slop-detector

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AI Slop Detection

AI冗余文本检测

AI slop is identified by patterns of usage rather than individual words. While a single "delve" might be acceptable, its proximity to markers like "tapestry" or "embark" signals generated text. We analyze the density of these markers per 100 words, their clustering, and whether the overall tone fits the document type.

AI冗余文本是通过使用模式而非单个词汇来识别的。虽然单独使用一次“delve”可能是可接受的，但如果它与“tapestry”或“embark”这类特征词汇同时出现，就表明文本是AI生成的。我们会分析每100个单词中这些特征词汇的密度、它们的聚集情况，以及整体语气是否符合文档类型。

Execution Workflow

执行流程

Start by identifying target files and classifying them as technical docs, narrative prose, or code comments. This allows for context-aware scoring during analysis.

首先确定目标文件，并将其分类为技术文档、叙事散文或代码注释。这能让我们在分析时结合上下文进行评分。

Vocabulary and Phrase Detection

词汇与短语检测

Load:

@modules/vocabulary-patterns.md

We categorize markers into three tiers based on confidence. Tier 1 words appear dramatically more often in AI text and include "delve," "multifaceted," and "leverage." Tier 2 covers context-dependent transitions like "moreover" or "subsequently," while Tier 3 identifies vapid phrases such as "In today's fast-paced world" or "cannot be overstated."

Word	Context	Human Alternative
delve	"delve into"	explore, examine, look at
tapestry	"rich tapestry"	mix, combination, variety
realm	"in the realm of"	in, within, regarding
embark	"embark on a journey"	start, begin
beacon	"a beacon of"	example, model
spearheaded	formal attribution	led, started
multifaceted	describing complexity	complex, varied
comprehensive	describing scope	thorough, complete
pivotal	importance marker	key, important
nuanced	sophistication signal	subtle, detailed
meticulous/meticulously	care marker	careful, detailed
intricate	complexity marker	detailed, complex
showcasing	display verb	showing, displaying
leveraging	business jargon	using
streamline	optimization verb	simplify, improve

加载：

@modules/vocabulary-patterns.md

我们根据置信度将特征标记分为三个等级。Tier 1词汇在AI文本中的出现频率显著更高，包括“delve”“multifaceted”和“leverage”。Tier 2涵盖依赖上下文的过渡词，如“moreover”或“subsequently”，而Tier 3则识别空洞短语，例如“In today's fast-paced world”或“cannot be overstated”。

词汇	语境	人类替代表达
delve	"delve into"	explore, examine, look at
tapestry	"rich tapestry"	mix, combination, variety
realm	"in the realm of"	in, within, regarding
embark	"embark on a journey"	start, begin
beacon	"a beacon of"	example, model
spearheaded	正式归因表达	led, started
multifaceted	描述复杂性	complex, varied
comprehensive	描述范围	thorough, complete
pivotal	重要性标记	key, important
nuanced	复杂度信号	subtle, detailed
meticulous/meticulously	细致度标记	careful, detailed
intricate	复杂度标记	detailed, complex
showcasing	展示类动词	showing, displaying
leveraging	商业术语	using
streamline	优化类动词	simplify, improve

Tier 2: Medium-Confidence Markers (Score: 2 each)

Tier 2：中等置信度标记（分值：每个2分）

Common but context-dependent:

Category	Words
Transition overuse	moreover, furthermore, indeed, notably, subsequently
Intensity clustering	significantly, substantially, fundamentally, profoundly
Hedging stacks	potentially, typically, often, might, perhaps
Action inflation	revolutionize, transform, unlock, unleash, elevate
Empty emphasis	crucial, vital, essential, paramount

常见但依赖语境：

类别	词汇
过渡词滥用	moreover, furthermore, indeed, notably, subsequently
强度词汇聚集	significantly, substantially, fundamentally, profoundly
模糊表达堆叠	potentially, typically, often, might, perhaps
夸大动作表达	revolutionize, transform, unlock, unleash, elevate
空洞强调词	crucial, vital, essential, paramount

Tier 3: Phrase Patterns (Score: 2-4 each)

Tier 3：短语模式（分值：每个2-4分）

Phrase	Score	Issue
"In today's fast-paced world"	4	Vapid opener
"It's worth noting that"	3	Filler
"At its core"	2	Positional crutch
"Cannot be overstated"	3	Empty emphasis
"A testament to"	3	Attribution cliche
"Navigate the complexities"	4	Business speak
"Unlock the potential"	4	Marketing speak
"Treasure trove of"	3	Overused metaphor
"Game changer"	3	Buzzword
"Look no further"	4	Sales pitch
"Nestled in the heart of"	4	Travel writing cliche
"Embark on a journey"	4	Melodrama
"Ever-evolving landscape"	4	Tech cliche
"Hustle and bustle"	3	Filler

短语	分值	问题
"In today's fast-paced world"	4	空洞开篇
"It's worth noting that"	3	填充内容
"At its core"	2	位置类套话
"Cannot be overstated"	3	空洞强调
"A testament to"	3	归因类陈词滥调
"Navigate the complexities"	4	商务套话
"Unlock the potential"	4	营销类套话
"Treasure trove of"	3	过度使用的比喻
"Game changer"	3	流行术语
"Look no further"	4	销售话术
"Nestled in the heart of"	4	旅行写作类陈词滥调
"Embark on a journey"	4	夸张表达
"Ever-evolving landscape"	4	科技类陈词滥调
"Hustle and bustle"	3	填充内容

Step 3: Structural Pattern Detection

第三步：结构模式检测

Load:

@modules/structural-patterns.md

加载：

@modules/structural-patterns.md

Em Dash Overuse

破折号滥用

Count em dashes (—) per 1000 words:

0-2: Normal human range
3-5: Elevated, review usage
6+: Strong AI signal

bash

undefined

统计每1000个单词中的破折号（—）数量：

0-2个：正常人类写作范围
3-5个：数量偏高，需检查使用方式
6个及以上：强烈的AI生成信号

bash

undefined

Count em dashes in file

grep -o '—' file.md | wc -l

undefined

grep -o '—' file.md | wc -l

undefined

Tricolon Detection

三形容词排比检测

AI loves groups of three with alliteration:

"fast, efficient, and reliable"
"clear, concise, and compelling"
"robust, reliable, and resilient"

Pattern:

adjective, adjective, and adjective

with similar sounds.

AI偏爱押头韵的三词组合：

"fast, efficient, and reliable"
"clear, concise, and compelling"
"robust, reliable, and resilient"

模式：

形容词, 形容词, and 形容词

且发音相近。

List-to-Prose Ratio

列表与散文占比

Count bullet points vs paragraph sentences:

>60% bullets: AI tendency
Emoji-led bullets: Strong AI signal in technical docs

统计项目符号与段落句子的比例：

项目符号占比>60%：AI写作倾向
表情符号引导的项目符号：技术文档中强烈的AI生成信号

Sentence Length Uniformity

句子长度一致性

Measure standard deviation of sentence lengths:

Low variance (SD < 5 words): AI monotony
High variance (SD > 10 words): Human variation

测量句子长度的标准差：

低方差（标准差<5个单词）：AI写作的单调性
高方差（标准差>10个单词）：人类写作的多样性

Paragraph Symmetry

段落对称性

AI produces "blocky" text with uniform paragraph lengths. Check if paragraphs cluster around the same word count.

AI会生成“块状”文本，段落长度均匀。检查段落是否聚集在相同的单词数附近。

Step 4: Sycophantic Pattern Detection

第四步：谄媚模式检测

Especially relevant for conversational or instructional content:

Phrase	Issue
"I'd be happy to"	Servile opener
"Great question!"	Empty validation
"Absolutely!"	Over-agreement
"That's a wonderful point"	Flattery
"I'm glad you asked"	Filler
"You're absolutely right"	Sycophancy

These phrases add no information and signal generated content.

在对话式或指导性内容中尤为常见：

短语	问题
"I'd be happy to"	过度客套的开篇
"Great question!"	空洞的肯定
"Absolutely!"	过度赞同
"That's a wonderful point"	奉承表达
"I'm glad you asked"	填充内容
"You're absolutely right"	谄媚表达

这些短语没有实际信息，是AI生成内容的信号。

Step 5: Calculate Slop Density Score

第五步：计算冗余内容密度得分

slop_score = (tier1_count * 3 + tier2_count * 2 + phrase_count * avg_phrase_score) / word_count * 100

Score	Rating	Action
0-1.0	Clean	No action needed
1.0-2.5	Light	Spot remediation
2.5-5.0	Moderate	Section rewrite recommended
5.0+	Heavy	Full document review

slop_score = (tier1_count * 3 + tier2_count * 2 + phrase_count * avg_phrase_score) / word_count * 100

得分	评级	操作建议
0-1.0	无冗余	无需操作
1.0-2.5	轻度冗余	局部修正
2.5-5.0	中度冗余	建议重写对应章节
5.0+	重度冗余	需全面审核文档

Step 6: Generate Report

第六步：生成报告

Output format:

markdown

undefined

输出格式：

markdown

undefined

Slop Detection Report: [filename]

Overall Score: X.X / 10 (Rating) Word Count: N words Markers Found: N total

High-Confidence Markers

Line 23: "delve into" -> consider: "explore"
Line 45: "rich tapestry" -> consider: "variety"

Line 23: "delve into" -> consider: "explore"
Line 45: "rich tapestry" -> consider: "variety"

Structural Issues

Em dash density: 8/1000 words (HIGH)
Bullet ratio: 72% (ELEVATED)
Sentence length SD: 3.2 words (LOW VARIANCE)

Em dash density: 8/1000 words (HIGH)
Bullet ratio: 72% (ELEVATED)
Sentence length SD: 3.2 words (LOW VARIANCE)

Phrase Patterns

Line 12: "In today's fast-paced world" (vapid opener)
Line 89: "cannot be overstated" (empty emphasis)

Line 12: "In today's fast-paced world" (vapid opener)
Line 89: "cannot be overstated" (empty emphasis)

Recommendations

Replace [specific word] with [alternative]
Convert bullet list at line 34-56 to prose
Vary sentence structure in paragraphs 3-5

undefined

Replace [specific word] with [alternative]
Convert bullet list at line 34-56 to prose
Vary sentence structure in paragraphs 3-5

undefined

Module Reference

模块参考

See
```
modules/fiction-patterns.md
```
for narrative-specific slop markers
See
```
modules/remediation-strategies.md
```
for fix recommendations

查看
```
modules/fiction-patterns.md
```
获取叙事类文本的冗余特征标记
查看
```
modules/remediation-strategies.md
```
获取修复建议

Integration with Remediation

与修复流程集成

After detection, invoke

Skill(scribe:doc-generator)

with

--remediate

flag to apply fixes, or manually edit using the report as a guide.

检测完成后，调用

Skill(scribe:doc-generator)

并添加

--remediate

参数来应用修复，或根据报告手动编辑内容。

Exit Criteria

退出标准

All target files scanned
Density scores calculated
Report generated with actionable recommendations
High-severity items flagged for immediate attention

所有目标文件已扫描
已计算密度得分
已生成包含可操作建议的报告
高优先级问题已标记为需立即处理