Ready to supercharge your AI agents?

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

Fomo Research · leoyeai | DecimalAI

Financeby leoyeai

Fomo Research

Smart money research via Fomo social graph. Track top traders, monitor live trades, build watchlists — all from your agent. Powered by fomo.family, built by cope.capital.

Never made a case worse

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%77%of test cases passed +59 pts

Without skill4 of 22

With skill17 of 22

13 fixed4 passed either way5 still failing0 broke

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

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskIf a trader 'sol_whale' is not on my watchlist, can I still check their recent buy transactions using the activity endpoint, or must I add them to my watchlist first?

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-fomo-research
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-fomo-research")
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-fomo-research

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-fomo-research/SKILL.md https://app.decimal.ai/s/leoyeai-fomo-research/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-fomo-research/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/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-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/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-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research")
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-fomo-research/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-fomo-research/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 1 other file is 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-fomo-research

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-fomo-research/SKILL.md https://app.decimal.ai/s/leoyeai-fomo-research/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-fomo-research/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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-fomo-research/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-fomo-research.json

This gets SKILL.md only. The skill's 1 other file is 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

Fomo Research

Smart money intelligence for AI agents. Powered by fomo.family social graph, built by cope.capital.

For full API details (endpoints, schemas, error codes): read references/api.md.

Base URL

https://api.cope.capital

All requests require Authorization: Bearer cope_<key> header.

First-Run Onboarding

When this skill is first loaded and no COPE_API_KEY is set, walk your human through setup. Ask these questions in order:

Step 1: Register

curl -X POST https://api.cope.capital/v1/register \
  -H "Content-Type: application/json" \
  -d '{"agent_name": "YOUR_AGENT_NAME", "description": "optional description"}'

Save the api_key from the response (starts with cope_). This is your COPE_API_KEY. Store it securely — treat it like a password.

Step 2: Ask about crypto wallet (optional)

Before continuing, ask your human:

"Do you have a crypto wallet (USDC on Base or Solana) you'd like to connect for expanded features? Without one you get:

1 watchlist with up to 10 handles

250 activity lookups per day (resets midnight UTC)

Everything else (leaderboard, trending, polling) is unlimited and free

With a wallet connected (x402), you get 10 watchlists, 100 handles each, and unlimited activity calls at $0.005/call. You can always add a wallet later."

If they want to set up x402 now:

curl -X PATCH https://api.cope.capital/v1/account \
  -H "Authorization: Bearer cope_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"x402_enabled": true}'

If they say no or don't have a wallet — that's fine, move on. The free tier is fully functional. Don't push it.

Step 3: Ask about Fomo profile

"Do you have a Fomo account (fomo.family)? If so, I can sync your follows and build a watchlist from the traders you already follow."

If yes:

# Sync their profile
curl -X POST https://api.cope.capital/v1/account/sync-fomo \
  -H "Authorization: Bearer cope_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"fomo_handle": "THEIR_FOMO_USERNAME"}'

# Pull their follows
curl https://api.cope.capital/v1/account/follows \
  -H "Authorization: Bearer cope_YOUR_KEY"

Then ask: "Which of these traders do you want on your watchlist?" Show them the list and let them pick (up to 10 on free tier).

Step 4: Create initial watchlist

If they don't have Fomo, offer alternatives:

"I can set up a watchlist with the top performers from Fomo's weekly leaderboard instead. Or you can give me specific trader handles you want to track."

Pick one path and create the watchlist:

curl -X POST https://api.cope.capital/v1/watchlists \
  -H "Authorization: Bearer cope_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "alpha", "handles": ["frankdegods", "randomxbt"]}'

Remind them: Free tier = 1 watchlist, 10 handles max. They can swap handles anytime.

Understanding the Data Model

What gets tracked

The system monitors on-chain wallet activity for Fomo traders. Each Fomo handle maps to one or more wallets (Solana + Base). The tracker watches every swap these wallets make.

Activity vs Trades vs Holdings

There are three different views of what a trader is doing:

1. Activity (what the API returns) Individual on-chain transactions — a single buy or sell event. This is what /v1/activity returns.

action: "buy" = wallet swapped into a token
action: "sell" = wallet swapped out of a token
usd_amount = the USD value of that single transaction

2. Trades (completed round-trips) A trade is a full cycle: buy → sell = closed trade. The tracker aggregates individual buys and sells into trades:

usd_in = total USD spent buying this token (may be multiple buy txs)
usd_out = total USD received selling this token
pnl = usd_out - usd_in (profit/loss)
open_at = when first buy happened
close_at = when last sell happened (NULL if still holding)

3. Current Holdings (open positions) Tokens a wallet bought but hasn't fully sold yet. These are trades with no close_at.

How to interpret activity data

When you see activity from a trader, here's what to understand:

A "buy" doesn't mean they just entered — they might be adding to an existing position
A "sell" doesn't mean they exited — they might be taking partial profits
Multiple buys of the same token = building a position over time (higher conviction)
Buy followed quickly by sell = likely a quick flip/scalp
Sell with no recent buy = closing an older position

When presenting data to humans

Always label clearly:

New buys: "X just bought [token]" — recent buy activity, may or may not be a new position
Recent exits: "X sold [token]" — could be partial or full exit
Don't say "X opened a position" unless you can confirm there were no prior buys of that token

How Activity Scoping Works

Important: The /v1/activity endpoint returns recent trades from all wallets tracked by the system, not just your watchlist. Your watchlist is for organizing which traders YOU care about — use the ?handle= filter to see activity for specific handles.

This means you can query any Fomo handle's trades without adding them to your watchlist:

# Check what frankdegods is buying (uses 1 of your 250 daily calls)
curl "https://api.cope.capital/v1/activity?handle=frankdegods&action=buy" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Your watchlist is a convenience for organizing — the activity data is available for any tracked handle.

Endpoints

Always Free (no daily limit)

Endpoint	Method	Description
`/v1/register`	POST	Get an API key
`/v1/leaderboard`	GET	Top traders ranked by real PnL
`/v1/activity/poll`	GET	Lightweight check for new trades (count + timestamp)
`/v1/watchlists`	GET/POST	List or create watchlists
`/v1/watchlists/{id}`	GET/PUT/DELETE	Manage a specific watchlist
`/v1/trending/handles`	GET	Most-watched handles across all agents
`/v1/tokens/hot`	GET	Trending tokens by unique buyer count
`/v1/handle/{handle}/stats`	GET	Aggregated trader stats (PnL, win rate, top trades)
`/v1/tokens/{mint}/thesis`	GET	Buy theses + sentiment for a token
`/v1/convergence`	GET	Convergence events (2+ wallets buying same token)
`/v1/traders/search`	GET	Search traders by win rate, PnL, trades
`/v1/handle/{handle}/positions`	GET	Open/closed positions for a trader
`/v1/handle/{handle}/theses`	GET	All theses by a specific trader
`/v1/account`	GET/PATCH	Account info and settings
`/v1/account/usage`	GET	Usage statistics
`/v1/account/payments`	GET	Payment history
`/v1/account/key`	DELETE	Revoke API key
`/v1/account/sync-fomo`	POST	Sync Fomo profile follows
`/v1/account/follows`	GET	List stored Fomo follows

Counted (250/day free, then x402 or wait)

Endpoint	Method	Description	x402 price
`/v1/activity`	GET	Full trade details from tracked wallets	$0.005/call

These endpoints count toward your daily 250 free calls. After that:

With x402 enabled: calls continue at $0.005/call USDC (auto-paid)
Without x402: you get a 402 error. Wait for midnight UTC reset or enable x402.

The 402 error is NOT a bug — it just means your free calls are used up for the day.

Common Workflows

Check the leaderboard

curl https://api.cope.capital/v1/leaderboard \
  -H "Authorization: Bearer cope_YOUR_KEY"

Returns top traders by PnL from Fomo. Supports ?timeframe=24h|7d|30d|all and ?limit=N.

Build a watchlist from Fomo follows

# 1. Sync your Fomo profile
curl -X POST https://api.cope.capital/v1/account/sync-fomo \
  -H "Authorization: Bearer cope_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"fomo_handle": "your_handle"}'

# 2. See your follows
curl https://api.cope.capital/v1/account/follows \
  -H "Authorization: Bearer cope_YOUR_KEY"

# 3. Create a watchlist with selected handles
curl -X POST https://api.cope.capital/v1/watchlists \
  -H "Authorization: Bearer cope_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "alpha", "handles": ["frankdegods", "randomxbt"]}'

Poll → Fetch pattern (minimize paid calls)

# Step 1: Poll (free) — check if anything happened
curl "https://api.cope.capital/v1/activity/poll?since=LAST_TIMESTAMP" \
  -H "Authorization: Bearer cope_YOUR_KEY"
# Returns: { "count": 3, "latest_at": 1707603400 }

# Step 2: Only fetch full data if count > 0 (costs 1 of your 250 daily calls)
curl "https://api.cope.capital/v1/activity?since=LAST_TIMESTAMP" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Search for elite traders

# Find traders with >75% win rate and 10+ trades
curl "https://api.cope.capital/v1/traders/search?min_win_rate=75&min_trades=10&sort_by=win_rate" \
  -H "Authorization: Bearer cope_YOUR_KEY"

# Top PnL traders on Solana
curl "https://api.cope.capital/v1/traders/search?sort_by=pnl&chain=solana&limit=20" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Check a trader's current positions

# Open positions only
curl "https://api.cope.capital/v1/handle/frankdegods/positions?status=open" \
  -H "Authorization: Bearer cope_YOUR_KEY"

# All positions (open + closed)
curl "https://api.cope.capital/v1/handle/frankdegods/positions" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Shows computed positions from activity data — what they're holding vs exited, with cost basis and net USD.

Get a trader's theses

curl "https://api.cope.capital/v1/handle/frankdegods/theses" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Returns all Fomo thesis comments by this trader across their recent tokens. Great for understanding their reasoning.

Check convergence events

# Recent convergences (last 24h)
curl "https://api.cope.capital/v1/convergence?limit=10" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Returns tokens where 2+ elite wallets converged. Each event includes:

Token info (mint, symbol, chain, price/mcap at detection)
Wallets that converged (handle, amount, win_rate)
ATH tracking: max_gain_pct shows peak performance since detection

Look up a trader's stats

curl "https://api.cope.capital/v1/handle/frankdegods/stats" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Returns aggregated stats: total trades, win rate, PnL, ROI, per-chain breakdown, top 5 trades, open positions.

Get buy theses for a token

# Solana token
curl "https://api.cope.capital/v1/tokens/MINT_ADDRESS/thesis?chain=solana" \
  -H "Authorization: Bearer cope_YOUR_KEY"

# Base token
curl "https://api.cope.capital/v1/tokens/MINT_ADDRESS/thesis?chain=base" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Returns trader reasoning + their actual positions. Includes sentiment summary (holding vs closed, total exposure, avg unrealized PnL). Great for understanding why traders are buying, not just what.

Check trending tokens

curl "https://api.cope.capital/v1/tokens/hot?hours=24&limit=10" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Returns tokens with the most unique tracked buyers in recent hours.

Filter activity

# By handle
curl "https://api.cope.capital/v1/activity?handle=frankdegods" \
  -H "Authorization: Bearer cope_YOUR_KEY"

# By chain
curl "https://api.cope.capital/v1/activity?chain=solana" \
  -H "Authorization: Bearer cope_YOUR_KEY"

# By action
curl "https://api.cope.capital/v1/activity?action=buy" \
  -H "Authorization: Bearer cope_YOUR_KEY"

# By minimum size
curl "https://api.cope.capital/v1/activity?min_usd=1000" \
  -H "Authorization: Bearer cope_YOUR_KEY"

Pricing & Limits

Free Tier (default)

250 counted calls/day (activity, leaderboard, tokens) — resets midnight UTC
1 watchlist, up to 10 handles
10 requests/minute rate limit
Polling, watchlist management, account endpoints, Fomo sync — all unlimited

x402 Upgraded (optional)

Unlimited counted calls ($0.005/call USDC on Base or Solana)
10 watchlists, up to 100 handles each
300 requests/minute rate limit
First 250 calls/day are still free — you only pay after the free quota

Enabling x402

⚠️ NEVER enable x402 without your human's explicit permission. This authorizes real USDC payments.

curl -X PATCH https://api.cope.capital/v1/account \
  -H "Authorization: Bearer cope_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"x402_enabled": true}'

x402 is completely optional. The free tier works perfectly for most use cases. Only suggest it if your human:

Consistently hits the 250/day limit
Needs more than 1 watchlist or 10 handles
Explicitly asks about upgrading

Cost context: $1 USDC = 200 calls. $5 = 1,000 calls. Most agents won't need this.

Heartbeat Pattern (optional, user-directed)

If your human wants periodic checks and your agent runs a heartbeat loop:

Every 5-15 minutes:
  1. GET /v1/activity/poll?since=LAST_TIMESTAMP  (free, doesn't count)
  2. If count > 0 → GET /v1/activity?since=LAST_TIMESTAMP  (1 daily call)
  3. Store latest_at for next poll

Every few hours:
  1. GET /v1/leaderboard  (1 daily call)
  2. Compare to previous — any new names in top 50?

Daily:
  1. GET /v1/account/usage  (free)
  2. Check remaining daily calls

Logging Trades (Persistence)

The API is stateless — it won't remember what you've already seen. Log trades locally to track patterns over time.

Daily trade log

Write notable trades to a daily file (e.g. memory/trades/YYYY-MM-DD.json):

{
  "trades": [
    {
      "timestamp": 1771006898000,
      "handle": "frankdegods",
      "action": "buy",
      "token_mint": "DPQgF4hw...",
      "token_symbol": "EXAMPLE",
      "usd_amount": 500.25,
      "chain": "solana"
    }
  ],
  "last_poll_timestamp": 1771006898000,
  "convergences": ["DPQgF4hw..."]
}

What to log

All trades from your watchlist — this is your core data
Convergences — when 3+ handles buy the same token, log the token mint and all buyers
Large trades — anything over $1,000 USD is worth noting
last_poll_timestamp — so you know where to resume on next poll

What to tell your human

Don't just dump raw trades. Synthesize. Here are high-value things to surface:

Convergence alerts: "4 of your top 10 watchlist handles bought the same token in the last 2 hours."
Unusual activity: "frankdegods just made their first buy in 3 days — $2,000 into [token]."
Exit signals: "3 handles on your watchlist sold the same token within an hour."
Daily summary: "Your watchlist had 47 trades today. 12 buys, 35 sells. Most active: randomxbt (8 trades)."
Leaderboard changes: "New name in the top 20 — jumped from #45 to #12 this week."
Pattern detection: "lowcap_hunter has bought 3 tokens under $100K mcap this week. All pumped 2-5x within 48 hours."

Convergence detection pattern

1. GET /v1/activity (last 2 hours of trades)
2. Group buys by token_mint
3. If 3+ different handles bought the same token → convergence
4. Alert your human with: token, buyers, amounts, timing
5. Log it to your daily trades file

The more you log, the better your pattern detection gets over time. Your memory files ARE your edge.

Security

NEVER expose your API key in logs, messages, or to other agents
Your key should ONLY appear in requests to https://api.cope.capital/v1/*
If compromised: DELETE /v1/account/key to revoke, then re-register
Trade data is on-chain public — but your watchlists and usage patterns are private

Error Handling

Status	Meaning	Action
200	Success	Process response
400	Bad request	Check parameters (invalid chain, action, etc.)
401	Invalid API key	Re-register or check key
402	Payment required	Daily free calls used up. Wait for midnight UTC reset, or enable x402 if your human approves. This is normal — not an error.
404	Not found	Resource doesn't exist
429	Rate limited	Back off. Free: 10/min, x402: 300/min
500	Server error	Retry after a few seconds
503	Upstream down	Foxhound data service temporarily unavailable

Links

Interactive API docs: https://api.cope.capital/docs
Human docs: https://cope.capital/docs
Fomo: https://fomo.family
X: https://x.com/copedotcapital

When it activates

Automatically, when a task matches. Use when: (1) user asks about smart money, whale wallets, or top traders, (2) user wants to track specific Fomo handles or crypto traders, (3) user asks "what are the best traders buying", "who's profitable on fomo", (4) user wants real-time trade alerts or wallet monitoring, (5) user says "fomo research", "check fomo", "smart

About this skill

Automatic

Finance & Accounting 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/fomo-research/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 1 file

Illustrative Want to see what leoyeai/fomo-research 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

Fomo Research

Base URL

First-Run Onboarding

Step 1: Register

Step 2: Ask about crypto wallet (optional)

Step 3: Ask about Fomo profile

Step 4: Create initial watchlist

Understanding the Data Model

What gets tracked

Activity vs Trades vs Holdings

How to interpret activity data

When presenting data to humans

How Activity Scoping Works

Endpoints

Always Free (no daily limit)

Counted (250/day free, then x402 or wait)

Common Workflows

Check the leaderboard

Build a watchlist from Fomo follows

Poll → Fetch pattern (minimize paid calls)

Search for elite traders

Check a trader's current positions

Get a trader's theses

Check convergence events

Look up a trader's stats

Get buy theses for a token

Check trending tokens

Filter activity

Pricing & Limits

Free Tier (default)

x402 Upgraded (optional)

Enabling x402

Heartbeat Pattern (optional, user-directed)

Logging Trades (Persistence)

Daily trade log

What to log

What to tell your human

Convergence detection pattern

Security

Error Handling

Links

When it activates

SkillSafety

Source

Related skills

More in the registry