Ready to supercharge your AI agents?

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

POETIZE Blog Automation · leoyeai | DecimalAI

Marketingby leoyeai

POETIZE Blog Automation

专为开源版 awesome-poetize-open 设计的 POETIZE 博客自动化技能。通过 `/api/api/*` 接口完成文章发布、更新、隐藏、分类标签维护、主题切换、数据分析和 SEO 运维。Use only when the task explicitly targets a POETIZE site or POETIZE admin API workflow.

Never made a case worse

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

14%95%of test cases passed +82 pts

Without skill3 of 22

With skill21 of 22

18 fixed3 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI want to publish a new markdown post about Python tips. Here is my brief detail: primaryGoal is user engagement. Which mandatory command-line parameter must be passed to the publishing script alongside the markdown file?

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 leoyeai-poetize-blog-automation
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("leoyeai-poetize-blog-automation")
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 leoyeai-poetize-blog-automation

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/leoyeai-poetize-blog-automation/SKILL.md https://app.decimal.ai/s/leoyeai-poetize-blog-automation/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-poetize-blog-automation/SKILL.md

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/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/leoyeai-poetize-blog-automation/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add leoyeai-poetize-blog-automation

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("leoyeai-poetize-blog-automation")
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/leoyeai-poetize-blog-automation/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-poetize-blog-automation/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-poetize-blog-automation

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/leoyeai-poetize-blog-automation/SKILL.md https://app.decimal.ai/s/leoyeai-poetize-blog-automation/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-poetize-blog-automation/SKILL.md

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/leoyeai-poetize-blog-automation/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-poetize-blog-automation.json

This gets SKILL.md only. The skill's 14 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Not for

Generic writing, generic SEO advice, or non-POETIZE CMS work.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
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

POETIZE Blog Automation

Use this skill to operate a POETIZE blog as a personal publishing and maintenance system. It is built on the existing POETIZE API feature, not browser automation. It is free-first, growth-first, and maintenance-first. It is not monetization-first.

中文简介

这是一个面向 POETIZE 博客的 OpenClaw skill，用来通过 POETIZE 的 /api/api/* 接口进行文章发布、更新、隐藏、分类标签维护、主题切换、数据分析和 SEO 运维。
目前仅支持 awesome-poetize-open 开源分支，不适用于原版 POETIZE。
专为开源版 awesome-poetize-open 设计。
它更适合“个人博客运营”而不是“泛内容生成”，默认坚持免费优先、维护优先、质量优先。

Public Distribution Position

Treat this as an OpenClaw integration for the open-source awesome-poetize-open release.
It is designed for the open-source branch of POETIZE.
Before publishing to ClawHub, remove secrets, local machine paths, and private content from any bundled files.
When publishing publicly, link back to the source repository and keep the applicable license and attribution notices intact.
Prefer a project-prefixed public slug such as awesome-poetize-open-blog-automation so the registry entry stays tied to the open-source project.

Compatibility

Required project version: awesome-poetize-open.
Expected API surface: the POETIZE admin API routes documented in references/poetize-api.md.
Do not use this skill with the original POETIZE project.
For other forks, verify endpoint names and payload shapes before the first write action.

OpenClaw-First Execution Rules

Use {baseDir} for any file path that points inside this skill folder.
Prefer single-line shell commands in examples so they remain portable across shells.
Use python in examples and switch to python3 when that is the installed binary.
Invoke this skill only for explicit POETIZE tasks. Do not route generic writing or generic SEO requests here.
Prefer scripts/render_openclaw_config.py to generate OpenClaw config instead of hand-writing JSON.
Run scripts/openclaw_smoke_test.py before the first real write action on a new OpenClaw environment.
Point POETIZE_BASE_URL at the public nginx/domain origin.
Actual request path = ${POETIZE_BASE_URL}/api/api/...; do not append /api inside the variable value itself.

Read references/poetize-api.md before publishing, updating, querying, or operating articles. Read references/openclaw-setup.md when connecting the skill to OpenClaw. Read references/strategy-playbook.md before deciding whether to create, refresh, or hide content. Read references/decision-matrix.md before setting publish posture, search posture, or paywall posture. Read references/creativity-workflow.md before drafting article copy. Read references/evaluation-scenarios.md when validating the strategy layer. Run scripts/run_strategy_evals.py to verify the local strategy layer before shipping skill changes.

Breaking change:

All mutating commands now require --brief-file.
OpenClaw should treat assets/article-brief.template.json and assets/ops-brief.template.json as the starting point for strategy briefs.

Operating Position

Act like a blog editor, content operator, and maintenance assistant.
Optimize for long-term content quality, search visibility, and low-effort maintenance.
Default to free, public, searchable content unless the user clearly asks for a draft or private post.
Treat paid posts as an uncommon edge case for established blogs with clear conversion intent.
Prefer improving old content, reorganizing taxonomy, and maintaining content quality over pushing paywalls.

Workflow

Gather the publishing intent. Decide whether the user wants a draft or a public article. Decide whether the task is new content, old-content maintenance, taxonomy cleanup, SEO follow-up, or article takedown by hiding. Default to free content unless the user explicitly asks for a draft or a paywalled post. Create a strategy brief before any mutating action.
Create the strategy brief. Use {baseDir}/assets/article-brief.template.json for article creation or article refresh work. Use {baseDir}/assets/ops-brief.template.json for update or hide operations. Fill primaryGoal, reasoning, and the required brief fields before calling any mutating script. If required brief information is missing, stop and ask for it.
Diverge, then converge. Produce 2 or 3 candidate angles first. Choose one final direction and record it as selectedAngle. Record the rejected candidates in alternativesConsidered.
Write the article in Markdown. Prefer a single H1 at the top. Keep the body as clean Markdown. Use short lead paragraphs, clear section headings, lists only when they improve readability, and avoid HTML unless required. If the article includes images, save them as local files first and reference them from the Markdown file with relative paths such as ![示意图](./assets/diagram.png). publish_post.py will upload those local article images through /api/resource/upload before publishing and replace them with returned URLs. When the task is maintenance, prefer revising existing articles over creating duplicates.
Add front matter for routing and publishing metadata. Use the front matter keys documented in references/poetize-api.md. At minimum provide title, sort or sortId, and label or labelId. Prefer existing sort and label names when IDs are unknown. The script will query /api/categories and /api/tags first and reuse exact matches. If exact matches fail, the script may return close category or tag candidates for confirmation. Close matches are suggestions only and must not be auto-selected. It will not create a new category or tag unless you explicitly allow it. Be explicit about article switches when the user mentions them: commentStatus for comments recommendStatus for recommendation viewStatus for visibility submitToSearchEngine for search-engine push Only set paid fields when the user explicitly wants a paywall and the content clearly deserves it. For most personal blogs, keep payType: 0. When the user does not want to upload a cover, set coverBlank: true or cover: " ".
Publish through the bundled publish script. Use {baseDir}/scripts/publish_post.py for create or content update flows driven by Markdown. OpenClaw runtime only needs: POETIZE_BASE_URL POETIZE_API_KEY --brief-file is mandatory. If the markdown body references local images or local <img src="..."> files, the script uploads them automatically before sending the article payload. For paid posts, the script will check /api/payment/plugin/status first, but paid publishing is not the default path for this skill. If the payment plugin is installed but not configured, provide paymentPluginKey in front matter and optionally pass --payment-config-file payment.json.
Operate existing articles, themes, analytics, and SEO through the management script. Use {baseDir}/scripts/manage_blog.py. It supports: article listing exact-title lookup article detail article update article hide global article theme switching article analytics site visit trends controlled SEO config sitemap update It does not support article deletion. If the user wants a post effectively removed from public view, hide it by setting viewStatus: false. update-article and hide-article now require --brief-file.
Return the final result. Prefer --wait so the script polls until the async task finishes. Report the returned articleId, articleUrl, task status, visibility state, and any follow-up analytics when requested.

Guardrails

Treat public publishing as a deliberate action. If the user asks for a draft, keep viewStatus: false or run with --draft.
Treat free content as the default operating mode for personal blogs.
Do not proactively suggest paywalls for ordinary blog posts.
Only suggest a paid article when the user explicitly wants monetization or the content is unusually high-value, structured, and conversion-oriented.
Prefer article maintenance, article refresh, taxonomy cleanup, and SEO hygiene over monetization features.
Every mutating action must be backed by a strategy brief.
If the strategy brief is missing, incomplete, or contradictory, stop instead of guessing.
Do not guess article switches from vague phrasing. Confirm or set commentStatus, recommendStatus, viewStatus, and submitToSearchEngine explicitly when the user mentions them.
If viewStatus: false, the script will auto-fill a draft password and preview tip when omitted.
Do not invent sortId or labelId. Use sort and label names when IDs are unknown.
Do not silently create categories or tags. If the requested sort or label does not exist, stop and ask for confirmation unless allowCreateTaxonomy, allowCreateSort, or allowCreateLabel is explicitly set.
Taxonomy fuzzy matching is for candidate suggestions only.
Never auto-select a category or tag from fuzzy candidates without explicit confirmation.
If the user gives only a topic, generate the article first, then publish it. Do not send placeholder content to the API.
If a manual translation is provided, pass pendingTranslationLanguage, pendingTranslationTitle, and pendingTranslationContent.
For article updates, omit category/tag/status fields when they should stay unchanged.
Do not delete articles through this skill.
If the user asks to delete a post, explain that this skill does not support deletion and use article hiding instead.
Hiding an article is the supported "take it down" action and is implemented with viewStatus: false.
For paid articles, keep the chosen payType explicit. Do not guess a paywall mode from prose alone.
Paid articles require an enabled and configured payment plugin in POETIZE plugin management. The script can configure an installed payment plugin through the API-key payment endpoints, but it will not install plugin packages.
If paid publishing is unavailable and the user did not insist on a paywall, allow the script to downgrade to payType: 0.
If no cover should be uploaded, prefer coverBlank: true over inventing a fake cover URL.
If the user provides images, keep them as local files until publish time and reference them from Markdown instead of inventing remote URLs.
If a Markdown image points to a local file that does not exist, stop and fix the file path before publishing.
publish_post.py uses hard strategy validation.
manage_blog.py update-article and hide-article use hard strategy validation.

Script Usage

Generate a usable OpenClaw config that points OpenClaw at this repo's openclaw-skills directory:

python {baseDir}/scripts/render_openclaw_config.py --output openclaw.poetize.local.json --api-key "replace-with-poetize-api-key"

Run a read-only smoke test before the first publish or update:

python {baseDir}/scripts/openclaw_smoke_test.py --base-url "https://your-blog.example.com" --api-key "replace-with-poetize-api-key"

Start from the bundled strategy templates:

Create article-brief.json from {baseDir}/assets/article-brief.template.json. Create ops-brief.json from {baseDir}/assets/ops-brief.template.json.

Front matter example with the common publish switches:

---
title: "示例文章"
sort: "AI实践"
label: "自动化"
commentStatus: true
recommendStatus: false
viewStatus: true
submitToSearchEngine: true
---

# 示例文章

正文...

Markdown image example with local files:

---
title: "带图文章示例"
sort: "AI实践"
label: "自动化"
---

# 带图文章示例

这里是一张本地图片：

![流程图](./assets/flow.png)

At publish time, publish_post.py uploads ./assets/flow.png and rewrites the Markdown image target to the returned URL.

Publish a new draft and wait:

python {baseDir}/scripts/publish_post.py --markdown-file draft.md --brief-file article-brief.json --draft --wait

Publish a public article and wait:

python {baseDir}/scripts/publish_post.py --markdown-file article.md --brief-file article-brief.json --publish --wait

Update an existing article:

python {baseDir}/scripts/publish_post.py --markdown-file article.md --brief-file article-brief.json --article-id 123 --publish --wait

Publish a paid article and require payment readiness:

python {baseDir}/scripts/publish_post.py --markdown-file paid-article.md --brief-file article-brief.json --payment-plugin-key afdian --payment-config-file payment.json --require-paid --publish --wait

Start an async task without waiting:

python {baseDir}/scripts/publish_post.py --markdown-file article.md --brief-file article-brief.json

Allow creating a missing category and tag only when explicitly confirmed:

python {baseDir}/scripts/publish_post.py --markdown-file article.md --brief-file article-brief.json --allow-create-taxonomy --publish --wait

List articles for运营筛选:

python {baseDir}/scripts/manage_blog.py list-articles --search-key "AI" --sort-name "AI实践" --label-name "自动化" --current 1 --size 10

If an exact category or tag name does not match, the management script returns close candidates and stops. OpenClaw should surface those candidates for confirmation instead of guessing.

Hide an existing article:

python {baseDir}/scripts/manage_blog.py hide-article --article-id 123 --brief-file ops-brief.json --wait

Deletion policy:

This skill does not support deleting articles.
To achieve a deletion-like effect, hide the article instead.
Hiding removes it from normal public visibility by updating viewStatus to false.

Switch the global article theme:

python {baseDir}/scripts/manage_blog.py activate-theme --plugin-key academic

Update controlled SEO config:

python {baseDir}/scripts/manage_blog.py seo-set-config --config-file seo.json

Expected Inputs

Topic, outline, or markdown draft
Existing article ID or exact title when operating on an existing post
Strategy brief JSON for every mutating command
Target category and tag
Whether the task is publishing, updating, hiding, reorganizing, or maintaining old content
Whether to save as draft or publish
Whether comments are enabled, whether the article is recommended, whether it is visible, and whether it should be pushed to search engines
Whether the article is free or paid, though free should be treated as the default
Whether to upload a cover, reuse a cover URL, or intentionally leave it blank
Whether the article includes local images that should be uploaded and rewritten during publish
Whether to switch the global article theme
Whether to read article analytics, site visit trends, or controlled SEO status/config
Base URL and API key, usually via OpenClaw runtime variables

Expected Outputs

Final markdown article
Strategy-normalized brief decisions
Normalized publish payload
Uploaded cover URL when a local cover file is provided
Uploaded article image URLs when local Markdown images are provided
Async taskId and task status URL when not waiting
Final articleId
Final articleUrl
Existing article detail or exact-title lookup result when operating on old content
Hidden article result when the user wants deletion-like takedown behavior
Global article theme status or activation result
Article analytics and site visit trend data when requested
Controlled SEO status/config result and sitemap trigger result when requested

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 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

LeoYeAI / openclaw-master-skills

skills/awesome-poetize-open-blog-automation/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 14 files · scripts

Illustrative Want to see what leoyeai/poetize-blog-automation 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

Not for

POETIZE Blog Automation

中文简介

Public Distribution Position

Compatibility

OpenClaw-First Execution Rules

Operating Position

Workflow

Guardrails

Script Usage

Expected Inputs

Expected Outputs

SkillSafety

Source

Related skills

More in the registry