Ready to supercharge your AI agents?

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

Market News Analyst · LeoYeAI | DecimalAI

Financeby LeoYeAI

Market News Analyst

This skill should be used when analyzing recent market-moving news events and their impact on equity markets and commodities.

SkillScore

SkillScore41/100

Test results 41

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

0%41%of test cases passed +41 pts

Without skill0 of 22

With skill9 of 22

9 fixed0 passed either way13 still failing0 broke

Measured on gemini-3.6-flash7/27/2026v116 comparable

Track record

Agent runs: 0; All time

Use this skill

Your agent runs on

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

pip install "decimalai>=0.15"
decimalai skills add market-news-analyst
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("market-news-analyst")
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 market-news-analyst

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/market-news-analyst/SKILL.md https://app.decimal.ai/s/market-news-analyst/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/market-news-analyst/SKILL.md

This gets SKILL.md only. The skill's 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/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/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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("market-news-analyst")
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/market-news-analyst/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/market-news-analyst/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 4 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 market-news-analyst

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/market-news-analyst/SKILL.md https://app.decimal.ai/s/market-news-analyst/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/market-news-analyst/SKILL.md

This gets SKILL.md only. The skill's 4 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/market-news-analyst/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/market-news-analyst.json

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/27/2026
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

Market News Analyst

Overview

This skill enables comprehensive analysis of market-moving news events from the past 10 days, focusing on their impact on US equity markets and commodities. The skill automatically collects news from trusted sources using WebSearch and WebFetch tools, evaluates market impact magnitude, analyzes actual market reactions, and produces structured English reports ranked by market impact significance.

When to Use This Skill

Use this skill when:

User requests analysis of recent major market news (past 10 days)
User wants to understand market reactions to specific events (FOMC decisions, earnings, geopolitical)
User needs comprehensive market news summary with impact assessment
User asks about correlations between news events and commodity price movements
User requests analysis of how central bank policy announcements affected markets

Example user requests:

"Analyze the major market news from the past 10 days"
"How did the latest FOMC decision impact the market?"
"What were the most important market-moving events this week?"
"Analyze recent geopolitical news and commodity price reactions"
"Review mega-cap tech earnings and their market impact"

Analysis Workflow

Follow this structured 6-step workflow when analyzing market news:

Step 1: News Collection via WebSearch/WebFetch

Objective: Gather comprehensive news from the past 10 days covering major market-moving events.

Search Strategy:

Execute parallel WebSearch queries covering different news categories:

Monetary Policy:

Search: "FOMC meeting past 10 days", "Federal Reserve interest rate", "ECB policy decision", "Bank of Japan"
Target: Central bank decisions, forward guidance changes, inflation commentary

Inflation/Economic Data:

Search: "CPI inflation report [current month]", "jobs report NFP", "GDP data", "PPI producer prices"
Target: Major economic data releases and surprises

Mega-Cap Earnings:

Search: "Apple earnings [current quarter]", "Microsoft earnings", "NVIDIA earnings", "Amazon earnings", "Tesla earnings", "Meta earnings", "Google earnings"
Target: Results, guidance, market reactions for largest companies

Geopolitical Events:

Search: "Middle East conflict oil prices", "Ukraine war", "US China tensions", "trade war tariffs"
Target: Conflicts, sanctions, trade disputes affecting markets

Commodity Markets:

Search: "oil prices news past week", "gold prices", "OPEC meeting", "natural gas prices", "copper prices"
Target: Supply disruptions, demand shifts, price movements

Corporate News:

Search: "major M&A announcement", "bank earnings", "tech sector news", "bankruptcy", "credit rating downgrade"
Target: Large corporate events beyond mega-caps

Recommended News Sources (Priority Order):

Official sources: FederalReserve.gov, SEC.gov (EDGAR), Treasury.gov, BLS.gov
Tier 1 financial news: Bloomberg, Reuters, Wall Street Journal, Financial Times
Specialized: CNBC (real-time), MarketWatch (summaries), S&P Global Platts (commodities)

Search Execution:

Use WebSearch for broad topic searches
Use WebFetch for specific URLs from official sources or major news outlets
Collect publication dates to ensure news is within 10-day window
Capture: Event date, source, headline, key details, market context (pre-market, trading hours, after-hours)

Filtering Criteria:

Focus on Tier 1 market-moving events (see references/market_event_patterns.md)
Prioritize news with clear market impact (price moves, volume spikes)
Exclude: Stock-specific small-cap news, minor product updates, routine filings

Think in English throughout collection process. Document each significant news item with:

Date and time
Event type (monetary policy, earnings, geopolitical, etc.)
Source reliability tier
Initial market reaction (if observable)

Step 2: Load Knowledge Base References

Objective: Access domain expertise to inform impact assessment.

Load relevant reference files based on collected news types:

Always Load:

references/market_event_patterns.md - Comprehensive patterns for all major event types
references/trusted_news_sources.md - Source credibility assessment

Conditionally Load (Based on News Collected):

If monetary policy news found:

Focus on: market_event_patterns.md → Central Bank Monetary Policy Events section
Key frameworks: Interest rate hike/cut reactions, QE/QT impacts, hawkish/dovish tone

If geopolitical events found:

Load: references/geopolitical_commodity_correlations.md
Focus on: Energy Commodities, Precious Metals, regional frameworks matching event

If mega-cap earnings found:

Load: references/corporate_news_impact.md
Focus on: Specific company sections, sector contagion patterns

If commodity news found:

Load: references/geopolitical_commodity_correlations.md
Focus on: Specific commodity sections (Oil, Gold, Copper, etc.)

Knowledge Integration: Compare collected news against historical patterns to:

Predict expected market reactions
Identify anomalies (market reacted differently than historical pattern)
Assess whether reaction was typical magnitude or outsized
Determine if contagion occurred as expected

Step 3: Impact Magnitude Assessment

Objective: Rank each news event by market impact significance.

Impact Assessment Framework:

For each news item, evaluate across three dimensions:

1. Asset Price Impact (Primary Factor):

Measure actual or estimated price movements:

Equity Markets:

Index-level: S&P 500, Nasdaq 100, Dow Jones
- Severe: ±2%+ in day
- Major: ±1-2%
- Moderate: ±0.5-1%
- Minor: ±0.2-0.5%
- Negligible: <0.2%
Sector-level: Specific sector ETFs
- Severe: ±5%+
- Major: ±3-5%
- Moderate: ±1-3%
- Minor: <1%
Stock-specific: Individual mega-caps
- Severe: ±10%+ (and index weight causes index move)
- Major: ±5-10%
- Moderate: ±2-5%

Commodity Markets:

Oil (WTI/Brent):
- Severe: ±5%+
- Major: ±3-5%
- Moderate: ±1-3%
Gold:
- Severe: ±3%+
- Major: ±1.5-3%
- Moderate: ±0.5-1.5%
Base Metals (Copper, etc.):
- Severe: ±4%+
- Major: ±2-4%
- Moderate: ±1-2%

Bond Markets:

10-Year Treasury Yield:
- Severe: ±20bps+ in day
- Major: ±10-20bps
- Moderate: ±5-10bps

Currency Markets:

USD Index (DXY):
- Severe: ±1.5%+
- Major: ±0.75-1.5%
- Moderate: ±0.3-0.75%

2. Breadth of Impact (Multiplier):

Assess how many markets/sectors affected:

Systemic (3x multiplier): Multiple asset classes, global markets
- Examples: FOMC surprise, banking crisis, major war outbreak
Cross-Asset (2x multiplier): Equities + commodities, or equities + bonds
- Examples: Inflation surprise, geopolitical supply shock
Sector-Wide (1.5x multiplier): Entire sector or related sectors
- Examples: Tech earnings cluster, energy policy announcement
Stock-Specific (1x multiplier): Single company (unless mega-cap with index impact)
- Examples: Individual company earnings, M&A

3. Forward-Looking Significance (Modifier):

Consider future implications:

Regime Change (+50%): Fundamental market structure shift
- Examples: Fed pivot from hiking to cutting, major geopolitical realignment
Trend Confirmation (+25%): Reinforces existing trajectory
- Examples: Consecutive strong inflation prints, sustained earnings beats
Isolated Event (0%): One-off with limited forward signal
- Examples: Single data point within range, company-specific issue
Contrary Signal (-25%): Contradicts prevailing narrative
- Examples: Good news ignored by market, bad news rallied

Impact Score Calculation:

Impact Score = (Price Impact Score × Breadth Multiplier) + Forward-Looking Modifier

Price Impact Score:
- Severe: 10 points
- Major: 7 points
- Moderate: 4 points
- Minor: 2 points
- Negligible: 1 point

Example Calculations:

FOMC 75bps Rate Hike (hawkish tone):

Price Impact: S&P 500 -2.5% (Severe = 10 points)
Breadth: Systemic (equities, bonds, USD, commodities all moved) = 3x
Forward: Trend confirmation (ongoing tightening) = +25%
Score: (10 × 3) × 1.25 = 37.5

NVIDIA Earnings Beat:

Price Impact: NVDA +15%, Nasdaq +1.5% (Severe = 10 points)
Breadth: Sector-wide (semis, tech broadly) = 1.5x
Forward: Trend confirmation (AI demand) = +25%
Score: (10 × 1.5) × 1.25 = 18.75

Geopolitical Flare-up (Middle East):

Price Impact: Oil +8%, S&P -1.2% (Severe = 10 points)
Breadth: Cross-asset (oil, equities, gold) = 2x
Forward: Isolated event (no escalation) = 0%
Score: (10 × 2) × 1.0 = 20

Single Stock Earnings (Non-Mega-Cap):

Price Impact: Stock +12%, no index impact (Major = 7 points)
Breadth: Stock-specific = 1x
Forward: Isolated = 0%
Score: (7 × 1) × 1.0 = 7

Ranking: After scoring all news items, rank from highest to lowest impact score. This determines report ordering.

Step 4: Market Reaction Analysis

Objective: Analyze how markets actually responded to each event.

For each significant news item (Impact Score >5), conduct detailed reaction analysis:

Immediate Reaction (Intraday):

Direction: Positive, negative, mixed
Magnitude: Align with price impact categories
Timing: Pre-market, during trading, after-hours
Volatility: VIX movement, bid-ask spreads

Multi-Asset Response:

Equities:

Index performance (S&P 500, Nasdaq, Dow, Russell 2000)
Sector rotation (which sectors outperformed/underperformed)
Individual stock moves (mega-caps, relevant companies)
Growth vs Value, Large vs Small Cap divergences

Fixed Income:

Treasury yields (2Y, 10Y, 30Y)
Yield curve shape (steepening, flattening, inversion)
Credit spreads (IG, HY)
TIPS breakevens (inflation expectations)

Commodities:

Energy: Oil (WTI, Brent), Natural Gas
Precious Metals: Gold, Silver
Base Metals: Copper, Aluminum (if relevant)
Agricultural: Wheat, Corn, Soybeans (if relevant)

Currencies:

USD Index (DXY)
EUR/USD, USD/JPY, GBP/USD
Emerging market currencies
Safe havens (JPY, CHF)

Derivatives:

VIX (volatility index)
Options activity (put/call ratio, unusual volume)
Futures positioning

Pattern Comparison:

Compare observed reaction against expected pattern from knowledge base:

Consistent: Reaction matched historical pattern
- Example: Fed hike → Tech stocks down, USD up (as expected)
Amplified: Reaction exceeded typical pattern
- Example: Inflation print +0.3% above consensus → Selloff 2x typical
- Investigate: Positioning, sentiment, cumulative factors
Dampened: Reaction less than historical pattern
- Example: Geopolitical event → Oil barely moved
- Investigate: Already priced in, other offsetting factors
Inverse: Reaction opposite of historical pattern
- Example: Good news ignored, bad news rallied
- Investigate: "Good news is bad news" dynamics, Fed pivot hopes

Anomaly Identification:

Flag reactions that deviate significantly from patterns:

Market shrugged off typically market-moving news
Overreaction to typically minor news
Contagion failed to spread as expected
Safe havens didn't work (correlations broke)

Sentiment Indicators:

Risk-On vs Risk-Off: Which regime dominated
Positioning: Evidence of crowded trades unwinding
Momentum: Follow-through in subsequent sessions or reversal

Step 5: Correlation and Causation Assessment

Objective: Distinguish direct impacts from coincidental timing.

Multi-Event Analysis:

When multiple significant events occurred in the 10-day period, assess interactions:

Reinforcing Events:

Same directional impact
Example: Hawkish FOMC + hot CPI → Both bearish for equities, amplified move
Combined impact often non-linear (greater than sum of parts)

Offsetting Events:

Opposite directional impacts
Example: Strong earnings (positive) + geopolitical tensions (negative) → Muted net reaction
Identify which factor dominated

Sequential Events:

One event set up reaction to next
Example: First rate hike modest reaction, second rate hike severe (cumulative tightening concerns)
Path dependence matters

Coincidental Timing:

Events unrelated but occurred simultaneously
Difficult to isolate individual impacts
Note uncertainty in attribution

Geopolitical-Commodity Correlations:

For geopolitical events, specifically analyze commodity market reactions using geopolitical_commodity_correlations.md:

Energy:

Map conflict/sanction to supply disruption risk
Assess actual vs feared supply impact
Duration: Temporary spike vs sustained elevation

Precious Metals:

Safe-haven flows vs real rate drivers
Gold response to risk-off events
Central bank buying implications

Industrial Metals:

Demand destruction from economic slowdown fears
Supply chain disruptions
China factor in copper, aluminum

Agriculture:

Black Sea grain exports (Russia-Ukraine)
Weather overlays
Food security policy responses

Transmission Mechanisms:

Trace how news impacts flowed through markets:

Direct Channel:

News → Immediate asset price reaction
Example: OPEC cuts → Oil prices up immediately

Indirect Channels:

News → Economic impact → Asset prices
Example: Rate hike → Mortgage rates up → Housing slows → Homebuilder stocks down

Sentiment Channel:

News → Risk appetite shift → Broad asset reallocation
Example: Banking crisis → Flight to quality → Treasuries rally, stocks sell

Feedback Loops:

Initial reaction creates secondary effects
Example: Stock selloff → Margin calls → Forced selling → Deeper selloff

Step 6: Report Generation

Objective: Create structured English Markdown report ranked by market impact.

Report Structure:

# Market News Analysis Report - [Date Range]

## Executive Summary

[3-4 sentences covering:]
- Period analyzed (specific dates)
- Number of significant events identified
- Dominant market theme/regime (risk-on/risk-off, sector rotation)
- Top 1-2 highest-impact events

## Market Impact Rankings

[Table format, sorted by Impact Score descending]

| Rank | Event | Date | Impact Score | Asset Classes Affected | Market Reaction |
|------|-------|------|--------------|------------------------|-----------------|
| 1 | [Event] | [Date] | [Score] | [Equities, Commodities, etc.] | [Brief reaction] |
| 2 | ... | ... | ... | ... | ... |

---

## Detailed Event Analysis

[For each event in rank order, provide comprehensive analysis]

### [Rank]. [Event Name] (Impact Score: [X])

**Event Date:** [Date, Time]
**Event Type:** [Monetary Policy / Earnings / Geopolitical / Economic Data / Corporate]
**News Source:** [Source, with credibility tier]

#### Event Summary
[3-4 sentences describing what happened]
- Key details (e.g., rate decision, earnings beat/miss magnitude, conflict developments)
- Context (was this expected, surprise factor)
- Forward guidance or implications stated

#### Market Reaction

**Immediate (Day-of):**
- **Equities:** S&P 500 [+/-X%], Nasdaq [+/-X%], Sector rotation [details]
- **Bonds:** 10Y yield [change], credit spreads [movement]
- **Commodities:** Oil [+/-X%], Gold [+/-X%], Copper [+/-X%] (if relevant)
- **Currencies:** USD [+/-X%], [other relevant pairs]
- **Volatility:** VIX [level/change]

**Follow-Through (Subsequent Sessions):**
- [Direction: sustained, reversed, or consolidated]
- [Additional price action details if significant]

**Pattern Comparison:**
- **Expected Reaction:** [Based on historical patterns from knowledge base]
- **Actual vs Expected:** [Consistent / Amplified / Dampened / Inverse]
- **Explanation of Deviation:** [If applicable, why reaction differed]

#### Impact Assessment Detail

**Asset Price Impact:** [Severe/Major/Moderate/Minor] - [Justification]
**Breadth:** [Systemic/Cross-Asset/Sector/Stock-Specific] - [Affected markets]
**Forward Significance:** [Regime Change/Trend Confirmation/Isolated/Contrary] - [Rationale]

**Calculated Score:** ([Price Score] × [Breadth Multiplier]) × [Forward Modifier] = [Total]

#### Sector-Specific Impacts

[If relevant, detail which sectors/industries were most affected]
- [Sector 1]: [Impact and reason]
- [Sector 2]: [Impact and reason]
- [Example: Technology -3% (rate sensitivity), Energy +5% (oil price spillover)]

#### Geopolitical-Commodity Correlation Analysis

[Include this section only for geopolitical events]
- [Specific commodity affected]: [Price movement]
- [Supply/demand mechanism]: [Explanation]
- [Historical precedent]: [Comparison to similar past events]
- [Expected duration]: [Temporary shock vs sustained impact]

[Repeat detailed analysis for each ranked event]

---

## Thematic Synthesis

### Dominant Market Narrative
[Identify overarching theme across the 10-day period]
- [E.g., "Persistent inflation concerns dominated despite mixed economic data"]
- [E.g., "Tech sector strength drove markets higher despite geopolitical headwinds"]

### Interconnected Events
[Analyze how events related or compounded]
- [Event A] + [Event B] → [Combined impact analysis]
- [Sequential causation if applicable]

### Market Regime Assessment
**Risk Appetite:** [Risk-On / Risk-Off / Mixed]
**Evidence:**
- [Supporting indicators: sector performance, safe haven flows, credit spreads, VIX]

**Sector Rotation Trends:**
- [Growth vs Value]
- [Cyclicals vs Defensives]
- [Outperformers and underperformers]

### Anomalies and Surprises
[Highlight unexpected market reactions]
1. [Event]: Market reacted [unexpectedly] because [explanation]
2. [Continue for significant anomalies]

---

## Commodity Market Deep Dive

[Dedicated section for commodity movements]

### Energy
- **Crude Oil (WTI/Brent):** [Price level, % change over period, key drivers]
- **Natural Gas:** [If significant movement]
- **Key Events:** [Specific news impacting energy: OPEC, geopolitics, inventory data]

### Precious Metals
- **Gold:** [Price level, % change, safe-haven flows vs real rate dynamics]
- **Silver:** [If significant divergence from gold]
- **Drivers:** [Geopolitical risk premium, inflation hedging, USD strength]

### Base Metals
- **Copper:** [As economic barometer - demand signals]
- **Aluminum, Nickel:** [If relevant supply/demand news]
- **China Factor:** [Impact of Chinese economic data/policy]

### Agricultural (If Relevant)
- **Grains:** [Wheat, Corn, Soybeans - weather, Ukraine conflict impacts]

[For each commodity, reference geopolitical events from main analysis and draw correlations]

---

## Forward-Looking Implications

### Market Positioning Insights
[What the news suggests for current market positioning]
- [Trend continuation or reversal signals]
- [Overvaluation or undervaluation indications]
- [Sentiment extremes (complacency or panic)]

### Upcoming Catalysts
[Events on horizon that may be set up by recent news]
- [Next FOMC meeting expectations post-recent decision]
- [Upcoming earnings seasons based on guidance]
- [Geopolitical developments to monitor]

### Risk Scenarios
[Based on recent news, identify key risks]
1. **[Risk Name]:** [Description, probability, potential impact]
2. **[Risk Name]:** [Description, probability, potential impact]
3. [Continue for 3-5 key risks]

---

## Data Sources and Methodology

### News Sources Consulted
[List primary sources used, organized by tier]
- **Official Sources:** [e.g., FederalReserve.gov, SEC.gov]
- **Tier 1 Financial News:** [e.g., Bloomberg, Reuters, WSJ]
- **Specialized:** [e.g., S&P Global Platts for commodities]

### Analysis Period
- **Start Date:** [Specific date]
- **End Date:** [Specific date]
- **Total Days:** 10

### Market Data
- Equity indices: [Data sources]
- Commodity prices: [Data sources]
- Economic data: [Government sources]

### Knowledge Base References
- `market_event_patterns.md` - Historical reaction patterns
- `geopolitical_commodity_correlations.md` - Geopolitical-commodity frameworks
- `corporate_news_impact.md` - Mega-cap impact analysis
- `trusted_news_sources.md` - Source credibility assessment

---

*Analysis Date: [Date report generated]*
*Language: English*
*Analysis Thinking: English*

File Naming Convention: market_news_analysis_[START_DATE]_to_[END_DATE].md

Example: market_news_analysis_2024-10-25_to_2024-11-03.md

Report Quality Standards:

Objective, fact-based analysis (no speculation beyond probability-weighted scenarios)
Quantify price movements with specific percentages
Cite sources for major claims
Distinguish between correlation and causation
Acknowledge uncertainty when attributing market moves to specific news
Use proper financial terminology
Maintain consistent English throughout

Key Analysis Principles

When conducting market news analysis:

Impact Over Noise: Focus on truly market-moving news, filter out minor events
Multi-Asset Perspective: Analyze across equities, bonds, commodities, currencies to understand full impact
Pattern Recognition: Compare against historical precedents while noting unique aspects
Causation Discipline: Be rigorous about attributing market moves to specific news vs coincidental timing
Forward-Looking: Emphasize implications for future market behavior, not just backward-looking description
Objectivity: Separate market reaction (what happened) from personal market view (what should happen)
Quantification: Use specific numbers (%, bps) rather than vague terms ("significant," "large")
Source Credibility: Weight official sources and Tier 1 news over rumors and unverified reports
Breadth Analysis: Individual stock moves only significant if mega-cap or systemic signal
English Consistency: All thinking, analysis, and output in English for consistency

Common Pitfalls to Avoid

Over-Attribution:

Not every market move is news-driven (technicals, flows, month-end rebalancing exist)
Acknowledge when attribution is uncertain

Recency Bias:

Latest news isn't always most important
Rank by actual impact, not chronological order

Hindsight Bias:

Distinguish "obvious in retrospect" from "surprising at the time"
Note consensus expectations vs actual outcomes

Single-Factor Analysis:

Markets respond to multiple factors simultaneously
Acknowledge interaction effects

Ignoring Magnitude:

A "hot" CPI that's 0.1% above consensus is different from 0.5% above
Quantify surprise factor

Resources

references/

market_event_patterns.md - Comprehensive knowledge base covering:

Central bank monetary policy events (FOMC, ECB, BOJ, PBOC)
Inflation data releases (CPI, PPI, PCE)
Employment data (NFP, unemployment, wages)
GDP reports
Geopolitical events (conflicts, trade wars, sanctions)
Corporate earnings (mega-cap technology, banks, energy)
Credit events and rating changes
Commodity-specific events (OPEC, weather, supply disruptions)
Recession indicators
Historical case studies (2008 crisis, COVID-19, 2022 inflation)
Pattern recognition framework and sentiment analysis

geopolitical_commodity_correlations.md - Detailed correlations covering:

Energy commodities (crude oil, natural gas, coal) and geopolitical conflicts
Precious metals (gold, silver, platinum, palladium) safe-haven dynamics
Base metals (copper, aluminum, nickel, zinc) and economic/political risks
Agricultural commodities (wheat, corn, soybeans) and weather/policy
Rare earth elements and critical minerals (China dominance, supply security)
Regional geopolitical frameworks (Middle East, Russia-Europe, Asia-Pacific, Latin America)
Correlation summary tables
Time horizon considerations

corporate_news_impact.md - Mega-cap analysis framework:

"Magnificent 7" technology stocks (NVIDIA, Apple, Microsoft, Amazon, Meta, Google, Tesla)
Financial sector mega-caps (JPMorgan, Bank of America, etc.)
Healthcare mega-caps (UnitedHealth, Pfizer, J&J, Merck)
Energy mega-caps (Exxon Mobil, Chevron)
Consumer staples mega-caps (P&G, Coca-Cola, PepsiCo)
Industrial mega-caps (Boeing, Caterpillar)
Earnings impact frameworks, product launches, M&A, regulatory issues
Sector contagion patterns
Impact magnitude framework

trusted_news_sources.md - Source credibility guide:

Tier 1 primary sources (central banks, government agencies, SEC)
Tier 2 major financial news (Bloomberg, Reuters, WSJ, FT, CNBC)
Tier 3 specialized sources (energy, tech, emerging markets, China-specific, crypto)
Tier 4 analysis and research (independent research, central bank publications, think tanks)
Search and aggregation tools
Source quality assessment criteria
Speed vs accuracy trade-offs
Recommended search strategies for 10-day analysis
Source credibility framework
Red flag sources to avoid

Important Notes

All analysis thinking must be conducted in English
All output Markdown files must be in English
Use WebSearch and WebFetch tools to collect news automatically
Focus on trusted news sources as defined in references
Rank events by impact score (price impact × breadth × forward significance)
Target analysis period: Past 10 days from current date
Emphasize US equity markets and commodities as primary analysis subjects
FOMC and other central bank policy decisions receive highest priority analysis
Distinguish between correlation and causation rigorously
Quantify all market reactions with specific percentages
Load appropriate reference files based on news types collected
Generate comprehensive reports ranked by market impact (highest impact first)

When it activates

Automatically, when a task matches. Use this skill when the user requests analysis of major financial news from the past 10 days, wants to understand market reactions to monetary policy decisions (FOMC, ECB, BOJ), needs assessment of geopolitical events' impact on commodities, or requires comprehensive review of earnings announcements from mega-cap stocks. The skill automatically collects news using WebSear

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 — 7/30/2026

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/market-news-analyst-en/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 4 files

Illustrative Want to see what market-news-analyst 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

Market News Analyst

Overview

When to Use This Skill

Analysis Workflow

Step 1: News Collection via WebSearch/WebFetch

Step 2: Load Knowledge Base References

Step 3: Impact Magnitude Assessment

Step 4: Market Reaction Analysis

Step 5: Correlation and Causation Assessment

Step 6: Report Generation

Key Analysis Principles

Common Pitfalls to Avoid

Resources

references/

Important Notes

When it activates

SkillSafety

Source

Related skills

More in the registry