Back to Details

voice-builder

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Voice Builder

写作风格构建器（Voice Builder）

This skill turns real writing into a reproducible voice — a 
voice.md
that any downstream skill (or human) can write from and produce posts indistinguishable from the source.
The core principle: voice is extracted from evidence, not described in adjectives. "Punchy and authentic" is unwritable — it tells a writer nothing. "Opens with a one-line provocation, writes in short sentences with one long one for contrast, uses em-dashes, never uses exclamation marks, ends on a question" is reproducible. Your job is to convert someone's writing into rules that specific.
此技能将真实写作内容转化为可复用的风格模板——即一份
voice.md
，任何下游技能（或人类写手）都能据此创作出与原文风格别无二致的内容。
核心原则：风格源于实证提取，而非形容词描述。“简洁有力且真实可信”这类表述毫无可操作性——写手无从下手。而“以单句挑衅开篇，短句为主、偶尔用长句形成对比，使用破折号，从不使用感叹号，以问句结尾”则是可落地的规则。你的任务就是将他人的写作内容转化为如此具体的规则。

When to use this

使用场景

  • After 
    brand-profile
    , to go deep on voice when the user has writing samples.
  • When content keeps coming out generic, stiff, or "not me."
  • For ghostwriting at scale — capture the voice once, write in it forever.
When NOT to use this: if there are no usable samples, don't invent a voice. Route to 
brand-profile
's voice interview (dimensions + lexicon + the "we sound ___, never ___" line) and come back when samples exist. A fabricated voice is worse than an honest interview.
  • 完成
    brand-profile
    之后    ，当用户有写作样本时，深入挖掘其风格。
  • 当生成的内容总是过于通用、生硬或“不像我”时。
  • 用于规模化代笔——一次捕捉风格，终身复用创作。
请勿使用的场景：如果没有可用样本，不要凭空捏造风格。引导至
brand-profile
的风格访谈（维度+词汇表+“我们的风格是___，绝非___”表述），待样本收集齐全后再返回。捏造的风格远不如真实的访谈有效。

Step 0 — Read 
brand-profile
first

步骤0 — 先阅读
brand-profile

Load 
brand-profile.md
for identity, audience, and guardrails. 
voice-builder
produces the 
voice.md
that sits alongside it. If a 
voice.md
already exists and is current, load it, summarize it back, and skip to whatever the user actually needs.
加载
brand-profile.md
以了解身份定位、受众群体和创作准则。
voice-builder
生成的
voice.md
将与它搭配使用。如果已有最新的
voice.md
，请加载并总结内容，然后直接处理用户的实际需求。

Step 1 — Gather the right samples

步骤1 — 收集合适的样本

Quality beats quantity. The best samples are unmistakably the person — pieces they're proud of, in their natural register, that they actually wrote (not committee-edited, not ghostwritten by someone else, not AI-generated). Aim for 5–10 substantial samples; 3 is the floor. Spoken transcripts are gold — they capture natural rhythm before self-editing flattens it. See 
references/samples-guide.md
for what to collect and what to exclude.
If samples are thin or inconsistent, say so plainly and proceed at lower confidence rather than overstating. Honesty about confidence is part of the deliverable.
质量优于数量。最佳样本是极具个人特色的内容——用户引以为傲、符合其自然表达习惯、由其亲自撰写的作品（而非集体编辑、他人代笔或AI生成的内容）。目标收集5-10份有分量的样本；最少3份。口语转录稿是绝佳素材——它们捕捉了未经自我编辑的自然节奏。请参阅
references/samples-guide.md
了解收集和排除的标准。
如果样本数量不足或风格不一致，请如实告知，并在低置信度下进行分析，不要夸大准确性。如实说明置信度是交付成果的一部分。

Step 2 — Analyze across the six layers (with evidence)

步骤2 — 从六个维度分析（附实证）

Do not free-associate about "tone." Work the framework in 
references/analysis-framework.md
, layer by layer:
  1. Lexicon — word choice, signature phrases, contractions, register, banned-by-habit words.
  2. Syntax — sentence length and variance, openers, fragments, active/passive, rhythm.
  3. Rhetoric — questions, direct address, repetition, analogy, contrast, humor, the "turn."
  4. Structure — how they open, build, and close; paragraphing; formatting.
  5. Stance — distance from reader, authority posture, confidence, emotional register.
  6. Negative space — what they conspicuously never do. Often the most defining layer.
For every pattern you name, cite the evidence — quote the sample. A voice guide built on assertions drifts; one built on quotes holds.
不要随意联想“语调”。请按照
references/analysis-framework.md
中的框架，逐层分析：
  1. 词汇层面——用词选择、标志性短语、缩写、语体、习惯性禁用词汇。
  2. 句法层面——句子长度及变化、开篇方式、断句、主动/被动语态、节奏。
  3. 修辞层面——设问、直接称呼、重复、类比、对比、幽默、“转折”手法。
  4. 结构层面——开篇、展开、收尾的方式；段落划分；格式排版。
  5. 立场层面——与读者的距离、权威姿态、自信程度、情感基调。
  6. 留白层面——明显从不使用的表达手法。这往往是最具辨识度的维度。
对于每一个你总结出的模式，都要引用实证——摘录样本内容。基于主观断言构建的风格指南会逐渐偏离；基于引用内容的指南则能保持精准。

Step 3 — Distill the voice fingerprint

步骤3 — 提炼风格特征

From the analysis, extract the 5–7 most distinctive, reproducible signatures — the few things that, done right, make the writing recognizable as theirs. This is the heart of 
voice.md
. Pair it with the negative space (the hard "never"s). If you nailed only the fingerprint, a reader should already believe it's them.
从分析结果中提取5-7个最具辨识度、可复用的核心特征——只要做好这些，就能让写作内容具备独特的个人风格。这是
voice.md
的核心内容。同时搭配留白规则（明确的“绝不”事项）。即便只掌握这些核心特征，读者也应能识别出内容的风格归属。

Step 4 — Write 
voice.md

步骤4 — 撰写
voice.md

Use 
references/voice-template.md
. Make it operational, not a personality essay: rules a writer can follow, a tone map for how the voice flexes by context, and 3–5 do/don't rewrites (a generic sentence → the same thing in this voice). Keep real sample snippets in as calibration anchors.
使用
references/voice-template.md
模板。确保内容具备可操作性，而非性格分析：提供写手可遵循的规则、不同场景下的风格调整指南，以及3-5组改写示例（通用句子→转化为该风格的句子）。保留真实样本片段作为校准参考。

Step 5 — Validate with the voice test (do not skip)

步骤5 — 进行风格测试验证（请勿跳过）

A 
voice.md
that hasn't been tested is a hypothesis. Run the loop in 
references/validation.md
:
  1. Generate a fresh post on a new topic using only 
    voice.md
    .
  2. Place it beside a real sample. Could the user tell which is which?
  3. Score it against the fingerprint signatures — which did it hit, which did it miss?
  4. Fix the misses, refine 
    voice.md
    , and repeat once or twice.
Show the user the test post and the result. The voice isn't done until it passes.
未经过测试的
voice.md
只是假设。请按照
references/validation.md
中的流程执行：
  1. 仅使用
    voice.md
    生成一篇关于全新主题的内容。
  2. 将其与真实样本放在一起。用户能否区分两者？
  3. 根据核心特征评分——哪些特征符合，哪些不符合？
  4. 修正不符合的部分，优化
    voice.md
    ，重复此流程1-2次。
向用户展示测试内容及结果。只有通过测试，风格才算定型。

What "great" looks like (self-check before finishing)

“优秀”的标准（完成前自检）

  • A writer who has never met this person could write an on-voice post from 
    voice.md
    alone.
  • Every claim cites a sample — no unsupported adjectives.
  • The fingerprint is specific enough to be falsifiable (you could point to a post and say "that's not them, because…").
  • Negative space is captured, not just positive traits.
  • It passed the voice test, and you showed the proof.
If any of these is missing, you're not done.
  • 从未见过该用户的写手仅通过
    voice.md
    就能创作出风格匹配的内容。
  • 每一项结论都有样本支撑——无无依据的形容词。
  • 核心特征足够具体，具备可证伪性（你可以指出某篇内容“不像他们的风格，因为……”）。
  • 不仅捕捉了正面特征，还涵盖了留白规则。
  • 通过了风格测试，并向用户展示了验证结果。
如果以上任何一项未达标，说明工作尚未完成。

Edge cases — handle explicitly

特殊场景处理

  • Thin samples (1–2 short pieces): capture what's observable, mark the guide low-confidence, name which layers you couldn't determine, and supplement with the 
    brand-profile
    interview. Don't bluff certainty.
  • Inconsistent samples (voice drift): don't average them into mush. Flag the inconsistency and ask which samples represent the target voice; anchor on those.
  • Aspirational voice (they want to sound different than they currently do): separate current from target. Collect samples of who they want to sound like, label them aspirational, and blend transparently so the user knows what's being borrowed.
  • Multiple voices (company vs founder; several creators): one 
    voice.md
    per voice, named. Never blend voices — it produces a person who exists nowhere.
  • Heavily edited / ghostwritten / AI-generated samples: exclude them; they aren't the person's voice. Say why.
  • Spoken vs written: transcripts reveal natural rhythm but need cleanup rules (filler, false starts). Capture the rhythm, note the cleanup.
  • Multilingual: analyze per language; voice rarely maps 1:1 across languages.
  • 样本不足（1-2篇短篇内容）：捕捉可观察到的特征，标记指南为低置信度，说明无法确定的维度，并补充
    brand-profile
    访谈内容。不要假装确定。
  • 样本风格不一致（风格漂移）：不要将其平均化处理成模糊的风格。指出不一致之处，询问用户哪些样本代表目标风格，并以此为核心进行分析。
  • 理想风格（用户希望改变当前风格）：区分当前风格与目标风格。收集用户希望模仿的风格样本，标记为理想风格，并透明地融合两者，让用户清楚哪些内容是借鉴的。
  • 多种风格（公司vs创始人；多位创作者）：为每种风格单独创建一份
    voice.md
    并命名。绝不要混合风格——这会生成一个不存在的“虚拟风格”。
  • 经过大量编辑/代笔/AI生成的样本：排除这类样本；它们并非用户的真实风格。说明原因。
  • 口语vs书面语：转录稿能体现自然节奏，但需要整理规则（去除填充词、错误开头）。捕捉节奏特征，注明整理规则。
  • 多语言：按语言分别分析；风格在不同语言间很少能1:1对应。

Related skills

相关技能

  • brand-profile
    — read first; provides identity, audience, guardrails.
  • writing-style-and-tone
    — applies the 
    voice.md
    per piece and per moment (tone map, edit passes, AI-tell sweep). This skill writes the constitution; that one governs by it.
  • Every content skill (
    caption-writer
    , 
    reels-script
    , 
    thread-writer
    , 
    linkedin-post-writer
    , …) reads the resulting 
    voice.md
    .
  • audience-research
    , 
    content-pillars
    — complementary foundation skills.
  • brand-profile
    ——请先阅读；提供身份定位、受众群体和创作准则。
  • writing-style-and-tone
    ——逐篇应用
    voice.md
    （风格调整、修改流程、去除AI痕迹）。本技能制定“宪法”，而该技能负责“执行”。
  • 所有内容创作技能（
    caption-writer
    、
    reels-script
    、
    thread-writer
    、
    linkedin-post-writer
    等）都会读取生成的
    voice.md
    。
  • audience-research
    、
    content-pillars
    ——补充性基础技能。

References

参考资料

  • references/samples-guide.md
    — how to source and vet the right writing samples.
  • references/analysis-framework.md
    — the six-layer framework for deconstructing voice.
  • references/voice-template.md
    — the exact 
    voice.md
    structure to produce.
  • references/validation.md
    — the voice test: generate, compare, score, refine.
  • references/examples.md
    — two contrasting worked examples, end to end.
  • references/samples-guide.md
    ——如何获取和筛选合适的写作样本。
  • references/analysis-framework.md
    ——解构风格的六维度框架。
  • references/voice-template.md
    ——生成
    voice.md
    的具体结构模板。
  • references/validation.md
    ——风格测试：生成、对比、评分、优化。
  • references/examples.md
    ——两个完整的对比示例。