ane-voice

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ane Voice

A post-processing editor for prose. Audits AI-slop patterns and rewrites to the CLAUDE.md house style. Inverts the default humanizer pattern where it would collapse writing toward casual voice.

一款文稿后期编辑工具。审核AI冗余内容模式，并按照CLAUDE.md的内部风格重写文本。与常规人性化工具相反，不会将文本风格拉向随意化。

When to use

使用场景

Trigger when the user:

Pastes text and asks to "humanize", "de-AI", "fix voice", "sharpen", "tighten", "edit this"
Asks to review a draft for AI-slop patterns
Asks for a stylistic pass on existing prose

Do NOT trigger for:

New-document generation → route to

decision-memo

internal-comms

, or

doc-coauthoring

Citation enforcement alone → route to
```
mel-framework-citation
```
Summarisation or translation

当用户出现以下情况时触发：

粘贴文本并要求‘人性化处理’‘去AI化’‘调整语气’‘优化文本’‘精简内容’‘编辑此文本’
请求审阅草稿中的AI冗余内容模式
请求对现有文稿进行风格优化

请勿在以下场景触发：

新文档生成 → 转至

decision-memo

、

internal-comms

或

doc-coauthoring

工具

仅需规范引用格式 → 转至
```
mel-framework-citation
```
工具
摘要或翻译需求

Counter-behaviour (critical)

反向操作规则（关键）

This skill does NOT do what most public humanizers do. Specifically, do NOT:

Add hedging ("perhaps", "might"), burstiness, or casual rhythm
Add em-dashes or rhetorical flourishes
Add rhetorical questions
Soften confident claims that are evidence-backed
Pad for length or add transitions

If a public humanizer pattern would add any of the above, do the opposite.

此工具与大多数公开的人性化工具功能不同。尤其注意，请勿：

添加模糊表述（如“也许”“可能”）、突兀的节奏变化或随意语气
添加破折号或修辞修饰
添加反问句
弱化有证据支持的明确主张
为凑篇幅添加内容或过渡语句

如果常规人性化工具会添加上述内容，请执行相反操作。

Required inputs

必要输入

The text to edit (required)
Target register: internal memo, donor report, policy brief, research summary, email to external stakeholder (optional; default: donor-report register)
Permission to cut content that exists only as filler (default: yes)

待编辑文本（必填）
目标语体：内部备忘录、捐赠方报告、政策简报、研究摘要、致外部利益相关者的邮件（可选；默认：捐赠方报告语体）
是否允许删除仅作为冗余的内容（默认：是）

Eight-pass protocol

八步审核流程

Run passes in order. Show the audit first, then the rewrite.

按顺序执行审核步骤。先展示审核结果，再呈现重写后的文本。

Pass 1 — Kill nominalisations

第一步：消除名词化结构

Scan for nominalised verbs. Promote the verb, name the actor, drop the noun phrase.

AI pattern	Rewrite
make a decision	decide
provide support	support
conduct a review	review
ensure the implementation of	implement
reach an agreement	agree
take into consideration	consider
carry out an assessment	assess

扫描名词化动词。还原动词形式，明确主语，删除名词短语。

AI模式	改写后
make a decision	decide
provide support	support
conduct a review	review
ensure the implementation of	implement
reach an agreement	agree
take into consideration	consider
carry out an assessment	assess

Pass 2 — Cut filler

第二步：删除冗余内容

Remove and verify the sentence still parses. It will usually be shorter and clearer.

AI pattern	Rewrite
in order to	to
it should be noted that	delete; state directly
it is important to	delete
please be advised	delete
as per	under / according to
at this point in time	now
in the event that	if
due to the fact that	because
a number of	several (or the count)
plays a key role in	delete; state what it actually does

删除冗余内容后验证句子是否通顺。通常会更简短清晰。

AI模式	改写后
in order to	to
it should be noted that	删除；直接表述
it is important to	删除
please be advised	删除
as per	under / according to
at this point in time	now
in the event that	if
due to the fact that	because
a number of	several（或具体数字）
plays a key role in	删除；直接说明实际作用

Pass 3 — Flatten passive voice

第三步：转换被动语态

Scan for

was/were/has been/have been/will be + past participle

. If an actor exists or can be named, promote to subject.

"It was decided by the team..." → "The team decided..."
"Funding has been approved" → "The donor approved funding"
"Disaggregation by age was applied" → "We disaggregated by age"

Keep passive only when agent-neutrality is genuinely correct. In MEL work there is almost always a who.

扫描

was/were/has been/have been/will be + 过去分词

结构。如果存在或可以明确主语，将其提升为主语。

"It was decided by the team..." → "The team decided..."
"Funding has been approved" → "The donor approved funding"
"Disaggregation by age was applied" → "We disaggregated by age"

仅当确实需要保持主体中立时保留被动语态。在MEL工作中，几乎总能明确“谁”执行了动作。

Pass 4 — Split long sentences

第四步：拆分长句

Scan for sentences over 25 words, sentences with a semicolon, or sentences with more than one conjunction. Split. One idea per sentence.

扫描超过25个单词的句子、带有分号的句子或包含多个连词的句子。拆分句子，确保一句一义。

Pass 5 — Strip em-dashes

第五步：移除破折号

Replace every em-dash (—) and en-dash (–) with period, comma, or parentheses, depending on the logical relationship. Never preserve.

根据逻辑关系，将所有长破折号（—）和短破折号（–）替换为句号、逗号或括号。不得保留破折号。

Pass 6 — Audit hedging

第六步：审核模糊表述

Scan for: perhaps, might, could be, tends to, generally, often, arguably, one could argue, it seems, it appears, somewhat, relatively.

Decision rule:

Claim is evidence-backed → remove the hedge, state confidently.

Claim is genuinely uncertain → keep the hedge AND add

⚠️ Data gap: [claim] — [why confidence is limited] — [recommended source or test]

Default: most hedges are AI reflex. Test them.

扫描以下词汇：perhaps, might, could be, tends to, generally, often, arguably, one could argue, it seems, it appears, somewhat, relatively。

判断规则：

主张有证据支持 → 删除模糊表述，明确陈述。

主张确实存在不确定性 → 保留模糊表述，并添加

⚠️ 数据缺口：[主张] — [信心不足的原因] — [建议来源或测试方法]

。

默认规则：大多数模糊表述是AI的本能反应，需逐一验证。

Pass 7 — Replace abstract openings

第七步：替换抽象开头

Scan for paragraph openers like:

"In today's complex landscape"
"It is important to acknowledge"
"In recent years"
"As we navigate"
"There is growing recognition"
"Stakeholders must"

Replace with a direct claim or a concrete actor + action. The opening states the point; context follows.

扫描以下段落开头：

"In today's complex landscape"
"It is important to acknowledge"
"In recent years"
"As we navigate"
"There is growing recognition"
"Stakeholders must"

替换为直接主张或具体主语+动作。开头直接点明核心观点，背景信息后置。

Pass 8 — Verify citations

第八步：验证引用格式

Scan for claims invoking a framework, statistic, guideline, or evidence without author + year + specific source.

Claim uses Ane's standard framework list (from
```
mel-framework-citation
```
) → inject the full citation.

Claim uses another source → flag

⚠️ Citation missing: [claim] — needs source — [suggest library or web search]

Never leave "research shows", "experts agree", "studies suggest" unsourced.

扫描提及框架、统计数据、指南或证据但未标注作者+年份+具体来源的主张。

主张使用Ane的标准框架列表（来自
```
mel-framework-citation
```
）→ 补充完整引用信息。

主张使用其他来源 → 标记

⚠️ 引用缺失：[主张] — 需要补充来源 — [建议查阅图书馆或网络搜索]

。

不得保留“研究表明”“专家一致认为”“研究显示”等无来源表述。

Pattern catalog — AI-slop to flag

AI冗余内容模式清单

Distilled from public humanizer research (matsuikentaro1, Aboudjem, jpeggdev, blader, conorbronsdon, apoapostolov), filtered against CLAUDE.md rules. Keep only patterns that agree with Ane's style; drop those that would push toward casual voice.

基于公开人性化工具研究（matsuikentaro1, Aboudjem, jpeggdev, blader, conorbronsdon, apoapostolov）提炼，并根据CLAUDE.md规则筛选。仅保留符合Ane风格的模式；剔除会导致语气随意的模式。

Lexical tells

词汇特征

Empty superlatives: crucial, critical, vital, essential — replace with the specific consequence
Corporate abstractions: synergy, leverage, landscape, ecosystem, journey — replace with a specific noun
Hype words: game-changing, transformative, paradigm-shifting — delete or ground in cited evidence
Filler adjectives: robust, comprehensive, holistic, innovative — keep only when a concrete property is named
Weasel phrases: it is increasingly recognised that, there is growing consensus — needs citation or delete

空泛最高级：crucial, critical, vital, essential — 替换为具体后果
企业抽象词：synergy, leverage, landscape, ecosystem, journey — 替换为具体名词
夸张词汇：game-changing, transformative, paradigm-shifting — 删除或结合引用证据具体化
冗余形容词：robust, comprehensive, holistic, innovative — 仅当明确具体属性时保留
含糊表述：it is increasingly recognised that, there is growing consensus — 需要补充引用或删除

Structural tells

结构特征

Tricolons (three-item lists) pasted in for rhythm rather than content
Parallel structures padded beyond what the meaning needs
Headers phrased as questions
Bullet lists of complete sentences that could be prose
Nested bullets beyond one level

为营造节奏而非内容需求添加的三项式列表
超出表意需求的平行结构
以问句形式呈现的标题
可转换为普通文稿的完整句子式项目符号列表
嵌套层级超过一级的项目符号

Tonal tells

语气特征

"I hope this helps" and other performative softeners
"Feel free to" and similar permission grants
"Let me" statements explaining what is about to happen
Meta-commentary ("This document will explore...") instead of doing

“I hope this helps”及其他刻意软化语气的表述
“Feel free to”及类似许可表述
“Let me”等解释后续动作的语句
元评论（如“本文将探讨...”）而非直接表述内容

MEL-specific AI tells

MEL领域专属AI特征

Generic framework mentions without author and year ("using contribution analysis" without Mayne 2019)
Indicator lists without disaggregation specified
Gender references that do not say what the lens actually changed in the analysis
Donor-report language that conflates output, outcome, and impact
"Evidence-based" or "rights-based" used as labels without the specific evidence or rights framework named

提及通用框架但未标注作者和年份（如“使用贡献分析”但未标注Mayne 2019）
指标列表未明确分类标准
提及性别视角但未说明该视角对分析的具体改变
捐赠方报告语言混淆产出、成果和影响
将“循证”或“基于权利”作为标签使用，但未明确具体证据或权利框架

Output format

输出格式

Return in two parts:

分为两部分返回：

Audit

审核结果

A numbered list of issues found, grouped by pass. Each entry:

Location: the sentence or phrase in quotes
Pattern: name of the AI-slop pattern
Fix: what the rewrite will do

按步骤分组的编号问题列表。每条条目包含：

位置：引号标注的句子或短语
模式：AI冗余内容模式名称
修正方案：重写将采取的措施

Rewrite

重写文本

The full rewritten text. Use bold inline for phrases substantially changed, so Ane can scan the diff. Do not add commentary inside the rewrite itself.

Follow the two sections with a one-line Length delta:

Original N words → Rewrite M words (−X%)

Shorter is usually better. If the rewrite is longer than the original, explain why in one clause.

If any pass surfaced genuine uncertainty or missing citations, add a final Data and citation gaps section with

⚠️

entries.

完整的重写后文本。对大幅修改的短语使用加粗格式，以便Ane快速查看差异。重写文本内不得添加注释。

在两部分之后添加一行篇幅变化：

原文 N 词 → 重写后 M 词（−X%）

通常篇幅越短越好。如果重写后篇幅比原文长，请用一句话说明原因。

若任何步骤发现确实存在不确定性或引用缺失，添加最后一个数据与引用缺口部分，包含

⚠️

标记的条目。

Writing rules applied during rewrite

重写时遵循的写作规则

Every sentence you produce must:

Lead with the actor or the action
Use a specific verb, not a nominalisation
Fit under 25 words
Name who does what by when, if the content is actionable
Carry a source if the claim is evidential

生成的每一个句子必须：

以主语或动作开头
使用具体动词，而非名词化结构
字数不超过25词
若内容具有可操作性，明确说明谁在何时做什么
若主张基于证据，标注来源

Limitations

局限性

Does not fetch new sources. Flags gaps; Ane or
```
evidence-synthesis
```
closes them.
Does not translate between languages.
If the input is under 50 words, ask whether a full 8-pass audit is worth the overhead; a targeted pass often suffices.
If text already matches house style, say so and return it unchanged. Do not fabricate issues to justify running all eight passes.
Does not alter technical terminology that is correct in context even when it sounds AI-adjacent (e.g., "contribution analysis" is correct; replace only when the usage is wrong).

不会获取新来源。仅标记缺口；由Ane或
```
evidence-synthesis
```
工具补充。
不支持语言翻译。
若输入文本不足50词，询问是否值得进行完整的八步审核；针对性的单步审核通常已足够。
若文本已符合内部风格，直接说明并返回原文。不得编造问题以执行全部八步审核。
若技术术语在语境中使用正确，即使听起来类似AI生成内容也不得修改（例如，“contribution analysis”使用正确时无需替换；仅当使用错误时才修改）。