npx skills add https://github.com/jwynia/agent-skills --skill voice-analysis提取并记录作者的独特语音模式,以实现一致的复现。创建一个"语音指南",使得写作能够真实地模仿来源,而不是一个通用的近似。
捕捉精髓,而不仅仅是技巧。 目标是让来源作者说"是的,这就是我",而不是"我猜这很准确"。
巅峰语音 - 他们认为是"最像自己"的写作
非典型语音 - 不能很好代表他们的写作
不同语境:
重写练习: 提问:"用你的语音重写这个中性段落:"
"新政策将于下个月实施。它包括对当前程序的几项更改。员工应在截止日期前查阅文档并提交问题。"
打破规则: "你一贯忽略哪些写作'规则'?为什么?"
写作忌讳: "哪些写作选择会立即表明这不是你写的?"
演变: "你的写作在 5 年里发生了怎样的变化?哪些保持不变?"
| 模式 | 需要追踪的内容 |
|---|
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
| 平均长度 | 每句单词数 |
| 范围 | 最短到最长 |
| 片段句 | 使用频率、语境 |
| 连写句 | 倾向性、是否故意 |
| 开头模式 | 句子通常如何开始 |
| 结尾模式 | 句子通常如何结束 |
| 元素 | 需要追踪的内容 |
|---|---|
| 平均长度 | 每段句子数 |
| 主题句 | 开头、中间、结尾、缺失 |
| 过渡 | 显性词语、隐性流动、突兀 |
| 信息顺序 | 递进式、前置式、循环式 |
| 符号 | 追踪使用模式 |
|---|---|
| 长破折号 | 中断、强调、列表、旁白 |
| 括号 | 频率、内容类型 |
| 分号 | 使用、不使用、替代方式 |
| 省略号 | 结尾、停顿、省略 |
| 感叹号 | 频率、语境 |
| 反问句 | 频率、功能 |
| 类别 | 偏好 | 避免 | 特征性示例 |
|---|---|---|---|
| 技术术语 | |||
| 口语化表达 | |||
| 强调词 | very, extremely, quite... | ||
| 模糊限制语 | perhaps, might, seems... | ||
| 抽象/具体 |
列出出现 3 次以上的短语/模式:
| 来源域 | 目标域 | 示例 | 频率 |
|---|---|---|---|
| (战争、旅程、建筑...) | (想法、过程...) |
按 1-5 分评估普遍性:
| 低 | 中 | 高 |
|---|---|---|
| (含蓄) | (平衡) | (富有表现力) |
| 风格 | 使用时机 | 标志 |
|---|---|---|
| 直接 | "这是错误的,因为..." | |
| 外交辞令 | "一个考虑可能是..." | |
| 幽默 | "嗯,这也是一种方式..." | |
| 分析性 | "问题可以分解为..." |
作者将自己定位为:
用 2-3 句话捕捉精髓:
当一篇文章具备以下特点时,就捕捉到了这种语音:1. 2. 3.
当出现以下情况时,绝对不是这种语音:1. 2. 3.
在最终确定语音指南之前:
[单一段落精髓]
当写作变得普通时,添加:1. 2. 3.
语音指南完成后,在提示中包含相关部分,以引导生成真实的语音复现。
作者可以使用此框架来理解自己的语音,识别其写作的独特之处,并有意识地应用这些模式。
在编辑时使用语音指南作为检查清单,以确保一致性和真实性。
模式: 编目每一个语言特征,而不理解是什么让语音感觉独特。失败原因: 完美的词汇频率和句子长度清单可以产生技术上准确但感觉像模仿的写作。语音是整体,不是组件的总和。修正: 从"是什么让这种语音感觉如此?"开始。反向推导到技巧。清单服务于理解;理解不会从清单中单独产生。
模式: 从一种类型的写作中分析语音,然后将其应用于所有语境。失败原因: 作者在不同语境中会转换语音。技术写作语音不同于随意电子邮件语音。捕捉一种语境并强行应用于各处会产生不自然的痕迹。修正: 跨语境采样。映射语音如何转换。在语音指南中包含语境切换规则。理解哪些元素是恒定的,哪些是语境依赖的。
模式: 如果他们使用长破折号的比例是 8%,语音指南就规定使用 8% 的长破折号。失败原因: 频率是统计平均值,不是风格规则。强制频率会造成尴尬的放置。自然的作者不会计算标点符号。修正: 理解他们何时使用长破折号,而不是使用频率。"使用长破折号进行戏剧性插话,很少用于列表"是可操作的。"8% 的长破折号"则不是。
模式: 语音引导的写作感觉像某人在做模仿——技术上准确但过度表演。失败原因: 当孤立时,独特特征变成了怪癖。真实的语音平衡了独特和中性。只编目独特特征的指南会产生漫画效果。修正: 在独特特征旁边包含中性基线。大多数句子应该听起来自然,独特特征在适当的时刻出现,而不是持续不断。
模式: 将语音指南视为永久性的,不随作者的演变而更新。失败原因: 作者会改变。2020 年的语音指南可能不适合 2025 年的写作。使用过时的指南会产生感觉像作者旧版本的写作。修正: 注明捕获日期。计划定期更新。包含作者对自己语音如何演变的反思。将指南视为活的文档。
| 技能 | 提供的内容 |
|---|---|
| (写作样本) | 分析的原始材料 |
| prose-style | 用于分析的句子层面工艺框架 |
| 技能 | 此技能提供的内容 |
|---|---|
| prose-style | 特定语音的句子构建指导 |
| dialogue | 用于角色语音的语音模式 |
| (AI 生成) | 用于一致 AI 辅助写作的语音指南 |
| 技能 | 关系 |
|---|---|
| prose-style | 语音分析捕捉"是什么";prose-style 提供"如何做"。先使用语音分析来理解目标,然后使用 prose-style 来实现它 |
| dialogue | 语音分析用于作者语音;对话技能用于小说中的角色语音 |
每周安装量
123
代码仓库
GitHub 星标数
37
首次出现
2026 年 1 月 20 日
安全审计
安装于
opencode102
codex96
gemini-cli95
cursor94
claude-code91
github-copilot88
Extract and document a writer's distinctive voice patterns for consistent reproduction. Creates a "voice guide" that enables authentic writing that sounds like the source, not a generic approximation.
Capture spirit, not just mechanics. The goal is writing that makes the source say "yes, that's me" not "I guess that's accurate."
Peak Voice - Writing they identify as "most them"
Off-Voice - Writing that doesn't represent them well
Different Contexts:
Rewrite Exercise: Ask: "Rewrite this neutral paragraph in your voice:"
"The new policy will be implemented next month. It includes several changes to current procedures. Employees should review documentation and submit questions by the deadline."
Rule Breaking: "What writing 'rules' do you consistently ignore? Why?"
Pet Peeves: "What writing choices immediately signal something wasn't written by you?"
Evolution: "How has your writing changed in 5 years? What stayed constant?"
| Pattern | What to Track |
|---|---|
| Average length | Words per sentence |
| Range | Shortest to longest |
| Fragments | Usage frequency, contexts |
| Run-ons | Tendency, intentionality |
| Opening patterns | How sentences typically start |
| Closing patterns | How sentences typically end |
| Element | What to Track |
|---|---|
| Average length | Sentences per paragraph |
| Topic sentences | Beginning, middle, end, absent |
| Transitions | Explicit words, implicit flow, abrupt |
| Information order | Build-up, front-load, circular |
| Mark | Track Usage Pattern |
|---|---|
| Em dash | Interruption, emphasis, list, asides |
| Parentheses | Frequency, content type |
| Semicolon | Presence, absence, alternative |
| Ellipsis | Trailing, pause, omission |
| Exclamation | Frequency, contexts |
| Rhetorical questions | Frequency, function |
| Category | Preferred | Avoided | Signature Examples |
|---|---|---|---|
| Technical terms | |||
| Colloquialisms | |||
| Intensifiers | very, extremely, quite... | ||
| Hedging | perhaps, might, seems... | ||
| Abstract/concrete |
List phrases/patterns appearing 3+ times:
| Source Domain | Target Domain | Example | Frequency |
|---|---|---|---|
| (war, journey, building...) | (ideas, processes...) |
Rate 1-5 for prevalence:
| Low | Medium | High |
|---|---|---|
| (understated) | (balanced) | (expressive) |
| Style | When Used | Markers |
|---|---|---|
| Direct | "This is wrong because..." | |
| Diplomatic | "One consideration might be..." | |
| Humorous | "Well, that's one way to..." | |
| Analytical | "The issue breaks down to..." |
The writer positions as:
In 2-3 sentences, capture the essence:
A piece captures this voice when: 1. 2. 3.
Definitely NOT this voice when: 1. 2. 3.
Before finalizing the voice guide:
[Single paragraph essence]
When writing has gone generic, add: 1. 2. 3.
Once the voice guide is complete, include relevant sections in the prompt to guide generation toward authentic voice reproduction.
Writers can use this framework to understand their own voice, identify what makes their writing distinctive, and consciously apply those patterns.
Use the voice guide as a checklist when editing to ensure consistency and authenticity.
Pattern: Cataloging every linguistic feature without understanding what makes the voice feel distinctive. Why it fails: A perfect inventory of word frequencies and sentence lengths can produce writing that's technically accurate but feels like a parody. Voice is gestalt, not components. Fix: Start from "what makes this voice feel like this?" Work backward to mechanics. The inventory serves understanding; understanding doesn't emerge from inventory alone.
Pattern: Analyzing voice from one type of writing, then applying it to all contexts. Why it fails: Writers shift voice across contexts. Technical writing voice differs from casual email voice. Capturing one context and forcing it everywhere creates uncanny artifacts. Fix: Sample across contexts. Map how voice shifts. Include context-switching rules in the voice guide. Understand which elements are constant vs. context-dependent.
Pattern: If they use em-dashes 8% of the time, the voice guide prescribes 8% em-dash usage. Why it fails: Frequency is a statistical average, not a style rule. Forced frequency creates awkward placement. Natural writers don't count punctuation. Fix: Understand when they use em-dashes, not how often. "Uses em-dashes for dramatic interjections, rarely for lists" is actionable. "8% em-dashes" is not.
Pattern: Voice-guided writing that feels like someone doing an impression—technically accurate but overperformed. Why it fails: Distinctive features become tics when isolated. Real voice balances distinctive and neutral. Guides that catalog only distinctive features produce caricature. Fix: Include neutral baseline alongside distinctive features. Most sentences should sound natural, with distinctive features emerging at appropriate moments, not constantly.
Pattern: Treating the voice guide as permanent, not updating as the writer evolves. Why it fails: Writers change. A voice guide from 2020 may not fit 2025 writing. Using outdated guides produces writing that feels like an old version of the person. Fix: Note the capture date. Plan periodic updates. Include the writer's own reflections on how their voice has evolved. Treat the guide as living documentation.
| Skill | What it provides |
|---|---|
| (writing samples) | Raw material for analysis |
| prose-style | Sentence-level craft framework for analysis |
| Skill | What this provides |
|---|---|
| prose-style | Voice-specific sentence construction guidance |
| dialogue | Voice patterns for character speech |
| (AI generation) | Voice guides for consistent AI-assisted writing |
| Skill | Relationship |
|---|---|
| prose-style | Voice-analysis captures what; prose-style provides how. Use voice-analysis first to understand the target, then prose-style to achieve it |
| dialogue | Voice-analysis for authorial voice; dialogue skill for character voices within fiction |
Weekly Installs
123
Repository
GitHub Stars
37
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
opencode102
codex96
gemini-cli95
cursor94
claude-code91
github-copilot88
内容引擎:AI驱动的内容创作与多平台分发工具,实现高效内容再利用与原生适配
1,500 周安装