Ready to supercharge your AI agents?

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

Get Started Free →

深度阅读 (Deep Reading) · leoyeai | DecimalAI

Documentationby leoyeai

深度阅读 (Deep Reading)

书/长文/研报/论文的深度消化，产出结构笔记+原子笔记+知识网络连接。关键词：深度阅读、深度学习、结构笔记、deep learning。

SkillScore

SkillScore73/100

Test results 73

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

41%73%of test cases passed +32 pts

Without skill9 of 22

With skill16 of 22

8 fixed8 passed either way5 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 taskI am organizing reading notes for an article on high-throughput streaming architecture. Model developers often write Chinese tags like 'tags: [数据流, 高并发]' in YAML frontmatter. Create the YAML frontmatter block for this note following standard vault practices.

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-deep-reading
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-deep-reading")
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-deep-reading

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-deep-reading/SKILL.md https://app.decimal.ai/s/leoyeai-deep-reading/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-deep-reading/SKILL.md

This gets SKILL.md only. The skill's 6 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-deep-reading

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-deep-reading")
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-deep-reading/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-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/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-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading")
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-deep-reading/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-deep-reading/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 6 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-deep-reading

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-deep-reading/SKILL.md https://app.decimal.ai/s/leoyeai-deep-reading/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-deep-reading/SKILL.md

This gets SKILL.md only. The skill's 6 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-deep-reading/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-deep-reading.json

This gets SKILL.md only. The skill's 6 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

深度阅读 (Deep Reading)

核心理念：不仅要理解世界（Understand），还要改变世界（Act）。 适用范围：Book, Long-form Article, Research Report, Academic Paper.

专家座席 (The Council)

Mortimer Adler (The Architect): 负责结构化，提取核心命题和逻辑树。
The Pragmatist (The Engineer): 负责工具化，提取可执行的 SOP、模板和清单。
Richard Feynman (The Teacher): 负责解释力，确保概念去魅，用人话讲清楚。
Niklas Luhmann (The Librarian): 负责连接性，确保知识入网，有机生长。
The Critics (The Stress Testers): Musk, Socrates, Munger 负责压力测试和辩论。

核心法则 (The Iron Rules)

Always Deep: 无论输入长短，默认按最高规格处理（结构+工具+辩论）。
Case Fidelity (案例保真):
- 有原文/书在手：禁止概括性改写；原子笔记中涉及案例、研究处须保留具体数字、作者/机构、时间线、原话（可标页码）。
- 无原文、仅摘要或记忆：在笔记中标注 来源: 本书/摘要，未核对原文；保留能确定的专有名词与结论，禁止编造细节；Feynman 验收时标「案例保真：部分（无原文）」。
No Vague Verbs (模糊词禁令): 禁止使用 "优化"、"加强"、"适当" 等虚词。必须转化为具体动作或量化指标。
Metadata Mandatory (元数据强制): 所有笔记必须包含 YAML Frontmatter，禁止省略以下字段（与仓库 CLAUDE.md / core-entry「笔记元数据规范」一致；键名一律英文，便于 Obsidian 标签系统识别 tags 等）：
```
type: ...
tags: [english-tag-one, english-tag-two]   # 或 YAML 多行列表；取值一律英文
links: [...]
description: ...          # 费曼式洞察，100字内
date: YYYYMMDD
source_skill: deep-reading
epistemic_status: borrowed    # 书/文默认 borrowed；自推分析可改为 working / speculative
```
- tags（取值）：YAML 键名必须是 tags；数组内每条标签为英文（建议小写 kebab-case，或 Obsidian 嵌套 parent/child）。禁止用中文、空格或未规范化的中文短语作标签字面量；中文主题名写在正文与 [[链接]]，不塞进 tags。 description 回答：这张笔记最值得告诉别人的一个洞察是什么？费曼会怎么介绍；供 index-note 归网时快速定性。

归位与入网（与 file-organize 对齐）

本 skill 的产出归位与入网规则与 file-organize 一致：物理按天落 05_每日记录，MOC 在 03_索引用链接拉取；入网步骤与 file-organize 共用同一套定义。

事项	规则	详见
归位	在 `05_每日记录/YYYY/MM/YYYYMMDD/` 下新建本次任务文件夹（若日期目录不存在则先创建），本次任务笔记默认落在该文件夹内。索引笔记例外：物理位置在 `03_索引/`，创建后从 05 任务目录移动到 03 下（与 file-organize 类型表一致）	Phase 2.5 步骤 2
入网	索引笔记：在已存在索引中添加入口（挂载），本索引笔记底部链回父索引。结构/原子/方法笔记：在 `03_索引/` 的 MOC 里按关键词添加入口 + 笔记底部反链（与 file-organize 入网步骤一致）	索引笔记入网见 Phase 2.5 步骤 1；结构/原子/方法入网见 file-organize `references/03索引实现MOC流程.md`，Phase 6 执行

结构笔记命名：YYYYMMDD_00_[标题]_结构笔记.md。日期文件夹不存在则创建。

工作流程 (The Workflow)

执行顺序：Phase 0 → 1 → 2 → 2.5 → 2.75 → 3 → 4 → 5 → 6 → 6.5（流程执行审查，强制），不可跳步；Phase 2.5 须在 Phase 2 完成后立即执行；Phase 2.75 须在 Phase 3 开始前完成；Phase 6.5 须在 Phase 6 完成后立即执行。

Phase 0: Pre-game Plan (准备)

在开始 Phase 1 前产出执行计划；落盘为 YYYYMMDD_01_[书名]_执行计划.md（与结构笔记同目录），并在 task.md 的 Preparation 下链接该文件。

确保包含：

TODO List (≥6 项)：如全书论证骨架、关键概念、论证链、框架提取、方法提取、案例核实、批判性审查、入网连接。
Context：读取意图（我要解决什么问题？）。

Phase 1: Overview & Structure (概览与骨架)

Agent: Mortimer Adler

任务: 创建结构笔记；产出须符合 templates/structure_note_template.md，含核心命题、逻辑支撑链与阅读顺序 (Reading Sequence)（每序列列出笔记顺序；该顺序将作为 Phase 3「阅读顺序链」的权威来源）。逻辑树与阅读顺序中的 [[链接]] 须为真实暂定标题（非模板占位），否则 Phase 2.75 无法通过。
说明: 强制调用 structure-note skill

Phase 2: Index Design (索引设计)

Agent: Niklas Luhmann

"不要问它属于哪个分类，问它和谁对话。"

任务: 为本书/本文创建索引笔记；产出须符合 templates/index_note_template.md，含关键词与多入口。
索引命名（强制）：索引文件名与标题必须按领域命名，与 file-organize references/03索引实现MOC流程.md 的「索引层级与命名约定」一致：
- 必须：从材料内容提炼知识领域（如「AI产品观与能力观」「多Agent与一人公司」），用领域名作为 索引_<主题>_<领域>.md 中的 <领域>。
- 禁止：用材料名（书名/文章名/作者/来源/活动名/日期）作为索引名；这些信息只写在索引正文的「来源说明」或 frontmatter，不得进入文件名。
- 执行顺序：先定领域名 → 再创建索引笔记 → 正文内写来源说明（例：「本索引内容主要来自 [书名/访谈名]，深度阅读产出见 [路径]」）。
说明: 强制调用 index-note skill；调用前先完成「领域名」决策。

Phase 2.5: 索引笔记入网（挂载）+ 归位

Agent: Niklas Luhmann

索引笔记创建完成后立即执行：入网（在已存在索引中挂载）→ 归位（物理移动到 03_索引）。

入网（挂载）：在 03_索引/ 下选定一个（或多个）与本书主题相关的已存在索引，在其中添加入口指向本索引笔记（如子专题表追加 - [[本索引笔记名]] — 领域简述，YYYYMMDD；说明用领域简述，不用书名/来源）。本索引笔记底部链回该父索引。
归位：将本索引笔记文件从当前任务目录（05_每日记录/.../）移动到 03_索引/ 下合适位置（根目录或某主题子文件夹）。移动后父索引中的 [[本索引笔记名]] 仍有效（仅文件名，不依赖路径）。
多索引挂载检查延后至 Phase 6：本索引内提到的笔记还可挂到哪些其他索引，届时统一检查并添加入口。

Phase 2.75: Phase 3 前置门禁（显式链接全集）

Agent: Mortimer Adler + Niklas Luhmann

脆弱步骤低自由度：未通过本节不得开始 Phase 3 的 Sweep 2+（血肉/边缘）；仅允许在通过后执行「扩展型」建卡。详见 skill-creator 工作流模式。

显式链接全集（Round-1 清单） 的权威定义：

从结构笔记中收集全部 [[wikilink]]：逻辑树 (Logic Tree) 与 所有 Reading Sequence 小节中出现的链接并集，去重。
排除：不属于本轮要建原子的链接（若结构笔记链向「仅作导航」的父索引且明确不建卡，须在结构笔记中注释说明，并不计入全集）。
禁止占位：凡仍为模板占位符的链接（如 [[概念笔记A]]、[[笔记A]] 等未替换为真实概念名）不得计入「已通过」的全集；须返回 Phase 1，将链接改为可建卡的暂定标题后再重做本节。

task.md 对齐（强制）：在 task.md 增加 # 显式链接全集（Phase 2.75） 区块，将上款全集逐条复制为 - [ ] [[概念名]]，与结构笔记双向一致（结构里有的每条 task 里必有；task 里有的结构里必有）。

门禁判定：

结构笔记中无未替换占位链接；
task.md 中「显式链接全集」与结构笔记并集一致；
通过后方可进行 Phase 3 Sweep 2+；若仅部分通过，只允许先完成 Sweep 1 中已有条目的原子笔记正文 + 每张必做 Luhmann Scan 记录，不得将 Scan 新发现的笔记落盘为正式原子笔记（可先记在 task 或 findings 为待 Sweep 2）。

Phase 3: Recursive Growth (递归生长)

Agent: Luhmann & Feynman

核心创新：边创建边发现 (Luhmann Scan)。

术语（避免混淆）：

用语	含义
显式链接全集	Phase 2.75 锁定；即本轮必须先落地的概念卡清单（骨架）。
Phase 3 Sweep 1 / 2 / 3+	工作波次：骨架 → 血肉 → 边缘；见下列流程。
Scan-R2 / Scan-R3（记录标签）	仅用于 `task.md` 中 Luhmann Scan 行内格式，指「由 Scan 发现的后续待建链接批次」，与 Sweep 编号不同；完整定义见 `references/luhmann_scan.md`「Scan 产出轮次」。

保真 vs 扩展：本书/材料主论证链上的原子笔记优先满足 Case Fidelity（案例保真）。Scan 产生的外围概念：若超出本书范围或仅需占位，允许 stub（短定义 + 链）或仅记链接待以后扩展；止损条件见 luhmann_scan.md「何时停止？」。

流程:

Sweep 1 (骨架): 为 显式链接全集中的每个链接创建 Atomic Note (概念)；每张创建后执行 Luhmann Scan（见 references/luhmann_scan.md）。
Luhmann Scan (每张必做)：三项——前置依赖、潜在连接、方法论发现（若概念附带可执行 how → 记入 task，Phase 4 创建 Method Note）。在 task.md 中每张卡记录格式：前置 → Scan-R2: [[A]]. 连接 → Scan-R3: [[B]]. 方法论 → [[方法名]] (Phase 4).（Scan-R2/R3 为 Scan 记录标签，勿与 Sweep 编号混用。）
Sweep 2 (血肉)（仅 Phase 2.75 通过后）: 创建 Scan 发现的、理解本书仍需要的笔记，继续 Luhmann Scan。
Sweep 3+ (边缘)（仅 Phase 2.75 通过后）: 直到完成或超出范围（见 luhmann_scan.md 止损条款）。

Atomic Note 规范:

模板: templates/atomic_note_template.md
聚焦: 定义 (Definition)、机制 (Mechanism)、语境 (Context)。
验收: 费曼测试 (外行能听懂)。

阅读顺序链 (Reading-Order Chain)（强制）:

卢曼策略：阅读路径应长在网络里，而非只存在于结构笔记这一张「地图」。Folgezettel 思维——序列本身是一条链，每张卡带「上一张 / 下一张」，读者无需回到结构笔记即可顺次阅读。
技能契约：凡被列入结构笔记「阅读顺序」的笔记，必须在笔记内建立序列内前后链接（见 atomic 模板「阅读顺序导航」）。结构笔记是入口；一旦进入某 Sequence，由各笔记的「上一张 / 下一张」承担延续阅读。
执行：Sweep 1 创建完某 Sequence 中的笔记后，逐张检查并补全「阅读顺序导航」：首张无上一张、末张无下一张可标「—」或省略；中间张必须含 ← [[上一张]] | [[下一张]] →。

Phase 4: Methodology Consolidation (方法论整理)

Agent: The Pragmatist

将 Phase 3 发现的方法论创建为 Method Note。

Method Note 规范 (高优先级):

模板: templates/method_note_template.md
聚焦: 可执行步骤 (SOP)、模板 (Template)、检查清单 (Checklist)。
约束:
- No Vague Verbs: 无模糊动词。
- Mechanism & Leverage: 为什么有效？
- MVE: 下一步最小可行性实验，必须精确到"今天能做的第一个动作"。
实战化要求（"操作手册版"而不是学术交流）:
- 步骤用表格：若工具有多步骤，每步用 | 步骤 | What（做什么） | How（怎么做） | Why（为什么） | 表格；禁止只用纯段落描述步骤。
- 每步必须有原文案例：每个步骤下必须有来自原文的真实案例锚定（人名/数据/场景），不能悬空。无案例的步骤是抽象的，不是方法论。
- 每步必须有完成标准：明确说明"做到什么程度算完成这步"，不能留给读者自行判断。
- 卡点随步走：每步之后嵌入「最常见的错 → 即时对策」，不要把所有避坑集中到最后。
- 使用者自评清单：除了产出验收清单（结果是否达标），再加一份「我自己做得对不对」的执行行为自检。
- 准备阶段独立：需有独立的「准备阶段清单 (Pre-flight)」——开始前需确认的事项。
费曼测试（完成后必做）：把写好的 Method Note 交给一个"刚意识到自己有这个问题的人"，问他："明天你会做什么？" 如果他答不上来具体动作，说明 Method Note 仍然太抽象，必须返工。

Phase 5: Final Review (终极审视)

Agent: Richard Feynman

用 Feynman 标准审视整个知识网络：

去魅检验: 术语是否已"翻译"为日常语言？
比喻检验: 复杂概念是否有恰当比喻？
逻辑检验: 论证链是否有断裂？
拓扑检验: 是否形成了"意外的惊喜"连接？

Phase 6: Network Review (入网审视)

Agent: Niklas Luhmann

检查: 确认每张笔记（非结构父子）至少有 2 条双向链接。
入网: 结构笔记与原子笔记（及方法笔记）在 03_索引/ 相关 MOC 中完成接入。按 file-organize 的入网步骤执行（与 file-organize 共用同一套定义）：提取关键词 → 索引候选发现 → 在选中索引中添加入口（Inbox 或关键词条目）→ 笔记底部加反链。详见 file-organize 的 references/03索引实现MOC流程.md；无需调用其他 skill。
多索引挂载检查: 针对本索引内提到的笔记，逐条评估是否还应挂到 03_索引/ 下其他索引；若某笔记也是其他主题的优质入口，则在对应索引中添加入口。输出简要清单：[[笔记A]] → 已入索引_X；建议补充入索引_Y（理由）。

Phase 6.5: 流程执行审查（强制）

Phase 6 完成后必须执行。调用 workflow-audit skill，以德明+葛文德视角对本流程执行完成度逐项核对与系统闭环检查：

审查对象：本 skill（deep-reading）；产出：本次任务目录（执行计划、结构笔记、索引、原子笔记、task.md 等）。
产出：落盘审查报告（YYYYMMDD_[任务名]_流程审查报告_德明与葛文德视角.md），含逐项清单、系统闭环、DoD 勾选、多索引挂载清单；对审查中标为 ❌ 的项必须补执行，直至 DoD 全部通过。
workflow-audit 主文件：.cursor/skills/workflow-audit/SKILL.md；报告模板：workflow-audit/references/audit_report_template.md。

不可跳过。未通过流程执行审查并补全漏项，则本流程视为未完成。

任务追踪 (Task Tracking)

在 task.md 中维护进度：

# Preparation
- [ ] Pre-game Plan Created (≥6 项 TODO + Context；对话内区块或落盘文件)

# Structure & Index
- [ ] Structure Note Created (Adler)
- [ ] Index Note Created (Luhmann)
- [ ] Index Note Onboarding (Phase 2.5): 挂载到已存在索引 + 归位到 03_索引

# 显式链接全集（Phase 2.75；与结构笔记逻辑树 ∪ Reading Sequence 并集一致）
- [ ] [[概念一]]
- [ ] [[概念二]]

# Extraction Loop (Phase 3)
- [ ] [[笔记A (Concept)]] + Luhmann Scan
- [ ] [[笔记B (Concept)]] + Luhmann Scan

# Methodology (Phase 4)
- [ ] [[工具A (Method)]] (SOP/Checklist/MVE)

# Review (Phase 5 & 6)
- [ ] Feynman Check (De-jargon check)
- [ ] Network Check (2+ Links per note；入网按 file-organize 的 03索引实现MOC流程；多索引挂载检查)

# Workflow Audit (Phase 6.5，强制)
- [ ] 调用 **workflow-audit** 做流程执行审查（德明+葛文德视角），产出审查报告并对 ❌ 项补执行，直至 DoD 全部通过

质量验收清单 (Definition of Done)

Phase 0: 执行计划已产出（≥6 项 TODO + Context）。
Phase 2.75: 显式链接全集已从结构笔记提取并与 task.md 双向一致；无占位链接；门禁通过后才进行 Sweep 2+。
Overview: 5个问题回答清晰，费曼测试通过。
Fidelity: 有原文时案例含数字/专有名词/原话；无原文时已标注来源限制且未编造细节。
Actionability: Method Note 的每步有 What/How/Why 表格 + 原文案例锚定 + 完成标准 + 最常见的错；有使用者自评清单；有 Pre-flight；MVE 精确到今天能做的第一个动作；费曼测试通过（问一个刚意识到有这个问题的人"明天做什么"，他能立刻回答）。
Network: 所有笔记双向可达 (≥2 links)；已按 file-organize 入网步骤在 03_索引相关 MOC 中接入；本索引已挂载并位于 03_索引下；多索引挂载检查已完成。
阅读顺序链：凡出现在结构笔记「阅读顺序」中的笔记，已含「阅读顺序导航」（上一张 / 下一张），读者可不回结构笔记顺次阅读。
Insight: 产生了新的连接或意外发现。
流程执行审查：Phase 6.5 已执行，workflow-audit 已产出审查报告，且所有 ❌ 项已补执行、DoD 全部通过。

About this skill

Automatic

Knowledge Management 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/mikonos-deep-reading/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 6 files

Illustrative Want to see what leoyeai/deep-reading 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

深度阅读 (Deep Reading)

专家座席 (The Council)

核心法则 (The Iron Rules)

归位与入网（与 file-organize 对齐）

工作流程 (The Workflow)

Phase 0: Pre-game Plan (准备)

Phase 1: Overview & Structure (概览与骨架)

Phase 2: Index Design (索引设计)

Phase 2.5: 索引笔记入网（挂载）+ 归位

Phase 2.75: Phase 3 前置门禁（显式链接全集）

Phase 3: Recursive Growth (递归生长)

Phase 4: Methodology Consolidation (方法论整理)

Phase 5: Final Review (终极审视)

Phase 6: Network Review (入网审视)

Phase 6.5: 流程执行审查（强制）

任务追踪 (Task Tracking)

质量验收清单 (Definition of Done)

SkillSafety

Source

Related skills

More in the registry