Ready to supercharge your AI agents?

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

YouTube Packaging (Title + Thumbnail) · hassancs91 | DecimalAI

Marketingby hassancs91

YouTube Packaging (Title + Thumbnail)

Generates click-optimized YouTube packaging — 3 thumbnail bets under one fixed title, engineered for YouTube's built-in A/B/C thumbnail test, plus a value-forward description, then renders the thumbnails as real images. Use this whenever you want to package a long-form video or turn a video idea into titles and thumbnails. Triggers include how would you package this, title ideas for, thumbnail concept, package this video, A/B variations, and make this clickable. Calibrates to your channel's own

Maintained

SkillScore

SkillScore54/100

Test results 54

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

21%54%of test cases passed +33 pts

Without skill5 of 24

With skill13 of 24

9 fixed4 passed either way10 still failing1 broke

Measured on gemini-3.6-flash9/26/2026v122 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhen generating thumbnail PNG files for YouTube packaging, which local execution tool script path and face reference kit directory must be used?

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 hassancs91-youtube-packaging
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("hassancs91-youtube-packaging")
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 hassancs91-youtube-packaging

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/hassancs91-youtube-packaging/SKILL.md https://app.decimal.ai/s/hassancs91-youtube-packaging/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/hassancs91-youtube-packaging/SKILL.md

This gets SKILL.md only. The skill's 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/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/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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("hassancs91-youtube-packaging")
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/hassancs91-youtube-packaging/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/hassancs91-youtube-packaging/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 2 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 hassancs91-youtube-packaging

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/hassancs91-youtube-packaging/SKILL.md https://app.decimal.ai/s/hassancs91-youtube-packaging/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/hassancs91-youtube-packaging/SKILL.md

This gets SKILL.md only. The skill's 2 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/hassancs91-youtube-packaging/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/hassancs91-youtube-packaging.json

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 9/26/2026
Source: hassancs91/claude-youtube-editor ↗
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

YouTube Packaging (Title + Thumbnail)

Turns a video idea into one locked title + 3 distinct thumbnail bets built for YouTube's native A/B/C thumbnail test, plus one value-forward description — then renders the three thumbnails as real images with Nano Banana Pro.

The whole skill optimizes for one number: CTR (click-through rate). It's the metric YouTube Studio reports per thumbnail, and the only one that isolates packaging from topic and algorithm.

Where these rules come from, and what to do about it

The rules below are not generic YouTube advice — they were derived from Studio CTR data across 20 long-form videos on a real ~1M-subscriber beginner/AI channel, read in CTR order. That dataset isn't shipped (it's another channel's numbers, and its absolutes wouldn't transfer). The patterns do transfer, and they're a much better prior than guessing.

But an inherited rule is a bet, not a fact — about YOUR audience. So:

Cold start (no channel data yet). Use these rules as-is. Say so when you package: "these are uncalibrated defaults — your own CTR data will beat them." Then tell the creator to start logging CTR from video 1.
Calibrated (~10+ long-form videos with CTR). Run references/channel-calibration.md first, then follow that file's numbers wherever it disagrees with this one. Their data wins over anything written here.

Ask which mode you're in if it isn't obvious. Never quote a target CTR the creator hasn't measured.

The core model — read this first

Views = Reach × CTR. Two different levers, driven by two different things.

Reach (how many people YouTube serves it to) comes from the topic and from riding known discovery waves — a tool everyone's searching, a real news moment, a broad money/free promise. Packaging cannot fix a low-ceiling topic.
CTR comes from packaging craft — concrete promise, magnet word, barrier-drop, one bold thumbnail hook. This is the only lever this skill controls.

Good packaging on a narrow topic produces good CTR and low views. That is correct behavior, not a packaging failure. Never blame a title when CTR is healthy and views are small — and never expect a title to rescue a topic nobody wants.

The one guardrail that stops this becoming hollow clickbait: the promise must be one the video actually keeps. Overpromise → the viewer bounces in 30 seconds → retention craters → YouTube chokes the exact reach you were chasing. The widest promise that also holds is what makes YouTube widen distribution. Reality beats expectations.

The flow

Run it in order. Stages 1–2 are fast; the value is getting the promise right before generating, because a wrong promise wastes all three bets.

Stage 1 — Intake

Ask in one message:

Core idea — what's the video about / the rabbit hole.
The concrete takeaway — the one clear thing the viewer walks away with. This becomes the promise. If you can't say it in a sentence, the packaging will be vague — push to name it.
Audience — who clicks this: beginners, practitioners, or a mixed/wide audience? This sets how much jargon a title can carry. (A wide/beginner channel should package for the widest clickable promise and do its segmentation inside the video, never by narrowing the title.)
Locked angle or term? — any angle already committed to, especially a coined/branded phrase.
Conversion target — what the video pitches (a course, a tool, a repo, a newsletter, nothing). Needed for the description. "Nothing" is a valid answer.
Channel data? — do they have ~10+ long-form videos with Studio CTR? Sets calibrated vs cold start. If calibrated and references/channel-calibration.md is still empty, offer to run it first.

Stage 2 — Ceiling + promise (checkpoint before generating)

Gate 1 — Topic ceiling. Classify honestly:

HIGH = broad demand riding a known wave (money / save-money, a broadly useful free capability, a major tool everyone knows).
NARROW = niche format, niche tool, or an insider flex.

If narrow, say so plainly and reset the view expectation before generating: packaging will still maximize CTR, but views are capped by demand. Then decide whether the topic is worth making for conversion even if reach is low. That's a real strategy, but it should be a choice.

Gate 2 — The promise. Draft the core promise as the clearest concrete takeaway, stated plainly — NOT a withheld-drama curiosity gap.

Spell out the takeaway: name the number, the tool, the saving, the outcome.
Don't withhold or moralize. "X Can Do More Than You Think" and "X Is Dead" are the classic floor.
If the video is built on a mechanism — an experiment, a build-off, a comparison — the lesson is the headline; the mechanism is only how the lesson surfaces. Never lead with the mechanism.

CHECKPOINT: State the ceiling classification and the one-line promise. Confirm or fix the promise before generating. Do not skip — three bets off a wrong promise is wasted work.

Stage 3 — Generate the packaging

Structure this correctly, it's the thing people get wrong: YouTube's Test & Compare is thumbnail-only. The title is FIXED across all three variants. So the deliverable is ONE primary title × 3 thumbnail bets, not 3 independent title+thumbnail pairs.

First, lock ONE title. It must pass most of the Title Checklist below. Output with it:

Implied expectation — one line: what the viewer expects walking in. The intro must pay this off. Carry it into the script.

Then 3 thumbnail bets under that fixed title. Each pulls a different lever, so YouTube compares real alternatives rather than three flavors of one idea. For each:

Thumbnail concept — composition per the Thumbnail Checklist: face + expression, the one dominant hook (word or number), color pop, any object.
Thumbnail text — a 1–3 word fragment that combines with the title, never repeats it.
Lever — which lever it tests, one line on the bet.
Honesty check — does this frame stay true under the fixed title, and does the video keep it? A thumbnail promising a beat the video doesn't have must be pulled or the beat must be built.

Lever menu — pick 3 different ones:

Magnet-word lead — Free / Unlimited / 100% / $0
Number/$ lead — a specific figure as the hook
Barrier-drop lead — for beginners / no coding / without [skill]
Object / curiosity-anchored lead — a tangible thing + a value contrast, or a named valuable thing the viewer wants ("the one skill")
News / "Now" lead — only if something genuinely changed
Own-term / brand-fit lead — a coined term. Lower reach (rides no wave) but strong identity — good as one of three, rarely all three.

Then close Stage 3 with:

One description (one per video). Save to videos/<project>/packaging/description.txt:
1. 2-line value hook — the concrete payoff in plain words; name the specific things they'll learn (the real number, the free tool, the exact capability). The title sells the takeaway; these two lines make it specific and undeniable.
2. CTAs — lead with the one matching the Stage 1 conversion target, then any others (repo, free resources, newsletter). If something is free, say so plainly.
3. Timestamps / chapters — first chapter at 0:00, keyword-rich labels. Derive from the edit plan / final cut; re-confirm if the cut length changed.
4. Short like/subscribe nudge.
Self-check — run the title and each thumbnail against both checklists; flag any rule bent and why it's worth it.
Baseline note — if calibrated, restate their measured median + stretch target. If cold start, say plainly that there's no baseline yet and this is the first data point. You may predict which bet lands highest and why — but the test decides. Never crown a winner; the deliverable is 3 worth shipping.

Stage 4 — Refine

Iterate — tighten the title, swap a lever, adjust a hook. All 3 run live in the A/B/C test, so the goal is 3 you're willing to ship, not one.

Stage 5 — Render the thumbnails (Nano Banana Pro)

Turn the 3 locked concepts into actual images. The dedicated /thumbnail skill is the interactive render engine for this stage — it interviews for style elements (environment, text budget, extras) with the creator's calibrated defaults (minimal text) and owns the verify/iterate loop; use it whenever the creator is in the loop. Mechanics, prompt template, and model details live in references/thumbnail-generation.md — load it before generating. The flow:

Build a prompt per concept from its Stage 3 fields using the template in the reference doc. Nano Banana Pro renders the hook word itself (deliberate), so state the exact word, spell it letter-by-letter, and forbid all other text.
Generate into videos/<project>/packaging/thumbs/A|B|C.png with tools/gen_thumbnail.py, passing the media/library/faces/ kit as reference so the face stays consistent. (You supply that kit — see its README. No face kit, no face renders.)
Verify every render before showing it — run the verify checklist in the reference doc (text spelled right + legible, face reads as the creator, one dominant hook, bright/saturated/positive, sane hands, 16:9 <2MB). Regenerate any that fail; only surface passes. This catches the one real risk of model-rendered text: a garbled word.
Iterate — review A/B/C together; change one thing at a time, holding --seed to keep composition steady. Keep each prompt in thumbs/A.txt so refinements are diffs.
Deliver the 3 finals to YouTube spec (--jpg, ≤2MB) plus prompts/seeds, so any winner is re-renderable later.

Remember the loud-vs-calm rule: the thumbnail is intentionally louder than the calm in-video brand (brand.md) — never tone it down to match. See the reference doc.

Title Checklist

A strong title passes most of these. Use as a generator and a filter.

Concrete promise — quantified ($ / count) or absolute (Unlimited / 100% / Free)? Vague = dead.
At least one magnet word — Free, Unlimited, 100%, Money, Easiest.
Outcome-framed, not feature-framed — the viewer's gain, not what the tool does. Selling a tool's capability instead of the viewer's outcome is a reliable floor.
Zero unknown / own-product names — see the self-brand rule below.
Barrier-drop or authenticity rider where the topic invites skepticism — "for beginners," "no coding," "without [skill]," "(No BS)."
News / "Now / New" hook if something genuinely changed — borrows the discovery wave.
A specific noun, not vague curiosity — "the one skill," never "WAY more" / "you won't believe."
No hot-take / "DEAD" / negative framing — make/save/build outperforms opinions. (Test this against your own data; it's one of the most channel-dependent rules here.)
Leads with the takeaway, not the mechanism.

Thumbnail Checklist

Ranked by signal strength. Re-rank against your own data once calibrated.

One dominant hook — never a busy frame. One magnet word OR one big number as the focal element. This is the top-tier device. The multi-logo "kill the competitors" graveyard splits attention and reliably lands only mid-tier — even when the enemy-kill works in the title, render the thumbnail as one clean hook.
Lead with a number/$ when the topic has one — huge, bright. Strong but not sufficient: a number in a busy frame on a narrow topic still sinks.
Big, high-energy positive face. Kill negative emotion. Wide-eyed / excited / shocked, looking at camera, large in frame. Facepalms and flat smiles are the floor.
Bright saturated color pop — green (money), yellow (highlight), red (FREE). Dark and muted frames underperform.
Tangible object in hand for curiosity, especially a value contrast (a small price pointing at something that looks expensive, or vice versa).
No DEAD / negative framing visually — mirrors title rule 8.
Thumbnail text ≠ title — a 1–3 word fragment that combines with the title, never repeats it. Title and thumbnail are two halves of one message.

Hard rules

Long-form only. If asked to package a Short, decline and note this skill is long-form; Shorts are a different packaging game.
One title, three thumbnails. Test & Compare is thumbnail-only. Never ship "3 title+thumbnail pairs" — the test can't measure that.
Clear takeaway over withheld drama — always. Curiosity is allowed only when anchored to a named, valuable thing ("the one skill you need"), never pure mystery.
The self-brand rule: unknown / own-product names stay OUT of titles. They don't kill clicks — they kill reach, because an unknown name rides no discovery wave, so YouTube serves it less. Known brands help and are fine. Own products belong in the thumbnail and the video, never the title.
No hot-take / "DEAD" / negative framing.
3 distinct bets, never 3 flavors of one frame.
Never quote a CTR target the creator hasn't measured. Their median or nothing.
The creator's data beats this file. When references/channel-calibration.md has real numbers that contradict a rule here, the rule is wrong for that channel. Update it.

References

references/channel-calibration.md — how to pull your own CTR from Studio (it is not in the API), build the dataset, derive your baseline and your real levers, and reconcile them back into this file. Run it once you have ~10+ long-form videos.
references/thumbnail-generation.md — Stage 5 render engine: the Nano Banana Pro model/tool (tools/gen_thumbnail.py), the media/library/faces/ reference kit, the prompt template, the per-render verify loop, the loud-vs-calm brand rule, and failure-mode fixes. Load before rendering.

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 v5 — 8/26/2026

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

hassancs91 / claude-youtube-editor

.claude/skills/packaging/SKILL.md

View on GitHub ↗

License MITImported 8/26/2026Version v1Bundled 2 files

Illustrative Want to see what hassancs91/youtube-packaging 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

YouTube Packaging (Title + Thumbnail)

Where these rules come from, and what to do about it

The core model — read this first

The flow

Stage 1 — Intake

Stage 2 — Ceiling + promise (checkpoint before generating)

Stage 3 — Generate the packaging

Stage 4 — Refine

Stage 5 — Render the thumbnails (Nano Banana Pro)

Title Checklist

Thumbnail Checklist

Hard rules

References

SkillSafety

Source

Related skills

More in the registry