Ready to supercharge your AI agents?

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

Meta Tags Optimizer · LeoYeAI | DecimalAI

Marketingby LeoYeAI

Meta Tags Optimizer

Use when the user asks to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "social media preview", "my title tag needs work", "low click-through rate", "fix my meta tags", or "OG tags not showing". Creates and optimizes meta tags including title tags, meta descriptions, Open Graph tags, and Twitter cards for maximum click-through rates and social sharing engagement. For a broader on-page audit, see on-page-seo-auditor. For structured data markup, see schema-marku

Never made a case worse

SkillScore

SkillScore38/100

Test results 38

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

13%38%of test cases passed +25 pts

Without skill3 of 24

With skill9 of 24

6 fixed3 passed either way15 still failing0 broke

Measured on gemini-3.6-flash7/27/2026v1

Track record

Agent runs: 0; All time

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 meta-tags-optimizer
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("meta-tags-optimizer")
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 meta-tags-optimizer

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/meta-tags-optimizer/SKILL.md https://app.decimal.ai/s/meta-tags-optimizer/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/meta-tags-optimizer/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/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/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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("meta-tags-optimizer")
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/meta-tags-optimizer/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/meta-tags-optimizer/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 1 other file is 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 meta-tags-optimizer

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/meta-tags-optimizer/SKILL.md https://app.decimal.ai/s/meta-tags-optimizer/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/meta-tags-optimizer/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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/meta-tags-optimizer/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/meta-tags-optimizer.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/27/2026
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

Meta Tags Optimizer

SEO & GEO Skills Library · 20 skills for SEO + GEO · Install all: npx skills add aaron-he-zhu/seo-geo-claude-skills

Research · keyword-research · competitor-analysis · serp-analysis · content-gap-analysis

Build · seo-content-writer · geo-content-optimizer · meta-tags-optimizer · schema-markup-generator

Optimize · on-page-seo-auditor · technical-seo-checker · internal-linking-optimizer · content-refresher

Monitor · rank-tracker · backlink-analyzer · performance-reporter · alert-manager

Cross-cutting · content-quality-auditor · domain-authority-auditor · entity-optimizer · memory-management

This skill creates compelling, optimized meta tags that improve click-through rates from search results and enhance social media sharing. It covers title tags, meta descriptions, and social meta tags.

When to Use This Skill

Creating meta tags for new pages
Optimizing existing meta tags for better CTR
Preparing pages for social media sharing
Fixing duplicate or missing meta tags
A/B testing title and description variations
Optimizing for specific SERP features
Creating meta tags for different page types

What This Skill Does

Title Tag Creation: Writes compelling, keyword-optimized titles
Meta Description Writing: Creates click-worthy descriptions
Open Graph Optimization: Prepares pages for social sharing
Twitter Card Setup: Optimizes Twitter-specific meta tags
CTR Analysis: Suggests improvements for better click rates
Character Counting: Ensures proper length for SERP display
A/B Test Suggestions: Provides variations for testing

How to Use

Create Meta Tags

Create meta tags for a page about [topic] targeting [keyword]

Write title and meta description for this content: [content/URL]

Optimize Existing Tags

Improve these meta tags for better CTR: [current tags]

Social Media Tags

Create Open Graph and Twitter card tags for [page/URL]

Data Sources

See CONNECTORS.md for tool category placeholders.

With ~~search console + ~~SEO tool connected: Automatically pull current meta tags, CTR data by query, competitor title/description patterns, SERP preview data, and impression/click metrics to identify optimization opportunities.

With manual data only: Ask the user to provide:

Current title and meta description (if optimizing existing)
Target primary keyword and 2-3 secondary keywords
Page URL and main content/value proposition
Competitor URLs or examples of well-performing titles in the SERP

Proceed with the full workflow using provided data. Note in the output which metrics are from automated collection vs. user-provided data.

Instructions

When a user requests meta tag optimization:

Gather Page Information

### Page Analysis

**Page URL**: [URL]
**Page Type**: [blog/product/landing/service/homepage]
**Primary Keyword**: [keyword]
**Secondary Keywords**: [keywords]
**Target Audience**: [audience]
**Primary CTA**: [action you want users to take]
**Unique Value Prop**: [what makes this page special]

Create Optimized Title Tag

### Title Tag Optimization

**Requirements**:
- Length: 50-60 characters (displays fully in SERP)
- Include primary keyword (preferably near front)
- Make it compelling and click-worthy
- Match search intent
- Include brand name if appropriate

**Title Tag Formula Options**:

1. **Keyword | Benefit | Brand**
   "[Primary Keyword]: [Benefit] | [Brand Name]"
   
2. **Number + Keyword + Promise**
   "[Number] [Keyword] That [Promise/Result]"
   
3. **How-to Format**
   "How to [Keyword]: [Benefit/Result]"
   
4. **Question Format**
   "What is [Keyword]? [Brief Answer/Hook]"
   
5. **Year + Keyword**
   "[Keyword] in [Year]: [Hook/Update]"

**Generated Title Options**:

| Option | Title | Length | Power Words | Keyword Position |
|--------|-------|--------|-------------|------------------|
| 1 | [Title] | [X] chars | [words] | [Front/Middle] |
| 2 | [Title] | [X] chars | [words] | [Front/Middle] |
| 3 | [Title] | [X] chars | [words] | [Front/Middle] |

**Recommended**: Option [X]
**Reasoning**: [Why this option is best]

**Title Tag Code**:
```html
<title>[Selected Title]</title>

Write Meta Description

### Meta Description Optimization

**Requirements**:
- Length: 150-160 characters (displays fully in SERP)
- Include primary keyword naturally
- Include clear call-to-action
- Match page content accurately
- Create urgency or curiosity
- Avoid duplicate descriptions

**Meta Description Formula**:

[What the page offers] + [Benefit to user] + [Call-to-action]

**Power Elements to Include**:
- Numbers and statistics
- Current year
- Emotional triggers
- Action verbs
- Unique value proposition

**Generated Description Options**:

| Option | Description | Length | CTA | Emotional Trigger |
|--------|-------------|--------|-----|-------------------|
| 1 | [Description] | [X] chars | [CTA] | [Trigger] |
| 2 | [Description] | [X] chars | [CTA] | [Trigger] |
| 3 | [Description] | [X] chars | [CTA] | [Trigger] |

**Recommended**: Option [X]
**Reasoning**: [Why this option is best]

**Meta Description Code**:
```html
<meta name="description" content="[Selected Description]">

Create Open Graph Tags

### Open Graph Tags (Facebook, LinkedIn, etc.)

**Required OG Tags**:

```html
<!-- Primary Open Graph Tags -->
<meta property="og:type" content="[article/website/product]">
<meta property="og:url" content="[Full canonical URL]">
<meta property="og:title" content="[OG-optimized title - up to 60 chars]">
<meta property="og:description" content="[OG description - up to 200 chars]">
<meta property="og:image" content="[Image URL - 1200x630px recommended]">

<!-- Optional but Recommended -->
<meta property="og:site_name" content="[Website Name]">
<meta property="og:locale" content="en_US">

OG Type Selection Guide:

Page Type	og:type
Blog post	article
Homepage	website
Product	product
Video	video.other
Profile	profile

OG Title Considerations:

Can be different from title tag
Optimize for social sharing context
More conversational tone acceptable
Up to 60 characters ideal

OG Description Considerations:

Can be longer than meta description (up to 200 chars)
Focus on shareability
What would make someone click when shared?

OG Image Requirements:

Recommended size: 1200x630 pixels
Minimum size: 600x315 pixels
Format: JPG or PNG
Keep text to less than 20% of image
Include branding subtly

Create Twitter Card Tags

### Twitter Card Tags

**Card Type Selection**:

| Card Type | Best For | Image Size |
|-----------|----------|------------|
| summary | Articles, blogs | 144x144 min |
| summary_large_image | Visual content | 300x157 min |
| player | Video/audio | 640x360 min |
| app | Mobile apps | 800x418 |

**Twitter Card Code**:

```html
<!-- Twitter Card Tags -->
<meta name="twitter:card" content="[summary_large_image/summary]">
<meta name="twitter:site" content="@[YourTwitterHandle]">
<meta name="twitter:creator" content="@[AuthorTwitterHandle]">
<meta name="twitter:title" content="[Title - 70 chars max]">
<meta name="twitter:description" content="[Description - 200 chars max]">
<meta name="twitter:image" content="[Image URL]">
<meta name="twitter:image:alt" content="[Image description for accessibility]">

Twitter-Specific Considerations:

Shorter titles work better (under 70 chars)
Include @mentions if relevant
Hashtag-relevant terms can help discovery
Test with Twitter Card Validator

Additional Meta Tags

### Additional Recommended Meta Tags

**Canonical URL** (Prevent duplicates):
```html
<link rel="canonical" href="[Preferred URL]">

Robots Tag (Indexing control):

<meta name="robots" content="index, follow">

Viewport (Mobile optimization):

<meta name="viewport" content="width=device-width, initial-scale=1">

Author (For articles):

<meta name="author" content="[Author Name]">

Language:

<html lang="en">

Article-Specific (For blog posts):

<meta property="article:published_time" content="[ISO 8601 date]">
<meta property="article:modified_time" content="[ISO 8601 date]">
<meta property="article:author" content="[Author URL]">
<meta property="article:section" content="[Category]">
<meta property="article:tag" content="[Tag 1]">

Generate Complete Meta Tag Block

## Complete Meta Tags

Copy and paste this complete meta tag block:

```html
<!-- Primary Meta Tags -->
<title>[Optimized Title]</title>
<meta name="title" content="[Optimized Title]">
<meta name="description" content="[Optimized Description]">
<link rel="canonical" href="[Canonical URL]">

<!-- Open Graph / Facebook -->
<meta property="og:type" content="[type]">
<meta property="og:url" content="[URL]">
<meta property="og:title" content="[OG Title]">
<meta property="og:description" content="[OG Description]">
<meta property="og:image" content="[Image URL]">
<meta property="og:site_name" content="[Site Name]">

<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:url" content="[URL]">
<meta name="twitter:title" content="[Twitter Title]">
<meta name="twitter:description" content="[Twitter Description]">
<meta name="twitter:image" content="[Image URL]">

<!-- Additional -->
<meta name="robots" content="index, follow">
<meta name="author" content="[Author]">

CORE-EEAT Alignment Check

Verify meta tags align with content quality standards. Reference: CORE-EEAT Benchmark

### CORE-EEAT Meta Tag Alignment

| Check | Status | Notes |
|-------|--------|-------|
| **C01 Intent Alignment**: Title promise matches actual content delivery | ✅/⚠️/❌ | [Does the title accurately represent what the page delivers?] |
| **C02 Direct Answer**: Meta description reflects the core answer available in first 150 words | ✅/⚠️/❌ | [Does the description preview the direct answer?] |

**If C01 fails**: Title is misleading — rewrite to match actual content.
**If C02 fails**: Content may need restructuring to front-load the answer, or description should better reflect available content.

Provide CTR Optimization Tips

## CTR Optimization Analysis

### Power Words Used
- [Word 1] - Creates [emotion/action]
- [Word 2] - Creates [emotion/action]

### CTR Boosting Elements

| Element | Present | Impact |
|---------|---------|--------|
| Numbers | Yes/No | +20-30% CTR |
| Current Year | Yes/No | +15-20% CTR |
| Power Words | Yes/No | +10-15% CTR |
| Question | Yes/No | +10-15% CTR |
| Brackets | Yes/No | +10% CTR |

### A/B Test Suggestions

Test these variations:

**Version A** (Current):
- Title: [Title]
- Description: [Description]

**Version B** (Test):
- Title: [Alternative title]
- Description: [Alternative description]
- Hypothesis: [Why this might perform better]

Validation Checkpoints

Input Validation

Primary keyword confirmed and matches page content
Page type identified (blog/product/landing/service/homepage)
Target audience and search intent clearly defined
Unique value proposition articulated

Output Validation

Title length 50-60 characters (displays fully in SERP)
Meta description length 150-160 characters
Primary keyword appears in both title and description
Open Graph image specified (1200x630px recommended)
All HTML syntax valid (no unclosed quotes or tags)
Source of each data point clearly stated (~~search console CTR data, ~~SEO tool competitor data, user-provided, or estimated)

Example

User: "Create meta tags for a blog post about 'how to start a podcast in [current year]'"

Output:

## Meta Tags: How to Start a Podcast ([current year])

### Title Tag
```html
<title>How to Start a Podcast in [current year]: Complete Beginner's Guide</title>

Length: ~55 characters ✅ Keyword: "how to start a podcast" at front ✅ Power Words: "Complete", "Beginner's" ✅

Meta Description

<meta name="description" content="Learn how to start a podcast in [current year] with our step-by-step guide. Covers equipment, hosting, recording, and launching your first episode. Start podcasting today!">

Length: ~163 characters ✅ Keyword: Included naturally ✅ CTA: "Start podcasting today!" ✅

Complete Meta Tag Block

<!-- Primary Meta Tags -->
<title>How to Start a Podcast in [current year]: Complete Beginner's Guide</title>
<meta name="description" content="Learn how to start a podcast in [current year] with our step-by-step guide. Covers equipment, hosting, recording, and launching your first episode. Start podcasting today!">
<link rel="canonical" href="https://yoursite.com/how-to-start-a-podcast/">

<!-- Open Graph / Facebook -->
<meta property="og:type" content="article">
<meta property="og:url" content="https://yoursite.com/how-to-start-a-podcast/">
<meta property="og:title" content="How to Start a Podcast in [current year] (Complete Guide)">
<meta property="og:description" content="Everything you need to launch your podcast: equipment recommendations, hosting platforms, recording tips, and step-by-step launch checklist. No experience required.">
<meta property="og:image" content="https://yoursite.com/images/podcast-guide.jpg">
<meta property="og:site_name" content="Your Site Name">

<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:title" content="How to Start a Podcast in [current year]">
<meta name="twitter:description" content="Complete beginner's guide to launching your podcast. Equipment, hosting, recording, and more.">
<meta name="twitter:image" content="https://yoursite.com/images/podcast-guide.jpg">
<meta name="twitter:site" content="@YourHandle">

<!-- Article Tags -->
<meta property="article:published_time" content="[YYYY-MM-DD]T08:00:00+00:00">
<meta property="article:author" content="https://yoursite.com/author/name">
<meta property="article:section" content="Podcasting">
<meta property="article:tag" content="podcasting">
<meta property="article:tag" content="content creation">

A/B Test Variations

Title Variation B: "Start a Podcast in [current year]: Step-by-Step Guide (+ Free Checklist)"

Title Variation C: "How to Start a Podcast: [current year] Guide [Equipment + Software + Tips]"

Description Variation B: "Want to start a podcast in [current year]? This guide covers everything: equipment ($100 budget option), best hosting platforms, recording tips, and how to get your first 1,000 listeners."


## Page-Type Templates

### Homepage

```html
<title>[Brand Name] - [Primary Value Proposition]</title>
<meta name="description" content="[Brand] helps [audience] [achieve goal]. [Key feature/benefit]. [CTA]">

Product Page

<title>[Product Name] - [Key Benefit] | [Brand]</title>
<meta name="description" content="[Product] [key features]. [Price/offer if applicable]. [Social proof]. [CTA]">

Blog Post

<title>[How to/What is/Number] [Keyword] [Benefit/Year]</title>
<meta name="description" content="[What they'll learn]. [Key points covered]. [CTA]">

Service Page

<title>[Service] in [Location] - [Brand] | [Differentiator]</title>
<meta name="description" content="[Service description]. [Experience/credentials]. [Key benefit]. [CTA]">

Tips for Success

Front-load keywords - Put important terms at the beginning
Match intent - Description should preview what page delivers
Be specific - Vague descriptions get ignored
Test variations - Small changes can significantly impact CTR
Update regularly - Add current year, refresh messaging
Check competitors - See what's working in your SERP

Title Tag Formula Patterns

Proven Title Formulas

Formula	Template	Example	Best For
How-To	How to [Achieve Result] ([Year])	How to Improve SEO Rankings (2026)	Informational guides
Number List	[Number] [Adjective] [Topic] for [Audience]	15 Proven SEO Strategies for E-commerce	Listicles
Question	[Question]? Here's [Answer Preview]	What Is Technical SEO? Complete Guide	Definition content
Comparison	[Option A] vs [Option B]: [Differentiator]	Ahrefs vs SEMrush: Which SEO Tool Wins?	Comparison pages
Year-Based	Best [Topic] in [Year] ([Tested/Ranked])	Best SEO Tools in 2026 (Expert Tested)	Evergreen + fresh
Benefit-Driven	[Benefit]: [How to Achieve It]	Rank #1 on Google: 10-Step SEO Checklist	High-CTR pages
Parenthetical	[Topic] ([Modifier])	Link Building Guide (With Templates)	Adding value signal
Negative	[Number] [Topic] Mistakes [Consequence]	7 SEO Mistakes That Kill Your Rankings	Problem-awareness content

Title Tag Power Words

Category	Power Words	Use Sparingly
Urgency	Now, Today, Quick, Fast, Instant, 2026	Don't overuse; pair with substance
Value	Free, Proven, Complete, Essential, Ultimate	Avoid hyperbole without backing
Specificity	[Exact number], Step-by-Step, Checklist, Template	More specific = more clicks
Curiosity	Secret, Little-Known, Surprising, Actually	Must deliver on the promise
Authority	Expert, Research-Backed, Data-Driven, Tested	Only use when genuinely expert content
Emotional	Best, Worst, Mistakes, Warning, Powerful	Balance emotion with credibility

Title Tag Length Optimization

Length Range	SERP Behavior	Recommendation
<30 characters	May appear thin	Expand with modifier or brand
30-50 characters	Fully displayed on all devices	Ideal for mobile-first
50-60 characters	Full display on desktop, may truncate mobile	Sweet spot for desktop
60-65 characters	Truncated on some devices	Front-load keywords
>65 characters	Truncated everywhere	Avoid — key info gets cut

Meta Description Copywriting Frameworks

AIDA Framework

Element	What It Does	Example
Attention	Hook with a bold claim or question	"Want to double your organic traffic?"
Interest	Build relevance	"This guide covers 15 proven strategies..."
Desire	Show benefit	"...used by top-ranking sites to increase traffic by 200%."
Action	CTA	"Read the full guide now."

Full Example: "Want to double your organic traffic? This guide covers 15 proven SEO strategies used by top-ranking sites to increase traffic by 200%. Read the full guide now." (158 chars)

PAS Framework

Element	What It Does	Example
Problem	Identify pain point	"Struggling to rank on Google?"
Agitate	Amplify the problem	"Most SEO guides are outdated and miss key ranking factors."
Solution	Offer the solution	"Our 2026 guide covers what actually works. Read now."

Benefit-Proof-CTA Framework

Element	Example
Benefit	"Learn the exact SEO process that grew our traffic 5x"
Proof	"— with real data from 200+ audits."
CTA	"Get the free checklist."

CTR Optimization Data

Factors That Increase Organic CTR

Factor	CTR Impact	Implementation
Number in title	+20-30%	"7 Ways", "15 Tips", "2026"
Question in title	+14%	Start with How, What, Why
Emotional words	+7%	"Proven", "Essential", "Mistake"
Brackets/parentheses	+38%	"[Guide]", "(With Examples)"
Current year	+10-15%	"Best SEO Tools 2026"
Power words	+12%	See Power Words table above
Match search intent	+15-25%	Align title with SERP expectations
Rich results (schema)	+30%	FAQ, HowTo, Review stars

Open Graph Best Practices by Platform

Platform-Specific OG Optimization

Platform	Image Size	Title Length	Description Length	Special Tags
Facebook	1200x630px	40-60 chars	125-155 chars	og:type, og:locale
Twitter/X	1200x600px	70 chars max	200 chars	twitter:card, twitter:site
LinkedIn	1200x627px	70 chars	150 chars	Standard OG tags
Pinterest	1000x1500px (2:3)	100 chars	500 chars	og:type=article preferred
Slack	500x500px min	Full title	First ~300 chars	Standard OG tags

OG Tag Checklist

Tag	Required?	Notes
og:title	Yes	Can differ from HTML title; optimize for social sharing
og:description	Yes	Social-optimized; can differ from meta description
og:image	Yes	Must be absolute URL; minimum 200x200px, ideal 1200x630px
og:url	Yes	Canonical URL
og:type	Yes	"website" for homepage, "article" for blog posts
og:site_name	Recommended	Your brand name
og:locale	Recommended	e.g., "en_US"
twitter:card	Recommended	"summary_large_image" for articles
twitter:site	Recommended	@yourbrand

Reference Materials

Meta Tag Formulas — Proven title and description formulas with templates, power words, and CTR data

Related Skills

seo-content-writer — Create content for meta tags
schema-markup-generator — Add structured data
on-page-seo-auditor — Audit all meta tags
serp-analysis — Analyze competitor meta tags
geo-content-optimizer — GEO optimization complements meta tag improvements
content-quality-auditor — Full CORE-EEAT audit includes C01/C02 items that meta tags address

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 — 7/30/2026

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/meta-tags-optimizer-2/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/2/2026Version v1Bundled 1 file

Illustrative Want to see what meta-tags-optimizer 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.

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

Meta Tags Optimizer

When to Use This Skill

What This Skill Does

How to Use

Create Meta Tags

Optimize Existing Tags

Social Media Tags

Data Sources

Instructions

Validation Checkpoints

Input Validation

Output Validation

Example

Meta Description

Complete Meta Tag Block

A/B Test Variations

Product Page

Blog Post

Service Page

Tips for Success

Title Tag Formula Patterns

Proven Title Formulas

Title Tag Power Words

Title Tag Length Optimization

Meta Description Copywriting Frameworks

AIDA Framework

PAS Framework

Benefit-Proof-CTA Framework

CTR Optimization Data

Factors That Increase Organic CTR

Open Graph Best Practices by Platform

Platform-Specific OG Optimization

OG Tag Checklist

Reference Materials

Related Skills

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry