Ready to supercharge your AI agents?

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

lovable-cleanup · sickn33 | DecimalAI

Frontendby sickn33

lovable-cleanup

Audits and strips Lovable scaffolding from Vite + React projects — removes lovable-tagger, swaps placeholder assets, prunes unused Radix deps, and cleans generated docs so the codebase ships as yours.

Maintained

SkillScore

SkillScore87/100

Test results 74 · Live runs 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

61%74%of test cases passed +13 pts

Without skill14 of 23

With skill17 of 23

3 fixed14 passed either way6 still failing0 broke

Measured on gemini-3.6-flash9/3/2026v2 · latest is v320 comparable

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 31; 13 in the last 30 days

See one task, with and without the skill

One test taskWhat specific items should you search for when inspecting `src/main.tsx` and `src/App.tsx` during an export cleanup pass?

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 sickn33-lovable-cleanup
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("sickn33-lovable-cleanup")
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 sickn33-lovable-cleanup

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/sickn33-lovable-cleanup/SKILL.md https://app.decimal.ai/s/sickn33-lovable-cleanup/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/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/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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("sickn33-lovable-cleanup")
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/sickn33-lovable-cleanup/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/sickn33-lovable-cleanup/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 sickn33-lovable-cleanup

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/sickn33-lovable-cleanup/SKILL.md https://app.decimal.ai/s/sickn33-lovable-cleanup/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/sickn33-lovable-cleanup/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/sickn33-lovable-cleanup/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/sickn33-lovable-cleanup.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: v3 (v2 tested 9/3/2026)
Source: sickn33/antigravity-awesome-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

lovable-cleanup

Remove unwanted Lovable scaffolding while preserving required attribution, licenses and useful project history. Made with agentic-awesome-skills · author: whoisabhishekadhikari

Overview

Lovable (lovable.dev) bootstraps Vite + React + shadcn/ui projects with its own tagger dependency, branding, placeholder assets, and generated markdown docs baked in. Most developers export from Lovable and want a clean, ownable codebase before shipping or open-sourcing. This skill covers all 15 areas where Lovable leaves fingerprints.

When to Use This Skill

User says "clean up my Lovable project" or "remove Lovable branding"
User says "de-Lovable", "I exported from Lovable", or "audit for Lovable leftovers"
Project contains lovable-tagger in package.json
Project contains CLEANUP_SUMMARY.md, DEPLOYMENT_GUIDE.md, or DEVELOPMENT_SUMMARY.md
index.html still has a generic <title> or Lovable favicon
User wants to audit a Vite/React project for scaffolding leftovers before shipping

Core Concepts

What Lovable injects

Lovable adds three categories of scaffolding that must be removed:

Dependency — lovable-tagger dev dep + componentTagger() call in vite.config.ts. Verify all configuration/import references and project-specific use before removal.
Branding artifacts — favicon.ico/png, og-image.png, logo.png, generic <title>, and a Lovable project URL in README.md.
Generated docs — CLEANUP_SUMMARY.md, DEPLOYMENT_GUIDE.md, DEVELOPMENT_SUMMARY.md, LOGO_UPDATE.md in the project root.

Why the execution order matters

Inspect source/config references before removing dependencies; update the manifest and lockfile with the project’s existing package manager. Cleaning docs last means the README reflects the already-cleaned project.

Unused dep footprint

Lovable pre-installs the full shadcn/ui component set (~29 components) and all Radix UI primitives (~30 packages). Most projects use 5–10. The unused ones are safe to remove but @radix-ui/react-slot must be kept — it is an indirect dep used internally by many shadcn components via the asChild prop.

Recommended Execution Order

Audit source/config and dependencies (Areas 2 & 7) — establish each removal candidate first
Build config (Area 3) — remove the tagger from Vite
Entry points (Areas 4 & 6) — clear runtime references
Assets (Area 5) — swap brand files (defer if assets not ready yet)
Docs & README (Areas 1 & 10) — clean last so README reflects the cleaned project
Environment & Git (Areas 9 & 12) — security sweep
SEO / deploy (Area 11) — usually a no-op; confirm and move on
Unused deps (Area 13) — safe to defer until after ship if on a deadline
Favicon / CDN cache (Area 15) — do ASAP after assets are swapped; browser or CDN caching can keep the old icon visible, so verify the live response

Step-by-Step Guide

Area 1 · README.md

Line 1: Replace # Welcome to your Lovable project with the real project title
Line 5: Remove https://lovable.dev/projects/REPLACE_WITH_PROJECT_ID
Lines 11–19: Delete the "Use Lovable" instructions block
Lines 65–73: Delete the "Deploy via Lovable / custom domain docs" block

✅ After stripping, read the README end-to-end. Offer to write a replacement intro paragraph if large sections were removed.

Area 2 · package.json

Remove "lovable-tagger" from devDependencies
Rename "name" from "vite_react_shadcn_ts" to the real project name (kebab-case)
Scan the scripts block for "lovable" or "lovable:*" entries and remove them

grep -n "lovable" package.json

Area 3 · vite.config.ts

Remove import { componentTagger } from "lovable-tagger"
Remove mode === 'development' && componentTagger() from the plugins array
Remove .filter(Boolean) if it was only present to handle the conditional tagger

grep -n "lovable\|componentTagger\|filter(Boolean)" vite.config.ts

Area 4 · index.html

Replace the generic <title> with the real product name
Remove any  comments or Lovable meta tags
Replace the Lovable favicon reference if present

grep -in "lovable\|generator" index.html

Area 5 · public/ assets

Replace these files (keep filenames, swap content):

File	Action
`favicon.ico`	Overwrite with real icon — do NOT just delete, see Area 15
`favicon.png`	Replace with real icon
`og-image.png` / `logo.png`	Replace with real brand assets
`placeholder.svg`	Delete only after checking source, CSS, dynamic paths and deployed references

✅ Flag which files are actually referenced in <head> vs dead weight so the user knows what to prioritise.

Area 6 · Source files

src/main.tsx — scan for Lovable HOCs, wrappers, or comments
src/App.tsx — same
Auto-generated components — look for // generated by Lovable headers

grep -rn "lovable\|Lovable" src/ --include="*.tsx" --include="*.ts"

Area 7 · Lockfile

npm uninstall lovable-tagger
grep "lovable-tagger" package-lock.json

Use yarn remove or pnpm remove if the project uses those instead.

Area 8 · package.json scripts (follow-up)

Double-check after Area 2 — scripts are sometimes injected separately from deps:

grep -n '"lovable' package.json

Area 9 · Environment files

# Print filenames only: matching values may contain credentials.
rg -l -i "lovable" -- .env .env.local .env.example 2>/dev/null

Remove any Lovable API keys or project IDs. If a variable is Lovable-only, delete the entire line — don't leave an empty key.

Area 10 · Root markdown docs

Delete or repurpose these common Lovable-generated files:

CLEANUP_SUMMARY.md
DEPLOYMENT_GUIDE.md
DEVELOPMENT_SUMMARY.md
LOGO_UPDATE.md

grep -rln "lovable\|Lovable" *.md 2>/dev/null

✅ Skim each file before deleting — Lovable docs sometimes contain useful architecture notes worth preserving in a rewritten CONTRIBUTING.md or ARCHITECTURE.md.

Area 11 · SEO & deploy config

Usually clean — confirm and move on:

grep -in "lovable" \
  public/robots.txt public/sitemap.xml public/_redirects \
  vercel.json netlify.toml 2>/dev/null

After replacing og-image.png, update OG meta in index.html:

<meta property="og:image" content="/og-image.png" />
<meta property="og:url" content="https://your-domain.com" />
<meta property="og:title" content="Your Real Title" />

Area 12 · Git config

grep -in "lovable" .gitignore
ls .git/hooks/

Inspect Lovable-specific entries/hooks. Preserve secret/build ignores, license notices and useful safety hooks; remove only confirmed obsolete behavior.

Area 13 · Unused dependencies

Step 1 — Map what's actually imported

tmpdir="$(mktemp -d "${TMPDIR:-/tmp}/lovable-cleanup.XXXXXX")" || exit 1
grep -rh "from [\"']@radix-ui/" src/ --include="*.tsx" --include="*.ts" \
  | grep -oP "from [\"']\K@radix-ui/[^\"']+" | sort -u > "$tmpdir/radix-used.txt"

grep -rh "from [\"']@/components/ui/" src/ --include="*.tsx" \
  | grep -oP "from [\"']\K@/components/ui/[^\"']+" | sort -u > "$tmpdir/shadcn-used.txt"

Step 2 — Diff against installed

grep -oP '"@radix-ui/[^"]+' package.json | tr -d '"' | sort > "$tmpdir/radix-installed.txt"
diff "$tmpdir/radix-installed.txt" "$tmpdir/radix-used.txt"

Step 3 — Bulk remove & verify

npm uninstall @radix-ui/react-accordion @radix-ui/react-alert-dialog  # etc.
npm run build

Area 14 · Generic Lovable artifacts

components.json — verify style, baseColor, and aliases match the real project
eslint.config.js — usually standard; quick scan only

grep -in "lovable" components.json eslint.config.js

Area 15 · Favicon removal & stale CDN caches (Vercel)

Lovable ships a default favicon.ico that browsers auto-request from site root and that can remain visible after cleanup through browser or CDN caching. Handle the four steps — replace the path, link all icon flavours, keep unversioned icon URLs revalidatable, and verify after deploy — then purge the confirmed Vercel project cache only if the live response stays stale. Full commands/JSON live in references/favicon-vercel-cleanup.md.

Master Scan Command

rg -l -i "lovable|lovable-tagger|lovable\.dev" --glob "!node_modules/**" --glob "!.git/**" --glob "!dist/**" --glob "!build/**" .

Examples

Example 1: Full audit from scratch

User: I just exported my project from Lovable. Clean it up.

Agent:
1. Runs master scan — finds 23 matches across 8 files
2. Uninstalls lovable-tagger, renames package.json "name"
3. Strips vite.config.ts of componentTagger
4. Updates index.html title, removes generator comment
5. Flags 4 markdown docs for deletion, skims each first
6. Produces cleanup report

Example 2: Targeted dep pruning only

User: Just prune the unused Radix packages from my Lovable project.

Agent:
1. Runs grep diff (Area 13 only)
2. Identifies 18 unused @radix-ui packages
3. Confirms each candidate including indirect/dynamic imports, then removes only unused packages
4. Runs npm run build to verify — passes clean

Best Practices

✅ Do: Inspect source/config imports before removing dependencies
✅ Do: Skim Lovable-generated docs before deleting — may contain useful arch notes
✅ Do: Verify npm run build passes after every batch of changes
✅ Do: Replace favicons at the existing paths (Area 15), then verify the live response and purge only the confirmed project if it remains stale
✅ Do: Deploy replacement favicon content and cache headers in the same commit
✅ Do: Replace OG image before launch — it directly affects social sharing previews
❌ Don't: Remove @radix-ui/react-slot — it's an indirect dep of most shadcn components
❌ Don't: Leave empty env vars like LOVABLE_PROJECT_ID= — delete the whole line

Limitations

This skill does not create or source real brand assets (favicons, OG images). Area 15 generates a transparent placeholder ICO only — the user must supply genuine artwork.
Dep pruning (Area 13) is a candidate audit, not proof of safety — some Radix packages are indirect deps not caught by a direct grep. Always verify with npm run build.
The skill does not modify components.json aliases automatically — it only scans and flags mismatches for the user to fix manually.
Does not cover Lovable-specific backend integrations (Supabase row-level security, edge functions) — those require separate review.

Troubleshooting

Problem: Build fails after removing Radix packages

Symptoms: Module not found error for a @radix-ui/* package
Solution: Re-add the missing package. Open src/components/ui/*.tsx and search for the from '@radix-ui/...' import to find which component depends on it.

Problem: lovable-tagger still in lockfile after uninstall

Symptoms: grep "lovable-tagger" package-lock.json returns results
Solution: Check direct/transitive dependency references, workspaces and package-manager consistency. Use its supported uninstall/lockfile update; preserve the lockfile and investigate remaining references before any clean reinstall.

Problem: Generic title still showing in browser after updating index.html

Symptoms: Browser tab shows "Lovable" or "Vite App" despite edits
Solution: Check for a <Helmet> or <Head> component in src/App.tsx or a layout wrapper — React-level title tags override index.html at runtime.

Problem: Old favicon still serving after deletion (Vercel)

Symptoms: curl -sI https://<domain>/favicon.ico returns the old ETag with x-vercel-cache: HIT after the replacement deployment. Solution: Overwrite public/favicon.ico with replacement content (a transparent 1×1 ICO if no real asset yet), verify the custom domain, then use the explicit Vercel CDN purge only if the response remains stale — see Area 15.

Related Skills

@vite-config — Vite configuration best practices
@shadcn-setup — shadcn/ui installation and customization
@react-cleanup — general React project hygiene

Additional Resources

Output Format

After completing the audit, produce a cleanup report:

## ✅ Cleaned
<list of changes made>

## ⚠️ Needs your input
<items needing a decision — brand assets, project name, domain>

## 🗑️ Deferred (safe to do later)
<e.g. unused dep pruning, OG image swap>

Made with agentic-awesome-skills · author: whoisabhishekadhikari

Audit limits and authority

Fixed README line numbers and import greps are hints, not deletion rules. Include dynamic imports, CSS/assets, workspaces, tests and package metadata before pruning; a passing build alone does not establish runtime behavior or license clearance. Preserve third-party copyright/license and contributor attribution even when changing product branding. GNU grep -P examples require GNU grep and can miss imports; use an available parser/search tool and review candidates. Package-manager removal can execute lifecycle scripts or access the network: inspect scripts and use the project’s dependency policy. Do not expose secret values in scan results; filename-only matching avoids the incomplete redaction pattern. Back up replaced assets and review the diff before deployment or cache purge. The favicon helper overwrites the selected regular file atomically; its checks assume a trusted, non-concurrently-mutated directory and are not a race-proof hostile-filesystem sandbox. Link SVG/Apple icons only when those files actually exist; verify response bytes as well as headers.

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 v8 — 10/29/2026

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

sickn33 / antigravity-awesome-skills

skills/lovable-cleanup/SKILL.md

View on GitHub ↗

License MITImported 11/8/2026Version v3Bundled 2 files · scripts

Illustrative Want to see what sickn33/lovable-cleanup 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

lovable-cleanup

Overview

When to Use This Skill

Core Concepts

What Lovable injects

Why the execution order matters

Unused dep footprint

Recommended Execution Order

Step-by-Step Guide

Area 1 · README.md

Area 2 · package.json

Area 3 · vite.config.ts

Area 4 · index.html

Area 5 · public/ assets

Area 6 · Source files

Area 7 · Lockfile

Area 8 · package.json scripts (follow-up)

Area 9 · Environment files

Area 10 · Root markdown docs

Area 11 · SEO & deploy config

Area 12 · Git config

Area 13 · Unused dependencies

Area 14 · Generic Lovable artifacts

Area 15 · Favicon removal & stale CDN caches (Vercel)

Master Scan Command

Examples

Example 1: Full audit from scratch

Example 2: Targeted dep pruning only

Best Practices

Limitations

Troubleshooting

Problem: Build fails after removing Radix packages

Problem: lovable-tagger still in lockfile after uninstall

Problem: Generic title still showing in browser after updating index.html

Problem: Old favicon still serving after deletion (Vercel)

Related Skills

Additional Resources

Output Format

Audit limits and authority

SkillSafety

Source

Related skills

More in the registry