Token导航 LogoToken导航

Agent Skill · 研究检索

audiobook-production(有声读物制作)

用于辅助音频、音乐、语音转写、语音合成或声音素材处理。它适合让 Agent 生成配乐说明、整理音频流程、调用语音工具或处理播客和视频配音素材。使用时需要确认输入音频来源、输出格式、时长和模型限制;涉及人声克隆、版权音乐或公开发布时,应先核对授权和合规边界。

audiobook-production 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 34,318。

总安装 2,246周安装 90GitHub Stars 85下载 727核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:audiobook-production(有声读物制作)
来源仓库:https://github.com/guia-matthieu/clawfu-skills
仓库路径:skills/audiobook-production
安装命令:
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill audiobook-production
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill audiobook-production

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

基于 Audible ACX 标准和 Richard Mayer 多媒体学习理论的有声读物制作。适用于 Audible 分发、课程音频化和作者自助出版等专业场景。提供技术规范与认知负荷优化策略,确保听感舒适且符合平台要求。安装方式:github,通过 npx skills add 命令从指定仓库添加。

注意:需遵守 ACX 分发条款,避免版权争议内容进入制作流程。

来源仓库内路径:skills/audiobook-production

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/guia-matthieu/clawfu-skills --skill audiobook-…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

audiobook-production 怎么安装?

在终端执行 npx skills add https://github.com/guia-matthieu/clawfu-skills --skill audiobook-production。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

audiobook-production 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

audiobook-production 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

audiobook-production 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

audiobook-production 用的人多吗?

公开数据是累计安装 2,246 次,近一周安装 90 次,下载 727 次,GitHub 85 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

audiobook-production 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
audiobook-production

有声读物制作 · 本页

2,24685只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Audiobook Production

Master ACX-compliant audiobook production using Audible's technical standards and Richard Mayer's multimedia learning principles for engaging, professional audio.

When to Use This Skill

  • Producing an audiobook for Audible/ACX distribution
  • Creating audio versions of courses or written content
  • Setting up narration workflow for long-form content
  • Ensuring audio meets professional distribution standards
  • Self-producing an audiobook as an author
  • Managing audiobook production projects

Methodology Foundation

Source: ACX (Audiobook Creation Exchange) + Richard Mayer (Multimedia Learning)

Core Principle: Professional audiobook production balances technical excellence (meeting strict ACX standards) with engaging delivery (applying learning science principles). As Mayer's research shows: "People learn better from friendly human voice than machine voice" (Voice Principle).

Why This Matters: ACX/Audible rejects audiobooks that don't meet technical specifications, wasting production time and money. Beyond technical compliance, understanding how listeners process audio enables production choices that maximize engagement and retention.

What Claude Does vs What You Decide

Claude DoesYou Decide
Structures production workflowFinal creative direction
Suggests technical approachesEquipment and tool choices
Creates templates and checklistsQuality standards
Identifies best practicesBrand/voice decisions
Generates script outlinesFinal script approval

What This Skill Does

  1. Ensures ACX technical compliance - Specs for bit rate, sample rate, RMS, peaks, and noise floor
  2. Structures audiobook projects - Chapter organization, credits, retail samples
  3. Applies learning principles - Pacing, tone, and delivery that aid comprehension
  4. Manages production workflow - From script to final master
  5. Handles proofing and QC - Catching errors before submission

How to Use

Check ACX Compliance

Help me verify this audiobook meets ACX submission requirements.
[provide audio specs or describe setup]

Plan Audiobook Structure

Help me structure an audiobook from this manuscript:
Total word count: [X]
Chapters: [Y]
Type: [Fiction/Non-fiction]

Create Production Workflow

Create a production plan for my audiobook project:
Book length: [word count]
Narrator: [self/hired]
Deadline: [date]

Instructions

When producing audiobooks, follow this methodology:

Step 1: Understand ACX Technical Requirements

ACX has strict specifications that must be met for acceptance.

## ACX Audio Specifications (2026)

### File Format
- MP3, 192 kbps or higher (constant bit rate)
- 44.1 kHz sample rate
- Mono (single channel)

### Audio Levels
- RMS: -23dB to -18dB
- Peak values: -3dB maximum (no clipping)
- Noise floor: -60dB or lower

### File Naming
- Chapter files: [BookTitle]_[ChapterNumber].mp3
- Opening credits: [BookTitle]_Opening_Credits.mp3
- Closing credits: [BookTitle]_Closing_Credits.mp3

### Content Requirements
- Opening credits (first file): Title, author, narrator
- Closing credits (last file): "This has been [title] by [author], narrated by [narrator]"
- Each chapter file is standalone (no cross-file audio)
- Consistent room tone throughout

### Quality Requirements
- No extraneous sounds (mouth clicks, pops, page turns)
- Consistent audio quality across all files
- Retail sample: ~5 minutes of representative content

Critical: Run ACX Check tool on every file before submission.


Step 2: Prepare the Manuscript

Before recording, optimize the text for audio delivery.

## Manuscript Preparation Checklist

### Structure
□ Chapter breaks clearly marked
□ Section breaks identified (longer pause points)
□ Footnotes converted to in-text explanations or removed
□ Visual content (charts, tables) adapted for audio or noted for skip

### Pronunciation Guide
□ Character names with phonetic spelling
□ Foreign words and phrases
□ Technical terms and jargon
□ Place names and proper nouns
□ Acronyms expanded or spelled out

### Narrator Notes
□ Tone shifts marked
□ Character voice cues (if fiction)
□ Emphasis suggestions (minimal)
□ "As shown in Figure X" → adapted for audio
□ Author asides or commentary identified

### Timing Estimate
□ Word count per chapter
□ Total word count
□ Estimated runtime: words ÷ 9,300 = hours (approx)
   - 50,000 words ≈ 5-6 hours
   - 80,000 words ≈ 8-9 hours

Step 3: Set Up Recording Environment

Consistent, quality recording requires proper setup.

## Home Studio Essentials

### Minimum Equipment
- **Microphone**: USB condenser (AT2020, Blue Yeti) or XLR setup
- **Pop filter**: Essential for plosives
- **Mic stand**: Stable positioning
- **Headphones**: Closed-back, wired

### Room Treatment
- Record in smallest, most furnished room available
- Hang blankets on hard surfaces
- Use reflection filter behind mic
- Close windows, turn off HVAC
- Eliminate electronic hum (fridges, computers)

### Recording Software (DAW)
- Free: Audacity, GarageBand
- Professional: Adobe Audition, Reaper, Pro Tools
- ACX-specific: Hindenburg Pro (audiobook workflow)

### Test Recording Checklist
□ Record 30 seconds of room tone
□ Record test passage
□ Check RMS levels (-23 to -18 dB)
□ Check peak levels (below -3 dB)
□ Check noise floor (below -60 dB)
□ Listen for room echo or hum
□ Verify consistent mic positioning

Step 4: Apply Mayer's Multimedia Learning Principles

Science-backed techniques for engaging audio.

## Mayer's Principles for Audiobook Delivery

### Voice Principle
"People learn better from human voice than machine voice."
→ Warm, conversational delivery beats polished broadcast voice
→ Let personality come through
→ Avoid monotone "reading" voice

### Personalization Principle
"People learn better when words are conversational rather than formal."
→ Write/deliver as if talking to one person
→ Use "you" and "we"
→ Contractions are encouraged

### Segmenting Principle
"People learn better when content is in learner-paced segments."
→ Clear chapter breaks
→ Section pauses for complex material
→ Chapter summaries for dense non-fiction

### Redundancy Principle (for video/slides)
"People learn better from graphics and narration than graphics + narration + text."
→ For audiobooks: don't describe visual elements you can't show
→ Adapt visual content or acknowledge it's omitted

### Coherence Principle
"People learn better when extraneous material is excluded."
→ Cut verbal filler
→ Remove tangents that don't serve the chapter
→ Every word earns its place

Step 5: Production Workflow

Systematic process from script to master.

## Audiobook Production Pipeline

### Phase 1: Pre-Production (Week 1-2)
□ Manuscript finalized and proofread
□ Pronunciation guide complete
□ Chapter structure confirmed
□ Recording schedule created
□ Test recordings approved

### Phase 2: Recording (Weeks 2-6, varies by length)
□ Opening credits recorded first
□ Chapters recorded in order (usually)
□ Room tone captured each session
□ Daily backup of raw files
□ Notes logged for pickups needed

### Phase 3: Editing (Concurrent or following)
□ Remove mistakes and restart takes
□ Remove excessive breaths (keep natural ones)
□ Eliminate mouth clicks and pops
□ Smooth edits (crossfade)
□ Consistent pacing throughout

### Phase 4: Mastering
□ Noise reduction applied (light touch)
□ Compression for consistent levels
□ Limiting to prevent peaks
□ Final RMS check (-23 to -18 dB)
□ Export to ACX specs (192 kbps MP3, 44.1kHz, mono)

### Phase 5: Quality Control
□ Listen to every file start to finish
□ Check first/last 5 seconds of each file
□ Verify file naming convention
□ Run ACX Check or similar tool
□ Create retail sample (5 min)

Step 6: Credits and Sample

Specific requirements for opening, closing, and retail sample.

## Opening Credits Script
(Must be first audio file)

"[Book Title]"
Written by [Author Name]
Narrated by [Narrator Name]

[Optional: Publisher name]
[Optional: Copyright year]

---

## Closing Credits Script
(Must be last audio file)

"This has been [Book Title], written by [Author Name],
narrated by [Narrator Name]."

[Optional: "Visit [website] for more" or other approved callout]
[Optional: "Audiobook production by [producer]"]

---

## Retail Sample Guidelines

**Length**: Approximately 5 minutes
**Content**: Representative excerpt that hooks listeners
**Selection criteria**:
- Showcases narrator's ability
- Engages interest without major spoilers
- Demonstrates the book's voice/style
- Often from early chapters (context not required)

**Do NOT include**: Credits or chapter announcements in sample

Examples

Example 1: Self-Published Non-Fiction Audiobook

Context: An author is self-narrating their business book.

Input:

Help me plan audiobook production for my 55,000-word business book. I'm self-narrating. I have a Blue Yeti mic and record in my home office.

Output:

Production Plan: Business Book Audiobook

Project Specifications

  • Word count: 55,000 words
  • Estimated runtime: 5.5-6 hours
  • Narrator: Author (self-narrated)
  • Equipment: Blue Yeti USB mic (adequate for ACX)

Pre-Production (Days 1-3)

Manuscript Prep

  • Review all 12 chapters for audio adaptation
  • Convert/adapt 8 figures referenced in text
  • Create pronunciation guide for industry terms
  • Mark chapter breaks and section pauses
  • Estimate 4,500 words/chapter average = ~29 min/chapter

Room Preparation

  • Assess home office acoustics
  • Add blanket on wall behind recording position
  • Use closet with clothes as recording booth alternative
  • Test recordings at 3 different times of day (HVAC, traffic noise)

Sample Script: "As shown in Figure 3" → "Here's how it works: imagine a funnel with three stages..."

Recording Schedule (Weeks 1-3)

Daily recording block: 2 hours max (voice fatigue) Target per session: 1.5-2 chapters (8,000 words) Total sessions needed: ~8-10

Schedule:

  • Day 1: Opening credits + Chapter 1
  • Day 2: Chapters 2-3
  • Day 3: Chapters 4-5
  • [continue pattern]
  • Day 8: Chapter 12 + Closing credits
  • Days 9-10: Pickups and problem sections

Session Ritual:

  1. Hydrate 30 min before (room temp water)
  2. Vocal warmup (5 min)
  3. Record room tone (10 sec)
  4. Test recording, check levels
  5. Record chapter(s)
  6. Log pickup notes

Post-Production (Week 4)

Editing workflow per chapter:

  1. Import raw audio
  2. Remove mistakes and alternate takes
  3. Clean up breaths and mouth clicks
  4. Apply light noise reduction
  5. Normalize RMS to -20 dB
  6. Check peaks (below -3 dB)
  7. Export as MP3 (192 kbps, 44.1 kHz, mono)

File naming:

  • BusinessBookTitle_Opening_Credits.mp3
  • BusinessBookTitle_001.mp3
  • BusinessBookTitle_002.mp3
  • ...
  • BusinessBookTitle_012.mp3
  • BusinessBookTitle_Closing_Credits.mp3

Quality Control (Days 1-2)

  • Listen through every file with checklist
  • Run ACX Check on all files
  • Create 5-minute retail sample from Chapter 2
  • Verify consistent sound across all chapters
  • Final review of opening/closing credits

Technical Settings

Recording:

  • 44.1 kHz, 24-bit WAV (edit in high quality)
  • Mono input
  • Gain set for peaks at -12 dB

Export (ACX compliant):

  • MP3, 192 kbps CBR
  • 44.1 kHz
  • Mono
  • RMS: -20 dB (within -23 to -18)
  • Peak: -3 dB max

Example 2: ACX Troubleshooting

Context: Audiobook files are being rejected by ACX.

Input:

My audiobook submission was rejected. ACX says "RMS levels out of spec" and "noise floor too high." How do I fix this?

Output:

ACX Rejection Fix: RMS and Noise Floor

Diagnosis

RMS out of spec: Your audio is either too quiet (below -23 dB) or too loud (above -18 dB)

Noise floor too high: Background hiss or hum is above -60 dB

Step-by-Step Fix

Fix 1: RMS Levels

In Audacity:

  1. Select all audio (Ctrl+A)
  2. Effect → Loudness Normalization
  3. Set to: -20 dB RMS (middle of ACX range)
  4. Apply

In Adobe Audition:

  1. Select all
  2. Effects → Amplitude → Match Loudness
  3. Set Target Loudness to -20 LUFS
  4. Process

Fix 2: Noise Floor

*If noise is mild (just room tone)*:

  1. Find 2-3 seconds of "silence" (room tone only)
  2. Select it as noise profile
  3. Apply noise reduction to full track
  4. Use minimal settings (6-12 dB reduction) to avoid artifacts

In Audacity:

  • Effect → Noise Reduction → Get Noise Profile
  • Select all → Noise Reduction → 6-12 dB, 6 Sensitivity

*If noise is significant*:

  • Re-record in quieter environment
  • Use noise gate (removes sound below threshold)
  • Consider iZotope RX for professional repair

Fix 3: Verify Peaks

After RMS adjustment, peaks may exceed -3 dB:

  1. Effect → Limiter
  2. Set ceiling to -3.0 dB
  3. Apply

Verification Workflow

  1. Make fixes to one chapter first
  2. Run ACX Check plugin or online tool
  3. Verify all specs pass:

- RMS: -23 to -18 dB ✓ - Peak: -3 dB or lower ✓ - Noise floor: -60 dB or lower ✓

  1. Apply same process to all files
  2. Re-check each file before resubmitting

Prevention for Future

Recording checklist:

  • Noise floor below -60 dB before recording
  • Gain set so peaks hit -12 dB when speaking
  • Room tone recorded each session
  • Test file checked before full session

Checklists & Templates

ACX Pre-Submission Checklist

## Technical Compliance

□ All files are 192 kbps MP3, 44.1 kHz, mono
□ RMS levels between -23 and -18 dB
□ Peak values at or below -3 dB
□ Noise floor at or below -60 dB
□ No clipping or distortion
□ Consistent levels across all chapters

## File Structure

□ Opening credits file present
□ Closing credits file present
□ Files named correctly: [Title]_[Number].mp3
□ Chapter numbers are sequential
□ No missing chapters
□ Retail sample created (≈5 minutes)

## Content Quality

□ First/last 5 seconds of each file are clean (room tone or fade)
□ No extraneous sounds (clicks, pops, breaths)
□ No room echo or reverb issues
□ Consistent voice quality throughout
□ All pickups and corrections completed
□ Credits read correctly (title, author, narrator)

## Final Review

□ Listened to complete audiobook
□ Spot-checked transitions between chapters
□ Verified retail sample is representative
□ Cover art meets ACX specs (if applicable)
□ All metadata entered correctly

Production Schedule Template

## Audiobook Production Schedule

**Title**: ________________________________
**Word count**: ___________ | **Est. runtime**: ___________
**Narrator**: _____________________________
**Target completion**: ____________________

### Pre-Production: Week ___

| Task | Due | Done |
|------|-----|------|
| Manuscript finalized | | □ |
| Pronunciation guide | | □ |
| Room/equipment tested | | □ |
| Opening credits scripted | | □ |

### Recording: Weeks ___ - ___

| Session | Chapters | Words | Est. Time | Done |
|---------|----------|-------|-----------|------|
| 1 | Credits + Ch 1 | | | □ |
| 2 | Ch 2-3 | | | □ |
| 3 | Ch 4-5 | | | □ |
| ... | | | | □ |

### Post-Production: Week ___

| Task | Due | Done |
|------|-----|------|
| Editing complete | | □ |
| Mastering complete | | □ |
| ACX specs verified | | □ |
| QC listen-through | | □ |
| Retail sample created | | □ |

### Submission: ___________

Skill Boundaries

What This Skill Does Well

  • Structuring audio production workflows
  • Providing technical guidance
  • Creating quality checklists
  • Suggesting creative approaches

What This Skill Cannot Do

  • Replace audio engineering expertise
  • Make subjective creative decisions
  • Access or edit audio files directly
  • Guarantee commercial success

References

  • ACX. "Audio Submission Requirements" - Official technical specifications
  • Richard Mayer. "Multimedia Learning" (2009) - Scientific principles for audio learning
  • iZotope. "Professional Voice Over Recording Tips" - Technical recording guidance
  • Audacity Team. "Audacity Manual" - Free editing software

Related Skills


Skill Metadata (Internal Use)

name: audiobook-production
category: audio
subcategory: voiceover
version: 1.0
author: MKTG Skills
source_expert: ACX, Richard Mayer
source_work: ACX Submission Requirements, Multimedia Learning
difficulty: intermediate
estimated_value: $500-2,000 per audiobook (equivalent production management)
tags: [audiobook, acx, audible, narration, production]
created: 2026-01-26
updated: 2026-01-26

平台分布

Codex

34.53%
按下载量换算251

Claude

31.6%
按下载量换算230

Cursor

21.23%
按下载量换算154

Gemini CLI

10.28%
按下载量换算75

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills