Token导航 LogoToken导航

Agent Skill · 研究检索

voice-analyzer(语音分析仪)

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。

voice-analyzer 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,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 56,510。

总安装 449周安装 18GitHub Stars 9下载 145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:voice-analyzer(语音分析仪)
来源仓库:https://github.com/cdeistopened/skill-stack
仓库路径:skills/voice-analyzer
安装命令:
npx skills add https://github.com/cdeistopened/skill-stack --skill voice-analyzer
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/cdeistopened/skill-stack --skill voice-analyzer

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。

分析写作样本提取语音特征模式,生成可复制的个性化写作风格。适用于品牌声音建立、作者风格模仿和内容一致性维护场景。使用时需收集 3-5 个代表性样本,识别深层写作模式和节奏特征。通过 GitHub 安装,支持主流宿主环境,建议核对样本版权和使用授权。

voice-analyzer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/voice-analyzer

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/cdeistopened/skill-stack --skill voice-analyze…;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

voice-analyzer 怎么安装?

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

voice-analyzer 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。

voice-analyzer 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。

voice-analyzer 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。

voice-analyzer 用的人多吗?

公开数据是累计安装 449 次,近一周安装 18 次,下载 145 次,GitHub 9 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。

voice-analyzer 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。
  • 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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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
voice-analyzer

语音分析仪 · 本页

4499只读未明确有提醒

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

Voice Analyzer

Transform writing samples into a codified voice style that can be replicated consistently.

Purpose

This skill analyzes 3-5 samples of writing to extract the patterns, techniques, and characteristics that define a distinctive voice. The output is a complete voice skill that can be used alongside anti-ai-writing to produce content in that voice.

Core Philosophy: Every distinctive writer has patterns - conscious or unconscious. By identifying and codifying these patterns, we can replicate voice authentically without losing what makes it human.

When to Use This Skill

  • Establishing your own writing voice for consistent content
  • Codifying a brand voice for team use
  • Creating voice guides for ghostwriting clients
  • Analyzing competitors or inspirations to understand their approach
  • Building a library of voice styles for different contexts

Requires: 3-5 writing samples of 500+ words each (more samples = better analysis)

Output: A complete voice-[name]/SKILL.md file ready for use


The Analysis Process

Phase 1: Gather Samples

Collect 3-5 writing samples that represent the voice at its best:

Ideal samples:

  • Published content the author is proud of
  • Writing that received strong engagement or feedback
  • Pieces that "sound like" the author
  • Content from the same medium (all newsletters, all blog posts, etc.)

Avoid:

  • Heavily edited or committee-written pieces
  • Content written under constraints (legal, corporate)
  • Very old writing that doesn't reflect current voice
  • Mixed media (don't combine tweets with long-form)

Sample preparation:

  1. Paste each sample into a separate section
  2. Note the source/context for each
  3. Remove any content that was clearly written by others (quotes, etc.)

Phase 2: Extract Voice Characteristics

Analyze the samples across these dimensions:

2.1 Sentence Structure

Questions to answer:

  • What's the average sentence length? (Short and punchy? Long and flowing?)
  • Does the writer vary length deliberately?
  • Are sentences simple or complex?
  • How does the writer use punctuation?

Patterns to identify:

  • Signature sentence structures (e.g., "X. But Y." or "Here's the thing: Z")
  • Use of fragments
  • Paragraph length and rhythm
  • Opening and closing patterns

Document findings as:

## Sentence Structure
- Average length: [short/medium/long]
- Variation pattern: [describe]
- Signature structures: [list specific patterns]
- Punctuation style: [describe]
2.2 Word Choice

Questions to answer:

  • Does the writer use simple or sophisticated vocabulary?
  • Are there signature words or phrases that appear repeatedly?
  • What's the formality level?
  • Does the writer use jargon, slang, or technical terms?

Patterns to identify:

  • Favorite words (appears 3+ times across samples)
  • Avoided words (never appears despite opportunity)
  • Contractions (always, never, sometimes)
  • Profanity or strong language (level and style)

Document findings as:

## Word Choice
- Vocabulary level: [simple/moderate/sophisticated]
- Formality: [1-5 scale, casual to formal]
- Signature words: [list]
- Avoided patterns: [list]
- Contractions: [always/sometimes/never]
2.3 Tone & Attitude

Questions to answer:

  • What's the overall emotional register?
  • How does the writer relate to the reader?
  • Is there humor? What kind?
  • What's the confidence level?

Patterns to identify:

  • Dominant tone (playful, serious, irreverent, warm, etc.)
  • Relationship to reader (peer, mentor, friend, expert)
  • Humor style (sarcasm, wordplay, self-deprecation, observational)
  • Certainty level (definitive vs. exploratory)

Document findings as:

## Tone & Attitude
- Primary tone: [describe]
- Reader relationship: [describe]
- Humor: [type and frequency]
- Certainty: [definitive/exploratory/mixed]
2.4 Structural Patterns

Questions to answer:

  • How does the writer open pieces?
  • How do they transition between ideas?
  • How do they close?
  • What's the overall architecture?

Patterns to identify:

  • Opening hooks (story, question, bold claim, etc.)
  • Transition style (seamless, signposted, abrupt)
  • Closing patterns (call to action, question, summary, callback)
  • Section/paragraph organization

Document findings as:

## Structural Patterns
- Opening style: [describe]
- Transitions: [describe]
- Closing style: [describe]
- Overall architecture: [describe]
2.5 Distinctive Techniques

Questions to answer:

  • What rhetorical devices appear repeatedly?
  • Are there signature moves unique to this writer?
  • How does the writer handle examples and evidence?
  • What makes this voice recognizable?

Patterns to identify:

  • Rhetorical devices (questions, lists, analogies, callbacks)
  • Signature moves (e.g., "Let me tell you a story...")
  • Evidence style (data, anecdotes, authority, logic)
  • Pattern interrupts (how do they surprise the reader?)

Document findings as:

## Distinctive Techniques
- Rhetorical devices: [list with examples]
- Signature moves: [describe]
- Evidence style: [describe]
- Pattern interrupts: [describe]
2.6 What They DON'T Do

Just as important as what they do:

  • Phrases they never use
  • Structures they avoid
  • Topics or approaches they skip
  • Formality levels they never hit

Document findings as:

## Avoidances
- Never uses: [list patterns]
- Never does: [list approaches]
- Avoids: [list topics/structures]

Phase 3: Synthesize the Voice Profile

Combine findings into a coherent voice description:

The Voice in One Paragraph

Write a single paragraph that captures the essence:

"[Name]'s voice is [primary characteristics]. They write like [relationship to reader], using [key techniques]. Their tone is [tone], with [humor style if applicable]. Sentences tend to be [structure]. They favor [word choice] and avoid [avoidances]. The overall effect is [feeling/impact]."

Example:

"Mike's voice is direct and confident, with an undercurrent of irreverent humor. He writes like a smart friend who's figured something out and can't wait to share it. His tone is casual but authoritative - he'll drop an f-bomb but back it up with data. Sentences are short and punchy, often fragments. He favors concrete specifics over vague claims and avoids corporate jargon entirely. The overall effect is someone talking straight to you, cutting through the BS."
The Voice Spectrum

Place the voice on these spectrums:

Formal ←――――――――――→ Casual         [1-5]
Expert ←――――――――――→ Peer           [1-5]
Serious ←―――――――――→ Playful        [1-5]
Reserved ←――――――――→ Opinionated    [1-5]
Abstract ←――――――――→ Concrete       [1-5]

Phase 4: Generate the Voice Skill

Create the output skill file with this structure:

---
name: voice-[author-name]
description: Write in [Author Name]'s distinctive voice. This style is [brief description]. Use with anti-ai-writing for content that authentically matches [Author]'s approach.
---

# Voice: [Author Name]

[One paragraph voice description from Phase 3]

## Voice Spectrum

- Formal/Casual: [1-5]
- Expert/Peer: [1-5]
- Serious/Playful: [1-5]
- Reserved/Opinionated: [1-5]
- Abstract/Concrete: [1-5]

## Core Characteristics

### Sentence Structure
[From Phase 2]

### Word Choice
[From Phase 2]

### Tone & Attitude
[From Phase 2]

### Structural Patterns
[From Phase 2]

### Distinctive Techniques
[From Phase 2]

### Avoidances
[From Phase 2]

## Example Patterns

### Signature Openings
[3-5 examples from samples with pattern explanation]

### Signature Transitions
[3-5 examples from samples]

### Signature Closings
[3-5 examples from samples]

### Signature Sentences
[5-10 exemplary sentences that capture the voice]

## The [Author] Test

Before publishing, ask:
- [ ] Would [Author] actually write this sentence?
- [ ] Does it match the voice spectrum above?
- [ ] Are signature patterns present?
- [ ] Are avoidances absent?
- [ ] Does it feel like [Author] talking?

## Anti-Patterns

If you see these, you've drifted from the voice:
- [List 5-10 patterns that would violate this voice]

Phase 5: Validate & Refine

Test the voice skill:

  1. Write a short piece using only the voice skill
  2. Compare to original samples
  3. Identify gaps or mischaracterizations
  4. Refine the skill based on testing

Validation checklist:

  • Voice description captures the essence
  • Spectrum ratings feel accurate
  • Example patterns are genuinely representative
  • Test output sounds like the samples
  • Nothing important was missed

Output Deliverable

Save the completed voice skill to:

voice-[author-name]/
├── SKILL.md         # The voice guide
└── references/
    └── samples.md   # Original samples for reference (optional)

Naming convention: Use lowercase, hyphenated names

  • voice-mike-caulfield
  • voice-brand-acme
  • voice-newsletter-weekly

Example Analysis Output

See references/example-analysis.md for a complete worked example showing:

  • Raw samples
  • Phase 2 analysis notes
  • Phase 3 synthesis
  • Phase 4 output skill

Tips for Better Analysis

More Samples = Better Results

  • 3 samples: Basic patterns only
  • 5 samples: Good pattern coverage
  • 10+ samples: Comprehensive voice capture

Same Context Matters

  • Analyze newsletters separately from tweets
  • Blog posts separate from documentation
  • Different contexts may need different voice skills

Look for Unconscious Patterns

  • Writers often don't know their own patterns
  • Count word frequency objectively
  • Note structures that repeat across all samples

Validate with the Source

  • If analyzing someone else's voice, have them review
  • Ask: "Does this sound like how you think about your writing?"
  • Refine based on feedback

Bundled Resources

  • references/example-analysis.md - Complete worked example
  • references/voice-template.md - Blank template for output skill
  • references/analysis-worksheet.md - Structured worksheet for Phase 2

Related Skills

  • anti-ai-writing - Core engine for humanization (use with voice skills)
  • voice-[style] - Example voice skills to reference
  • skill-creator - For creating other types of skills

*Run this analysis once per voice. The output skill can then be used indefinitely for consistent content in that voice.*

平台分布

Codex

36.29%
按下载量换算53

Claude

30.67%
按下载量换算44

Cursor

20.2%
按下载量换算29

Gemini CLI

8.85%
按下载量换算13

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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