| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 15 | | adverbTagCount | 1 | | adverbTags | | 0 | "A woman laughed somewhere [somewhere]" |
| | dialogueSentences | 59 | | tagDensity | 0.254 | | leniency | 0.508 | | rawRatio | 0.067 | | effectiveRatio | 0.034 | |
| 95.54% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 2240 | | totalAiIsmAdverbs | 2 | | found | | | highlights | | |
| 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) | |
| 84.38% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 2240 | | totalAiIsms | 7 | | found | | | highlights | | 0 | "measured" | | 1 | "footsteps" | | 2 | "velvet" | | 3 | "silence" | | 4 | "absolutely" |
| |
| 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 | 198 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 4 | | narrationSentences | 198 | | filterMatches | | | hedgeMatches | | 0 | "began to" | | 1 | "seem to" | | 2 | "appeared to" |
| |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 241 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 38 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 2238 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 20 | | unquotedAttributions | 0 | | matches | (empty) | |
| 83.13% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 62 | | wordCount | 1944 | | uniqueNames | 13 | | maxNameDensity | 1.34 | | worstName | "Quinn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Quinn" | | discoveredNames | | Quinn | 26 | | Camden | 2 | | Raven | 1 | | Nest | 1 | | Herrera | 19 | | Soho | 1 | | Metropolitan | 1 | | Police | 1 | | Saint | 2 | | Christopher | 2 | | Morris | 4 | | Officer | 1 | | Tube | 1 |
| | persons | | 0 | "Quinn" | | 1 | "Camden" | | 2 | "Raven" | | 3 | "Herrera" | | 4 | "Police" | | 5 | "Saint" | | 6 | "Christopher" | | 7 | "Morris" | | 8 | "Officer" |
| | places | | | globalScore | 0.831 | | windowScore | 0.833 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 139 | | glossingSentenceCount | 1 | | matches | | 0 | "seemed genuinely sorry" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 2238 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 2 | | totalSentences | 241 | | matches | | 0 | "seen that mark" | | 1 | "explained that some" |
| |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 134 | | mean | 16.7 | | std | 17.81 | | cv | 1.067 | | sampleLengths | | 0 | 9 | | 1 | 44 | | 2 | 6 | | 3 | 5 | | 4 | 83 | | 5 | 6 | | 6 | 5 | | 7 | 17 | | 8 | 7 | | 9 | 67 | | 10 | 52 | | 11 | 6 | | 12 | 3 | | 13 | 6 | | 14 | 42 | | 15 | 5 | | 16 | 10 | | 17 | 3 | | 18 | 10 | | 19 | 54 | | 20 | 11 | | 21 | 8 | | 22 | 32 | | 23 | 3 | | 24 | 38 | | 25 | 13 | | 26 | 8 | | 27 | 1 | | 28 | 5 | | 29 | 1 | | 30 | 18 | | 31 | 7 | | 32 | 23 | | 33 | 4 | | 34 | 69 | | 35 | 4 | | 36 | 28 | | 37 | 11 | | 38 | 4 | | 39 | 4 | | 40 | 2 | | 41 | 4 | | 42 | 8 | | 43 | 16 | | 44 | 41 | | 45 | 11 | | 46 | 4 | | 47 | 16 | | 48 | 4 | | 49 | 2 |
| |
| 98.17% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 4 | | totalSentences | 198 | | matches | | 0 | "was frightened" | | 1 | "been returned" | | 2 | "been scraped" | | 3 | "were fixed" |
| |
| 88.27% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 6 | | totalVerbs | 358 | | matches | | 0 | "was sprinting" | | 1 | "was going" | | 2 | "was arguing" | | 3 | "were not watching" | | 4 | "were lowering" | | 5 | "was doing" |
| |
| 95.44% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 2 | | semicolonCount | 2 | | flaggedSentences | 4 | | totalSentences | 241 | | ratio | 0.017 | | matches | | 0 | "Something swung at his throat—a Saint Christopher medallion, bright for an instant beneath a security lamp." | | 1 | "London’s muffled traffic faded after the first turn; by the third, Quinn could no longer hear the rain." | | 2 | "One carried a long iron bar; the other carried a folded canvas bag." | | 3 | "Cheekbones, mouth, eyes—each detail slid away as soon as she moved to the next." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1952 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 54 | | adverbRatio | 0.027663934426229508 | | lyAdverbCount | 16 | | lyAdverbRatio | 0.00819672131147541 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 241 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 241 | | mean | 9.29 | | std | 6.51 | | cv | 0.702 | | sampleLengths | | 0 | 9 | | 1 | 22 | | 2 | 22 | | 3 | 6 | | 4 | 5 | | 5 | 19 | | 6 | 36 | | 7 | 28 | | 8 | 3 | | 9 | 3 | | 10 | 3 | | 11 | 2 | | 12 | 3 | | 13 | 7 | | 14 | 7 | | 15 | 7 | | 16 | 8 | | 17 | 31 | | 18 | 7 | | 19 | 11 | | 20 | 10 | | 21 | 12 | | 22 | 13 | | 23 | 16 | | 24 | 11 | | 25 | 6 | | 26 | 3 | | 27 | 6 | | 28 | 10 | | 29 | 16 | | 30 | 16 | | 31 | 5 | | 32 | 5 | | 33 | 5 | | 34 | 3 | | 35 | 10 | | 36 | 9 | | 37 | 11 | | 38 | 20 | | 39 | 14 | | 40 | 11 | | 41 | 8 | | 42 | 6 | | 43 | 26 | | 44 | 3 | | 45 | 15 | | 46 | 12 | | 47 | 11 | | 48 | 3 | | 49 | 8 |
| |
| 59.20% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 9 | | diversityRatio | 0.3775933609958506 | | totalSentences | 241 | | uniqueOpeners | 91 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 6 | | totalSentences | 179 | | matches | | 0 | "Only a steel access door" | | 1 | "Then the stairwell opened, and" | | 2 | "Then she looked at the" | | 3 | "Somewhere deep in the tunnel," | | 4 | "Instead, he closed his medical" | | 5 | "Then Herrera switched on a" |
| | ratio | 0.034 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 50 | | totalSentences | 179 | | matches | | 0 | "She had sat at the" | | 1 | "She had followed his cab" | | 2 | "He went fast." | | 3 | "He glanced back." | | 4 | "His face was frightened, but" | | 5 | "She followed, past shuttered stalls" | | 6 | "She ran with military precision" | | 7 | "They looked for light, for" | | 8 | "He ran downhill." | | 9 | "He knew where he was" | | 10 | "She nearly had him at" | | 11 | "Her fingers closed on his" | | 12 | "It was not a threat." | | 13 | "He kicked open a side" | | 14 | "He did not seem to" | | 15 | "Her warrant card was already" | | 16 | "He looked at the card," | | 17 | "She put her face closer" | | 18 | "She had seen that mark" | | 19 | "It had occupied the final" |
| | ratio | 0.279 | |
| 91.28% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 132 | | totalSentences | 179 | | matches | | 0 | "Herrera ran before Quinn had" | | 1 | "The next he was sprinting" | | 2 | "Quinn swore and went after" | | 3 | "She had sat at the" | | 4 | "She had followed his cab" | | 5 | "He went fast." | | 6 | "He glanced back." | | 7 | "Rain streamed from his short," | | 8 | "His face was frightened, but" | | 9 | "That stung more than it" | | 10 | "A bus swept between them," | | 11 | "Quinn put a hand on" | | 12 | "Herrera cut left beneath a" | | 13 | "She followed, past shuttered stalls" | | 14 | "Camden’s neon broke apart in" | | 15 | "She ran with military precision" | | 16 | "They looked for light, for" | | 17 | "Herrera did none of those" | | 18 | "He ran downhill." | | 19 | "He knew where he was" |
| | ratio | 0.737 | |
| 83.80% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 3 | | totalSentences | 179 | | matches | | 0 | "Now she knew." | | 1 | "If he came out." | | 2 | "Now it showed no service." |
| | ratio | 0.017 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 89 | | technicalSentenceCount | 2 | | matches | | 0 | "Behind her lay the street: passing cars, lit windows, the clean procedural world of logged decisions and radios and officers who arrived when called." | | 1 | "For one second, Quinn saw the whole of her other life above her: wet streets, locked doors, forms completed in triplicate, a world that could be searched and en…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 15 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 14 | | fancyCount | 2 | | fancyTags | | 0 | "she shouted (shout)" | | 1 | "A woman laughed somewhere (laugh)" |
| | dialogueSentences | 59 | | tagDensity | 0.237 | | leniency | 0.475 | | rawRatio | 0.143 | | effectiveRatio | 0.068 | |