Ready to supercharge your AI agents?

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

Get Started Free →

YQ Windows Trash Cleaner · ethanyoq | DecimalAI

DevOpsby ethanyoq

YQ Windows Trash Cleaner

Windows C盘、项目垃圾、Docker/WSL、Git worktree、CodeGraph、Agent 会话或内存异常需要安全审计、清理和验证时使用。

Never made a case worse

SkillScore

SkillScore73/100

Test results 73

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%73%of test cases passed +55 pts

Without skill4 of 22

With skill16 of 22

12 fixed4 passed either way6 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v121 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI collected 6 hours of memory metrics on a running workstation and RAM usage remained stable under load. Which memory assessment outcome label should be assigned?

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 ethanyoq-yq-windows-trash-cleaner
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("ethanyoq-yq-windows-trash-cleaner")
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 ethanyoq-yq-windows-trash-cleaner

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/ethanyoq-yq-windows-trash-cleaner/SKILL.md https://app.decimal.ai/s/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/ethanyoq-yq-windows-trash-cleaner/SKILL.md

This gets SKILL.md only. The skill's 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/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/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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("ethanyoq-yq-windows-trash-cleaner")
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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/ethanyoq-yq-windows-trash-cleaner/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 17 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 ethanyoq-yq-windows-trash-cleaner

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/ethanyoq-yq-windows-trash-cleaner/SKILL.md https://app.decimal.ai/s/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/ethanyoq-yq-windows-trash-cleaner/SKILL.md

This gets SKILL.md only. The skill's 17 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/ethanyoq-yq-windows-trash-cleaner/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/ethanyoq-yq-windows-trash-cleaner.json

This gets SKILL.md only. The skill's 17 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: ethanyoq/skill-hub ↗
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

YQ Windows Trash Cleaner

Run an evidence-first Windows maintenance workflow that is safe to invoke at any time and is not tied to one project, drive, application, or prior incident.

Route the request

Distinguish storage from RAM before collecting data:

Storage intent: C drive/full disk, rapid GB growth, caches, projects, worktrees, Docker/WSL images, backups, sessions, compression, or cleanup.
RAM intent: processes consuming memory, paged/nonpaged pool, pool tags, startup storms, long-running workload growth, Fast Startup, or suspected leaks.
Mixed intent: run the storage and memory tracks separately and reconcile them only in the final report.

Classify authorization:

AUDIT_ONLY: inspect and report. Phrases such as “哪些可以删” do not authorize deletion.
PLAN_ONLY: produce exact manifest IDs, commands, recovery, and predicted impact without changing state.
APPLY_APPROVED: execute only the candidate IDs the user explicitly approved or an exact safe-clean scope the user explicitly requested after seeing the classification.

Scanning is always read-only. A report, HTML button, color, ignored status, or large size is never authorization.

Safety contract

Protect user work before reclaiming space:

Never delete documents, downloads, sessions, databases, credentials, models, evidence, backups, dirty/unmerged worktrees, release artifacts, Docker volumes, system files, or unknown directories by category name alone.
Do not run whole-repository git clean -fdX, blanket docker volume prune, or raw recursive worktree deletion.
Do not hand-delete WinSxS, DriverStore, Windows Installer, pagefile, hiberfil, recovery data, or VSS data.
Do not follow reparse points while measuring or deleting. Resolve every target and reject a target equal to an approved root, outside it, or sharing only a text prefix.
Keep active projects protected. Read repository instructions and current-state documents; check Git state, worktrees, running processes, locks, manifests, lockfiles, evidence paths, and regeneration commands.
Prefer semantic maintenance: package-manager prune commands, git worktree remove, Docker object IDs, official DISM analysis/cleanup, transactional SQLite maintenance, or moving a review item to the Recycle Bin.
Hard deletion is off by default. It requires a fresh explicit decision, exact paths/IDs, full preflight, and an action log.

Run layout

Create a timestamped run directory outside all scanned or cleaned targets:

run/
  scope.json
  baseline/
  projects/projects.json
  storage/storage.json
  memory/
  cleanup-manifest.json
  changes/action-log.jsonl
  verification/
  report.html
  final-report.md

Record timestamps, boot time, scan roots, excluded roots, access failures, commands and exit codes, tool availability, free bytes, and whether sizes are logical, allocated, compressed, sparse, or unknown.

Whole-computer storage workflow

1. Establish current volume state and historical delta

Enumerate fixed volumes, capacity, filesystem, free bytes, BitLocker visibility when available, and prior trustworthy snapshots. Do not call normal variation “rapid growth” without a before/after delta.

Run scripts/Get-ComputerProjectInventory.ps1 with explicit scan roots. Start with every known development root, registered Git worktree root, user Documents/Desktop, temporary development roots, and additional fixed-volume workspace roots. Avoid broad Windows and application-install roots unless the evidence points there.

For one repository or a small set of known repositories, run scripts/Get-ProjectCleanupAudit.ps1 first. It adds git clean -ndX and git clean -nd previews, release/evidence summaries, active-owner evidence without exporting command lines, and explicit review_required_ignored_paths. This is still an audit: it never deletes or stops processes. Read project-cleanup-classification.md.

Run scripts/Get-ComputerStorageInventory.ps1 for system and user storage candidates. Use scripts/Measure-PathUsage.ps1 for exact follow-up measurements. Record inaccessible trees instead of silently treating them as zero.

Default root discovery is heuristic, not proof of complete-computer coverage. For a whole-computer claim, explicitly enumerate all fixed volumes, known workspace roots, and every path returned by git worktree list --porcelain; list excluded and inaccessible roots in the report.

2. Inventory every project semantically

For each discovered Git repository, worktree, or manifest-backed project, record:

canonical root, remote/default branch, branch/HEAD, dirty and untracked state;
registered worktrees and whether each HEAD is contained in the verified remote default branch;
active process command lines that point inside the root;
project instructions and current-state/evidence documents;
manifests and lockfiles that prove a cache can be rebuilt;
generated candidates such as node_modules, .venv, target, .next, test caches, browser output, CodeGraph databases, and build directories;
ambiguous data such as output, dist, release, datasets, models, reports, validation runs, and agent context.

Do not infer that dist, build, output, .runtime, .codex, .claude, or .codegraph is disposable. Classify their contents and role first. Read whole-computer-project-audit.md.

3. Inventory cross-project and application storage

Inspect, when present:

npm, pnpm, yarn, Bun, pip, uv, Cargo, NuGet, Gradle, Maven, browser, model, and updater caches;
Codex/Claude/other agent sessions, runtimes, plugins, managed caches, and worktrees;
Docker logical objects separately from VHDX physical allocation;
WSL distributions and VHDX files;
Temp, Recycle Bin, WER/dumps, update delivery, driver installers, application backups, and databases;
pagefile, hiberfil, component store, DriverStore, Installer cache, Reserved Storage, VSS, and restore points as system-managed or official-tool-only categories.

Use package managers' own inventory/prune operations. A cache's total size is an upper bound, not guaranteed reclaimable space. Read storage-classification.md and docker-storage.md.

4. Classify decisions, not just directories

Use stable machine classes; colors may mirror them in the human report but never grant permission:

SAFE_REBUILDABLE: exact generated object with a proven regeneration path, inactive owner, contained target, and no evidence/user data.
REVIEW_REQUIRED: useful history, project dependencies, clean but unverified clones, backups, sessions, installers, downloads, models, inactive Docker objects, or anything with judgement cost.
KEEP_USER_OR_EVIDENCE: source, dirty work, current/archived evidence, databases, restore volumes, current sessions, and unknown ownership.
SYSTEM_MANAGED_DO_NOT_DELETE: protected Windows files, component/installer/driver/recovery stores, or storage whose official analysis is unavailable.
ADMIN_EVIDENCE_REQUIRED: DISM, VSS, restore-point, Reserved Storage, VHDX compaction, or other facts not visible without elevation.

The detailed deletion gates are also summarized in cleanup-classification.md.

Every candidate needs a confidence level, current bytes, owner, activity check, deletion impact, recovery/regeneration, exact action, expected verification, and approval state.

5. Produce both JSON and a local report

Keep scan data separate from analysis. Generate a local static report with scripts/New-StorageAuditReport.ps1 after classifications are present. Use this reading order:

volume overview and coverage gaps;
top space consumers;
recommended priority;
candidates by class;
retained risks and long-term prevention.

The report may contain private project names and absolute paths. Keep it local by default and redact before sharing. It must not expose direct hard-delete controls. The report information architecture has documented design provenance; see design-provenance.md.

Manifest and controlled execution

Create cleanup-manifest.json before any state change:

{
  "id": "project-cache-001",
  "class": "SAFE_REBUILDABLE",
  "action": "pnpm-store-prune",
  "target": "C:\\absolute\\path-or-object-id",
  "expected_command_path": "C:\\absolute\\path\\to\\pnpm.cmd",
  "bytes": 123,
  "owner": "tool-or-project",
  "preconditions": ["path-contained", "size-rechecked", "owner-inactive"],
  "recovery": "documented regeneration command",
  "approved": false
}

Before applying an approved item:

Resolve and contain the exact target; reject reparse escapes.
Recheck size, owner, Git state, process state, and other drift fields.
Confirm the action type is compatible with the class.
Capture the pre-action free bytes and relevant backup/status evidence.
Execute only this ID. Stop on drift or unexpected output; never widen scope.
Record exit status, released bytes, recovery status, and post-action verification.

For the built-in semantic allowlist, run scripts/Invoke-ApprovedCleanupManifest.ps1 first without -Apply and pass the exact -ApprovedId values. Record its PreflightToken. Apply only after the entire batch passes, using the same manifest and IDs plus -Apply -PreflightToken <token>; the executor reruns all preflights and rejects a stale token before the first mutation. Package actions must bind target to the cache path reported by the owning tool and bind expected_command_path to the reviewed .exe or .cmd. The executor intentionally rejects arbitrary commands, raw recursive deletion, string booleans, unapproved items, non-SAFE_REBUILDABLE classes, active or ambiguous owners, reparse paths, and unverified worktrees. Unsupported actions remain manual review items; never broaden the script's allowlist during a cleanup run merely to make an item pass.

For multiple IDs, complete preflight for the entire batch before the first mutation, then execute in smallest-risk order. A failed later item does not make earlier actions transactional; the action log must say exactly what happened.

Special storage rules

Docker and WSL

Run scripts/Get-DockerStorageAudit.ps1. Keep logical objects separate from VHDX physical storage. Do not start an auto-restarting container fleet only to obtain inventory without considering impact. VHDX compaction requires a current logical inventory, all consumers stopped, wsl --shutdown, detached/no-handle proof, and administrator access. Never promise the arithmetic sparse difference. Read docker-storage.md.

Git worktrees and temporary clones

A worktree becomes eligible only when it is registered, clean including untracked files, inactive, and its HEAD is contained in the verified remote default branch. Remove it with git worktree remove, then prune metadata. A standalone temporary clone also needs clean status and remote containment; prefer recoverable removal when value is uncertain.

CodeGraph

Treat .codegraph as rebuildable only after verifying it is an index, not project evidence, and that the project has no active indexing transaction. Separate the main database from WAL/SHM. Prefer fixing codegraph.json exclusions and rebuilding rather than repeatedly deleting a growing WAL. Exclusions change semantic search coverage, not project build inputs, unless project code explicitly reads that configuration.

Sessions, backups, databases, and models

Retain by default. Consider transparent compression or retention review before deletion. Database maintenance requires owner shutdown, a verified recovery copy, integrity checks, transactional changes, and post-checks. Keep at least one current backup and one pre-maintenance recovery point unless the user approves a different retention policy.

Memory workflow

Run scripts/Collect-WindowsHealthSnapshot.ps1 at clean login, during representative workload, after it ends, and at long-run milestones. Separate processes, paged/nonpaged kernel pool, pool tags, cache/standby, and pagefile. Never join trends across different boot times.

Use scripts/Get-LongRunMemoryAssessment.ps1 and these outcome labels:

VERIFIED_FIXED: representative workload plus valid 48-hour same-boot coverage, no warning/critical sample, no sustained pool growth, and functional gates pass.
HEALTHY_SO_FAR_PENDING_LONG_RUN: healthy evidence but less than 48 hours or incomplete representative workload.
ROOT_CAUSE_NOT_PROVEN: abnormal growth exists but no reproducible component/driver A/B proves ownership.
WARNING_REVIEW_REQUIRED: thresholds or sustained growth are exceeded.
ROLLBACK_REQUIRED: a change caused functional or event-log regression.

Fast Startup affects shutdown plus power-on, not Restart. It can preserve a leaking kernel session but does not create the leak. Restore it only after 24/48-hour stability evidence and an explicit experience tradeoff. Do not disable Defender, storage, network, audio, graphics, or other drivers from one sample or a tag-name association. Read memory-diagnosis.md and quality-gates.md.

Verification and outcome

Measure actual volume free-byte change; do not sum candidate logical sizes as released bytes. Re-run affected project status, worktree lists, package/cache status, Docker/WSL inventory, database checks, and application smoke tests. For system changes, verify networking/VPN, audio/microphone, OneDrive, input/Fn controls, search, and touched vendor software.

Lead with the outcome and use these sections:

Verified facts
Cleanup actions taken
Actual released bytes
Retained and protected items
Unverified/admin-blocked items
Rollback or regeneration
Next maintenance milestone

Never call an audit a cleanup, a candidate size released space, or healthy current memory a proven root-cause fix.

About this skill

Automatic

DevOps & SRE pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ethanyoq / skill-hub

skills/01-agent-engineering/yq-windows-trash-cleaner/SKILL.md

View on GitHub ↗

License MITImported 10/24/2026Version v1Bundled 17 files · scripts

Illustrative Want to see what ethanyoq/yq-windows-trash-cleaner 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

YQ Windows Trash Cleaner

Route the request

Safety contract

Run layout

Whole-computer storage workflow

1. Establish current volume state and historical delta

2. Inventory every project semantically

3. Inventory cross-project and application storage

4. Classify decisions, not just directories

5. Produce both JSON and a local report

Manifest and controlled execution

Special storage rules

Docker and WSL

Git worktrees and temporary clones

CodeGraph

Sessions, backups, databases, and models

Memory workflow

Verification and outcome

SkillSafety

Source

Related skills

More in the registry