Ready to supercharge your AI agents?

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

MLX Swift Framework · timmyy123 | DecimalAI

AI/MLby timmyy123

MLX Swift Framework

MLX Swift - High-performance ML framework for Apple Silicon with lazy evaluation, automatic differentiation, and unified memory

Never made a case worseMaintained

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

50%95%of test cases passed +45 pts

Without skill11 of 22

With skill21 of 22

10 fixed11 passed either way1 still failing0 broke

Measured on gemini-3.8-flash11/2/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI have a Swift MLX tensor known at compile time to use `.float16` precision, and I need to obtain its maximum finite upper bound without unwrapping an optional. Which property on DType provides this value directly?

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 timmyy123-swift-mlx
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("timmyy123-swift-mlx")
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 timmyy123-swift-mlx

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/timmyy123-swift-mlx/SKILL.md https://app.decimal.ai/s/timmyy123-swift-mlx/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/timmyy123-swift-mlx/SKILL.md

This gets SKILL.md only. The skill's 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/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/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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("timmyy123-swift-mlx")
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/timmyy123-swift-mlx/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/timmyy123-swift-mlx/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 10 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 timmyy123-swift-mlx

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/timmyy123-swift-mlx/SKILL.md https://app.decimal.ai/s/timmyy123-swift-mlx/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/timmyy123-swift-mlx/SKILL.md

This gets SKILL.md only. The skill's 10 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/timmyy123-swift-mlx/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/timmyy123-swift-mlx.json

This gets SKILL.md only. The skill's 10 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 11/2/2026
Source: timmyy123/llm-hub ↗
License: NOASSERTION

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

MLX Swift Framework

MLX Swift is Apple's high-performance machine learning framework designed specifically for Apple Silicon. It provides NumPy-like array operations with lazy evaluation, automatic differentiation, and unified CPU/GPU memory.

When to Use This Skill

Array operations on Apple Silicon (MLXArray)
Building neural networks (MLXNN)
Training models with automatic differentiation
Custom Metal kernels via MLXFast
Performance optimization with JIT compilation

Architecture Overview

MLXOptimizers (Adam, AdamW, SGD, etc.)
       ↓
MLXNN (Layers, Modules, Losses)
       ↓
MLX (Arrays, Ops, Transforms, FFT, Linalg, Random)
       ↓
Cmlx (C/C++ bindings, Metal GPU)

Key File Reference

Purpose	File Path
Core array	Source/MLX/MLXArray.swift
Operations	Source/MLX/Ops.swift
Transforms	Source/MLX/Transforms.swift
Factory methods	Source/MLX/Factory.swift
Neural layers	Source/MLXNN/*.swift
Optimizers	Source/MLXOptimizers/Optimizers.swift
Fast ops	Source/MLX/MLXFast.swift
Custom kernels	Source/MLX/MLXFastKernel.swift
Wired memory coordinator	Source/MLX/WiredMemory.swift
GPU working-set helper	Source/MLX/GPU+Metal.swift
DType & numeric limits (finfo)	Source/MLX/DType.swift
Attention mask fill	Source/MLX/MLXArray+maskFill.swift

Quick Start

Basic Array Creation

import MLX

// Create arrays
let a = MLXArray([1, 2, 3, 4])
let b = MLXArray(0 ..< 12, [3, 4])  // Shape [3, 4]

// Nested arrays give the shape directly (any depth)
let c = MLXArray([[1, 2, 3], [4, 5, 6]])  // Shape [2, 3]

let d = MLXArray.zeros([2, 3])
let e = MLXArray.ones([4, 4], dtype: .float32)

// Random arrays (use MLXRandom namespace or free functions)
let uniform = MLXRandom.uniform(0.0 ..< 1.0, [3, 3])
let normal = MLXRandom.normal([100])

Array Properties

let array = MLXArray(0 ..< 12, [3, 4])
array.shape    // [3, 4]
array.ndim     // 2
array.size     // 12
array.dtype    // .int64
array.count    // 3 (first dimension)

DType Numeric Limits (`finfo`)

Floating-point limits for a DType, analogous to numpy.finfo. finfo is optional — nil for non-floating-point dtypes, so integer dtypes are rejected safely instead of returning a bogus value:

if let info = DType.float16.finfo {   // FInfo? — nil for non-float dtypes
    info.max               // 65504.0   (largest finite value)
    info.min               // -65504.0  (== -max)
    info.eps               // ulp of 1.0   (float16: 2^-10)
    info.smallestNormal    //              (float16: 2^-14)
    info.smallestSubnormal //              (float16: 2^-24)
}

DType.int32.finfo          // nil

When the dtype is statically known to be floating point, use the non-optional greatestFiniteMagnitude (mirrors Float.greatestFiniteMagnitude; traps on a non-float dtype):

let bound = DType.float16.greatestFiniteMagnitude   // 65504.0 (Double)

Attention Mask Fill (`maskFill`)

MLXArray.maskFill(for:) builds the value for masked-out positions before a softmax — -finfo(dtype).max, constructed directly in dtype so masked scores vanish under softmax with no asType to forget:

scores = MLX.where(causalMask, scores, MLXArray.maskFill(for: scores.dtype))

Requires a floating-point dtype (traps otherwise) — attention scores are float even when the KV cache is quantized.

Basic Operations

let a = MLXArray([1.0, 2.0, 3.0])
let b = MLXArray([4.0, 5.0, 6.0])

// Arithmetic (lazy - not computed until eval)
let sum = a + b
let product = a * b
let matmul = a.matmul(b.T)

// Force evaluation
eval(sum, product)
// or
sum.eval()

Building a Neural Network

import MLX
import MLXNN

class MLP: Module, UnaryLayer {
    @ModuleInfo var fc1: Linear
    @ModuleInfo var fc2: Linear

    init(inputDim: Int, hiddenDim: Int, outputDim: Int) {
        self.fc1 = Linear(inputDim, hiddenDim)
        self.fc2 = Linear(hiddenDim, outputDim)
        super.init()
    }

    func callAsFunction(_ x: MLXArray) -> MLXArray {
        var x = fc1(x)
        x = relu(x)
        return fc2(x)
    }
}

let model = MLP(inputDim: 784, hiddenDim: 256, outputDim: 10)
eval(model)  // Initialize parameters

Training Loop

import MLXOptimizers

let model = MLP(inputDim: 784, hiddenDim: 256, outputDim: 10)
let optimizer = Adam(learningRate: 0.001)

func loss(model: MLP, x: MLXArray, y: MLXArray) -> MLXArray {
    let logits = model(x)
    return crossEntropy(logits: logits, targets: y, reduction: .mean)
}

// Compute loss and gradients - valueAndGrad returns a function
let lossAndGrad = valueAndGrad(model: model, loss)
let (lossValue, grads) = lossAndGrad(model, x, y)

// Update model
optimizer.update(model: model, gradients: grads)
eval(model, optimizer)

Primary Workflow: Array Operations

See arrays.md for detailed array creation and indexing.

Creation Functions

// Zeros and ones
MLXArray.zeros([3, 4])
MLXArray.ones([2, 2], dtype: .float16)

// Ranges
arange(0, 10, 2)           // [0, 2, 4, 6, 8]
linspace(0.0, 1.0, 5)      // [0.0, 0.25, 0.5, 0.75, 1.0]

// Identity and diagonal
MLXArray.identity(3)
diagonal(array, offset: 0)

// Full
MLXArray.full([2, 3], values: 7.0)

Indexing

let a = MLXArray(0 ..< 12, [3, 4])

// Single element
a[0, 1]

// Slicing
a[0...]           // All rows
a[..<2]           // First 2 rows
a[1..., 2...]     // From row 1, column 2 onwards

// Advanced indexing
a[.ellipsis, 0]       // First column of all dimensions
a[.newAxis, .ellipsis]  // Add dimension at front

Shape Manipulation

let a = MLXArray(0 ..< 12, [3, 4])

a.reshaped([4, 3])
a.reshaped(-1, 6)     // Infer first dimension
a.T                    // Transpose
a.transposed(1, 0)     // Explicit transpose
a.squeezed()           // Remove size-1 dimensions
a.expandedDimensions(axis: 0)

Secondary Workflow: Neural Networks

See neural-networks.md for complete layer reference.

Built-in Layers

// Linear layers
Linear(inputDim, outputDim, bias: true)
Bilinear(in1, in2, out)

// Convolutions
Conv1d(inputChannels, outputChannels, kernelSize: 3)
Conv2d(inputChannels, outputChannels, kernelSize: 3, stride: 1, padding: 1)

// Normalization
LayerNorm(dimensions)
RMSNorm(dimensions)
BatchNorm(featureCount)
GroupNorm(groupCount, dimensions)

// Attention
MultiHeadAttention(dimensions: 512, numHeads: 8)

// Recurrent
RNN(inputSize, hiddenSize)
LSTM(inputSize, hiddenSize)
GRU(inputSize, hiddenSize)

// Regularization
Dropout(p: 0.1)

Module Property Wrappers

class MyLayer: Module {
    @ModuleInfo var layer: Linear           // Tracked module
    @ModuleInfo(key: "w") var weights: Linear  // Custom key

    let constant: MLXArray  // NOT tracked (no wrapper)
}

Loss Functions

crossEntropy(logits: logits, targets: targets, reduction: .mean)
binaryCrossEntropy(logits: logits, targets: targets)
l1Loss(predictions: predictions, targets: targets, reduction: .mean)
mseLoss(predictions: predictions, targets: targets, reduction: .mean)
smoothL1Loss(predictions: predictions, targets: targets, beta: 1.0)
klDivLoss(inputs: inputs, targets: targets, reduction: .mean)

Tertiary Workflow: Training

See transforms.md for automatic differentiation details.

Gradient Computation

// Simple gradient
let gradFn = grad { x in
    sum(x * x)
}
let g = gradFn(MLXArray([1.0, 2.0, 3.0]))

// Value and gradient together
let (value, gradient) = valueAndGrad { x in
    sum(x * x)
}(MLXArray([1.0, 2.0, 3.0]))

// Model gradients - valueAndGrad returns a function, call it to get results
let lossAndGradFn = valueAndGrad(model: model) { model in
    model(input)
}
let (loss, grads) = lossAndGradFn(model)

Optimizers

See optimizers.md for all optimizers.

// Common optimizers
let sgd = SGD(learningRate: 0.01, momentum: 0.9)
let adam = Adam(learningRate: 0.001, betas: (0.9, 0.999))
let adamw = AdamW(learningRate: 0.001, weightDecay: 0.01)

// Training step
optimizer.update(model: model, gradients: grads)
eval(model, optimizer)

Compilation for Performance

// Compile a pure array function for faster execution
let compiledOp = compile { (a: MLXArray, b: MLXArray) -> MLXArray in
    let x = a + b
    return sum(x * x)
}

// Use compiled version
let output = compiledOp(arrayA, arrayB)

// compile() also supports compiling a Module/Optimizer training step: pass
// them via inputs:/outputs: (they conform to Updatable) so compile observes
// in-place updates (e.g. optimizer.update(model:gradients:), LoRA weight swaps).
// If a captured Module/Optimizer is left out of inputs:/outputs:, compile()
// silently freezes its parameter values at trace time -- see
// references/transforms.md for the full pitfall and example.

Quaternary Workflow: Wired Memory Coordination

See wired-memory.md for full policy, hysteresis, and admission guidance.

import MLX

let policy = WiredSumPolicy()

// Reservation: participates in admission but does not keep the wired limit high while idle.
let weightsTicket = policy.ticket(size: weightsBytes, kind: .reservation)
_ = await weightsTicket.start()

// Active work: raises limit while inference runs.
let inferenceTicket = policy.ticket(size: kvCacheBytes, kind: .active)
try await inferenceTicket.withWiredLimit {
    // run model inference
}

_ = await weightsTicket.end()

Best Practices

DO

Use lazy evaluation: MLX arrays are computed lazily. Call eval() strategically to control memory and compute.
Batch eval calls: eval(a, b, c) is more efficient than separate calls.
Use @ModuleInfo for all module properties to enable quantization and updates.
Use actors for concurrent code: Encapsulate MLX state within actors for thread safety.
Use namespaced functions: MLXRandom.uniform(), FFT.fft(), Linalg.inv().
Use ticket-based wired memory coordination: Prefer WiredMemoryTicket.withWiredLimit and WiredMemoryManager.shared.

DON'T

Don't share MLXArrays across tasks: MLXArray is NOT Sendable by design.
Don't use deprecated module imports: Use import MLX not import MLXRandom.
Don't forget to eval(): Unevaluated arrays can accumulate large compute graphs.
Don't mutate arrays directly: Use operations that return new arrays.
Don't call deprecated wired-limit APIs: Avoid GPU.withWiredLimit(...) and Memory.withWiredLimit(...).

Deprecated Patterns

If you see...	Use instead...
`import MLXRandom`	`import MLX` then `MLXRandom.uniform()` or free function `uniform()`
`import MLXFFT`	`import MLX` then `FFT.fft()`
`import MLXLinalg`	`import MLX` then `Linalg.inv()`
`GPU.activeMemory`	`Memory.activeMemory`
`GPU.withWiredLimit(...)`	`WiredMemoryTicket(...).withWiredLimit { ... }` via `WiredMemoryManager`
`Memory.withWiredLimit(...)`	`WiredMemoryTicket(...).withWiredLimit { ... }`
`repeat(_:count:)`	`repeated(_:count:)`
`addmm()`	`addMM()`
`LogSoftMax`	`LogSoftmax`
`SoftMax`	`Softmax`

See deprecated.md for the complete migration guide.

Swift Concurrency Notes

MLX has specific concurrency behavior:

MLXArray is NOT Sendable: This is intentional. Arrays contain references to compute graphs.
evalLock protects eval/stream creation: The global lock serializes evaluation and stream operations.
Lazy operations are NOT thread-safe: Don't share arrays across tasks without proper synchronization.
Use actors to encapsulate MLX state: Create and use MLXArrays within the same actor.
Use wired-memory tickets for concurrent inference: Coordinate active/reservation budgets through the shared manager.

See concurrency.md for thread safety details.

Reference Documentation

Arrays - Array creation, properties, indexing
Operations - Math ops, broadcasting, reductions
Transforms - grad, vmap, compile, eval
Neural Networks - Layers and modules
Optimizers - Training optimizers
Custom Layers - Building custom modules
Custom Kernels - Metal kernels with MLXFast
Wired Memory - Ticket-based wired limit coordination
Concurrency - Thread safety guide
Deprecated - Migration guide

About this skill

Automatic

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/25/2026

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

timmyy123 / llm-hub

ios/LLMHub/LocalPackages/mlx-swift/skills/mlx-swift/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 10/25/2026Version v1Bundled 10 files

Illustrative Want to see what timmyy123/swift-mlx 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

MLX Swift Framework

When to Use This Skill

Architecture Overview

Key File Reference

Quick Start

Basic Array Creation

Array Properties

DType Numeric Limits (finfo)

Attention Mask Fill (maskFill)

Basic Operations

Building a Neural Network

Training Loop

Primary Workflow: Array Operations

Creation Functions

Indexing

Shape Manipulation

Secondary Workflow: Neural Networks

Built-in Layers

Module Property Wrappers

Loss Functions

Tertiary Workflow: Training

Gradient Computation

Optimizers

Compilation for Performance

Quaternary Workflow: Wired Memory Coordination

Best Practices

DO

DON'T

Deprecated Patterns

Swift Concurrency Notes

Reference Documentation

SkillSafety

Source

Related skills

More in the registry

DType Numeric Limits (`finfo`)

Attention Mask Fill (`maskFill`)