Ready to supercharge your AI agents?

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

Get Started Free →

Vibe知识大赏 · 精品知识短片工作室 · andyhuo520 | DecimalAI

Design & Mediaby andyhuo520

Vibe知识大赏 · 精品知识短片工作室

「Vibe知识大赏」精品知识短片工作室：一个知识点 → 一条 45 秒～5 分钟、有旁白、每句有出处的精品知识短片（抖音

Never made a case worseMaintained

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%91%of test cases passed +73 pts

Without skill4 of 22

With skill20 of 22

16 fixed4 passed either way2 still failing0 broke

Measured on gemini-3.8-flash11/3/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test task在给用户推荐风格方案时，如果包含『敦煌壁画』或『铜版博物』这类需要 AI 画面生成的风格，在选项说明中必须明确告知用户什么预算信息？

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 andyhuo520-vibe-knowledge
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("andyhuo520-vibe-knowledge")
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 andyhuo520-vibe-knowledge

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/andyhuo520-vibe-knowledge/SKILL.md https://app.decimal.ai/s/andyhuo520-vibe-knowledge/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/andyhuo520-vibe-knowledge/SKILL.md

This gets SKILL.md only. The skill's 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/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/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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("andyhuo520-vibe-knowledge")
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/andyhuo520-vibe-knowledge/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/andyhuo520-vibe-knowledge/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 17 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 andyhuo520-vibe-knowledge

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/andyhuo520-vibe-knowledge/SKILL.md https://app.decimal.ai/s/andyhuo520-vibe-knowledge/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/andyhuo520-vibe-knowledge/SKILL.md

This gets SKILL.md only. The skill's 17 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/andyhuo520-vibe-knowledge/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/andyhuo520-vibe-knowledge.json

This gets SKILL.md only. The skill's 17 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 11/3/2026
Source: andyhuo520/vibe-knowledge ↗
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

Vibe知识大赏 · 精品知识短片工作室

一期 = 一个知识点 → 一条有旁白的精品短片（默认 16:9 1080p60）。时长由用户定：先按复杂度给四档建议（速览 / 精讲 / 标准 / 深挖），每档写清能讲多细、要砍什么（references/13-duration.md）。引擎复用 ai-teardown 的 cine（旁白驱动的 seek(t) 代码成片），本 skill 加四样东西：6 种脚本母版（讲法）、风格库（长相 + 讲法，styles/，44 套 · 8 个家族已验证（每个家族至少 3 套） + 用户自己的风格）、知识片组件库 know.js、Renoise 增强层（图 / 视频 / 配乐 / 音效）。

一期 = 母版 × 风格 × 手法（≤2）× 档位。风格分 8 个家族：东方、暗场概念、明亮流行、印刷与纸、图解与设计、剪辑与纪实、电影感、游戏；其中敦煌壁画、青花、木刻、半调拼贴、长卷、铜版博物是增强档风格（每段约 2 张生图）。风格可以用库里的、改成自己的、或从空白做（references/09-style-studio.md）。

两档制作（references/08-tiers.md）：

基础档 · 0 积分：Opus 手写 SVG 分层插画 + 粒子 / 3D + 数据组件，小米 MiMo 配音（限免），默认 BGM（见下），earshot 代码音效（references/10-earshot.md，两档通用）。
增强档 · 按镜头挑：只把代码做不好的镜头（写实场景、最需要被记住的 1–3 个时刻、真实运动）交给 Renoise，其余照样代码。轻 ≈25–40 / 标准 ≈250–300 / 旗舰 ≈600–700 积分，每次先报价再生成。
同一份 film.js 两档通用（ENH 开关：plate/vclip ↔ layers）。

BGM（强制，2026-10-28 起，两档通用）

每条视频都必须有这首 BGM，音量统一（用户规定）。唯一例外：用户在对话里明确要求换曲——那条音乐写 bgm: true, user_request: "用户原话"，它就当 BGM，vibe-bgm 让位，音量照样校准；没写原话的一律不认。强制在混音环节完成：finish.py 打了 bgm_force.py 钩子——film.js 没放 BGM 就自动按片长补上；其他 ≥20 秒的整段配乐（Lyria、曲库）一律停用；BGM 音量不看 film.js 写的 gain，统一校准到「说话时比人声低 10 dB」（用户要求音量高一点；停顿处自动抬起约 2–4 dB），gain_curve 只保留起伏形状。qa.py 会检测成片里有没有这首 BGM，没有就报 ⚠⚠，不能交付。

所有知识大赏默认用同一首 BGM：assets/music/vibe-bgm.m4a（用户指定，112.9 BPM，160 秒，节拍网格在同名 .json）。配音定稿后一条命令按片长裁好，切点都在小节线上，开头照原曲、结尾接原曲的自然淡出，片子更长时按 8 小节循环：

$CINE_PY ~/.claude/skills/vibe-knowledge/tools/fit_bgm.py $L/assets/audio/bgm.wav --lesson $L --tail 3   # 总长 = 旁白 + 尾卡
# 同时输出 bgm.beats.json（成片里每一拍 / 每一小节的秒数），film.js 想卡点就读它

film.js 里：music.push({ src: P("audio/bgm.wav"), from: 0, at: 0, dur: END + TAIL, gain_curve: [[0, -11], [END, -11], [END + TAIL, -8]], fade_in: 0.3, fade_out: 1.8 })（旁白段 finish.py 会自动再压低）。不再生成 Lyria 整段配乐（生成了也会被强制停用）；Renoise 只用来做短音效。

首次使用与风格推荐（先做这一步）

首次使用（~/.vibe-knowledge/welcomed 不存在）：先跑 python3 ~/.claude/skills/vibe-knowledge/tools/welcome.py，生成并打开本地「风格图鉴」（~/Desktop/vibe-knowledge/风格图鉴/index.html：风格快闪片、样片集、按家族分组的风格卡、三种开口方式、两档、流程），然后在对话里用 5–6 句话介绍：母版 × 风格 × 档位、8 个家族各举一两套、三种开口方式，最后问「想先做哪个选题？」。风格库更新后用 --force 重新生成。
用户给了选题：先跑 python3 ~/.claude/skills/vibe-knowledge/tools/recommend.py "<选题>"，拿到 3 套推荐后用 AskUserQuestion 问（推荐第一的排第一、标「（推荐）」、description 写理由和搭配母版；preview 写一句画面描述和风格图路径），同时用 SendUserFile 把 3 张风格图发给用户对照。用户点名了风格就跳过推荐。推荐到增强档风格时，在选项 description 里写明「需生图，约 8 积分/段」。
风格目录的唯一来源是 styles/catalog.json（推荐、图鉴、快闪片都读它）；加新风格时同步 catalog.json、STYLE.md、still.jpg。

核心主张（不能丢）

精品标准是硬门槛（references/02-premium.md）：三层构图、没有静止超 3 秒的画面、每章一个「王炸」镜头（增强档 Renoise 动态镜头 / 基础档代码粒子、视差）、分层声音、整期一个视觉系统。
没出处不上屏：数字、人名、年份、引文全部进 facts.md；示意画面标明；分歧两说并列。
旁白讲故事，画面给关键词：画面字 ≤8 字一组、同屏最多两组；整句交给旁白和自动字幕。
先猜后讲、标题延后、一个主道具贯穿、结尾回问（母版共用规则，references/01-templates.md）。
旁白对位硬规则：没念到不露面、计数在念到时落定、强调有预算、最长静止 ≤3 秒（references/11-absorbed.md 第一节）。
能代码就代码，花积分先确认：Renoise 只补代码做不好的镜头；所有生成先列表报价，用户在对话里明确同意才提交（references/04-renoise.md、08-tiers.md）。配音用小米 MiMo（限免）。

工作区

python3 ~/.claude/skills/vibe-knowledge/tools/new_film.py <期号> --template A --title "本福特定律"
#   默认工作区 ~/Desktop/vibe-knowledge、系列 vk；第一次会自动建 cine 系列、装 know.js、给录制工具打补丁、放用户克隆音色
S=~/Desktop/vibe-knowledge/examples/vk; L=$S/lessons/<期号>

依赖：ai-teardown skill（cine 引擎、make_lesson 配音）、CINE_PY（numpy scipy pillow playwright 的 Python；本机是 /usr/local/bin/python3.12，跑之前 PYTHONPATH= 清空，否则会加载坏掉的 PIL）、MiMo 密钥 ~/.config/ai-teardown/mimo.env、Renoise MCP（只有增强档需要；缺的话按 references/04-renoise.md「接入 Renoise」一节引导，注册链接原样给 https://renoise.ai/mcp?utm_medium=xcom&utm_source=official ）、ffmpeg、swiftc（OCR）。

流水线（三个确认点）

段	做什么	产出
① 选题	三问：能不能让人 3 秒内先猜 / 先选？有没有贯穿道具？有没有反转？给用户 3–5 个候选 + 推荐母版	选题
确认 1	用户选题、母版、时长（先跑 `duration.py` 按复杂度给四档，推荐档排第一；用户选的档跟复杂度差两级以上要提醒）、风格（库里的 / 我的 / 改一套 / 从空白，见 09-style-studio.md；推荐项排第一附风格图）、做哪一档（基础 / 增强轻 / 标准 / 旗舰）
② 查	事实清单（T1/T2/T3 分级、原文摘录、用在哪拍）	`facts.md`
③ 写	按母版骨架写旁白（字数上限见骨架 `_guide`）→ 子 agent 对抗审查（钩子、出处、字数）→ 改	`narration.json`
④ 分镜 / 资产单	每拍画面分镜（标明哪些镜头代码做、哪些增强）；增强档写 assets.json + estimate_cost 报价；基础档选曲	`assets.json`
确认 2	用户看旁白稿 + 分镜（+ 增强镜头清单和报价），明确同意后才生成
⑤ 生成	增强档：Renoise 先图 + 音效 → 用户挑图 → 视频（首帧用选中的图）→ 下载、改名、clip2frames。基础档跳过	`assets/`
⑥ 配音 + 配乐	先出 15–20 秒开场试听让用户定音色和语速 → `tts_mimo.py --gap 0.2` → `speed.py` → `check_timings.py` → `voice_post.py` → `fit_bgm.py` 按片长裁默认 BGM	`build/timings.json`、`assets/audio/bgm.wav`
⑦ 编	film.js（know.js 组件）→ stills.py 接触表逐张看（含动画中途帧）	`stills/`
⑧ 渲	queue.sh（record → finish → deliver）	成片
⑨ 质检	`qa.py` 接触表 + OCR 回读对照 facts.md + 响度；接触表里整段画面不变 = 录制出事，重录	`qa/`
确认 3	用户看成片；改完出发布包，封面用 `cover_first.py` 接成开头帧	`post.txt`、封面

常用命令

cd ~/Desktop/vibe-knowledge; S=examples/vk; L=$S/lessons/<期号>
python3 scripts/tts_mimo.py $L/narration.json $L/build --gap 0.2 --lead 0.3 --qa --jobs 2 > $L/voice.log 2>&1   # 配音 + 逐字对齐 + 回读（拍间只留 0.2 秒，别用 make_lesson 默认的 0.8）
python3 scripts/speed.py $L 1.1                                        # 需要时整体提速，目标 5.5–6 字/秒
(cd $S && python3 tools/check_timings.py <期号>)                       # 对齐有没有断
python3 ~/.claude/skills/vibe-knowledge/tools/voice_post.py $L         # 人声后期（克隆音色定稿那条 EQ + 压缩）
python3 ~/.claude/skills/vibe-knowledge/tools/clip2frames.py $L/assets/clips/v01.mp4 $L/assets/clips/v01   # 视频拆帧 → 打印帧数
cd $S && $CINE_PY cine/tools/stills.py <期号> lessons/<期号>/stills/sheet.png 1 B01+1 B02.title B05.count+0.5 …
echo "<期号>|<片名>|<封面秒>" >> cine/queue.txt   # 只能追加！queue.txt 多会话共用
pgrep -f cine/tools/queue.sh || CINE_PY=$CINE_PY cine/tools/queue.sh   # 已有队列在跑就别再起第二个，否则两路录制写坏同一个 picture.mp4
python3 ~/.claude/skills/vibe-knowledge/tools/qa.py lessons/<期号>/build/lesson<期号>.mp4
python3 ~/.claude/skills/vibe-knowledge/tools/cover_first.py <成片.mp4> cover_16x9.jpg <交付.mp4>   # 封面接成开头帧（0.5 秒），每期交付必做

voice.log 里回读 <95% 的拍删掉 build/audio/<拍>.* 重配；专名用 lexicon 写读音。

参考文件

文件	内容
references/01-templates.md	6 种母版（有旁白版）：每拍做什么、画面、对标作品
references/02-premium.md	精品标准：画面、声音、内容、交付规格（交付前逐条过）
references/03-visual-systems.md	5 套视觉系统 + Renoise 画风前缀 + 时代拼贴
references/04-renoise.md	Renoise 增强层：单价、预算、流程、提示词写法、安全
references/05-publish.md	发布包：活动标题规则、话题、封面、简介、交付文件夹
references/06-benchmarks.md	对标作品数据与共性
references/07-kit.md	know.js 组件 API
references/09-style-studio.md	风格工作室：四个入口、一题一问（推荐排第一 / 你定 / 自由对话）、三分法、汇总 → 风格图 → demo → 固化到 ~/vibe-knowledge-styles/
styles/INDEX.md	风格库目录：44 套按 8 个家族分组（每套 STYLE.md + still.jpg，样片源码 styles/_samples/）
references/13-duration.md	时长与拆解细腻度：五项复杂度打分、四档时长（字数 / 拍数 / 细腻度 / 能讲到 / 要砍掉）、推荐规则、不匹配提醒、封面停留时长
references/14-pitfalls.md	制作踩坑清单（按环节）：渲染队列共用、AI 器物图结构错、配音对齐断、Wan 下载失败、CSS 清底色、AAC 峰值…
references/12-style-families.md	风格家族与扩充路线：为什么 7 套显得单薄、风格 × 手法两条轴、87 种 UI 风格的取舍表、从 promo-video 借了什么、增强档风格踩坑（MJ 画成器物、年代词带偏服饰、ESRGAN 分块错位、画布等解码、Vision 投影）
references/10-earshot.md	earshot 代码音效（252 个，MIT，0 积分）：安装、film.js 写法、知识片角色→音效对照表、对齐时机
references/11-absorbed.md	吸星大法：14 个开源同类项目的旁白对位规则、9 种解说语法、结构与发布技巧、质检流程、12 个新风格候选、Vox 纸拼贴做法、许可证边界
references/08-tiers.md	两档制作：基础档 0 积分怎么做到精品、增强档怎么挑镜头、预算、两档通用写法
templates/narration/A–F.json	6 个母版的旁白骨架（每拍字数上限、[[cue]]）
templates/film.skeleton.js	film.js 骨架（配乐、音效、冷开场、尾卡写法）
templates/facts.md / assets.json	事实清单、Renoise 资产清单模板
tools/	new_film.py、clip2frames.py、voice_post.py、qa.py（+ ocr.swift）、recommend.py（按选题推荐风格）、welcome.py（首次介绍图鉴）、style_reel.py（新风格样片集的时间轴 + 旁白）、vision_layers.swift（生图拆主体层 / 底层）、earshot_render.py / patch_earshot.py（代码音效）、fit_bgm.py（默认 BGM 按片长按小节裁剪 / 循环 + 节拍表）、cover_first.py（封面接成开头帧）、duration.py（按复杂度给时长建议）；qa.py 现在会报 >3 秒的静止画面

cine 引擎本身的契约、组件、渲染队列、坑：~/.claude/skills/ai-teardown/references/10-cine.md（改引擎前必读）。

About this skill

Automatic

Marketing & Content pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/2/2026

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

andyhuo520 / vibe-knowledge

skills/vibe-knowledge/SKILL.md

View on GitHub ↗

License MITImported 11/2/2026Version v1Bundled 17 files

Illustrative Want to see what andyhuo520/vibe-knowledge 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

Vibe知识大赏 · 精品知识短片工作室

BGM（强制，2026-10-28 起，两档通用）

首次使用与风格推荐（先做这一步）

核心主张（不能丢）

工作区

流水线（三个确认点）

常用命令

参考文件

SkillSafety

Source

Related skills

More in the registry