Ready to supercharge your AI agents?

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

China Mirror Resolver · leoyeai | DecimalAI

DevOpsby leoyeai

China Mirror Resolver

Self-healing China mirror source resolver. Automatically discovers, validates, and configures domestic mirror sources for pip/npm/yarn/pnpm/conda/Docker/Go/ Rust/Maven/Gradle/Homebrew/apt/yum/GitHub/HuggingFace when downloads are slow or timing out in mainland China. Trigger keywords: "换源", "镜像源", "下载慢", "超时", "timeout", "mirror", "registry", "proxy", "connection refused", "SSL error", "443", "ETIMEDOUT", "CondaHTTPError", "pip install failed".

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

60%40%of checks passed -20 pts

Without skill60%

With skill40%

4 fixed10 passed either way5 still failing4 broke

Measured on gemini-3.6-flash8/6/2026v1

Track record

Agent runs: 0; All time

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-china-mirror-resolver
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("leoyeai-china-mirror-resolver")
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 leoyeai-china-mirror-resolver

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/leoyeai-china-mirror-resolver/SKILL.md https://app.decimal.ai/s/leoyeai-china-mirror-resolver/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/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/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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("leoyeai-china-mirror-resolver")
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/leoyeai-china-mirror-resolver/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-china-mirror-resolver/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 leoyeai-china-mirror-resolver

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/leoyeai-china-mirror-resolver/SKILL.md https://app.decimal.ai/s/leoyeai-china-mirror-resolver/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-china-mirror-resolver/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/leoyeai-china-mirror-resolver/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-china-mirror-resolver.json

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

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/6/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

China Mirror Resolver

Mirror URLs break frequently. This skill teaches the agent a self-healing workflow: discover → validate → configure the best available source. A baseline table provides offline fallback; web search enables self-repair.

Execution Flow

User error / request
      │
      ▼
 1. Identify tool type (Section 1)
      │
      ▼
 2. Detect current source config
      │
      ▼
 3. Try ALL baseline sources for that tool (Section 2)
    Validate each with Section 4 thresholds (< 3s = good, 3–10s = acceptable)
      ├─ At least one source < 10s → pick fastest → go to step 6
      └─ All sources > 10s or failed ↓
      ▼
 4. [IF search capable] Search for latest sources (Section 3)
      ├─ Found candidates → go to step 5
      └─ No candidates found → report to user with baseline table as reference
    [IF no search] Report baseline failure to user, suggest manual URL
      │
      ▼
 5. Validate ALL candidates (Section 4), pick fastest passing one
      ├─ At least one passes → go to step 6
      └─ All fail → report failure to user, suggest checking network/proxy
      │
      ▼
 6. Backup original config → write new config → verify with test command
      │
      ▼
 7. Confirm result to user (show old source → new source, response time)

Graceful degradation: If the agent has no web search capability, skip step 4 and use only the baseline table. The skill remains functional with reduced self-healing ability.

Speed selection: When multiple sources pass validation, always select the one with the lowest response time. Test all candidates, not just the first.

1. Diagnostic Table

Match error keywords to identify the tool, then check current config:

Error keywords	Tool	Detect current source
`pip` / `PyPI` / `setup.py` / `No matching distribution`	pip	`pip config get global.index-url`
`npm ERR` / `FETCH_ERROR`	npm	`npm config get registry`
`yarn` / `ESOCKETTIMEDOUT`	yarn	`yarn config get registry` (v1) / `yarn config get npmRegistryServer` (v2+)
`pnpm` / `ERR_PNPM`	pnpm	`pnpm config get registry`
`conda` / `CondaHTTPError` / `PackagesNotFoundError`	conda	`conda config --show channels`
`docker` / `pull` / `manifest` / `toomanyrequests`	Docker	Linux/macOS: `docker info \| grep -A5 "Registry Mirrors"` / Win: Docker Desktop → Settings → Docker Engine
`go: downloading` / `GOPROXY` / `dial tcp`	Go	`go env GOPROXY`
`cargo` / `crates.io` / `Blocking waiting`	Rust (cargo)	check `~/.cargo/config.toml` (Linux/macOS) or `%USERPROFILE%\.cargo\config.toml` (Win)
`rustup` / `could not download`	Rust (rustup)	`echo $RUSTUP_DIST_SERVER` / `$env:RUSTUP_DIST_SERVER`
`maven` / `pom.xml` / `BUILD FAILURE` / `Could not resolve`	Maven	check `~/.m2/settings.xml` or `C:\Users\<user>\.m2\settings.xml`
`gradle` / `Could not resolve` / `build.gradle`	Gradle	check `build.gradle` / `build.gradle.kts` or `~/.gradle/init.gradle`
`brew` / `Homebrew` / `Fetching`	Homebrew	`echo $HOMEBREW_BOTTLE_DOMAIN`
`apt` / `dpkg` / `E: Failed to fetch`	apt (Debian/Ubuntu)	check `/etc/apt/sources.list`
`yum` / `dnf` / `Cannot find a valid baseurl`	yum/dnf (CentOS/RHEL/Fedora)	check `/etc/yum.repos.d/`
`git clone` / `github.com` / `RPC failed`	GitHub accelerator	N/A
`huggingface` / `hf_hub` / `ConnectionError`	Hugging Face	`echo $HF_ENDPOINT` / `$env:HF_ENDPOINT`

2. Baseline Sources

High-stability institutional mirrors. Try these first. If all fail or are too slow (> 10s), proceed to Section 3 (search). Agents without search capability stop here.

pip

Provider	URL
Tsinghua TUNA	`https://pypi.tuna.tsinghua.edu.cn/simple`
Aliyun	`https://mirrors.aliyun.com/pypi/simple/`
USTC	`https://pypi.mirrors.ustc.edu.cn/simple/`
Tencent	`https://mirrors.cloud.tencent.com/pypi/simple/`

npm / yarn / pnpm

Provider	URL
npmmirror	`https://registry.npmmirror.com`
Huawei	`https://repo.huaweicloud.com/repository/npm/`

conda

Provider	URL
Tsinghua TUNA	`https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main`
USTC	`https://mirrors.ustc.edu.cn/anaconda/pkgs/main`
Aliyun	`https://mirrors.aliyun.com/anaconda/pkgs/main`

Docker

Provider	URL
1ms.run	`https://docker.1ms.run`
xuanyuan.me	`https://docker.xuanyuan.me`
DaoCloud	`https://docker.m.daocloud.io`
linkedbus	`https://docker.linkedbus.com`

Go

Provider	URL
goproxy.cn	`https://goproxy.cn`
goproxy.io	`https://goproxy.io`

Rust

Provider	cargo registry	rustup server
USTC	`sparse+https://mirrors.ustc.edu.cn/crates.io-index/`	`https://mirrors.ustc.edu.cn/rustup`
Tsinghua TUNA	`sparse+https://mirrors.tuna.tsinghua.edu.cn/crates.io-index/`	`https://mirrors.tuna.tsinghua.edu.cn/rustup`
RsProxy.cn	`sparse+https://rsproxy.cn/crates.io-index/`	`https://rsproxy.cn/rustup`

Maven / Gradle

Provider	URL
Aliyun Public	`https://maven.aliyun.com/repository/public`
Aliyun Google	`https://maven.aliyun.com/repository/google`
Huawei	`https://repo.huaweicloud.com/repository/maven`

Homebrew (macOS / Linuxbrew)

Provider	HOMEBREW_BOTTLE_DOMAIN
Tsinghua TUNA	`https://mirrors.tuna.tsinghua.edu.cn/homebrew-bottles`
USTC	`https://mirrors.ustc.edu.cn/homebrew-bottles`

apt (Debian / Ubuntu)

Provider	Base URL
Tsinghua TUNA	`https://mirrors.tuna.tsinghua.edu.cn`
Aliyun	`https://mirrors.aliyun.com`
USTC	`https://mirrors.ustc.edu.cn`

yum / dnf (CentOS / RHEL / Fedora)

Provider	Base URL
Tsinghua TUNA	`https://mirrors.tuna.tsinghua.edu.cn`
Aliyun	`https://mirrors.aliyun.com`
USTC	`https://mirrors.ustc.edu.cn`

GitHub Accelerator

Provider	Prefix URL
ghfast.top	`https://ghfast.top/`
gh-proxy.com	`https://gh-proxy.com/`
ghp.ci	`https://ghp.ci/`

Hugging Face

Provider	HF_ENDPOINT
hf-mirror.com	`https://hf-mirror.com`

3. Search Strategy

Capability gate: This section requires web search. If the agent lacks search capability, skip to Section 5 using only baseline sources.

3.1 Search Query Templates

Replace <YEAR> with current year. Use the agent's available search mechanism. Provide both Chinese and English queries for better coverage:

Tool	Chinese query	English query
pip	`pip 国内镜像源 <YEAR> 可用`	`pip china mirror source <YEAR> working`
npm	`npm 国内镜像 registry <YEAR>`	`npm china registry mirror <YEAR>`
conda	`conda 国内镜像源 channels <YEAR>`	`conda china mirror channel <YEAR>`
Docker	`docker 镜像加速源 <YEAR> 可用`	`docker registry mirror china <YEAR> working`
Go	`GOPROXY 国内代理 <YEAR>`	`GOPROXY china proxy <YEAR>`
Rust	`cargo crates 国内镜像 <YEAR>`	`cargo crates china mirror <YEAR>`
Maven	`maven 国内镜像仓库地址 <YEAR>`	`maven china mirror repository <YEAR>`
Homebrew	`homebrew 国内镜像 <YEAR>`	`homebrew china mirror <YEAR>`
apt	`ubuntu apt 国内源 <YEAR>`	`ubuntu apt china mirror <YEAR>`
yum/dnf	`centos yum 国内镜像源 <YEAR>`	`centos yum china mirror <YEAR>`
GitHub	`github 加速代理镜像站 <YEAR>`	`github proxy accelerator china <YEAR>`
HuggingFace	`huggingface 国内镜像下载加速 <YEAR>`	`huggingface china mirror download <YEAR>`

3.2 Source Credibility

Prioritize results in this order:

Official mirror site docs (mirrors.tuna.tsinghua.edu.cn/help, developer.aliyun.com/mirror)
Mirror provider's own site/README (goproxy.cn, npmmirror.com)
Recent posts (< 3 months) from reputable tech communities
GitHub repos with > 100 stars that aggregate mirror lists

Reject: undated articles, posts > 6 months old, zero-reply forum threads, unverifiable personal blogs.

3.3 Candidate Extraction Rules

Extracted URLs must:

Use HTTPS protocol
Belong to known institutions (.edu.cn, major cloud vendors, well-known OSS orgs) OR be cross-referenced in 2+ independent articles
Come from articles published within the last 6 months

Security warning: Never use mirror sources from unknown individuals or unverifiable personal servers. Malicious mirrors can inject tampered packages. Especially for Docker and pip, only use sources from recognized institutions.

4. Validation

Every candidate must pass validation before being written to config.

4.1 Universal HTTP Check

# Linux / macOS
start=$(date +%s%N 2>/dev/null || perl -MTime::HiRes=time -e 'printf "%d\n",time()*1e9')
code=$(curl -o /dev/null -s -w "%{http_code}" --max-time 10 "<URL>")
end=$(date +%s%N 2>/dev/null || perl -MTime::HiRes=time -e 'printf "%d\n",time()*1e9')
echo "HTTP $code | $(( (end - start) / 1000000 ))ms"

# Windows PowerShell
$sw = [System.Diagnostics.Stopwatch]::StartNew()
try { $r = Invoke-WebRequest -Uri "<URL>" -TimeoutSec 10 -UseBasicParsing -ErrorAction Stop
  $sw.Stop(); "OK: HTTP $($r.StatusCode) | $($sw.ElapsedMilliseconds)ms"
} catch { $sw.Stop(); "FAIL: $_" }

4.2 Tool-Specific Validation

Tool	Command / Check	Success Criteria
pip	`pip install --dry-run requests -i <URL> --trusted-host <HOST>`	`Would install` or `already satisfied`
npm	`npm view lodash version --registry <URL>`	Returns version number
yarn v1	`yarn info lodash version --registry <URL>`	Returns version number
pnpm	`pnpm view lodash version --registry <URL>`	Returns version number
conda	`conda search numpy -c <URL> --override-channels`	Returns package list
Docker	HTTP GET `<URL>/v2/`	HTTP 401 (auth required = service alive)
Go	HTTP GET `<URL>/github.com/gin-gonic/gin/@v/list`	Returns version list
Rust	HTTP GET the sparse index URL	HTTP 200
Maven	HTTP GET `<URL>/org/apache/commons/commons-lang3/maven-metadata.xml`	Returns XML content
HuggingFace	HTTP GET `<URL>/api/models?limit=1`	Returns JSON

4.3 Acceptance Criteria

Response Time	Rating	Action
< 3000ms	Excellent	Use this source
3000–10000ms	Acceptable	Use if no faster alternative found
> 10000ms or timeout	Unusable	Try next candidate

Selection rule: Test ALL available candidates (baseline + search-discovered), then select the one with the lowest response time that passes validation.

4.4 Batch Validation Scripts

Pre-built scripts in scripts/:

scripts/validate.sh — Linux / macOS (bash). Supports --json flag for machine-readable output.
scripts/validate.ps1 — Windows (PowerShell)

bash scripts/validate.sh              # test all, colored output
bash scripts/validate.sh pip           # test pip only
bash scripts/validate.sh all --json    # machine-readable JSON output

4.5 Security Notes on Validation

trusted-host warning: Using --trusted-host with pip disables SSL certificate verification for that host. This is a security trade-off. Only use it when the mirror is a known institution (e.g., .edu.cn, major cloud vendor) and the connection is within a trusted network. Prefer mirrors that have valid SSL certificates and do not require trusted-host.

5. Configuration

Core Principles

Backup first — Always backup the original config file before modifying
Merge, don't overwrite — For JSON configs (Docker daemon.json), read existing content and merge new fields. Never blindly overwrite the entire file
Permanent config — Write to config files, not just CLI flags
Verify after write — Run a test command to confirm the new source works

Detailed configuration templates for each tool are in references/config-templates.md. Below is a quick reference of the key commands.

Quick Reference

pip: pip config set global.index-url <URL>

npm: npm config set registry <URL>

yarn v1: yarn config set registry <URL>

yarn v2+: yarn config set npmRegistryServer <URL>

pnpm: pnpm config set registry <URL>

conda: conda config --add channels <URL> && conda config --set show_channel_urls yes

Docker: Read existing daemon.json, add/update registry-mirrors array, write back, restart Docker. See references/config-templates.md for merge logic.

Go: go env -w GOPROXY=<URL>,direct && go env -w GOSUMDB=sum.golang.google.cn

Rust (cargo): Write [source.crates-io] + [source.mirror] to ~/.cargo/config.toml

Rust (rustup): Set RUSTUP_DIST_SERVER and RUSTUP_UPDATE_ROOT env vars

Maven: Add <mirror> block to ~/.m2/settings.xml

Gradle (Groovy): Add maven { url '<URL>' } to repositories block

Gradle (Kotlin): Add maven(url = "<URL>") to repositories block

Homebrew: Set HOMEBREW_BREW_GIT_REMOTE, HOMEBREW_CORE_GIT_REMOTE, HOMEBREW_BOTTLE_DOMAIN env vars

apt: Replace archive.ubuntu.com with mirror host in /etc/apt/sources.list, then sudo apt update

yum/dnf: Backup /etc/yum.repos.d/, replace baseurl in repo files, then sudo yum makecache

GitHub: Prepend accelerator prefix: git clone <PREFIX>https://github.com/<owner>/<repo>.git

HuggingFace: Set HF_ENDPOINT=<URL> env var

6. Restore Official Sources

Tool	Restore Command
pip	`pip config unset global.index-url`
npm	`npm config set registry https://registry.npmjs.org`
yarn v1	`yarn config set registry https://registry.yarnpkg.com`
yarn v2+	`yarn config set npmRegistryServer https://registry.yarnpkg.com`
pnpm	`pnpm config set registry https://registry.npmjs.org`
conda	`conda config --remove-key channels`
Go	`go env -w GOPROXY=https://proxy.golang.org,direct`
Docker	Remove `registry-mirrors` from daemon.json (keep other fields), restart
Rust (cargo)	Remove `[source.*]` sections from config.toml
Rust (rustup)	`unset RUSTUP_DIST_SERVER RUSTUP_UPDATE_ROOT`
Maven	Remove `<mirror>` block from settings.xml
Homebrew	`unset HOMEBREW_BREW_GIT_REMOTE HOMEBREW_CORE_GIT_REMOTE HOMEBREW_BOTTLE_DOMAIN`
apt	Restore `/etc/apt/sources.list` from backup, `sudo apt update`
yum/dnf	Restore `/etc/yum.repos.d/` from backup, `sudo yum makecache`
HuggingFace	`unset HF_ENDPOINT`

7. Notes

Docker & GitHub accelerators have the highest churn rate — always validate before configuring
If the user has an enterprise Nexus/Artifactory, prefer that over public mirrors
WSL 1 and WSL 2 have different network stacks; WSL 2 has its own IP and needs separate Docker/apt config
If HTTP_PROXY / HTTPS_PROXY env vars are set, some tools may bypass mirrors and go through the proxy instead
On ARM architectures (Apple Silicon, ARM Linux), verify that the mirror hosts packages for your architecture
When multiple Python/Node versions coexist (pyenv, nvm, conda envs), config may need to target specific environments rather than global settings
Use scripts/validate.sh or scripts/validate.ps1 for periodic health checks

8. Known Unstable Sources

This section is informational. Always validate before use rather than relying solely on this list, which may itself become outdated.

Source	Status (2026-03)	Notes
`pypi.douban.com` (pip)	Dead	Connection reset
`ghproxy.cc` (GitHub)	Dead	SSL certificate untrusted
`mirrors.aliyun.com/goproxy/` (Go)	Unstable	Homepage 404, module downloads intermittent

9. Cross-Agent Adaptation

Capability Requirements

Capability	Required?	Used in	If absent
Terminal/shell	Required	Steps 2, 4, 5, 6	Cannot function
File read/write	Required	Steps 5, 6	Cannot write config
Web search	Optional	Step 4	Use baseline table only (Section 2)
Web fetch	Optional	Step 4	Use `curl` / `Invoke-WebRequest` via terminal

Platform Adaptation

Claude Code / StepFun: Native support. Place folder in ~/.claude/skills/ or ~/.stepfun/skills/.

Cursor: Create .cursor/rules/china-mirror-resolver.mdc with this content:

---
description: Resolve slow package downloads in China by switching to domestic mirrors. Triggers on: timeout, mirror, 换源, 镜像源, 下载慢
globs:
alwaysApply: false
---

[Paste the content of this SKILL.md here, excluding the YAML frontmatter]

Windsurf: Create .windsurf/rules/china-mirror-resolver.md with this content:

---
trigger: auto
---

[Paste the content of this SKILL.md here, excluding the YAML frontmatter]

Generic LLM (no skill system): Include Section 2 (baseline table) and Section 5 (config quick reference) in the system prompt. Skip Section 3 (search) if the LLM has no search tool.

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

LeoYeAI / openclaw-master-skills

skills/china-mirror-resolver/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 2 files · scripts

Illustrative Want to see what leoyeai/china-mirror-resolver 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?

Safety

What it changes

Track record

Use this skill

China Mirror Resolver

Execution Flow

1. Diagnostic Table

2. Baseline Sources

pip

npm / yarn / pnpm

conda

Docker

Go

Rust

Maven / Gradle

Homebrew (macOS / Linuxbrew)

apt (Debian / Ubuntu)

yum / dnf (CentOS / RHEL / Fedora)

GitHub Accelerator

Hugging Face

3. Search Strategy

3.1 Search Query Templates

3.2 Source Credibility

3.3 Candidate Extraction Rules

4. Validation

4.1 Universal HTTP Check

4.2 Tool-Specific Validation

4.3 Acceptance Criteria

4.4 Batch Validation Scripts

4.5 Security Notes on Validation

5. Configuration

Core Principles

Quick Reference

6. Restore Official Sources

7. Notes

8. Known Unstable Sources

9. Cross-Agent Adaptation

Capability Requirements

Platform Adaptation

SkillSafety

Source

Related skills

More in the registry