Ready to supercharge your AI agents?

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

Squads Protocol Development Guide · internet-court | DecimalAI

Codingby internet-court

Squads Protocol Development Guide

Complete guide for Squads Protocol - Solana's leading smart account and multisig infrastructure. Covers Squads V4 Multisig for team treasury management, Smart Account Program for account abstraction and programmable wallets, and Grid for stablecoin rails and fintech infrastructure.

Maintained

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

43%91%of test cases passed +48 pts

Without skill10 of 23

With skill21 of 23

12 fixed9 passed either way1 still failing1 broke

Measured on gemini-3.6-flash9/8/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI am writing a script to monitor Squads V4 transactions on Solana mainnet. Which Program ID public key string should I pass to initialize my Solana web3.js PublicKey filter?

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 internet-court-squads
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("internet-court-squads")
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 internet-court-squads

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/internet-court-squads/SKILL.md https://app.decimal.ai/s/internet-court-squads/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/internet-court-squads/SKILL.md

This gets SKILL.md only. The skill's 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/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/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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("internet-court-squads")
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/internet-court-squads/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/internet-court-squads/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 3 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 internet-court-squads

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/internet-court-squads/SKILL.md https://app.decimal.ai/s/internet-court-squads/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/internet-court-squads/SKILL.md

This gets SKILL.md only. The skill's 3 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/internet-court-squads/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/internet-court-squads.json

This gets SKILL.md only. The skill's 3 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 9/8/2026
Source: internet-court/internet-court-skill ↗
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

Squads Protocol Development Guide

Squads Protocol is Solana's premier smart account infrastructure, securing over $10 billion in digital assets. This guide covers all three main products: Squads V4 Multisig, Smart Account Program, and Grid.

Overview

Squads Protocol provides:

Squads V4 Multisig - Multi-signature wallet for teams with proposals, voting, time locks, spending limits, and program upgrade management
Smart Account Program - Account abstraction infrastructure with session keys, passkeys, programmable policies, and direct debits
Grid - Open finance infrastructure for stablecoin rails, neobank platforms, and enterprise payment systems

Program IDs

Program	Mainnet	Devnet
Squads V4 Multisig	`SQDS4ep65T869zMMBKyuUq6aD6EgTu8psMjkvj52pCf`	`SQDS4ep65T869zMMBKyuUq6aD6EgTu8psMjkvj52pCf`
Smart Account	`SMRTzfY6DfH5ik3TKiyLFfXexV8uSG3d2UksSCYdunG`	`SMRTzfY6DfH5ik3TKiyLFfXexV8uSG3d2UksSCYdunG`
External Signature (Grid)	`ExtSgUPtP3JyKUysFw2S5fpL5fWfUPzGUQLd2bTwftXN`	`ExtSgUPtP3JyKUysFw2S5fpL5fWfUPzGUQLd2bTwftXN`

Eclipse Mainnet:

Program	Address
Squads V4 Multisig	`eSQDSMLf3qxwHVHeTr9amVAGmZbRLY2rFdSURandt6f`

Quick Start

Installation

# Squads V4 Multisig SDK
npm install @sqds/multisig @solana/web3.js

# Grid SDK
npm install @sqds/grid

# Grid React Native SDK
npm install @sqds/grid-react-native

Basic Setup

import * as multisig from "@sqds/multisig";
import { Connection, Keypair, PublicKey } from "@solana/web3.js";

// Setup connection
const connection = new Connection("https://api.mainnet-beta.solana.com", "confirmed");

// Load wallet
const wallet = Keypair.fromSecretKey(/* your secret key */);

// Program ID constant
const SQUADS_PROGRAM_ID = new PublicKey("SQDS4ep65T869zMMBKyuUq6aD6EgTu8psMjkvj52pCf");

Squads V4 Multisig

Squads V4 is the latest version of the multisig protocol, featuring enhanced security, time locks, spending limits, and batch transactions.

Core Concepts

Multisig Account: The main account that holds configuration (members, threshold, time lock settings).

Vault: A PDA controlled by the multisig where assets are stored. Each multisig can have multiple vaults (indexed 0, 1, 2...).

Proposal: A request to execute a transaction that requires approval from multisig members.

Transaction: The actual instruction(s) to be executed once a proposal is approved.

Permission System

Members can have different permissions:

import { Permission, Permissions } from "@sqds/multisig/lib/types";

// All permissions (can initiate, vote, and execute)
const fullPermissions = Permissions.all();

// Specific permissions
const voteOnly = Permissions.fromPermissions([Permission.Vote]);
const initiateAndVote = Permissions.fromPermissions([Permission.Initiate, Permission.Vote]);
const executeOnly = Permissions.fromPermissions([Permission.Execute]);

Permission	Description
`Initiate`	Can create new proposals
`Vote`	Can approve or reject proposals
`Execute`	Can execute approved proposals

Creating a Multisig

import * as multisig from "@sqds/multisig";

const { Permissions } = multisig.types;

// Generate a unique create key (one-time use)
const createKey = Keypair.generate();

// Derive the multisig PDA
const [multisigPda] = multisig.getMultisigPda({
  createKey: createKey.publicKey,
});

// Create a 2-of-3 multisig
const signature = await multisig.rpc.multisigCreateV2({
  connection,
  createKey,
  creator: wallet,
  multisigPda,
  configAuthority: null, // Immutable config
  threshold: 2,
  members: [
    { key: member1.publicKey, permissions: Permissions.all() },
    { key: member2.publicKey, permissions: Permissions.all() },
    { key: member3.publicKey, permissions: Permissions.fromPermissions([Permission.Vote]) },
  ],
  timeLock: 0, // No time lock (in seconds)
  rentCollector: null,
});

console.log("Multisig created:", multisigPda.toString());
console.log("Transaction:", signature);

Vault Operations

Vaults are PDAs that hold the multisig's assets:

// Derive vault PDA (index 0 is the default vault)
const [vaultPda] = multisig.getVaultPda({
  multisigPda,
  index: 0,
});

console.log("Vault address:", vaultPda.toString());

// Check vault balance
const balance = await connection.getBalance(vaultPda);
console.log("Vault balance:", balance / 1e9, "SOL");

Important: Always send funds to the vault PDA, not the multisig account itself.

Creating a Vault Transaction

import { SystemProgram, LAMPORTS_PER_SOL } from "@solana/web3.js";

// Get current transaction index
const multisigAccount = await multisig.accounts.Multisig.fromAccountAddress(
  connection,
  multisigPda
);
const transactionIndex = BigInt(Number(multisigAccount.transactionIndex) + 1);

// Derive transaction PDA
const [transactionPda] = multisig.getTransactionPda({
  multisigPda,
  index: transactionIndex,
});

// Create a transfer instruction
const transferIx = SystemProgram.transfer({
  fromPubkey: vaultPda,
  toPubkey: recipientPubkey,
  lamports: 0.1 * LAMPORTS_PER_SOL,
});

// Create the vault transaction
const signature = await multisig.rpc.vaultTransactionCreate({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  creator: wallet.publicKey,
  vaultIndex: 0,
  ephemeralSigners: 0,
  transactionMessage: new TransactionMessage({
    payerKey: vaultPda,
    recentBlockhash: (await connection.getLatestBlockhash()).blockhash,
    instructions: [transferIx],
  }),
});

console.log("Vault transaction created:", transactionPda.toString());

Creating and Managing Proposals

// Derive proposal PDA
const [proposalPda] = multisig.getProposalPda({
  multisigPda,
  transactionIndex,
});

// Create proposal for the transaction
const createProposalSig = await multisig.rpc.proposalCreate({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  creator: wallet,
});

console.log("Proposal created:", proposalPda.toString());

Voting on Proposals

// Approve the proposal
const approveSig = await multisig.rpc.proposalApprove({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  member: wallet,
});

console.log("Proposal approved");

// Or reject the proposal
const rejectSig = await multisig.rpc.proposalReject({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  member: wallet,
  memo: "Reason for rejection",
});

Executing Approved Transactions

// Check if proposal is approved and ready
const proposal = await multisig.accounts.Proposal.fromAccountAddress(
  connection,
  proposalPda
);

if (proposal.status.__kind === "Approved") {
  // Execute the vault transaction
  const executeSig = await multisig.rpc.vaultTransactionExecute({
    connection,
    feePayer: wallet,
    multisigPda,
    transactionIndex,
    member: wallet.publicKey,
  });

  console.log("Transaction executed:", executeSig);
}

Spending Limits

Spending limits allow members to execute transactions up to a certain amount without full multisig approval:

// Create a spending limit
const createSpendingLimitSig = await multisig.rpc.configTransactionCreate({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  creator: wallet.publicKey,
  actions: [{
    __kind: "AddSpendingLimit",
    createKey: spendingLimitCreateKey.publicKey,
    vaultIndex: 0,
    mint: SOL_MINT, // or token mint
    amount: BigInt(1 * LAMPORTS_PER_SOL), // 1 SOL
    period: multisig.types.Period.Day,
    members: [trustedMember.publicKey],
    destinations: [allowedDestination],
  }],
});

// Use spending limit (no proposal needed)
const useSpendingLimitSig = await multisig.rpc.spendingLimitUse({
  connection,
  feePayer: wallet,
  multisigPda,
  member: trustedMember,
  spendingLimit: spendingLimitPda,
  mint: SOL_MINT,
  vaultIndex: 0,
  amount: BigInt(0.5 * LAMPORTS_PER_SOL),
  decimals: 9,
  destination: allowedDestination,
});

Batch Transactions

Execute multiple transactions atomically:

// Create a batch
const [batchPda] = multisig.getBatchPda({
  multisigPda,
  batchIndex: transactionIndex,
});

const createBatchSig = await multisig.rpc.batchCreate({
  connection,
  feePayer: wallet,
  multisigPda,
  batchIndex: transactionIndex,
  creator: wallet,
  vaultIndex: 0,
});

// Add transactions to the batch
await multisig.rpc.batchAddTransaction({
  connection,
  feePayer: wallet,
  multisigPda,
  batchIndex: transactionIndex,
  transactionIndex: 1,
  vaultIndex: 0,
  transactionMessage: /* first transaction */,
});

await multisig.rpc.batchAddTransaction({
  connection,
  feePayer: wallet,
  multisigPda,
  batchIndex: transactionIndex,
  transactionIndex: 2,
  vaultIndex: 0,
  transactionMessage: /* second transaction */,
});

// Create proposal and execute as usual

Config Transactions

Modify multisig settings (requires proposal approval):

// Add a new member
const addMemberSig = await multisig.rpc.configTransactionCreate({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  creator: wallet.publicKey,
  actions: [{
    __kind: "AddMember",
    newMember: {
      key: newMemberPubkey,
      permissions: Permissions.all(),
    },
  }],
});

// Change threshold
const changeThresholdSig = await multisig.rpc.configTransactionCreate({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  creator: wallet.publicKey,
  actions: [{
    __kind: "ChangeThreshold",
    newThreshold: 3,
  }],
});

// Remove a member
const removeMemberSig = await multisig.rpc.configTransactionCreate({
  connection,
  feePayer: wallet,
  multisigPda,
  transactionIndex,
  creator: wallet.publicKey,
  actions: [{
    __kind: "RemoveMember",
    oldMember: memberToRemove,
  }],
});

Time Locks

Add a delay before approved transactions can execute:

// Create multisig with time lock (1 day = 86400 seconds)
const signature = await multisig.rpc.multisigCreateV2({
  connection,
  createKey,
  creator: wallet,
  multisigPda,
  configAuthority: null,
  threshold: 2,
  members: [...],
  timeLock: 86400, // 1 day in seconds
  rentCollector: null,
});

PDA Derivation Reference

import * as multisig from "@sqds/multisig";

// Multisig PDA
const [multisigPda] = multisig.getMultisigPda({
  createKey: createKeyPubkey,
});

// Vault PDA
const [vaultPda] = multisig.getVaultPda({
  multisigPda,
  index: 0, // vault index
});

// Transaction PDA
const [transactionPda] = multisig.getTransactionPda({
  multisigPda,
  index: transactionIndex,
});

// Proposal PDA
const [proposalPda] = multisig.getProposalPda({
  multisigPda,
  transactionIndex,
});

// Batch PDA
const [batchPda] = multisig.getBatchPda({
  multisigPda,
  batchIndex,
});

// Spending Limit PDA
const [spendingLimitPda] = multisig.getSpendingLimitPda({
  multisigPda,
  createKey: spendingLimitCreateKey,
});

// Program Config PDA
const [programConfigPda] = multisig.getProgramConfigPda({});

// Ephemeral Signer PDA (for CPI calls)
const [ephemeralSignerPda] = multisig.getEphemeralSignerPda({
  transactionPda,
  ephemeralSignerIndex: 0,
});

Smart Account Program

The Smart Account Program provides account abstraction features for Solana, enabling programmable wallets with session keys, passkeys, and policy-based execution.

Core Concepts

Smart Account: A programmable wallet controlled by policies rather than just private keys.

Session Key: Temporary keys with limited permissions for specific operations.

Passkey: WebAuthn/FIDO2 authentication using biometrics or hardware keys.

Policy: Rules that govern what transactions can be executed.

Features

Rent-free Deployment - No rent required for smart accounts
Atomic Policy Enforcement - All policy checks happen atomically
Account Compression - Efficient storage for multiple signers
Extensible Policies - Custom policy programs can be added
Direct Debits - Automated recurring payments
Subscriptions - Managed subscription billing

REST API Base URL

https://developer-api.squads.so/api/v1

Creating a Smart Account

// Via REST API
const response = await fetch("https://developer-api.squads.so/api/v1/accounts", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
    "Authorization": `Bearer ${apiKey}`,
  },
  body: JSON.stringify({
    email: "[email protected]",
    // or
    signer: signerPublicKey,
  }),
});

const account = await response.json();
console.log("Smart account:", account.address);

Session Key Management

Session keys allow delegated access with specific permissions:

// Create a session key
const sessionResponse = await fetch(
  `https://developer-api.squads.so/api/v1/accounts/${accountId}/sessions`,
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": `Bearer ${apiKey}`,
    },
    body: JSON.stringify({
      publicKey: sessionKeyPublicKey,
      expiresAt: Date.now() + 24 * 60 * 60 * 1000, // 24 hours
      permissions: ["transfer", "swap"],
      limits: {
        maxAmount: "1000000000", // 1 SOL in lamports
        dailyLimit: "5000000000", // 5 SOL daily
      },
    }),
  }
);

Passkey Authentication

// Register a passkey
const registerResponse = await fetch(
  `https://developer-api.squads.so/api/v1/accounts/${accountId}/passkeys`,
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": `Bearer ${apiKey}`,
    },
    body: JSON.stringify({
      credentialId: webAuthnCredential.id,
      publicKey: webAuthnCredential.publicKey,
      attestation: webAuthnCredential.attestation,
    }),
  }
);

// Authenticate with passkey
const authResponse = await fetch(
  "https://developer-api.squads.so/api/v1/auth/passkey",
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      credentialId: webAuthnCredential.id,
      assertion: webAuthnAssertion,
    }),
  }
);

Policy Configuration

// Set spending policy
const policyResponse = await fetch(
  `https://developer-api.squads.so/api/v1/accounts/${accountId}/policies`,
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": `Bearer ${apiKey}`,
    },
    body: JSON.stringify({
      type: "spending_limit",
      params: {
        mint: "So11111111111111111111111111111111111111112", // SOL
        amount: "10000000000", // 10 SOL
        period: "daily",
      },
    }),
  }
);

Grid

Grid is Squads' open finance infrastructure for stablecoin rails, enabling neobank platforms and enterprise payment systems.

Features

Stablecoin Rails - USDC/USDT payment infrastructure
Programmable Payments - Automated money flows
Virtual Accounts - Fiat on/off ramps
KYC Integration - Built-in compliance tools
Self-Custody - Users maintain control of assets

API Authentication

// Email OTP authentication
const otpResponse = await fetch("https://developer-api.squads.so/api/v1/auth/email/otp", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    email: "[email protected]",
  }),
});

// Verify OTP
const verifyResponse = await fetch("https://developer-api.squads.so/api/v1/auth/email/verify", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    email: "[email protected]",
    otp: "123456",
  }),
});

const { accessToken } = await verifyResponse.json();

Account Management

// Get account details
const accountResponse = await fetch(
  `https://developer-api.squads.so/api/v1/accounts/${accountId}`,
  {
    headers: {
      "Authorization": `Bearer ${accessToken}`,
    },
  }
);

const account = await accountResponse.json();
console.log("Balance:", account.balance);
console.log("Status:", account.status);

Payment Operations

// Create a payment intent
const paymentResponse = await fetch(
  "https://developer-api.squads.so/api/v1/payments",
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": `Bearer ${accessToken}`,
    },
    body: JSON.stringify({
      amount: "100000000", // 100 USDC (6 decimals)
      currency: "USDC",
      recipient: recipientAddress,
      memo: "Payment for services",
    }),
  }
);

const payment = await paymentResponse.json();
console.log("Payment ID:", payment.id);
console.log("Status:", payment.status);

Standing Orders (Recurring Payments)

// Create a standing order
const standingOrderResponse = await fetch(
  "https://developer-api.squads.so/api/v1/standing-orders",
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": `Bearer ${accessToken}`,
    },
    body: JSON.stringify({
      amount: "50000000", // 50 USDC
      currency: "USDC",
      recipient: recipientAddress,
      frequency: "monthly",
      startDate: "2024-02-01",
      memo: "Monthly subscription",
    }),
  }
);

Spending Limits

// Set spending limit
const limitResponse = await fetch(
  `https://developer-api.squads.so/api/v1/accounts/${accountId}/limits`,
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "Authorization": `Bearer ${accessToken}`,
    },
    body: JSON.stringify({
      type: "daily",
      amount: "1000000000", // 1000 USDC
      currency: "USDC",
    }),
  }
);

Best Practices

Security

Never share private keys - Use environment variables for sensitive data
Verify program IDs - Always confirm you're interacting with official programs
Use time locks - For high-value treasuries, add time locks for additional security
Limit permissions - Give members only the permissions they need
Test on devnet - Always test transactions on devnet before mainnet

Transaction Optimization

Use Address Lookup Tables - Reduce transaction size for complex operations
Batch transactions - Group related operations when possible
Set appropriate compute budget - Avoid transaction failures due to compute limits

import { ComputeBudgetProgram } from "@solana/web3.js";

// Add compute budget instruction
const computeBudgetIx = ComputeBudgetProgram.setComputeUnitLimit({
  units: 400_000,
});

// Add priority fee for faster inclusion
const priorityFeeIx = ComputeBudgetProgram.setComputeUnitPrice({
  microLamports: 10_000,
});

Error Handling

try {
  const signature = await multisig.rpc.proposalCreate({
    connection,
    feePayer: wallet,
    multisigPda,
    transactionIndex,
    creator: wallet,
  });
} catch (error) {
  if (error.message.includes("NotAMember")) {
    console.error("Wallet is not a member of this multisig");
  } else if (error.message.includes("Unauthorized")) {
    console.error("Wallet does not have required permissions");
  } else if (error.message.includes("InvalidTransactionIndex")) {
    console.error("Transaction index already used");
  } else {
    throw error;
  }
}

Fetching Account State

// Get multisig account
const multisigAccount = await multisig.accounts.Multisig.fromAccountAddress(
  connection,
  multisigPda
);

console.log("Threshold:", multisigAccount.threshold);
console.log("Members:", multisigAccount.members);
console.log("Transaction Index:", multisigAccount.transactionIndex.toString());

// Get proposal status
const proposal = await multisig.accounts.Proposal.fromAccountAddress(
  connection,
  proposalPda
);

console.log("Status:", proposal.status.__kind);
console.log("Approved:", proposal.approved.length);
console.log("Rejected:", proposal.rejected.length);

Common Patterns

Program Upgrade Multisig

Secure program upgrade authority with a multisig:

// Transfer upgrade authority to multisig vault
const transferAuthIx = createSetAuthorityInstruction(
  programDataAddress,
  currentAuthority,
  AuthorityType.UpgradeAuthority,
  vaultPda
);

// Execute via multisig proposal
// Now program upgrades require multisig approval

Treasury Management

// Create multiple vaults for different purposes
const [operationsVault] = multisig.getVaultPda({ multisigPda, index: 0 });
const [reserveVault] = multisig.getVaultPda({ multisigPda, index: 1 });
const [grantVault] = multisig.getVaultPda({ multisigPda, index: 2 });

// Set spending limits for operations vault
// Reserve vault requires full multisig approval

Validator Operations

// Manage validator identity and vote account with multisig
// Transfer validator identity to vault
// Set up spending limits for operational costs

Resources

Official Documentation

GitHub Repositories

Security Audits

OtterSec audit
Neodyme audit
Certora audit
Trail of Bits audit

Verify Program Builds

# Install solana-verify
cargo install solana-verify

# Verify Squads V4 program
solana-verify get-program-hash -u mainnet-beta SQDS4ep65T869zMMBKyuUq6aD6EgTu8psMjkvj52pCf

Skill Structure

squads/
├── SKILL.md                              # This file
├── resources/
│   ├── program-addresses.md              # All program IDs and PDAs
│   ├── multisig-api-reference.md         # @sqds/multisig SDK reference
│   ├── smart-account-api-reference.md    # Smart Account API reference
│   └── grid-api-reference.md             # Grid REST API reference
├── examples/
│   ├── multisig/
│   │   ├── create-multisig.ts            # Create multisig with members
│   │   ├── proposals-voting.ts           # Proposals and voting
│   │   ├── vault-transactions.ts         # Vault operations
│   │   └── spending-limits.ts            # Spending limit management
│   ├── smart-account/
│   │   ├── account-creation.ts           # Smart account setup
│   │   └── session-keys.ts               # Session key management
│   └── grid/
│       ├── api-quickstart.ts             # REST API basics
│       └── payments.ts                   # Payment operations
├── templates/
│   ├── multisig-setup.ts                 # Multisig client template
│   ├── smart-account-setup.ts            # Smart account template
│   └── grid-client.ts                    # Grid API client template
└── docs/
    └── troubleshooting.md                # Common issues and solutions

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/17/2026

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

internet-court / internet-court-skill

vendored/sendaifun/squads/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/17/2026Version v1Bundled 3 files

Illustrative Want to see what internet-court/squads 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

Squads Protocol Development Guide

Overview

Program IDs

Quick Start

Installation

Basic Setup

Squads V4 Multisig

Core Concepts

Permission System

Creating a Multisig

Vault Operations

Creating a Vault Transaction

Creating and Managing Proposals

Voting on Proposals

Executing Approved Transactions

Spending Limits

Batch Transactions

Config Transactions

Time Locks

PDA Derivation Reference

Smart Account Program

Core Concepts

Features

REST API Base URL

Creating a Smart Account

Session Key Management

Passkey Authentication

Policy Configuration

Grid

Features

API Authentication

Account Management

Payment Operations

Standing Orders (Recurring Payments)

Spending Limits

Best Practices

Security

Transaction Optimization

Error Handling

Fetching Account State

Common Patterns

Program Upgrade Multisig

Treasury Management

Validator Operations

Resources

Official Documentation

GitHub Repositories

Security Audits

Verify Program Builds

Skill Structure

SkillSafety

Source

Related skills

More in the registry