| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 2 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 13 | | tagDensity | 0.154 | | leniency | 0.308 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1331 | | totalAiIsmAdverbs | 0 | | found | (empty) | | highlights | (empty) | |
| 100.00% | AI-ism character names | Target: 0 AI-default names (17 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 100.00% | AI-ism location names | Target: 0 AI-default location names (33 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 47.41% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1331 | | totalAiIsms | 14 | | found | | | highlights | | 0 | "measured" | | 1 | "streaming" | | 2 | "shattered" | | 3 | "echo" | | 4 | "footsteps" | | 5 | "maw" | | 6 | "gloom" | | 7 | "intricate" | | 8 | "echoed" | | 9 | "depths" | | 10 | "velvet" | | 11 | "porcelain" | | 12 | "silk" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 0 | | maxInWindow | 0 | | found | (empty) | | highlights | (empty) | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 138 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 1 | | narrationSentences | 138 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 147 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 25 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1331 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 1 | | unquotedAttributions | 0 | | matches | (empty) | |
| 62.77% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 44 | | wordCount | 1261 | | uniqueNames | 18 | | maxNameDensity | 1.74 | | worstName | "Quinn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Quinn" | | discoveredNames | | Camden | 3 | | High | 1 | | Street | 1 | | Harlow | 1 | | Quinn | 22 | | Metropolitan | 1 | | Police | 1 | | Raven | 1 | | Nest | 1 | | Soho | 1 | | Deep | 1 | | Level | 1 | | Tube | 1 | | Veil | 2 | | Market | 2 | | London | 1 | | Morris | 2 | | Glock | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Police" | | 3 | "Raven" | | 4 | "Market" | | 5 | "Morris" |
| | places | | 0 | "Camden" | | 1 | "High" | | 2 | "Street" | | 3 | "Metropolitan" | | 4 | "Soho" | | 5 | "Deep" | | 6 | "London" |
| | globalScore | 0.628 | | windowScore | 0.833 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 103 | | glossingSentenceCount | 1 | | matches | | 0 | "sounded like grinding stones" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1331 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 147 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 55 | | mean | 24.2 | | std | 19.78 | | cv | 0.818 | | sampleLengths | | 0 | 50 | | 1 | 9 | | 2 | 45 | | 3 | 3 | | 4 | 20 | | 5 | 46 | | 6 | 35 | | 7 | 29 | | 8 | 4 | | 9 | 10 | | 10 | 36 | | 11 | 24 | | 12 | 17 | | 13 | 33 | | 14 | 3 | | 15 | 6 | | 16 | 76 | | 17 | 44 | | 18 | 28 | | 19 | 35 | | 20 | 23 | | 21 | 13 | | 22 | 17 | | 23 | 22 | | 24 | 13 | | 25 | 63 | | 26 | 3 | | 27 | 40 | | 28 | 6 | | 29 | 1 | | 30 | 25 | | 31 | 14 | | 32 | 27 | | 33 | 17 | | 34 | 15 | | 35 | 13 | | 36 | 36 | | 37 | 15 | | 38 | 68 | | 39 | 13 | | 40 | 15 | | 41 | 15 | | 42 | 29 | | 43 | 15 | | 44 | 9 | | 45 | 4 | | 46 | 20 | | 47 | 1 | | 48 | 15 | | 49 | 43 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 138 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 214 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 147 | | ratio | 0 | | matches | (empty) | |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1265 | | adjectiveStacks | 1 | | stackExamples | | 0 | "narrow, trash-strewn alley." |
| | adverbCount | 12 | | adverbRatio | 0.009486166007905139 | | lyAdverbCount | 3 | | lyAdverbRatio | 0.0023715415019762848 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 147 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 147 | | mean | 9.05 | | std | 4.96 | | cv | 0.547 | | sampleLengths | | 0 | 9 | | 1 | 17 | | 2 | 12 | | 3 | 12 | | 4 | 9 | | 5 | 7 | | 6 | 15 | | 7 | 10 | | 8 | 4 | | 9 | 9 | | 10 | 3 | | 11 | 4 | | 12 | 7 | | 13 | 9 | | 14 | 12 | | 15 | 23 | | 16 | 9 | | 17 | 2 | | 18 | 11 | | 19 | 11 | | 20 | 13 | | 21 | 4 | | 22 | 5 | | 23 | 8 | | 24 | 12 | | 25 | 4 | | 26 | 10 | | 27 | 2 | | 28 | 9 | | 29 | 3 | | 30 | 6 | | 31 | 16 | | 32 | 5 | | 33 | 3 | | 34 | 16 | | 35 | 4 | | 36 | 3 | | 37 | 10 | | 38 | 20 | | 39 | 10 | | 40 | 3 | | 41 | 3 | | 42 | 6 | | 43 | 4 | | 44 | 8 | | 45 | 4 | | 46 | 22 | | 47 | 6 | | 48 | 6 | | 49 | 15 |
| |
| 41.16% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 13 | | diversityRatio | 0.2789115646258503 | | totalSentences | 147 | | uniqueOpeners | 41 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 136 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 35 | | totalSentences | 136 | | matches | | 0 | "She closed the distance on" | | 1 | "Her closely cropped salt-and-pepper hair" | | 2 | "She checked the worn leather" | | 3 | "He sped up, his trainers" | | 4 | "She had tailed this man" | | 5 | "He thought the rain would" | | 6 | "Her fingers grazed the damp" | | 7 | "He kicked out." | | 8 | "His heel connected with her" | | 9 | "He twisted, tearing his jacket." | | 10 | "He tumbled down the other" | | 11 | "Her muscles burned." | | 12 | "She dropped to the other" | | 13 | "He disappeared into the subterranean" | | 14 | "She descended the stairs." | | 15 | "Her breathing slowed." | | 16 | "She regulated her heart rate," | | 17 | "He held a heavy iron" | | 18 | "She watched from the gloom." | | 19 | "He pulled out a small," |
| | ratio | 0.257 | |
| 0.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 126 | | totalSentences | 136 | | matches | | 0 | "Rain lashed the cracked pavement" | | 1 | "Detective Harlow Quinn pumped her" | | 2 | "She closed the distance on" | | 3 | "The suspect vaulted a stack" | | 4 | "Quinn cleared the obstacle without" | | 5 | "Her closely cropped salt-and-pepper hair" | | 6 | "She checked the worn leather" | | 7 | "The streets belonged to the" | | 8 | "The figure glanced back." | | 9 | "A pale face flashed beneath" | | 10 | "He sped up, his trainers" | | 11 | "Quinn pushed off her back" | | 12 | "She had tailed this man" | | 13 | "He thought the rain would" | | 14 | "The suspect hooked a sharp" | | 15 | "Puddles shattered under his soles," | | 16 | "A stray cat hissed from" | | 17 | "Quinn rounded the corner." | | 18 | "Brick walls boxed them in." | | 19 | "A rusted iron gate blocked" |
| | ratio | 0.926 | |
| 36.76% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 136 | | matches | | 0 | "Before he could double over," |
| | ratio | 0.007 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 57 | | technicalSentenceCount | 3 | | matches | | 0 | "Voices chattered in a dozen languages, some of them clicking and guttural, others whispering in a cadence that made Quinn's teeth ache." | | 1 | "The market sold banned alchemical substances, enchanted trinkets, and secrets that could topple governments." | | 2 | "Eyes with slit pupils, faces obscured by porcelain masks, and beings that defied anatomy all stared at the lone detective in the soaked trench coat." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 2 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |