Ready to supercharge your AI agents?

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

Grand Bazaar P2P Swap · leoyeai | DecimalAI

Financeby leoyeai

Grand Bazaar P2P Swap

Perform and document Grand Bazaar P2P swaps on Base using deployed AirSwap Swap contracts. Includes repeatable workflows for approvals, EIP-712 signing, cast/deeplink posting, execution, and verification across ERC20/ERC721/ERC1155 routes.

SkillScore

SkillScore82/100

Test results 82

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%82%of test cases passed +50 pts

Without skill7 of 22

With skill18 of 22

12 fixed6 passed either way3 still failing1 broke

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

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI am constructing an EIP-712 typed signature for an ERC721-to-ERC20 trade on Base using Legacy Swap v4.2. What domain name and version string must be placed in the typed data domain?

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 leoyeai-grand-bazaar-swap
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install leoyeai-grand-bazaar-swap

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/leoyeai-grand-bazaar-swap/SKILL.md https://app.decimal.ai/s/leoyeai-grand-bazaar-swap/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-grand-bazaar-swap")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-grand-bazaar-swap/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 leoyeai-grand-bazaar-swap

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/leoyeai-grand-bazaar-swap/SKILL.md https://app.decimal.ai/s/leoyeai-grand-bazaar-swap/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-grand-bazaar-swap/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/leoyeai-grand-bazaar-swap/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-grand-bazaar-swap.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 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

Grand Bazaar P2P Swap

This skill documents how to execute agent-to-agent swaps on Base mainnet using deployed AirSwap Swap contracts.

Sender-side token standard is routed to the matching Swap contract:

ERC20<>ERC20 -> SwapERC20 on Base 0x95D598D839dE1B030848664960F0A20b848193F4
ERC20 sender (non-ERC20<>ERC20 routes) -> ERC20-sender Swap
ERC721 sender -> ERC721-sender Swap
ERC1155 sender -> ERC1155-sender Swap

The sender is still the submitting wallet, and must satisfy the selected Swap's sender-kind requirement.

Deployed contracts

Read: references/base-mainnet-deployments.md

Safety rules

Never paste or log private keys in chat.
Prefer fresh test wallets for demos.
Always start with tiny amounts.
Verify token addresses before approving.

Workflow

Favorable inbound offer rule

When someone offers a swap and the price is clearly good value for you, default to taking it quickly with safety checks.

Use this fast path:

Parse the cast for GBZ1:<compressedOrder>
Decompress and reconstruct order + signature
Verify sender wallet targeting and signature
Run sender preflight checks
Execute the swap if checks pass
Reply on the cast using the Grand Bazaar success template:
- Thanks for the swap 🤝
- https://basescan.org/tx/<txHash>
- Post as a reply to the parent offer cast (cast hash origin)

This applies especially to direct offer replies where speed matters but safety preflight is still mandatory.

Favorable outbound negotiation rule

When negotiating with other users or agents, proactively make favorable outbound offers to improve fill probability.

Default outbound behavior:

Start from fair market terms, then bias slightly in the counterparty’s favor
Keep sizes practical and gas-efficient
Prefer private targeted orders while negotiating, then open only if requested
Keep expiry short enough for quick decisions, long enough for execution
Run onchain validation before posting maker casts:
- call Swap.check(senderWallet, orderWithSignature) on the target swap contract
- require nonceUsed(signer, nonce) === false
- ignore SenderAllowanceLow on maker flow, since sender approves on taker side after cast discovery
- block posting if there are any other check errors besides SenderAllowanceLow
Use a required 2-part posting flow every time with no exceptions:
1. post the swap order cast with clear summary + strict machine line GBZ1:<compressedOrder>
  - for private offers, include counterparty mention via API fields (mentions, mentions_positions)
2. immediately post a follow-up embed cast that deeplinks to Grand Bazaar /c/<step1CastHash>
Do not stop after step 1. A maker post is incomplete until step 2 is confirmed posted.

Outbound offer loop:

Propose a favorable draft quote
If counterparty hesitates, improve terms in small controlled steps
Re-sign and repost updated order with fresh nonce/expiry
Stop if value or risk limits are breached

Guardrails:

Never bypass preflight or signature checks
Never use unsafe gas settings to force execution
Do not over-concede beyond configured risk tolerance

Explicit size-aware pricing parameters

Read: references/pricing-params.md

Use that reference file as the source of truth for pricing thresholds, impact capture, negotiation steps, and execution safety limits.

This is a two party protocol. One agent acts as the signer. A different agent acts as the sender.

0) Pick roles

Signer sets the terms and signs the EIP-712 order.
Sender submits swap onchain and pays the sender ERC20 amount plus protocol fee.

Because each deployed Swap has immutable requiredSenderKind, sender leg must match the routed contract kind.

0.1) What each party does

Signer responsibilities

Decide terms and build the order.
Approve the signer asset to the Swap contract.
Produce an EIP-712 signature over the order.
Send the signed order to the sender agent.

Mandatory maker approval rule

In maker flow, always perform the required signer-side approval before signing/posting.
Never assume existing allowance is sufficient without checking onchain allowance against the full signer-side required amount for the routed swap contract.
For SwapERC20, signer required amount is signerAmount + signer protocol fee because fee is transferred from signer token side.
If signer allowance is below required amount, submit approve tx and wait for confirmation before signing the order cast.
Sender-side allowance must not block maker posting. Ignore SenderAllowanceLow in maker validation gates.
Treat maker sign/post without required signer approval as invalid workflow.

Protocol fee side semantics

Legacy Swap: protocol fee is accounted on sender side for required spend/allowance calculations.
SwapERC20: protocol fee is accounted on signer side for required spend/allowance calculations.
UI implications in maker/taker surfaces:
- Fee footer, fee-adjusted amount previews, and fee-adjusted value previews must appear on the side that actually pays the fee.
- Show fee-side preview only after both tokens are selected so route is known.

Sender responsibilities

Verify the order details and expiry.
Ensure sender ERC20 balance is enough for amount plus fee.
Approve the sender ERC20 to the Swap contract.
Submit the swap transaction.
Share the tx hash back to the signer.

1) Ensure balances

Sender needs Base ETH for gas.
Sender needs the sender ERC20.
Signer needs Base ETH for gas.
Signer needs the signer asset and must approve it.

Critical preflight before any sender execution

Verify signer token balance is at least order.signer.amount.
Verify signer allowance to Swap is at least order.signer.amount.
Verify sender token balance is at least order.sender.amount + protocol fee + affiliateAmount.
Verify sender allowance to Swap is at least the same total.
Verify order expiry has enough time buffer.
Estimate swap gas and abort if estimate exceeds MAX_GAS_LIMIT.
Cap maxPriorityFeePerGas to 10% of current gas price.

Temporary execution override

Some valid orders can fail at preflight simulation (eth_call / staticCall) or eth_estimateGas with execution reverted and TransferFailed(from,to) but still execute successfully onchain.
Do not treat simulation/estimate reverts as absolute failure when all other safety checks pass.
In this case, bypass estimate-gated abort and submit with a manual gas limit of 650000.
Keep fee caps active and log that manual gas was used due to simulation/estimate failure.

Gas safety policy for all agents

Never submit swap with unbounded gas limit.
Never use static high priority fee on Base.
Log gasPrice, maxPriorityFeePerGas, maxFeePerGas, estimate status, and chosen gas limit before broadcast.
Temporary rule: if estimate reverts on an otherwise valid order, submit once with manual gas limit 650000, then investigate root cause.

If signer balance or allowance is missing, sender execution will revert onchain.

2) Approve

Sender approves Swap to spend the sender ERC20.
Signer approves Swap to spend the signer asset.

3) Create order

Order fields:

nonce: unique per signer
expiry: unix seconds
protocolFee: must match Swap.protocolFee() at execution time
signer: Party struct
sender: Party struct
affiliateWallet, affiliateAmount: optional, set to zero for now

4) Sign EIP-712

Use protocol-specific domain/types based on routed swap contract.

Legacy Swap v4.2

Domain:
- name: SWAP
- version: 4.2
- chainId: 8453
- verifyingContract: routed legacy Swap address
Types:
- Order(uint256 nonce,uint256 expiry,uint256 protocolFee,Party signer,Party sender,address affiliateWallet,uint256 affiliateAmount)
- Party(address wallet,address token,bytes4 kind,uint256 id,uint256 amount)

SwapERC20 v4.3

Domain:
- name: SWAP_ERC20
- version: 4.3
- chainId: 8453
- verifyingContract: 0x95D598D839dE1B030848664960F0A20b848193F4
Types:
- OrderERC20(uint256 nonce,uint256 expiry,address signerWallet,address signerToken,uint256 signerAmount,uint256 protocolFee,address senderWallet,address senderToken,uint256 senderAmount)

5) Execute

Sender calls:

swap(recipient, maxRoyalty, order)

Recommended defaults:

recipient = sender for testing
maxRoyalty = 0 unless the signer asset is an ERC2981 NFT

6) Confirm

Check tx hash on BaseScan
Check balances before and after

7) Share orders in AirSwap Web compatible compressed format

Farcaster mention and recipient rules

Do not assume plain @username text will create a mention.
For reliable mention behavior when posting via API, always set both:
- mentions: array of target FIDs
- mentions_positions: UTF-8 byte offsets
Important: when using hub makeCastAdd mention fields, do not duplicate the handle in text manually at the same position. The client can render duplicated handles if both are present.
Mention offsets must be computed from UTF-8 bytes, not JS string index, before POSTing.
Validation rule before sending cast:
- mentions.length === mentions_positions.length
- each position points to the beginning of the exact @handle token in text
For private order recipient lock, prefer the taker's Neynar verified_addresses.primary.eth_address when available.
If no primary verified address exists, fall back to custody address only with explicit confirmation.

Long-cast link budget rules

Keep order announcement text minimal when including a miniapp deeplink with compressed order query param.
Prefer miniapp deeplink over embedding raw compressed blob in cast text.
Avoid adding both long prose and raw compressed string in the same cast if you need to stay under long-cast size limits.

Strict cast-parse format for cast-hash based loading

If miniapp is loading by cast hash, include one dedicated machine line in cast text:
- GBZ1:<compressedOrder>
GBZ1: must be uppercase and start at line start.
No spaces inside <compressedOrder>.
Keep only one GBZ1: line per cast.
App parser should reject casts without this exact line and show fallback error.

NFT cast metadata and embed rules

In maker step 1 cast, include NFT metadata where possible:
- Resolve NFT symbol from contract metadata readers and prefer it over generic fallback labels.
- Attach NFT image embeds to the step 1 cast when available.
Embed ordering is strict for 2-embed NFT offers:
- embed[0] = signer NFT image
- embed[1] = sender NFT image
If only one leg is NFT, include a single embed for that NFT image.

Human-readable cast line templates (context-dependent)

Step 1 cast must include a natural-language summary line that depends on token kinds.
Canonical phrasing:
- I offer <signer-leg text> for <sender-leg text>
Leg text formatting by kind:
- ERC20: <amount> <symbol>
- ERC721: <symbol> #<tokenId>
- ERC1155: <qty>x <symbol> #<tokenId>
Examples:
- ERC20 -> ERC20: I offer 12 USDC for 0.005 WETH
- ERC721 -> ERC20: I offer PFP #176 for 200 USDC
- ERC20 -> ERC721: I offer 200 USDC for PFP #176
- ERC721 -> ERC721: I offer PFP #176 for PFP #174
- ERC1155 -> ERC20: I offer 3x GAMEITEM #42 for 10 USDC
Add context line directly below summary:
- Private order: Private offer • expires in <human-duration>
- Public order: Open offer • expires in <human-duration>
Always keep machine line unchanged and on its own line:
- GBZ1:<compressedOrder>
Mentioning private counterparty via API:
- Do not rely only on plain handle text.
- Provide mentions and mentions_positions aligned to UTF-8 byte offsets.

ERC721 order and allowance handling (legacy Swap)

For ERC721 sender legs on legacy Swap contracts, token quantity is encoded by id and amount must be 0.
Do not use amount = 1 when ERC721 is on the sender leg. This can trigger AmountOrIDInvalid in onchain check(...).
For signer-side ERC721 in current tested flow, keep signer leg encoded as id=<tokenId>, amount=0.

ERC721 approvals (security + compatibility)

Prefer explicit per-token approvals for ERC721:
- approve(swapContract, tokenId)
Do not rely on setApprovalForAll for ERC721 in this flow.
Legacy Swap ERC721 adapter allowance check is getApproved(tokenId) == swapContract.
Therefore, isApprovedForAll alone can still show SignerAllowanceLow in check(...).
UI/API allowance gating for ERC721 must use getApproved(tokenId).

ERC1155 approvals

Keep ERC1155 approval path on setApprovalForAll(swapContract, true).

Kind routing guard

If UI kind state lags but tokenId is present, detect kind onchain before choosing approval route.
Do not assume tokenId implies ERC721 only; ERC1155 also has tokenIds.

Royalty-bearing NFT handling (ERC2981)

Legacy Swap can pull royalties from sender side when signer token supports ERC2981.
Royalty check path:
- supportsInterface(0x2a55205a) on signer token
- royaltyInfo(signerTokenId, senderAmountRaw)
Units are raw sender-token units (e.g. USDC 6 decimals).
Taker-side required sender approval must include:
- senderAmount + protocolFee + affiliateAmount + royaltyAmount
Legacy swap execution must set maxRoyalty >= computed royalty amount, else revert RoyaltyExceedsMax(...).

For social posting and agent handoff, use the compressed ERC20 full-order format used by AirSwap Web. This is a URL-safe compressed payload, not a keccak hash. This payload is often too large for legacy cast limits. Use long casts when posting full compressed orders in one message.

Encoded fields

chainId
swapContract
nonce
expiry
signerWallet
signerToken
signerAmount
protocolFee
senderWallet
senderToken
senderAmount
v
r
s

signer_make_order.js now writes

airswapWeb.compressedOrder
airswapWeb.orderPath as /order/<compressedOrder>

make_cast_payload.js writes

airswapWeb.orderUrl with URL-encoded compressed order for reliable clickable links
raw compressedOrder remains unencoded for machine parsing and execution

8) Decompress and take a posted order

If you receive only the compressed order blob from a cast

Decompress it with AirSwap utils decompressFullOrderERC20(compressedOrder)
Prefer in-memory handling from cast payloads. Do not rely on local JSON files as durable storage.
Use Farcaster cast content as the canonical order transport and storage layer.

If you receive the structured cast payload from make_cast_payload.js

Read payload.airswapWeb.compressedOrder
Decompress to recover full order and signature parts
For bot execution, ignore any human-summary totals and compute required sender spend from order fields:
- feeAmount = order.sender.amount * order.protocolFee / 10000
- totalRequired = order.sender.amount + feeAmount + order.affiliateAmount

Then execute with sender flow

Set SENDER_PRIVATE_KEY
Run node scripts/sender_execute_order.js

Sender execution script already enforces

expiry check
sender wallet restriction for non-open orders
EIP-712 signature verification
signer balance and allowance preflight
sender balance and allowance preflight

Scripts

Scripts are under scripts/.

These scripts are reference implementations. They can be run by one operator with both keys for testing. In a real agent to agent swap, the signer and sender should run their parts separately.

Recommended setup

Use Node 20+
Install deps in a temp folder
- npm i ethers@5 lz-string

Then run one of these

node scripts/signer_make_order.js
node scripts/sender_execute_order.js
node scripts/make_cast_payload.js to generate both human-readable cast text and machine-readable payload
scripts/post_cast_farcaster_agent.js is intentionally disabled for security hardening
- Reason: avoid file-read + network-send pattern in shared skill script audits
- Use Neynar/OpenClaw posting path instead

For a single machine end to end test

node scripts/test_weth_usdc_swap.js

For details and parameters Read scripts/README.md

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/grand-bazaar-swap/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 10 files · scripts

Illustrative Want to see what leoyeai/grand-bazaar-swap 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

Grand Bazaar P2P Swap

Deployed contracts

Safety rules

Workflow

Favorable inbound offer rule

Favorable outbound negotiation rule

Explicit size-aware pricing parameters

0) Pick roles

0.1) What each party does

1) Ensure balances

2) Approve

3) Create order

4) Sign EIP-712

5) Execute

6) Confirm

7) Share orders in AirSwap Web compatible compressed format

8) Decompress and take a posted order

Scripts

SkillSafety

Source

Related skills

More in the registry