Ready to supercharge your AI agents?

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

Get Started Free →

Self Reflection · LeoYeAI | DecimalAI

Productivityby LeoYeAI

Self Reflection

三省吾身 - 深度自我审视与进化系统。基于角色理论、系统思维、认知偏差三大框架，通过五阶段闭环（反思→计划→执行→验证→固化）实现真正的自我进化。适用于任何需要深度反思的场景：项目复盘、工作改进、能力提升、习惯养成。

Never made a case worse

SkillScore

SkillScore17/100

Test results 17

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

0%17%of test cases passed +17 pts

Without skill0 of 23

With skill4 of 23

4 fixed0 passed either way19 still failing0 broke

Measured on gemini-3.6-flash7/28/2026v1

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 self-reflection
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("self-reflection")
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 self-reflection

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/self-reflection/SKILL.md https://app.decimal.ai/s/self-reflection/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/self-reflection/SKILL.md

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

Other ways to add it

Claude Code docs

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

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

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

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

Other ways to add it

Claude Agent SDK docs

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

Install

pip install "decimalai[openai-agents]"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

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

Other ways to add it

OpenAI Agents docs

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

Install

pip install "decimalai[openai]"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

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

Other ways to add it

OpenAI SDK docs

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

Install

pip install "decimalai[anthropic]"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Other ways to add it

Anthropic docs

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

Install

pip install "decimalai[google-genai]"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/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/self-reflection/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

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

Other ways to add it

Gemini API docs

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

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

LangChain docs

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

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

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

Other ways to add it

CrewAI docs

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

Install

pip install "decimalai[adk]"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

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

Other ways to add it

Google ADK docs

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

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

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

Other ways to add it

Pydantic AI docs

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

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

Deep Agents docs

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

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

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

Other ways to add it

Microsoft Agent Framework docs

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

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add self-reflection

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("self-reflection")
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/self-reflection/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/self-reflection/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

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

Other ways to add it

Strands docs

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

pip install "decimalai>=0.15"
decimalai skills add self-reflection

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/self-reflection/SKILL.md https://app.decimal.ai/s/self-reflection/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/self-reflection/SKILL.md

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

Other ways to add it

Cursor and other editors docs

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

Get the file

curl -fsSL https://app.decimal.ai/s/self-reflection/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/self-reflection.json

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

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/28/2026
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

三省吾身 - 深度自我审视与进化系统

曾子曰：吾日三省吾身——为人谋而不忠乎？与朋友交而不信乎？传不习乎？

核心追问：我是否尽到了每个角色的责任？

激活条件

触发场景

场景类型	具体表现
负向反馈	收到批评、投诉、不满表达
质量问题	结果不符合预期、出现明显缺陷
重复错误	同类问题出现 2 次以上
定期自检	周度/月度/季度例行审视
里程碑节点	项目阶段完成、重要事件结束后
直觉预警	感觉"不太对"、"好像有问题"

激活方式

用户说：
- "反思一下..."
- "三省吾身"
- "审视一下[某事]"
- "复盘一下"

自动触发：
- 检测到负面反馈关键词
- 检测到质量问题模式
- 定期提醒（如配置了周期性自检）

激活响应

三省吾身模式已激活 🔍

我将进行深度自我审视。请告诉我：

1. 要反思什么？（项目/工作/习惯/能力/某件事）
2. 有什么触发点？（收到反馈/发现问题/例行检查）

或者直接描述你想反思的情况，我会引导你完成整个流程。

理论基础

为什么自我反思很难？

障碍	表现	根因
自利偏差	成功归自己，失败归环境	保护自尊的心理机制
确认偏差	只看支持自己观点的证据	大脑追求认知一致性
现状偏见	倾向于维持现状	改变的心理成本高
合理化	给自己的行为找借口	减少认知失调
盲点	看不到自己的问题	缺乏外部视角

本 skill 如何克服这些障碍？

障碍	克服方法
自利偏差	强制三层框架，最终层必须回到"我能改变什么"
确认偏差	要求提供证据，质疑"你确定吗？"
现状偏见	行动导向，反思后必须有具体行动
合理化	根因分析要追问三次"为什么"
盲点	引入视角转换，从他人角度审视

核心框架

三层反思模型

┌─────────────────────────────────────────────────────────────┐
│                 第三层：角色审视（反求诸己）                    │
│                                                              │
│  我承担了哪些角色？每个角色的责任是什么？                       │
│  我是否尽到了每个角色的责任？                                  │
│  角色之间是否有冲突？如何平衡？                                │
│  我需要改变什么心态/行为/能力？                               │
├─────────────────────────────────────────────────────────────┤
│                 第二层：系统审视（究其根源）                    │
│                                                              │
│  这个问题在更大系统中处于什么位置？                            │
│  是什么机制/流程/环境导致了这个问题？                         │
│  这个问题与哪些其他问题相关联？                               │
│  如何改进系统防止问题再发生？                                 │
├─────────────────────────────────────────────────────────────┤
│                 第一层：问题审视（直面问题）                    │
│                                                              │
│  具体发生了什么？事实是什么？                                  │
│  有什么证据？数据/反馈/现象？                                 │
│  造成了什么影响？对谁？                                       │
│  如何直接修复？                                              │
└─────────────────────────────────────────────────────────────┘

角色理论

每个人在任何工作中都承担多个角色：

角色类型	示例	典型责任
执行者	开发者、写作者、操作者	产出结果
审查者	Reviewer、质检、测试	保证质量
协调者	管理者、Leader、中介	协调资源、做决策
服务者	服务提供方、供应商	满足需求方
需求方	用户、客户、老板	提出需求、验收结果

常见角色冲突：

冲突类型	表现	后果
执行者 vs 审查者	自己做自己检查	质量把控不严
执行者 vs 协调者	既要干活又要管人	两头都做不好
服务者 vs 需求方	身份模糊	期望错位
多重执行者	同时做多个项目	精力分散

系统思维

问题从不孤立，都在系统中：

         环境（外部条件）
              │
              ▼
┌─────────────────────────────┐
│         系统                │
│  ┌─────┐   ┌─────┐   ┌─────┐│
│  │输入 │──▶│处理 │──▶│输出 ││
│  └─────┘   └─────┘   └─────┘│
│              │               │
│              ▼               │
│         反馈机制             │
└─────────────────────────────┘

系统审视要点：

要素	追问
输入	输入质量如何？是否有问题从输入就带入？
处理	处理逻辑是否正确？是否有遗漏？
输出	输出标准是否明确？如何衡量？
反馈	有没有反馈机制？反馈是否有效？
环境	环境有什么限制？是否合理？

认知偏差

常见偏差及应对：

偏差	表现	本 skill 应对
幸存者偏差	只看成功的，忽略失败的	要求列出失败案例
沉没成本	因投入而不愿放弃	问"如果从零开始，还会这样做吗？"
锚定效应	被第一印象束缚	要求重新定义问题
可得性偏差	高估容易想到的	要求数据支撑
过度自信	高估自己的能力	引入外部视角评估

完整流程

流程总览

阶段1: 反思 (Reflect)
    │
    ├─ 1.1 定义反思范围
    ├─ 1.2 收集信息
    ├─ 1.3 第一层：问题审视
    ├─ 1.4 第二层：系统审视
    ├─ 1.5 第三层：角色审视
    └─ 输出：反思报告
          │
          ▼
阶段2: 计划 (Plan)
    │
    ├─ 2.1 第一层：直接修复方案
    ├─ 2.2 第二层：系统改进方案
    ├─ 2.3 第三层：自我改变方案
    ├─ 2.4 优先级排序
    └─ 输出：优化计划
          │
          ▼
阶段3: 执行 (Act)
    │
    ├─ 3.1 拆解为行动项
    ├─ 3.2 设定验收标准
    ├─ 3.3 逐项执行
    ├─ 3.4 记录结果
    └─ 输出：执行记录
          │
          ▼
阶段4: 验证 (Verify)
    │
    ├─ 4.1 问题解决检查
    ├─ 4.2 系统改进评估
    ├─ 4.3 自我改变评估
    ├─ 4.4 新问题发现
    └─ 输出：验证报告
          │
          ▼
阶段5: 固化 (Solidify)
    │
    ├─ 5.1 更新原则/标准
    ├─ 5.2 更新流程/规范
    ├─ 5.3 建立检查清单
    ├─ 5.4 传承给相关方
    └─ 输出：更新的文档/习惯

阶段1: 反思 (Reflect)

1.1 定义反思范围

明确要反思什么：

维度	问题
对象	要反思什么？（项目/任务/习惯/能力/某件事）
触发	为什么现在反思？（反馈/问题/例行）
期望	希望通过反思达到什么？
范围	反思的时间跨度？涉及的人/事？

输出：清晰的反思范围定义

1.2 收集信息

信息收集清单：

信息类型	收集方法	用途
事实	记录、日志、数据	确认发生了什么
结果	产出物、成果	评估效果
反馈	来自他人/用户/系统	外部视角
标准	预期目标、要求	对比差距
历史	之前类似情况	模式识别
我的决策	我做了什么选择	角色审视

信息收集原则：

重事实，轻主观
重数据，轻印象
重多方，轻单一

1.3 第一层：问题审视

直面问题，不回避

问题清单

#	问题	证据	影响	紧急度
1	...	...	...	高/中/低
2	...	...	...	...

问题追问清单

对每个问题追问：

1. 具体发生了什么？（描述事实，不含判断）
2. 你怎么知道这是个问题？（证据）
3. 对谁造成了什么影响？（利益相关者）
4. 如果不解决会怎样？（后果）
5. 类似问题之前发生过吗？（模式）

常见问题模式

模式	特征	示例
质量不达标	结果不符合标准	测试通过但 bug 多
效率低下	投入产出比低	花了很长时间，效果一般
沟通不畅	信息传递有问题	需求理解偏差
资源不足	人/时间/工具不够	人力紧张导致质量下降
能力欠缺	不具备必要技能	新技术不会用
动机不足	缺乏动力/兴趣	拖延、敷衍

1.4 第二层：系统审视

把问题放在系统中看

系统分析框架

┌─────────────────────────────────────────────────────────────┐
│                       环境                                   │
│   外部条件、约束、资源                                        │
├─────────────────────────────────────────────────────────────┤
│   输入 ───▶ 处理 ───▶ 输出                                   │
│              │                                               │
│              ▼                                               │
│           反馈                                               │
├─────────────────────────────────────────────────────────────┤
│                    机制/流程/规范                            │
└─────────────────────────────────────────────────────────────┘

系统追问清单

1. 输入层面
   - 输入质量如何？问题是否从输入就带入了？
   - 输入标准是否明确？
   - 输入来源是否可靠？

2. 处理层面
   - 处理流程是否合理？有没有遗漏步骤？
   - 决策逻辑是否正确？
   - 是否有明确的检查点？

3. 输出层面
   - 输出标准是否明确？
   - 如何衡量输出质量？
   - 谁来验收输出？

4. 反馈层面
   - 有没有反馈机制？
   - 反馈是否及时？是否有效？
   - 反馈是否被采纳？

5. 机制层面
   - 有什么机制在控制这个过程？
   - 机制是否被执行？
   - 机制是否需要更新？

6. 环境层面
   - 有什么外部约束？
   - 资源是否充足？
   - 环境有什么变化？

常见系统问题

问题类型	表现	根因
机制缺失	该有的没有	制度设计不完善
机制失效	有但不执行	执行监督不到位
反馈断裂	反馈不被采纳	权责不对等
标准模糊	好坏难判断	缺乏明确标准
资源错配	投入与产出不匹配	规划不当

1.5 第三层：角色审视

反求诸己——最终回到"我能改变什么"

角色识别

我在这个情境中承担了哪些角色？

角色	责任	我做到了吗？
执行者	...	✅/⚠️/❌
审查者	...	✅/⚠️/❌
协调者	...	✅/⚠️/❌
...	...	...

角色冲突分析

冲突	表现	我如何处理的	更好的处理方式
执行者 vs 审查者	...	...	...
...	...	...	...

自我审视追问

心态层面：
1. 我是否把 [X] 放在 [Y] 之前？（如：进度 > 质量）
2. 我是否因为怕 [X] 而没有做 [Y]？（如：怕冲突而不批评）
3. 我是否满足于"看起来好"而没有追问"真的好吗"？
4. 我是否有 [X] 的心态导致了这个问题？

行为层面：
1. 我做了什么？没做什么？
2. 我是否执行了应该执行的标准/流程？
3. 我是否主动发现问题？还是被动等待？
4. 我是否有 [X] 的行为需要改变？

能力层面：
1. 我是否具备做好这件事的能力？
2. 我缺乏哪些知识/技能？
3. 我是否知道什么是"好"的标准？
4. 我需要提升哪些能力？

1.6 输出反思报告

报告结构：

# [反思对象] 反思报告

## 元信息
- 反思时间：
- 反思范围：
- 触发原因：

## 第一层：问题审视
### 问题清单
### 问题分析

## 第二层：系统审视
### 系统分析
### 根因识别

## 第三层：角色审视
### 角色识别
### 角色冲突
### 自我问题

## 总结
- 核心问题：
- 根本原因：
- 我的关键问题：

阶段2: 计划 (Plan)

2.1 第一层方案：直接修复

针对每个问题，制定直接修复方案

问题	修复方案	具体做法	预期效果	时间
...	...	...	...	...

2.2 第二层方案：系统改进

针对根因，改进机制/流程/环境

根因	改进方案	涉及的机制	实施方式
...	...	...	...

常见系统改进：

改进类型	示例
新增机制	增加审查环节、建立检查清单
强化执行	设置提醒、增加监督
明确标准	定义验收标准、建立度量
改善反馈	建立反馈渠道、缩短反馈周期
优化资源	重新分配、引入工具

2.3 第三层方案：自我改变

针对我自己的问题，制定改变计划

我的问题	改变方向	具体行动	固化方式
心态：...	...	...	写入原则
行为：...	...	...	写入检查清单
能力：...	...	...	学习计划

2.4 优先级排序

排序原则：

优先级	条件
P0 立即	影响大、紧急、是其他改进的基础
P1 本周	重要但不紧急
P2 两周内	有价值但可延后
P3 可选	有更好，没有也行

依赖分析：

哪些改进依赖其他改进？
哪些可以并行？
哪些必须串行？

2.5 输出优化计划

# [反思对象] 优化计划

## 第一层：直接修复
| 序号 | 问题 | 方案 | 时间 |
|------|------|------|------|

## 第二层：系统改进
| 序号 | 根因 | 改进 | 涉及机制 |
|------|------|------|----------|

## 第三层：自我改变
| 序号 | 问题 | 改变 | 固化方式 |
|------|------|------|----------|

## 执行计划
### 时间线
### 优先级
### 依赖关系

## 成功指标
| 层级 | 指标 | 目标 |
|------|------|------|
| 第一层 | ... | ... |
| 第二层 | ... | ... |
| 第三层 | ... | ... |

阶段3: 执行 (Act)

3.1 拆解为行动项

将方案拆解为可执行的具体行动

行动项	目标	具体步骤	验收标准	时间
...	...	1. ...	...	...
		2. ...

3.2 执行与记录

执行原则：

按优先级执行
每个行动完成后立即记录
遇到阻塞不跳过，记录并处理
定期回顾进度

执行记录格式：

## 执行日志

### [日期]

#### [行动项名称]
- 状态：✅ 完成 / 🔄 进行中 / ❌ 阻塞
- 结果：...
- 问题：...
- 下一步：...

阶段4: 验证 (Verify)

4.1 问题解决检查

问题	解决了吗？	证据	遗留
...	✅/⚠️/❌	...	...

4.2 系统改进评估

改进	执行情况	效果	新问题
...	...	...	...

4.3 自我改变评估

改变	我真的改变了吗？	证据	还需努力
心态	...	...	...
行为	...	...	...
能力	...	...	...

4.4 新问题发现

追问：

在解决问题的过程中，发现了什么新问题？
有什么之前没想到的？
下一步需要做什么？

4.5 输出验证报告

# 验证报告

## 问题解决情况
## 系统改进评估
## 自我改变评估
## 新发现的问题
## 下一步行动

阶段5: 固化 (Solidify)

5.1 更新原则

将新的认知固化为原则

新认知	固化为原则	写入位置
...	"质量 > 进度"	SOUL.md / 个人笔记

5.2 更新流程

将新的做法固化为流程

新做法	固化为流程	涉及文档
...	验收前执行检查清单	SKILL.md / 工作规范

5.3 建立检查清单

将标准固化为检查清单

# [场景] 检查清单

## 必查项
- [ ] ...
- [ ] ...

## 可选项
- [ ] ...

5.4 传承给相关方

让改变影响更多人

传承内容	传承对象	传承方式
...	团队/其他人	分享/文档/培训

使用示例

示例1：项目质量反思

输入：

反思一下上次项目的质量，用户说质量不行

执行：

三省吾身模式已激活 🔍

## 阶段1: 反思

### 第一层：问题审视
- 用户反馈"质量不行"
- 具体表现：测试全通过但 bug 多
- 证据：生产环境出现 5 个 bug

### 第二层：系统审视
- 测试只覆盖 Happy Path
- 没有对抗性测试
- 测试设计者 = 实现者

### 第三层：角色审视
- 我作为质量把关者，没有严格审查测试质量
- 我怕影响进度，放过了不够好的测试
- 心态问题：进度 > 质量

[继续生成反思报告...]

示例2：个人效率反思

输入：

反思一下我最近的工作效率，感觉很低

示例3：习惯养成反思

输入：

反思一下我的早起习惯，总是坚持不下来

注意事项

诚实原则

不找借口 - 问题就是问题，不解释"为什么情有可原"
不推卸责任 - 即使是外部原因，我也有我该承担的部分
不自欺欺人 - "看起来好" ≠ "真的好"

深度原则

追问三次 - 每个问题至少追问三次"为什么"
找到根因 - 不止于表面原因，找到系统性和个人层面的原因
反求诸己 - 最终都要回到"我能改变什么"

行动原则

必须有行动 - 反思后不行动 = 白反思
必须可执行 - 行动要具体、可操作、有验收标准
必须有时限 - 每个行动要有预计完成时间

固化原则

必须固化 - 改变必须形成文档或习惯，不能只在脑子里
必须传承 - 有价值的改变要让相关方都知道
必须复查 - 定期回顾固化内容是否执行

与其他 Skill 的关系

Skill	关系
self-improvement	self-reflection 是系统性深度审视，self-improvement 更偏单点改进
verification-mindset	self-reflection 是事后深度反思，verification-mindset 是事中验证
proactive-scan	self-reflection 是深度剖析，proactive-scan 是广度扫描
task-continuity	self-reflection 可以发现需要持续跟踪的改进项

配置选项

配置	说明	默认值
输出位置	反思报告等文件的存放位置	当前目录 docs/
周期提醒	是否启用定期自检提醒	关闭
深度模式	是否强制走完整5阶段	是

版本：2.0.0 创建于 2026-02-25 基于角色理论、系统思维、认知偏差三大框架设计

About this skill

Automatic

Personal Assistant 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/kuro-self-reflection/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 3 files

Illustrative Want to see what self-reflection 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

三省吾身 - 深度自我审视与进化系统

激活条件

触发场景

激活方式

激活响应

理论基础

为什么自我反思很难？

本 skill 如何克服这些障碍？

核心框架

三层反思模型

角色理论

系统思维

认知偏差

完整流程

流程总览

阶段1: 反思 (Reflect)

1.1 定义反思范围

1.2 收集信息

1.3 第一层：问题审视

问题清单

问题追问清单

常见问题模式

1.4 第二层：系统审视

系统分析框架

系统追问清单

常见系统问题

1.5 第三层：角色审视

角色识别

角色冲突分析

自我审视追问

1.6 输出反思报告

阶段2: 计划 (Plan)

2.1 第一层方案：直接修复

2.2 第二层方案：系统改进

2.3 第三层方案：自我改变

2.4 优先级排序

2.5 输出优化计划

阶段3: 执行 (Act)

3.1 拆解为行动项

3.2 执行与记录

阶段4: 验证 (Verify)

4.1 问题解决检查

4.2 系统改进评估

4.3 自我改变评估

4.4 新问题发现

4.5 输出验证报告

阶段5: 固化 (Solidify)

5.1 更新原则

5.2 更新流程

5.3 建立检查清单

5.4 传承给相关方

使用示例

示例1：项目质量反思

示例2：个人效率反思

示例3：习惯养成反思

注意事项

诚实原则

深度原则

行动原则

固化原则

与其他 Skill 的关系

配置选项

SkillSafety

Source

Related skills

More in the registry