Ready to supercharge your AI agents?

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

Audio Script Writer · leoyeai | DecimalAI

Design & Mediaby leoyeai

Audio Script Writer

Convert written medical content into podcast or video scripts optimized for audio delivery. Transforms academic papers, reports, and educational materials into engaging spoken-word formats with pronunciation guides, timing markers, and audio-friendly structure.

Never made a case worse

SkillScore

SkillScore86/100

Test results 86

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

77%86%of test cases passed +9 pts

Without skill17 of 22

With skill19 of 22

2 fixed17 passed either way3 still failing0 broke

Measured on gemini-3.6-flash8/6/2026v1

Track record

Agent runs: 0; All time
Forks: 1

See one task, with and without the skill

One test taskWhen scheduling studio time for a script estimated at 10 minutes of narration, what percentage time buffer should be added for natural retakes and pacing variations?

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-audio-script-writer
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-audio-script-writer")
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-audio-script-writer

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-audio-script-writer/SKILL.md https://app.decimal.ai/s/leoyeai-audio-script-writer/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-audio-script-writer/SKILL.md

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

Other ways to add it

Claude Code docs

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

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/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-audio-script-writer/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

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

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

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

Other ways to add it

Claude Agent SDK docs

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

Install

pip install "decimalai[openai-agents]"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

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

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

Other ways to add it

OpenAI Agents docs

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

Install

pip install "decimalai[openai]"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

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

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

Other ways to add it

OpenAI SDK docs

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

Install

pip install "decimalai[anthropic]"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

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

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

Other ways to add it

Anthropic docs

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

Install

pip install "decimalai[google-genai]"
decimalai skills add leoyeai-audio-script-writer

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

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

Other ways to add it

Gemini API docs

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

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

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

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

Other ways to add it

LangChain docs

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

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

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

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

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

Other ways to add it

CrewAI docs

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

Install

pip install "decimalai[adk]"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

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

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

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

Other ways to add it

Google ADK docs

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

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

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

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

Other ways to add it

Pydantic AI docs

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

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

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

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

Other ways to add it

Deep Agents docs

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

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

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

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

Other ways to add it

Microsoft Agent Framework docs

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

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer")
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-audio-script-writer/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

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

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

Other ways to add it

Strands docs

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

pip install "decimalai>=0.15"
decimalai skills add leoyeai-audio-script-writer

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-audio-script-writer/SKILL.md https://app.decimal.ai/s/leoyeai-audio-script-writer/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-audio-script-writer/SKILL.md

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

Other ways to add it

Cursor and other editors docs

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

Get the file

curl -fsSL https://app.decimal.ai/s/leoyeai-audio-script-writer/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-audio-script-writer.json

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

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/6/2026
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

Audio Script Writer

Overview

Content transformation tool that converts written medical and scientific materials into professionally structured audio scripts suitable for podcasts, educational videos, audiobooks, and voiceover narration.

Key Capabilities:

Format Conversion: Research papers → podcast scripts
Spoken Word Optimization: Sentence restructuring for listening
Pronunciation Guides: Medical terminology phonetic spelling
Timing Estimation: Duration calculations for production planning
Multi-Format Output: Podcast, video, lecture, audiobook templates
Voice Direction: Tone, pace, and emphasis cues for narrators

When to Use

✅ Use this skill when:

Creating medical education podcasts from journal articles
Converting conference presentations to video scripts
Developing audiobook versions of medical textbooks
Scripting patient education audio materials
Producing research summary videos for social media
Adapting written case reports for audio case studies
Creating voiceover scripts for e-learning modules

❌ Do NOT use when:

Live presentation without script → Use improvisation
Highly visual content (surgery videos) → Use visual-focused tools
Interactive audio (Q&A format) → Use dialogue scripting tools
Music or sound design planning → Use audio production software
Voice recording itself → This creates scripts, not audio

Integration:

Upstream: abstract-summarizer (content condensation), lay-summary-gen (patient-friendly language)
Downstream: medical-translation (multi-language scripts), voice-cloning-tool (AI narration)

Core Capabilities

1. Spoken Word Transformation

Convert written text to conversational audio style:

from scripts.audio_writer import AudioScriptWriter

writer = AudioScriptWriter()

# Transform written content
script = writer.convert_to_audio(
    source_text=research_paper,
    format="podcast",  # podcast, video, lecture, audiobook
    target_audience="medical_students",
    duration_minutes=15
)

print(script.spoken_text)
# Converts: "The pathophysiology of diabetes mellitus involves..."
# To: "So what exactly happens in diabetes? Well, it all starts when..."

Transformation Rules:

Written Style	Audio Style	Example
"Furthermore"	"Plus"	Less formal transitions
" et al."	"and their colleagues"	Expand abbreviations
Numbers in text	Spoken numbers	"15%" → "15 percent"
Long sentences	15-20 word max	Break into digestible chunks
Passive voice	Active voice	"was observed" → "we saw"
Citations	Omit or footnote	"(Smith et al., 2024)" → [reference tone]

2. Pronunciation Guide Generation

Create phonetic spelling for medical terms:

# Generate pronunciation guide
pronunciation = writer.create_pronunciation_guide(
    text=script,
    include_phonetic=True,
    include_syllables=True
)

# Output:
# "Hyperlipidemia: hi-per-lip-i-DEE-mee-uh"
# "Metformin: met-FOR-min"
# "Atherosclerosis: ath-er-oh-skleh-ROH-sis"

Guide Elements:

Phonetic Spelling: IPA or simplified phonetics
Syllable Breaks: hy-per-ten-sion
Emphasis Marking: Primary stress (CAPS), secondary stress
Alternative Pronunciations: Regional variations (UK vs US)
Sound-Alikes: "rhymes with..." for difficult terms

3. Timing and Pacing

Calculate speaking duration and mark pacing cues:

# Analyze timing
timing = writer.calculate_timing(
    script=script,
    speaking_rate="conversational",  # slow, conversational, fast
    include_pauses=True
)

print(f"Estimated duration: {timing.duration_minutes} minutes")
print(f"Word count: {timing.word_count}")
print(f"Pace: {timing.words_per_minute} WPM")

Speaking Rates:

Style	WPM	Use Case
Slow/Educational	120-130	Patient education, complex topics
Conversational	140-160	Podcasts, general audience
Fast/News	170-190	Time-constrained content
Variable	Varies	Dynamic pacing with pauses

Pacing Cues:

[BREATHE] - Brief pause for narrator
[PAUSE 2s] - Two-second pause for emphasis
[SLOW DOWN] - Reduce pace for key point
[SPEED UP] - Increase energy/excitement
[BEAT] - Dramatic pause

4. Multi-Format Templates

Generate scripts for different audio formats:

# Podcast episode
podcast = writer.create_podcast_script(
    content=article,
    episode_format="interview",  # solo, interview, panel
    include_intro_music=True,
    ad_breaks=[5, 12]  # minutes
)

# Educational video
video = writer.create_video_script(
    content=lecture_slides,
    visual_cues=True,  # Mark where visuals change
    b_roll_notes=True  # Suggest supplemental footage
)

Format Types:

Format	Characteristics	Best For
Podcast	Conversational, segments, ads	Long-form content, interviews
Video	Visual cues, B-roll notes	YouTube, educational platforms
Lecture	Structured, Q&A breaks	Online courses, training
Audiobook	Chapter markers, consistent tone	Textbooks, memoirs
News	Tight, factual, quick	Research briefs, updates

Common Patterns

Pattern 1: Research Paper to Podcast

Scenario: Convert published study to 15-minute podcast episode.

# Convert paper to podcast script
python scripts/main.py \
  --input paper.pdf \
  --format podcast \
  --duration 15 \
  --style conversational \
  --include-intro-outro \
  --output podcast_script.txt

# Generate pronunciation guide
python scripts/main.py \
  --input podcast_script.txt \
  --generate-pronunciation \
  --output pronunciation_guide.txt

Structure:

[INTRO MUSIC 5s]

HOST: Welcome to Medical Research Today. I'm your host...

[BREATHE]

HOST: Today we're diving into a fascinating study about...

[PAUSE]

HOST: So what did the researchers find? Well...

[BREATHE]

HOST: Dr. Smith, one of the study authors, explains...

[SOUND BITE: Interview clip]

...

[OUTRO MUSIC]

Pattern 2: Medical Lecture Recording

Scenario: Convert lecture notes to video script for online course.

# Create lecture script
lecture = writer.create_lecture_script(
    notes=lecture_content,
    duration=45,  # minutes
    break_intervals=[15, 30],  # minutes for student breaks
    interaction_points=True  # "Pause and think..." prompts
)

# Add visual cues
script = writer.add_visual_cues(
    script=lecture,
    slide_transitions=True,
    animation_notes=True
)

Lecture Elements:

Learning objectives at start
Periodic comprehension checks
Break reminders
Transition phrases between topics
Summary and key takeaways

Pattern 3: Patient Education Audio

Scenario: Create audio guide for diabetes management.

# Patient-friendly script
patient_script = writer.create_patient_script(
    medical_content=diabetes_guide,
    reading_level=6,  # 6th grade
    empathetic_tone=True,
    key_points_highlighted=True
)

# Slow, clear pacing
patient_script.adjust_pacing(
    wpm=130,
    pause_after_sentences=1.5  # seconds
)

Patient Script Features:

Simple language (avoid medical jargon)
Empathetic tone
Clear action steps
Reassuring statements
Repetition of key points

Pattern 4: Conference Presentation to Video

Scenario: Adapt live presentation to YouTube video format.

# Convert presentation script
python scripts/main.py \
  --input presentation_transcript.txt \
  --format video \
  --platform youtube \
  --include-hooks true \
  --engagement-cues true \
  --output youtube_script.txt

YouTube Optimization:

Hook in first 30 seconds
Engagement questions for comments
Call to action (subscribe, like)
Timestamp markers for chapters
B-roll suggestions for visual interest

Complete Workflow Example

From research paper to published podcast:

# Step 1: Extract and summarize content
python scripts/main.py \
  --input paper.pdf \
  --extract-key-points \
  --output key_points.txt

# Step 2: Convert to audio script
python scripts/main.py \
  --input key_points.txt \
  --format podcast \
  --duration 20 \
  --output raw_script.txt

# Step 3: Add production elements
python scripts/main.py \
  --input raw_script.txt \
  --add-music-cues \
  --add-sound-effects \
  --add-pacing-marks \
  --output production_script.txt

# Step 4: Generate pronunciation guide
python scripts/main.py \
  --input production_script.txt \
  --generate-pronunciation \
  --output pronunciations.txt

# Step 5: Create timing breakdown
python scripts/main.py \
  --input production_script.txt \
  --calculate-timing \
  --output timing_breakdown.txt

Python API:

from scripts.audio_writer import AudioScriptWriter
from scripts.pronunciation import PronunciationGuide
from scripts.timing import TimingCalculator

# Initialize
writer = AudioScriptWriter()
pronouncer = PronunciationGuide()
timing = TimingCalculator()

# Read source material
with open("research_article.txt", "r") as f:
    content = f.read()

# Step 1: Convert to spoken format
script = writer.convert_to_audio(
    text=content,
    format="podcast",
    target_duration=15,  # minutes
    audience="general_medical"
)

# Step 2: Add production elements
script_with_cues = writer.add_production_cues(
    script=script,
    music_stings=True,
    transition_effects=True
)

# Step 3: Generate pronunciation guide
medical_terms = pronouncer.extract_terms(script_with_cues)
pronunciation_guide = pronouncer.create_guide(medical_terms)

# Step 4: Calculate timing
timing_analysis = timing.calculate(
    script=script_with_cues,
    speaking_rate=150  # WPM
)

# Export complete production package
writer.export_production_package(
    script=script_with_cues,
    pronunciation=pronunciation_guide,
    timing=timing_analysis,
    output_dir="podcast_production/"
)

Quality Checklist

Content Quality:

Written content accurate and current
Sources cited (even if not spoken)
Medical facts verified by expert
Appropriate for target audience level
No confidential patient information

Audio Optimization:

Sentences 15-20 words maximum
Abbreviations expanded on first use
Complex terms have pronunciation guides
Active voice preferred over passive
Transitions smooth and conversational

Production Quality:

Timing realistic for content density
Pacing cues appropriate for subject
Music/sound cues marked clearly
Pronunciation guide comprehensive
Script formatted for easy reading

Before Recording:

CRITICAL: Script read aloud for flow
Difficult pronunciations practiced
Timing tested with stopwatch
Technical terms confirmed with subject expert
Copyright cleared for any quoted material

Common Pitfalls

Content Issues:

❌ Too dense → Information overload for listeners
- ✅ Break complex topics into multiple episodes
❌ Visual dependencies → "As shown in Figure 3..."
- ✅ Describe visuals or omit visual-dependent content
❌ Citation overload → Every sentence has reference
- ✅ Save citations for show notes, not narration

Audio Issues:

❌ Written-style language → "Furthermore, the aforementioned..."
- ✅ Conversational: "Plus, this thing we talked about..."
❌ No pauses → Relentless information delivery
- ✅ Build in breathing room; let points sink in
❌ Ignoring pronunciation → Mispronounced medical terms
- ✅ Research and practice all technical terms

Production Issues:

❌ Underestimating time → 10 minutes of script takes 12+ to record
- ✅ Add 20% buffer for retakes and natural pacing
❌ Complex sentence structures → Tongue twisters for narrator
- ✅ Short sentences; avoid nested clauses

References

Available in references/ directory:

audio_writing_best_practices.md - Broadcast writing guidelines
medical_pronunciation_guide.md - Common terms phonetics
podcast_production_standards.md - Industry format standards
accessibility_guidelines.md - Inclusive audio content
platform_requirements.md - YouTube, Spotify, Apple specs
voice_care_tips.md - Narrator health and performance

Scripts

Located in scripts/ directory:

main.py - CLI interface for script conversion
audio_writer.py - Core text-to-audio transformation
pronunciation.py - Medical terminology phonetics
timing.py - Duration calculation and pacing
format_templates.py - Podcast, video, lecture templates
voice_direction.py - Narrator cues and direction
accessibility.py - Alternative format generation

Limitations

Voice Performance: Script is text only; actual delivery varies by narrator
Accent Variations: Pronunciation guides may not match all dialects
Cultural Context: Humor and references may not translate across cultures
Copyright: Cannot use copyrighted material without permission
Technical Accuracy: Does not verify medical content (input-dependent)
Live Elements: Cannot script unscripted interviews or Q&A

Parameters

Parameter	Type	Default	Required	Description
`--input`, `-i`	string	-	No	Input text file path
`--output`, `-o`	string	-	No	Output JSON file path (default: stdout)
`--text`	string	-	No	Direct text input (alternative to --input)
`--duration`, `-d`	int	5	No	Target duration in minutes
`--pace`, `-p`	string	normal	No	Speaking pace (slow, normal, fast)
`--style`, `-s`	string	conversational	No	Script style (conversational, formal, educational)

Usage

Basic Usage

# Convert from file
python scripts/main.py --input article.txt --duration 5 --output script.json

# Direct text input
python scripts/main.py --text "Medical research findings..." --duration 3

# From stdin
cat article.txt | python scripts/main.py --duration 5 --style conversational

# With specific style and pace
python scripts/main.py --input paper.txt --style educational --pace slow

Risk Assessment

Risk Indicator	Assessment	Level
Code Execution	Python script executed locally	Low
Network Access	No external API calls	Low
File System Access	Read input files, write output files	Low
Instruction Tampering	Standard prompt guidelines	Low
Data Exposure	Output saved only to specified location	Low

Security Checklist

No hardcoded credentials or API keys
No unauthorized file system access
Output does not expose sensitive information
Prompt injection protections in place
Input validation for file paths
Output directory restricted to workspace
Script execution in sandboxed environment

Prerequisites

# Python 3.7+
# No additional packages required (uses standard library)

Evaluation Criteria

Success Metrics

Successfully converts text to audio-optimized script
Expands abbreviations and converts numbers to words
Calculates estimated duration based on word count
Applies style-specific formatting
Provides pronunciation notes for medical terms

Test Cases

Basic Conversion: Convert text file → Returns audio script with metadata
Abbreviation Handling: Text with "e.g., i.e., etc." → All expanded in output
Number Conversion: Input with "1 in 4" → Output with "one in four"

Lifecycle Status

Current Stage: Draft
Next Review Date: 2026-03-06
Known Issues: None
Planned Improvements:
- Add support for custom abbreviation dictionaries
- Integrate with text-to-speech engines
- Add multilingual support

🎙️ Pro Tip: The best audio scripts sound natural when spoken. Always read your script aloud before finalizing—if you stumble over a sentence, your narrator will too. Revise for the ear, not the eye.

About this skill

Automatic

Writing & Editing 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/audio-script-writer/SKILL.md

View on GitHub ↗

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

Illustrative Want to see what leoyeai/audio-script-writer 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

Audio Script Writer

Overview

When to Use

Core Capabilities

1. Spoken Word Transformation

2. Pronunciation Guide Generation

3. Timing and Pacing

4. Multi-Format Templates

Common Patterns

Pattern 1: Research Paper to Podcast

Pattern 2: Medical Lecture Recording

Pattern 3: Patient Education Audio

Pattern 4: Conference Presentation to Video

Complete Workflow Example

Quality Checklist

Common Pitfalls

References

Scripts

Limitations

Parameters

Usage

Basic Usage

Risk Assessment

Security Checklist

Prerequisites

Evaluation Criteria

Success Metrics

Test Cases

Lifecycle Status

SkillSafety

Source

Related skills

More in the registry