文字++→下划线；~~文字~~→荧光笔（纯色浅底）；>引用→引用高亮块。
来自通用增量库的组件：``` 代码块 ```→ 1a 深色 / 1b 浅色代码块，行内 `code`→ 1c；![说明](url)→ 2a 图片（有说明才加说明组件）、.gif→ 2b GIF；需要突出的小标题/强调→ 3a 左竖条小标题或 3b 药丸标签，金句→ 3d、提示旁注→ 3e。优先级：先查主题库映射规则表——该主题有等价语义组件（如自己的金句/提示块）就用主题库版本保持气质一致；主题库没有对应组件时才用通用库 3x 并按其换色规则换成主题色。
一篇文章只用所选主题的那一套组件，不跨主题混用。
强调与小标题用"小标签/左竖条"，不要用虚线框：要突出一个小标题或一段内容时，用左竖条小标题（3a）、药丸标签（3b）、左竖条金句/提示块（3d/3e）；不要用四周虚线框（dashed border）套一个标题，那样笨重抢戏。

5. 校验合规（强制）

把生成的 HTML 写入目标文件后，必须运行校验脚本，ERROR 清零才算完成：

# 用脚本所在 skill 的绝对路径调用，HTML 参数也用其实际路径（两者目录通常不同）
<SKILL_ROOT>/scripts/validate_gzh_html.py <生成的.html 的实际路径>

它确定性地检查平台禁用项和 <span leaf> 包裹。报 ERROR 就回到第 4 步修；半角标点 WARNING 同样要修复到 0 再交付（这是实际使用中最高频的返工点）。

渐变背景 WARNING 要逐项处理：文字高亮、引用/数据/引导卡背景默认改为主题内纯色或 rgba 纯色；用户明确要求保留时，交付注明可能触发 darkmode-no-gradient 弹窗。纯装饰渐变也会提示，尚未确认其不会触发弹窗，保留时同样说明风险。

6. 输出

产物格式：纯 <section>…</section> 正文片段，从全局容器开始，不要包 <!DOCTYPE>/<html>/<head>/<body>——公众号编辑器只接受正文片段，多余的文档外壳会被丢弃或干扰粘贴。

干净正文文件：HTML 保存到当前工作目录，文件名 {原文件名}_排版_{主题中文名}({英文标识}).html（英文标识 = theme-index 组件库文件名去掉 theme- 前缀与 .md 后缀）。这份用于校验和手动粘贴兜底。
带「复制」按钮的预览页（让用户一键复制，免去手动全选）：
```
<SKILL_ROOT>/scripts/wrap_preview.py <上面的干净正文.html>
```
产出 {...}_预览.html——浏览器打开后右上角有「复制到公众号」按钮，点一下即把渲染后的富文本复制到剪贴板（等价 Ctrl+A/Ctrl+C），再到公众号编辑器 Ctrl/⌘+V 粘贴。按钮和脚本只在预览外壳里、不在被复制的 section 内，所以粘到公众号的仍是干净合规正文。
告知用户：打开 {...}_预览.html → 点右上角「复制」→ 公众号编辑器粘贴；并给出干净正文文件路径作为兜底。附校验脚本结论（已通过 / 剩余 warning）。

生成时的智能处理（这些是本 skill 的特色，必须做）

章节自动编号：按 ## 出现顺序分配 01/02/03…；末章若为结语/总结类，用主题库指定的结语编号变体（如 ∞），主题库未指定时沿用数字编号。
英文标签：据中文章节标题生成英文标签（实测→TEST、教程→TUTORIAL、总结→SUMMARY、思考→THOUGHTS…），主题库有对应槽位时使用。
正文关键词下划线（核心特色）：对每个正文段落主动找出 1–3 个最重要的短语，用该主题的下划线 CSS（见 theme-index）标记。优先标核心观点、结论、关键数据、专有名词；短语 4–15 字；整段无要点可不标。即使原文没有任何加粗也要主动加下划线——它是出现频率最高的基础标记。
引言关键词高亮：识别开头金句里的核心词，用高亮组件标记。
目录提取：从所有 ## 取前 3 个作为导读/目录要点（主题库有目录组件时）。
开头引言卡署名：按文章的作者或主题而定——文章有署名就写"—— 作者名"，没有明确作者就用与主题相关的简短落款或直接省略。不要固定写"甲木"（尾部签名区同样用 {{作者名}} 占位，见第 7 条）。
尾部作者签名区（作者自填，仅末尾一处）：默认不写死任何人名，用占位署名让用户替换成自己的。
- 第一句（作者介绍）：我是 {{作者名}}，{{一句话简介，如：热衷于分享 AI 观察与干货}}——用户在请求/偏好里给了署名或简介就直接填入；没给就保留 {{作者名}} / {{简介}} 占位，并在交付时提示用户替换成自己的署名。
- 第二句（互动引导，通用可保留原样）：如果你觉得今天这篇有收获，欢迎**点赞、在看、转发**三连，我们下篇见
- 原文末尾已有作者签名段（如"我是 XXX…"）→ 直接沿用原文的署名，不替换成占位。
列表转换：按主题库映射规则处理；无专属列表组件时转为带缩进的正文段落。
中文全角标点：正文标点一律用全角（，。！？：；""''（）—— …），不要用半角 , . ! ? : 和英文直引号 " '。生成 HTML 时就直接写弯引号""''，不要先写直引号再事后替换——原文里的直引号在转写时当场转换。例外：代码块、行内代码、英文专名/URL/代码标识符内部保持原样。

视觉层级（3 层递进，所有主题通用）

层级	作用	频率	手段
锚点层	最强锚点：产品名/步骤/CTA/核心金句	全文 ≤ 5 处	主色加粗、深色底白字引用
标记层	正文关键词，每段 1–3 处	高频	下划线标记
容器层	引用块、概念标签、长句强调	按需	浅底引用、荧光笔、徽章

平台红线（核心，完整检查交给校验脚本）

禁止：<style>/<script>/<div>、class/id 属性、position:fixed/absolute/sticky、float、@media/@keyframes、display:grid、CSS 变量、外部字体/CSS。
必须：样式全部内联 style；所有文字节点用 <span leaf="">文字</span> 包裹（否则粘贴后样式丢失）。
可用：display:flex（有限）、border-radius、box-shadow、<section>/<p>/<span>/<strong>/<img>/<h3>。
渐变背景兼容性：渐变可渲染，但可能触发公众号 darkmode-no-gradient 内容结构检测；文字和卡片背景默认用纯色，不额外添加渐变。旧组件/自定义主题遇到此项也按第 5 步处理。

Gotchas（真实排版踩过的坑）

漏 <span leaf> 包裹是最常见致命错——粘贴到公众号后样式整片丢失。靠第 5 步校验脚本兜底，别跳过。
下划线：逐段落实、每段 1–3 个短语。不要整段划线（失去焦点），也不要有的段标有的段漏；列表项里的关键描述同样要标。
章节编号错乱：严格按 ## 顺序，不要跳号；结语编号变体只用于末章，中间章节不能用。
签名区有且仅有末尾一个：用固定文案，不在中间或多处出现；原文末尾若已有作者签名/"点赞在看转发三连"类段落，识别并并入这唯一的签名区/CTA 卡片，不要保留原文段又再生成一个。
图片说明硬造：只有 ![说明](url) 里真有说明文字才生成说明组件；![](url) 空 alt 不要编造说明。
图片自适应、不铺满：<img> 一律 max-width:100%;height:auto;display:block;margin:0 auto——按图片自身尺寸显示、居中，大图缩到容器宽、小图保持原尺寸。不用 width:100%（会把小图也拉伸变糊）；只有表格 / 封面卡 / 流程图这类布局元素才用 width:100%。
跨主题混用组件：一篇文章只用所选主题 + 通用库的组件，不从其它主题借组件。
锚点层滥用：最强强调全文 ≤ 5 处，到处加粗等于没有重点。
原文内容遗漏：每个段落、每张图都要转换，不得漏；不要自行增删原文实质内容。
占位图残留：签名区/CTA 组件里若带名片图占位（如 <img src="...名片或引导图URL">），没有真实图片 URL 时整行删掉，不要把占位符留在产物里。
目录是精选不是全量：前言导读/目录组件展示精选的 3 个核心看点，不是完整章节列表；章节多于 3 个时挑最重要的 3 个，不要硬塞或误导读者以为只有 3 章。
不用虚线框：突出标题/强调用小标签或左竖条（通用库 3a–3e），不要用 border:…dashed 四周虚线框包标题。例外：主题库明确定义的虚线组件（如摸鱼绿的 quote-box 引用框、oneliner-card 亮点卡）是该主题的风格特征，按主题库用法正常使用。
标点别混半角：正文出现半角逗号句号、英文直引号 " ' 都要改成全角；但代码块/行内代码内的半角符号保持原样，不要"全角化"代码。
代码/Prompt 必须用代码块：文章里的代码、命令、提示词用通用库代码块组件（1a/1b），不要塞进普通段落或引用块，否则缩进和等宽会丢失。
代码块要紧凑、忌大空白：用通用库 1a/1b 的"每行一个 <p style=\"margin:0\">"写法，绝不用 white-space:pre——它会把 HTML 源码里 span 前的缩进和行间换行原样渲染成大左缩进 + 空行；缩进只用全角空格　，行距靠 line-height:1.6。
待补素材居中：【插入…】、待录屏 / GIF / 视频 / 成果图等占位，用通用库 2c 居中素材占位板块（浅底柔虚线框 + 居中图标与说明），不要用左对齐的提示块。

自定义主题生成（第二条工作流）

用户想要内置主题之外的新风格（说「生成一套新主题 / 自定义风格 / 按这张参考图做一套组件库」，或对现有主题都不满意）时，读 references/theme-generator.md 并严格按其流程执行：

收集偏好：主题描述必填（或参考图），名称/ID/五色/字体/三类 TAG/圆角/阴影可空则自动补全；一次问全，不逐字段追问。
生成区块库 HTML：用 theme-generator.md 末尾的【生成提示词】原样执行，产出 45~75 个 Block 的完整区块库，保存到 assets/theme-previews/{theme-id}.html——全部区块在同一页面连续排布，用户浏览器打开整页一次浏览确认风格，不逐块展示确认。
转换 + 登记：用户确认风格后，转换为标准 references/theme-{标识}.md（必须补 <span leaf=""> 包裹、去掉预览用 id、补齐五章节，规则详见 theme-generator.md 第三步），登记 theme-index.md，跑 component_lint.py 到 0 ERROR。
交付后该主题即成为常驻可选主题，后续排版与内置主题完全同权。

生成阶段以提示词规则为准；转换进主题库阶段以本文件「平台红线」和「添加新主题的规范」为准（两者冲突时后者优先，因为主题库直接决定排版产物）。

添加新主题的规范

新主题以 references/theme-{英文标识}.md 命名，内容必须包含：

设计变量速查表（主色/浅底/深字/标题色/正文色/分割线色等）
各组件完整 HTML（内联样式 + <span leaf=""> 包裹，遵守上面"平台红线"）
完整文章模板骨架（组件装配顺序；若有目录/导航组件，明确其相对封面/引言的位置）
文章类型 → 组件组合配方表（每种文章类型的核心组件组合 + 点缀组件，配方是排版气质稳定的关键）
Markdown → 组件映射规则表

添加后在 references/theme-index.md 登记一行（主题名 / 主色 / 适用场景 / 组件库文件 / 正文下划线 CSS），并跑 python3 scripts/component_lint.py . 确认组件库无反模式（0 ERROR）。

触发与主题选择的回归用例见 references/eval-cases.md（维护时用于回归核对，不影响单次生成）。

About this skill

Automatic

Marketing & Content pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v6 — 10/16/2026

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

isjiamu / gzh-design-skill

SKILL.md

View on GitHub ↗

License NOASSERTIONImported 10/16/2026Version v2Bundled 18 files · scripts

Illustrative Want to see what isjiamu/gzh-design would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

aiworkskills/aws-wechat-article-formatting公众号排版｜Markdown 转 HTML｜排版主题｜段落样式 — 公众号一键排版工具，Markdown 文稿转微信后台可粘贴 HTML，多主题、多字号、段落样式切换，所见即所得。面向公众号编辑、独立作者、排版岗。触发词：「排版」「版式」「美化」「格式化」「字号」「段落样式」「换个排版主题」「换个版式」「转 HTML」「弄好看点」「调整格式」。换预设包/品牌包/整套主题配色请走 aws-wechat-article-assets；需要多环节串联（写+审+排+配图+发）请走 aws-wechat-article-main。Close match+43 pts pass-rate lift

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

公众号文章排版 Skill

工作流

0. 输入与格式归一化

1. 选主题（自动推荐制）

2. 读组件库（两份）

3. 解析 Markdown 结构

4. 按配方选组件组合 → 装配 HTML

5. 校验合规（强制）

6. 输出

生成时的智能处理（这些是本 skill 的特色，必须做）

视觉层级（3 层递进，所有主题通用）

平台红线（核心，完整检查交给校验脚本）

Gotchas（真实排版踩过的坑）

自定义主题生成（第二条工作流）

添加新主题的规范

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry