Ready to supercharge your AI agents?

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

Critical Analysis Skill (Is-It-Ture) · leoyeai | DecimalAI

Researchby leoyeai

Critical Analysis Skill (Is-It-Ture)

Conduct critical analysis of viewpoints, factual statements, or web content using the critical thinking framework from "Asking the Right Questions".

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

50%91%of test cases passed +41 pts

Without skill11 of 22

With skill20 of 22

10 fixed10 passed either way1 still failing1 broke

Measured on gemini-3.6-flash8/8/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskA wellness blog post claims: 'SuperCleanse Elixir completely flushes all heavy metals from your liver in 24 hours without diet changes!' Conduct a web content credibility analysis on this snippet.

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-is-it-ture
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-is-it-ture")
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-is-it-ture

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-is-it-ture/SKILL.md https://app.decimal.ai/s/leoyeai-is-it-ture/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-is-it-ture/SKILL.md

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/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-is-it-ture/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 2 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/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-is-it-ture/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 2 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/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 2 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add leoyeai-is-it-ture

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-is-it-ture")
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-is-it-ture/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-is-it-ture/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 2 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-is-it-ture

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-is-it-ture/SKILL.md https://app.decimal.ai/s/leoyeai-is-it-ture/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-is-it-ture/SKILL.md

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/leoyeai-is-it-ture/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-is-it-ture.json

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

Critical Analysis Skill (Is-It-Ture)

A comprehensive framework for systematic dialectical examination of viewpoints, factual statements, or web content, based on the critical thinking methodology of "Asking the Right Questions" by Browne and Keeley.

Core Analysis Process

Step 1: Determine Analysis Type

Classify the input into one of the following types:

Type	Characteristics	Analysis Focus
Factual Statement	Verifiable objective claims involving data, research, statistics, etc.	Authenticity, scientific basis, evidence support
Opinion-based Statement	Contains value judgments, opinions, or suggestions	Thesis, conclusion, argument, evidence, assumptions
Web/Article Content	Mixed content combining facts and opinions	Separate facts from opinions, then analyze each

Step 2: Factual Statement Verification Framework

For each factual statement, systematically verify the following dimensions:

2.1 Source Tracing

Original Source: Where did this data/conclusion originate?
Authority: Does the source have professional credentials (academic journals, government agencies, renowned research institutions)?
Timeliness: Is the information outdated? Are there more recent studies or data?

2.2 Multi-Source Cross-Validation (Mandatory Step)

Multi-source cross-validation must be performed for ALL types of input (factual statements, opinion-based statements, web content):

2.2.1 Verification Strategies

Verification Method	Action
Direct Search Verification	Use search engines to find reliable sources for original data/research
Cross-Validation	Verify the same fact through 3+ different reliable sources
Reverse Verification	Search whether the information has been denied by official/authoritative institutions
Deep Tracing	Trace the information dissemination chain to find the original source

2.2.2 Source Reliability Ratings

Grade	Type	Description
A+	Government official data, prestigious academic journals, peer-reviewed research	Highest credibility
A	Reports from renowned institutions (WHO, World Bank, etc.), verified mainstream media reports	Highly credible
B+	Professional media, industry association reports, content with clear source citations	Basically credible
B	General media reports, personal blogs without clear sources	Requires cross-validation
C	Social media, forum posts, content with untraceable sources	Suspicious
D	Anonymous posts, marketing content, confirmed misinformation	Not credible

2.2.3 Information Source Type Identification

Type	Characteristics	Risk Level
Misinformation	Content contradicts established facts, no reliable source support	High
Marketing Copy	Commercial purpose, exaggeration or out-of-context presentation	High
Unverifiable Private Information	No verifiable source, subjective statements presented as objective facts	Medium-High
Misleading Information	Partially true but deliberately misleading	High
Outdated Information	Previously correct data/conclusions that are now obsolete	Medium

2.2.4 Cross-Validation Checklist

Was the original source found? What is the original source?
Are there 3+ independent reliable sources supporting this information?
Are there any reliable sources that contradict this?
Has this information been denied or corrected by authoritative institutions?
Does the information come from known misinformation sources?
Is there any out-of-context or selective quoting?
Have the data/statistics been deliberately distorted (scale, base, comparison method)?

2.2.5 Information Tracing Path

Original Input
    ↓
Is a specific source mentioned? (research/report/institution/person)
    ├─ Yes → Trace that source → Verify source reliability → Find original data
    └─ No → Multi-keyword search → Attempt to find reliable sources
              ↓
        Reliable source found?
            ├─ Yes → Compare original statement with original information
            └─ No → Mark as "source unknown" → Lower credibility rating

2.3 Scientific Principle Verification

Consistency with Known Scientific Principles: Does the statement align with established scientific theories?
Mechanism Explanation: Can it explain the underlying causal mechanism?
Boundary Conditions: What are the applicable conditions and scope of this conclusion?

2.4 Evidence Quality Assessment

Direct Evidence: Is there direct experimental data, statistical data, or research results supporting it?
Indirect Evidence: Is the inference chain rigorous?
Sample Quality: Is the research sample representative? Is the sample size sufficient?
Research Design: Is the research methodology scientific? Are there design flaws?

2.5 Logical Consistency

Internal Consistency: Are there internal contradictions within the statement?
External Consistency: Does it align with other reliable evidence?
Causation vs. Correlation: Has causation been confused with correlation?

Step 3: Opinion-Based Statement Analysis Framework

Deconstruct opinion-based statements into their components for systematic analysis, while performing multi-source cross-validation on any factual content involved:

3.1 Thesis Identification

Core Question: What question is the author trying to answer?
Thesis Type: Descriptive (what is) or Prescriptive (what should be)?

3.2 Conclusion Extraction

Main Conclusion: What is the author's core claim?
Sub-conclusions: What specific points support the main conclusion?
Conclusion Priority: Which are main points and which are supporting arguments?

3.3 Argument Structure Analysis

Argument = Conclusion + Reasons + Evidence + Hidden Assumptions

Reasons: What reasons does the author use to support the conclusion?
Evidence Types:
- Personal experience/cases
- Unofficial expert opinions
- Eyewitness testimony
- Typical cases
- Quoted authorities/experts
- Personal observation
- Research results/statistical data
- Analogies
- Presumed premises
Evidence Quality: How strong a conclusion can this type of evidence support?

3.4 Assumption Identification

Explicit Assumptions (clearly stated by the author):

What are the author's preconditions?

Implicit Assumptions (unstated but necessary):

Value Assumption: What does the author consider more important? (efficiency vs. fairness, individual vs. collective, etc.)
Descriptive Assumption: What does the author believe about how the world works?

Questions for Examining Assumptions:

Is this assumption true/correct?
If the assumption is false, does the conclusion still hold?
Does this assumption conflict with reader or societal consensus?

3.5 Position Analysis

Author's Position: From what standpoint is the author speaking?
Beneficiary: Who benefits from this viewpoint?
Conflict of Interest: Is there obvious interest-driven motivation?
Reader's Position: Is the reader automatically placed in a certain position?

Step 4: Common Fallacy Identification

Examine arguments in opinion-based statements for logical fallacies:

Fallacy Type	Description	Verification Question
Ad Hominem	Attacking the person rather than the argument	Is it questioning the person rather than the argument?
Straw Man	Distorting the opposing view	Is it refuting a point the opponent didn't make?
Slippery Slope	Unwarranted chain inference	Is there sufficient evidence for each step?
Appeal to Authority	Using authority instead of argument	Is the authority an expert in this field? Is the issue within their expertise?
Appeal to Emotion	Using emotion instead of logic	Is it manipulating reader emotions rather than reasoning?
False Dilemma	Creating a false either/or situation	Are middle-ground or other possibilities ignored?
Equivocation	Changing key term definitions	Have key concepts changed during argumentation?
Circular Reasoning	Using the conclusion to prove the premise	Are the reasons merely restatements of the conclusion?
Hasty Generalization	Concluding from insufficient samples	Is the sample sufficient to represent the whole?
Post Hoc Ergo Propter Hoc	Assuming sequence equals causation	Is there another explanation?

Step 5: Web/Article Content Processing

For web content, additionally perform the following steps:

5.1 Source Reliability Assessment

Website Reputation: What is the nature of the website? (government/academic/commercial/personal blog)
Author Information: Is author information provided? What is the author's professional background?
Citations: Are reliable sources cited?
Update Date: Is the information current?

5.2 Content Structure Analysis

Fact vs. Opinion Separation: Distinguish between objective facts and subjective opinions
Contextual Completeness: Is it taken out of context? Is important background missing?
Presentation Method: Is the data presentation misleading (truncated scales, sample selection, etc.)?

5.3 Source Cross-Validation (Web-Specific)

Web content cross-validation requires special attention to:

Verification Item	Action
Domain Verification	Check if it's a spoofed/phishing website
Publication Time Verification	Find the original publication date and subsequent update records
Content Consistency Verification	Compare web snapshots to check for content tampering
Citation Source Tracing	Trace all external links cited in the webpage
Reverse Image Search	Perform reverse image search to verify if images have been misappropriated
Social Media Cross-Validation	Search whether this content was spread on social media and if there was subsequent debunking

Step 6: Comprehensive Assessment

Based on the above analysis, provide a structured assessment conclusion:

Assessment Standards

Grade	Rating	Meaning
Highly Credible	⭐⭐⭐⭐⭐	Sufficient reliable evidence, consistent with scientific principles, rigorous logic
Basically Credible	⭐⭐⭐⭐	Evidence basically sufficient, minor doubts may exist
Pending Verification	⭐⭐⭐	Insufficient evidence, more information needed
Questionable	⭐⭐	Obvious logical problems or insufficient evidence
Not Credible	⭐	Serious errors, misinformation, or malicious misleading

Assessment Report Structure

## Comprehensive Assessment Report

### Verdict
[Credibility rating and brief conclusion]

### Key Findings
1. [Primary finding 1]
2. [Primary finding 2]
3. [Primary finding 3]

### Multi-Source Cross-Validation Results
- Original Source Rating: [A+/A/B+/B/C/D]
- Cross-Validation Source Count: [X independent reliable sources]
- Verification Results:
  - Supported by: [X sources]
  - Contradicted by: [X sources]
  - No reliable source found: [description]
- Information Type Identification: [Misinformation/Marketing Copy/Unverifiable Private Information/Misleading Information/Outdated Information/Normal]

### Evidence Assessment
- Evidence Source: [description]
- Evidence Quality: [assessment]
- Evidence Gap: [existing deficiencies]

### Argumentation Quality
- Logical Structure: [assessment]
- Assumption Reasonableness: [assessment]
- Potential Fallacies: [identified issues]

### Position and Interest Analysis
- Author's Position: [identified]
- Potential Bias: [identified]
- Reader Impact: [analysis]

### Reasoning Process Supporting Conclusion
[detailed reasoning chain]

### Usage Recommendations
[How to use this information, any precautions]

Usage Examples

Example 1: Factual Statement Verification

Input: "A study shows that drinking coffee every day can extend lifespan."

Analysis Output:

### Analysis Type: Factual Statement

### Source Tracing
- Research Source: [tracing results]
- Authority: [assessment]
- Sample Size and Research Design: [analysis]

### Scientific Principle Verification
- Mechanism Explanation: [whether it exists]
- Causation vs. Correlation: [distinction result]

### Evidence Assessment
- Direct Evidence: [assessment]
- Confounding Variables: [whether considered]
- Reproducibility: [whether other research supports/contradicts]

### Comprehensive Assessment
[verdict and reasoning]

Example 2: Opinion-Based Statement Verification

Input: "We should completely ban artificial intelligence because it will replace human jobs."

Analysis Output:

### Analysis Type: Opinion-based Statement

### Thesis Identification
- Core Question: Should AI be banned?
- Thesis Type: Prescriptive

### Conclusion Extraction
- Main Conclusion: AI should be completely banned
- Implicit Premise: The harm of AI replacing jobs outweighs its benefits

### Argumentation Structure
- Reason: AI will replace human jobs
- Evidence: [missing argumentation]
- Assumptions: Work is the main value of life; banning AI won't cause other problems

### Fallacy Identification
- Slippery Slope: Assuming replacement will lead to complete replacement
- False Dilemma: Ignoring the possibility of "regulated development"
- Hasty Generalization: Using partial replacement cases to generalize the whole

### Comprehensive Assessment
[verdict]

Important Notes

Maintain Objectivity: Do not take sides during analysis; let evidence speak
Distinguish Certainty from Speculation: Clearly mark what is certain vs. what is speculation
Acknowledge Uncertainty: Be transparent about problems that cannot be determined rather than forcing conclusions
Focus on Evidence Quality: Not all evidence has equal value
Recognize Timeliness: Information may change over time; dynamic evaluation is needed
Multi-perspective Examination: Multiple reasonable perspectives may exist for the same issue
Prioritize Multi-Source Validation: For all input, multi-source cross-validation MUST be performed first; do not rely solely on a single source
Be Vigilant Against Source-less Information: For information that cannot be traced to reliable sources, credibility ratings must be lowered

Output Standards

The final output MUST contain ALL of the following sections:

Analysis Type Determination: Clearly state whether it is factual or opinion-based
Multi-Source Cross-Validation (Mandatory):
- Original source rating
- Cross-validation results (supported/contradicted/not found)
- Information type identification
Systematic Verification: Analyze item by item according to the above framework
Verdict: Clear credibility rating (⭐-⭐⭐⭐⭐⭐)
Reasoning Process: Complete reasoning chain supporting the conclusion
Usage Recommendations: How to correctly use this information

Credibility Downgrade Triggers

The following situations MUST trigger credibility rating downgrade:

Trigger Condition	Downgrade Magnitude
Original source cannot be found	At least 1 grade lower
No reliable source for cross-validation	At least 2 grades lower
Contradicting information found	At least 1 grade lower
Identified as misinformation/marketing/misleading	Directly mark as not credible
Information from anonymous/private sources	At least 2 grades lower

When it activates

Automatically, when a task matches. Use when users ask to verify information authenticity, examine viewpoint logic, analyze argument validity, distinguish facts from opinions, or need dialectical thinking based on the Socratic method.

About this skill

Automatic

Research 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/is-it-true/SKILL.md

View on GitHub ↗

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

Illustrative Want to see what leoyeai/is-it-ture 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

Critical Analysis Skill (Is-It-Ture)

Core Analysis Process

Step 1: Determine Analysis Type

Step 2: Factual Statement Verification Framework

2.1 Source Tracing

2.2 Multi-Source Cross-Validation (Mandatory Step)

2.3 Scientific Principle Verification

2.4 Evidence Quality Assessment

2.5 Logical Consistency

Step 3: Opinion-Based Statement Analysis Framework

3.1 Thesis Identification

3.2 Conclusion Extraction

3.3 Argument Structure Analysis

3.4 Assumption Identification

3.5 Position Analysis

Step 4: Common Fallacy Identification

Step 5: Web/Article Content Processing

5.1 Source Reliability Assessment

5.2 Content Structure Analysis

5.3 Source Cross-Validation (Web-Specific)

Step 6: Comprehensive Assessment

Assessment Standards

Assessment Report Structure

Usage Examples

Example 1: Factual Statement Verification

Example 2: Opinion-Based Statement Verification

Important Notes

Output Standards

Credibility Downgrade Triggers

When it activates

SkillSafety

Source

Related skills

More in the registry