Ready to supercharge your AI agents?

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

Get Started Free →

Web Asset Generator · valtterimelkko | DecimalAI

Design & Mediaby valtterimelkko

Web Asset Generator

Generate distribution-ready web assets such as favicons, app icons, PWA icons, and social sharing images.

SkillScore

SkillScore86/100

Test results 86

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

50%86%of test cases passed +36 pts

Without skill11 of 22

With skill19 of 22

8 fixed11 passed either way3 still failing0 broke

Measured on gemini-3.6-flash8/4/2026v119 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskDuring validation of generated assets, what are the maximum allowable file size limits for Facebook social images and Twitter social images, and what size warning threshold applies to browser favicons?

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 valtterimelkko-web-asset-generator
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("valtterimelkko-web-asset-generator")
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 valtterimelkko-web-asset-generator

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/valtterimelkko-web-asset-generator/SKILL.md https://app.decimal.ai/s/valtterimelkko-web-asset-generator/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/valtterimelkko-web-asset-generator/SKILL.md

This gets SKILL.md only. The skill's 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/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/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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("valtterimelkko-web-asset-generator")
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/valtterimelkko-web-asset-generator/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/valtterimelkko-web-asset-generator/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 5 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 valtterimelkko-web-asset-generator

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/valtterimelkko-web-asset-generator/SKILL.md https://app.decimal.ai/s/valtterimelkko-web-asset-generator/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/valtterimelkko-web-asset-generator/SKILL.md

This gets SKILL.md only. The skill's 5 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/valtterimelkko-web-asset-generator/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/valtterimelkko-web-asset-generator.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Not for

This for in-product icons, hero artwork, or broad visual rebranding; prefer web-create-assets or web-replace-assets for those.

Version: v1, tested 8/4/2026
Source: valtterimelkko/agent-workflow-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

Web Asset Generator

Generate professional web assets from logos or text slogans, including favicons, app icons, and social media meta images.

Quick Start

When a user requests web assets:

Use AskUserQuestion tool to clarify needs if not specified:
- What type of assets they need (favicons, app icons, social images, or everything)
- Whether they have source material (logo image vs text/slogan)
- For text-based images: color preferences
Check for source material:
- If user uploaded an image: use it as the source
- If user provides text/slogan: generate text-based images
Run the appropriate script(s):
- Favicons/icons: scripts/generate_favicons.py
- Social media images: scripts/generate_og_images.py
Provide the generated assets and HTML tags to the user

Using Interactive Questions

IMPORTANT: Always use the AskUserQuestion tool to gather requirements instead of plain text questions. This provides a better user experience with visual selection UI.

Why Use AskUserQuestion?

✅ Visual UI: Users see options as clickable chips/tags instead of typing responses ✅ Faster: Click to select instead of typing out answers ✅ Clearer: Descriptions explain what each option means ✅ Fewer errors: No typos or misunderstandings from free-form text ✅ Professional: Consistent with modern Claude Code experience

Example Flow

User request: "I need web assets"

Claude uses AskUserQuestion (not plain text):

What type of web assets do you need?                    [Asset type]
○ Favicons only - Browser tab icons (16x16, 32x32, 96x96) and favicon.ico
○ App icons only - PWA icons for iOS/Android (180x180, 192x192, 512x512)
○ Social images only - Open Graph images for Facebook, Twitter, WhatsApp, LinkedIn
● Everything - Complete package: favicons + app icons + social images

User clicks → Claude immediately knows what to generate

Question Patterns

Below are the standard question patterns to use in various scenarios. Copy the structure and adapt as needed.

Question Pattern 1: Asset Type Selection

When the user's request is vague (e.g., "create web assets", "I need icons"), use AskUserQuestion:

Question: "What type of web assets do you need?" Header: "Asset type" Options:

"Favicons only" - Description: "Browser tab icons (16x16, 32x32, 96x96) and favicon.ico"
"App icons only" - Description: "PWA icons for iOS/Android (180x180, 192x192, 512x512)"
"Social images only" - Description: "Open Graph images for Facebook, Twitter, WhatsApp, LinkedIn"
"Everything" - Description: "Complete package: favicons + app icons + social images"

Question Pattern 2: Source Material

When the asset type is determined but source is unclear:

Question: "What source material will you provide?" Header: "Source" Options:

"Logo image" - Description: "I have or will upload a logo/image file"
"Emoji" - Description: "Generate favicon from an emoji character"
"Text/slogan" - Description: "Create images from text only"
"Logo + text" - Description: "Combine logo with text overlay (for social images)"

Question Pattern 3: Platform Selection (for social images)

When user requests social images but doesn't specify platforms:

Question: "Which social media platforms do you need images for?" Header: "Platforms" Multi-select: true Options:

"Facebook/WhatsApp/LinkedIn" - Description: "Standard 1200x630 Open Graph format"
"Twitter" - Description: "1200x675 (16:9 ratio) for large image cards"
"All platforms" - Description: "Generate all variants including square format"

Question Pattern 4: Color Preferences (for text-based images)

When generating text-based social images:

Question: "What colors should we use for your social images?" Header: "Colors" Options:

"I'll provide colors" - Description: "Let me specify exact hex codes for brand colors"
"Default theme" - Description: "Use default purple background (#4F46E5) with white text"
"Extract from logo" - Description: "Auto-detect brand colors from uploaded logo"
"Custom gradient" - Description: "Let me choose gradient colors"

Question Pattern 5: Icon Type Clarification

When user says "create icons" or "generate icons" (ambiguous):

Question: "What kind of icons do you need?" Header: "Icon type" Options:

"Website favicon" - Description: "Small browser tab icon"
"App icons (PWA)" - Description: "Mobile home screen icons"
"Both" - Description: "Favicon + app icons"

Question Pattern 6: Emoji Selection

When user selects "Emoji" as source material:

Step 1: Ask for project description (free text):

"What is your website/app about?"
Use this to generate emoji suggestions

Step 2: Use AskUserQuestion to present the 4 suggested emojis:

Question: "Which emoji best represents your project?" Header: "Emoji" Options: (Dynamically generated based on project description)

Example: "🚀 Rocket" - Description: "Rocket, launch, startup, space"
Example: "☕ Coffee" - Description: "Coffee, cafe, beverage, drink"
Example: "💻 Laptop" - Description: "Computer, laptop, code, dev"
Example: "🎨 Art" - Description: "Art, design, creative, paint"

Implementation:

# Get suggestions
python scripts/generate_favicons.py --suggest "coffee shop" output/ all

# Then generate with selected emoji
python scripts/generate_favicons.py --emoji "☕" output/ all

Optional: Ask about background color for app icons:

Question: "Do you want a background color for app icons?" Header: "Background" Options:

"Transparent" - Description: "No background (favicons only)"
"White" - Description: "White background (recommended for app icons)"
"Custom color" - Description: "I'll provide a color"

Question Pattern 7: Code Integration Offer

When to use: After generating assets and showing HTML tags to the user

Question: "Would you like me to add these HTML tags to your codebase?" Header: "Integration" Options:

"Yes, auto-detect my setup" - Description: "Find and update my HTML/framework files automatically"
"Yes, I'll tell you where" - Description: "I'll specify which file to update"
"No, I'll do it manually" - Description: "Just show me the code, I'll add it myself"

If user selects "Yes, auto-detect":

Search for framework config files (next.config.js, astro.config.mjs, etc.)
Detect framework type
Find appropriate target file (layout.tsx, index.html, etc.)
Show detected file and ask for confirmation
Show diff of proposed changes
Insert tags if user confirms

If user selects "Yes, I'll tell you where":

Ask user for file path
Verify file exists
Show diff of proposed changes
Insert tags if user confirms

Framework Detection Priority:

Next.js: Look for next.config.js, update app/layout.tsx or pages/_app.tsx
Astro: Look for astro.config.mjs, update layout files in src/layouts/
SvelteKit: Look for svelte.config.js, update src/app.html
Vue/Nuxt: Look for nuxt.config.js, update app.vue or nuxt.config.ts
Plain HTML: Look for index.html or *.html files
Gatsby: Look for gatsby-config.js, update gatsby-ssr.js

Question Pattern 8: Testing Links Offer

When to use: After code integration (or if user declined integration)

Question: "Would you like to test your meta tags now?" Header: "Testing" Options:

"Facebook Debugger" - Description: "Test Open Graph tags on Facebook"
"Twitter Card Validator" - Description: "Test Twitter card appearance"
"LinkedIn Post Inspector" - Description: "Test LinkedIn sharing preview"
"All testing tools" - Description: "Get links to all validators"
"No, skip testing" - Description: "I'll test later myself"

Provide appropriate testing URLs:

Facebook: https://developers.facebook.com/tools/debug/
Twitter: https://cards-dev.twitter.com/validator
LinkedIn: https://www.linkedin.com/post-inspector/
Generic OG validator: https://www.opengraph.xyz/

Workflows

Generate Favicons and App Icons from Logo

When user has a logo image:

python scripts/generate_favicons.py <source_image> <output_dir> [icon_type]

Arguments:

source_image: Path to the logo/image file
output_dir: Where to save generated icons
icon_type: Optional - 'favicon', 'app', or 'all' (default: 'all')

Example:

python scripts/generate_favicons.py /mnt/user-data/uploads/logo.png /home/claude/output all

Generates:

favicon-16x16.png, favicon-32x32.png, favicon-96x96.png
favicon.ico (multi-resolution)
apple-touch-icon.png (180x180)
android-chrome-192x192.png, android-chrome-512x512.png

Generate Favicons and App Icons from Emoji

NEW FEATURE: Create favicons from emoji characters with smart suggestions!

Step 1: Get Emoji Suggestions

When user wants emoji-based icons, first get suggestions:

python scripts/generate_favicons.py --suggest "coffee shop" /home/claude/output all

This returns 4 emoji suggestions based on the description:

1. ☕  Coffee               - coffee, cafe, beverage
2. 🌐  Globe                - web, website, global
3. 🏪  Store                - shop, store, retail
4. 🛒  Cart                 - shopping, cart, ecommerce

Step 2: Generate Icons from Selected Emoji

python scripts/generate_favicons.py --emoji "☕" <output_dir> [icon_type] [--emoji-bg COLOR]

Arguments:

--emoji: Emoji character to use
output_dir: Where to save generated icons
icon_type: Optional - 'favicon', 'app', or 'all' (default: 'all')
--emoji-bg: Optional background color (default: transparent for favicons, white for app icons)

Examples:

# Basic emoji favicon (transparent background)
python scripts/generate_favicons.py --emoji "🚀" /home/claude/output favicon

# Emoji with custom background for app icons
python scripts/generate_favicons.py --emoji "☕" --emoji-bg "#F5DEB3" /home/claude/output all

# Complete set with white background
python scripts/generate_favicons.py --emoji "💻" --emoji-bg "white" /home/claude/output all

Generates same files as logo-based generation:

All standard favicon sizes (16x16, 32x32, 96x96)
favicon.ico
App icon sizes (180x180, 192x192, 512x512)

Note: Requires pilmoji library: pip install pilmoji

Generate Social Media Meta Images from Logo

When user has a logo and needs Open Graph images:

python scripts/generate_og_images.py <output_dir> --image <source_image>

Example:

python scripts/generate_og_images.py /home/claude/output --image /mnt/user-data/uploads/logo.png

Generates:

og-image.png (1200x630 - Facebook, WhatsApp, LinkedIn)
twitter-image.png (1200x675 - Twitter)
og-square.png (1200x1200 - Square variant)

Generate Social Media Meta Images from Text

When user provides a text slogan or tagline:

python scripts/generate_og_images.py <output_dir> --text "Your text here" [options]

Options:

--logo <path>: Include a logo with the text
--bg-color <color>: Background color (hex or name, default: '#4F46E5')
--text-color <color>: Text color (default: 'white')

Example:

python scripts/generate_og_images.py /home/claude/output \
  --text "Transform Your Business with AI" \
  --logo /mnt/user-data/uploads/logo.png \
  --bg-color "#4F46E5"

Generate Everything

For users who want the complete package:

# Generate favicons and icons
python scripts/generate_favicons.py /mnt/user-data/uploads/logo.png /home/claude/output all

# Generate social media images
python scripts/generate_og_images.py /home/claude/output --image /mnt/user-data/uploads/logo.png

Or for text-based:

# Generate favicons from logo
python scripts/generate_favicons.py /mnt/user-data/uploads/logo.png /home/claude/output all

# Generate social media images with text + logo
python scripts/generate_og_images.py /home/claude/output \
  --text "Your Tagline Here" \
  --logo /mnt/user-data/uploads/logo.png

Delivering Assets to User

After generating assets, follow this workflow:

1. Move to Outputs Directory

cp /home/claude/output/* /mnt/user-data/outputs/

2. Show Generated HTML Tags

Display the HTML tags that were automatically generated by the scripts.

Example output for favicons:

<!-- Favicons -->
<link rel="icon" type="image/png" sizes="32x32" href="/favicon-32x32.png">
<link rel="icon" type="image/png" sizes="16x16" href="/favicon-16x16.png">
<link rel="icon" type="image/png" sizes="96x96" href="/favicon-96x96.png">
<link rel="apple-touch-icon" sizes="180x180" href="/apple-touch-icon.png">
<link rel="icon" type="image/png" sizes="192x192" href="/android-chrome-192x192.png">
<link rel="icon" type="image/png" sizes="512x512" href="/android-chrome-512x512.png">

Example output for Open Graph images:

<!-- Open Graph / Facebook -->
<meta property="og:image" content="/og-image.png">
<meta property="og:image:width" content="1200">
<meta property="og:image:height" content="630">
<meta property="og:image:alt" content="Your description here">

<!-- Twitter -->
<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:image" content="/twitter-image.png">
<meta name="twitter:image:alt" content="Your description here">

3. Offer Code Integration (Use AskUserQuestion - Pattern 7)

IMPORTANT: Always ask if the user wants help adding the tags to their codebase.

Question: "Would you like me to add these HTML tags to your codebase?" Header: "Integration" Options:

"Yes, auto-detect my setup"
"Yes, I'll tell you where"
"No, I'll do it manually"

If User Selects "Yes, auto-detect my setup":

A. Detect Framework:

# Search for framework config files
find . -maxdepth 2 -name "next.config.js" -o -name "astro.config.mjs" -o -name "svelte.config.js" -o -name "nuxt.config.js" -o -name "gatsby-config.js"

# Or check package.json
grep -E "next|astro|nuxt|svelte|gatsby" package.json

B. Find Target Files Based on Framework:

Next.js (App Router): app/layout.tsx or app/layout.js
Next.js (Pages Router): pages/_app.tsx or pages/_document.tsx
Astro: src/layouts/*.astro (typically BaseLayout.astro or Layout.astro)
SvelteKit: src/app.html
Vue/Nuxt: app.vue or nuxt.config.ts (head section)
Gatsby: gatsby-ssr.js or src/components/seo.tsx
Plain HTML: index.html, public/index.html, or any *.html file

C. Confirm with User:

Use AskUserQuestion to confirm detected file:

Question: "I found [Framework Name]. Should I update [file_path]?"
Header: "Confirm"
Options:
- "Yes, update this file"
- "No, show me other options"
- "Cancel, I'll do it manually"

D. Show Diff and Insert:

Read the target file
Prepare the insertion (find <head> or appropriate section)
Show the diff to the user
If user confirms, use Edit tool to insert tags

Framework-Specific Insertion Examples:

For Plain HTML (insert before </head>):

<head>
  <meta charset="UTF-8">
  <!-- INSERT TAGS HERE -->
  <link rel="icon" type="image/png" sizes="32x32" href="/favicon-32x32.png">
  ...
</head>

For Next.js App Router (add to metadata export):

export const metadata = {
  icons: {
    icon: [
      { url: '/favicon-32x32.png', sizes: '32x32', type: 'image/png' },
      { url: '/favicon-16x16.png', sizes: '16x16', type: 'image/png' },
    ],
    apple: [
      { url: '/apple-touch-icon.png', sizes: '180x180', type: 'image/png' },
    ],
  },
  openGraph: {
    images: ['/og-image.png'],
  },
  twitter: {
    card: 'summary_large_image',
    images: ['/twitter-image.png'],
  },
}

For Astro (insert in <head> of layout file):

<head>
  <meta charset="UTF-8">
  <!-- Favicons -->
  <link rel="icon" type="image/png" sizes="32x32" href="/favicon-32x32.png">
  ...
</head>

If User Selects "Yes, I'll tell you where":

Ask user for the file path
Verify file exists using Read tool
Show where tags will be inserted
Show diff
Insert if user confirms

If User Selects "No, I'll do it manually":

Provide brief instructions:

Place asset files in the public/static directory of your website
Add the HTML tags to the <head> section of your HTML
Update placeholder values (title, description, URL, alt text)

4. Offer Testing Links (Use AskUserQuestion - Pattern 8)

Question: "Would you like to test your meta tags now?" Header: "Testing" Options:

"Facebook Debugger"
"Twitter Card Validator"
"LinkedIn Post Inspector"
"All testing tools"
"No, skip testing"

Provide Testing URLs:

Facebook Sharing Debugger: https://developers.facebook.com/tools/debug/
- Paste your URL and click "Debug" to see preview
- Click "Scrape Again" to refresh cache
Twitter Card Validator: https://cards-dev.twitter.com/validator
- Paste your URL to see how Twitter card will appear
LinkedIn Post Inspector: https://www.linkedin.com/post-inspector/
- Check how links appear when shared on LinkedIn
OpenGraph.xyz: https://www.opengraph.xyz/
- Generic Open Graph validator for quick checks

5. Final Instructions

Remind user to:

✅ Copy asset files to their public/static directory
✅ Update dynamic values in meta tags (og:title, og:description, og:url)
✅ Test on actual platforms after deployment
✅ Update alt text to be descriptive and accessible

Important Notes:

OG images must be accessible via HTTPS URLs (not localhost)
URLs in meta tags should be absolute (https://yourdomain.com/og-image.png)
Test after deploying to production/staging environment

Best Practices

Image Requirements

Logos: Should be square or nearly square for best results
High resolution: Provide largest available version (scripts will downscale)
Transparent backgrounds: PNG with transparency works best for favicons
Solid backgrounds: Recommended for app icons and social images

Text Content

Text length affects font size automatically:
- Short text (≤20 chars): 144px font - Large and impactful
- Medium text (21-40 chars): 120px font - Standard readable size
- Long text (41-60 chars): 102px font - Reduced for fit
- Very long text (>60 chars): 84px font - Minimal size
Keep text concise for maximum impact
Use 2-3 lines of text maximum for social images
Avoid special characters that may not render well

Color Choices

Ensure sufficient contrast (4.5:1 minimum for readability)
Use brand colors consistently
Consider both light and dark mode contexts

Validation and Quality Checks

Both generate_og_images.py and generate_favicons.py support automated validation with the --validate flag.

When to Use Validation

Always recommend validation when:

User is generating for production/deployment
User asks about file sizes or quality
User mentions platform requirements (Facebook, Twitter, etc.)
User is new to web assets and may not know requirements

Validation is optional for:

Quick prototypes or testing
Users who explicitly decline
When time is a concern

What Gets Validated

For Social Media Images (OG Images)

File Size Validation:

Facebook/LinkedIn/WhatsApp: Must be <8MB
Twitter: Must be <5MB
Warning if within 80% of limit

Dimension Validation:

Checks against platform-specific recommended sizes:
- Facebook/LinkedIn: 1200x630 (1.91:1 ratio)
- Twitter: 1200x675 (16:9 ratio)
- Square: 1200x1200 (1:1 ratio)
Warns if aspect ratio is >10% off target
Errors if below minimum dimensions

Format Validation:

Facebook/LinkedIn: PNG, JPG, JPEG
Twitter: PNG, JPG, JPEG, WebP
Errors if unsupported format

Accessibility (Contrast Ratio):

Only for text-based images
Calculates WCAG 2.0 contrast ratio
Reports compliance level:
- WCAG AAA: 7.0:1 (normal text) or 4.5:1 (large text)
- WCAG AA: 4.5:1 (normal text) or 3.0:1 (large text)
- Fails if below AA minimum

For Favicons and App Icons

File Size Validation:

Favicons: Warns if >100KB (recommended for fast loading)
App icons: Warns if >500KB (recommended for mobile)
No hard limits, but warnings help optimize performance

Dimension Validation:

Verifies each icon matches expected size (16x16, 32x32, etc.)
Ensures square aspect ratio

Format Validation:

Checks all files are PNG (or ICO for favicon.ico)

How to Use Validation

In generate_og_images.py:

python scripts/generate_og_images.py output/ --text "My Site" --validate

In generate_favicons.py:

python scripts/generate_favicons.py logo.png output/ all --validate

Output Format:

✓ Success (green): All checks passed
⚠ Warning (yellow): Issues to consider but not critical
❌ Error (red): Must be fixed before deployment

Example Validation Output

======================================================================
Running validation checks...
======================================================================

og-image.png:

Facebook Validation:
======================================================================
  ✓ File size 0.3MB is within Facebook limits
  ✓ Dimensions 1200x630 match Facebook recommended size
  ✓ Format PNG is supported by Facebook

LinkedIn Validation:
======================================================================
  ✓ File size 0.3MB is within LinkedIn limits
  ✓ Dimensions 1200x630 match LinkedIn recommended size
  ✓ Format PNG is supported by LinkedIn

======================================================================
Accessibility Checks:
======================================================================
  ✓ Contrast ratio 8.6:1 meets WCAG AAA standards (4.5:1 required)

======================================================================
Summary: 9/9 checks passed
✓ All validations passed!

Integrating Validation into Workflows

After generating assets, if validation was NOT run:

Show the tip message: "💡 Tip: Use --validate to check file sizes, dimensions, and accessibility"
Optionally ask: "Would you like me to run validation on these files now?"

If validation was run and issues found:

Explain any errors or warnings
Offer to fix issues (e.g., resize, recompress, adjust colors)
Re-run generation with fixes if user agrees

If validation passes:

Confirm: "✅ All validation checks passed!"
Proceed with code integration and testing links

Specifications and Platform Details

For detailed platform specifications, size requirements, and implementation guidelines, read:

references/specifications.md: Comprehensive specs for all platforms

Handling Common Requests

"Create a favicon for my site"

Use AskUserQuestion:

Question: "Do you have a logo image, or should I create a text-based favicon?"
Header: "Source"
Options:
- "Logo image" - Description: "I have/will upload a logo file"
- "Text-based" - Description: "Generate from text or initials"

Then ask:

Question: "Do you also need PWA app icons for mobile devices?"
Header: "Scope"
Options:
- "Favicon only" - Description: "Just browser tab icons (16x16, 32x32, 96x96)"
- "Include app icons" - Description: "Add iOS/Android icons for home screen (180x180, 192x192, 512x512)"

Generate: Use generate_favicons.py with appropriate parameters

"Make social sharing images"

Use AskUserQuestion:

Question: "Which social media platforms do you need images for?"
Header: "Platforms"
Multi-select: true
Options:
- "Facebook/WhatsApp/LinkedIn" - Description: "Standard 1200x630 format"
- "Twitter" - Description: "1200x675 (16:9 ratio)"
- "All platforms" - Description: "Generate all variants"

Then ask:

Question: "What should the images contain?"
Header: "Content"
Options:
- "Logo only" - Description: "Resize my logo for social sharing"
- "Text only" - Description: "Create images from text/slogan"
- "Logo + text" - Description: "Combine logo with text overlay"

Generate: Use generate_og_images.py with appropriate parameters

"I need everything for my website"

Use AskUserQuestion:

Question: "What source material will you provide?"
Header: "Source"
Options:
- "Logo image" - Description: "I have a logo to use for all assets"
- "Logo + tagline" - Description: "Logo for icons, logo+text for social images"
- "Text only" - Description: "Generate all assets from text/initials"

Generate:

Both favicons and Open Graph images with complete HTML implementation
Provide instructions for file placement and testing

User provides both logo and tagline

Use AskUserQuestion:

Question: "How should I use your logo and tagline?"
Header: "Layout"
Options:
- "Logo above text" - Description: "Logo at top, tagline centered below"
- "Logo + text side-by-side" - Description: "Logo on left, text on right"
- "Text only on social images" - Description: "Use logo for icons, text-only for social sharing"
- "Logo background with text" - Description: "Subtle logo background with prominent text"

Generate: Use --text and --logo parameters together in generate_og_images.py

Dependencies

The scripts require:

Python 3.6+
Pillow (PIL): pip install Pillow --break-system-packages
Pilmoji (for emoji support): pip install pilmoji (optional, only needed for emoji-based generation)
emoji (for emoji suggestions): pip install emoji (optional, only needed for emoji suggestions)

Install if needed before running scripts.

For emoji features, install both:

pip install pilmoji emoji --break-system-packages

When it activates

Automatically, when a task matches. Use when the user needs browser/site metadata imagery rather than core product illustration or UI asset replacement.

About this skill

Automatic

Frontend / UI pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

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

valtterimelkko / agent-workflow-skills

skills/web-asset-generator/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 5 files · scripts

Illustrative Want to see what valtterimelkko/web-asset-generator 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.

majiayu000/web-asset-generatorGenerate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags.Near-identical description

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Not for

Web Asset Generator

Quick Start

Using Interactive Questions

Why Use AskUserQuestion?

Example Flow

Question Patterns

Question Pattern 1: Asset Type Selection

Question Pattern 2: Source Material

Question Pattern 3: Platform Selection (for social images)

Question Pattern 4: Color Preferences (for text-based images)

Question Pattern 5: Icon Type Clarification

Question Pattern 6: Emoji Selection

Question Pattern 7: Code Integration Offer

Question Pattern 8: Testing Links Offer

Workflows

Generate Favicons and App Icons from Logo

Generate Favicons and App Icons from Emoji

Step 1: Get Emoji Suggestions

Step 2: Generate Icons from Selected Emoji

Generate Social Media Meta Images from Logo

Generate Social Media Meta Images from Text

Generate Everything

Delivering Assets to User

1. Move to Outputs Directory

2. Show Generated HTML Tags

3. Offer Code Integration (Use AskUserQuestion - Pattern 7)

If User Selects "Yes, auto-detect my setup":

If User Selects "Yes, I'll tell you where":

If User Selects "No, I'll do it manually":

4. Offer Testing Links (Use AskUserQuestion - Pattern 8)

5. Final Instructions

Best Practices

Image Requirements

Text Content

Color Choices

Validation and Quality Checks

When to Use Validation

What Gets Validated

For Social Media Images (OG Images)

For Favicons and App Icons

How to Use Validation

Example Validation Output

Integrating Validation into Workflows

Specifications and Platform Details

Handling Common Requests

"Create a favicon for my site"

"Make social sharing images"

"I need everything for my website"

User provides both logo and tagline

Dependencies

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry