| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 5 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 8 | | tagDensity | 0.625 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 92.52% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 2005 | | totalAiIsmAdverbs | 3 | | found | | | highlights | | 0 | "suddenly" | | 1 | "quickly" | | 2 | "softly" |
| |
| 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) | |
| 85.04% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 2005 | | totalAiIsms | 6 | | found | | | highlights | | 0 | "glint" | | 1 | "stomach" | | 2 | "footsteps" | | 3 | "echo" | | 4 | "rhythmic" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 1 | | maxInWindow | 1 | | found | | 0 | | label | "eyes widened/narrowed" | | count | 1 |
|
| | highlights | | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 157 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 1 | | narrationSentences | 157 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 160 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 42 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 2005 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 6 | | unquotedAttributions | 0 | | matches | (empty) | |
| 83.33% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 64 | | wordCount | 1975 | | uniqueNames | 19 | | maxNameDensity | 0.91 | | worstName | "Quinn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Herrera" | | discoveredNames | | London | 6 | | Soho | 2 | | Harlow | 1 | | Quinn | 18 | | Raven | 2 | | Nest | 3 | | Saint | 1 | | Christopher | 1 | | Herrera | 16 | | Morris | 4 | | Met | 1 | | Chinese | 1 | | Piccadilly | 1 | | Police | 1 | | Islington | 1 | | English | 1 | | Veil | 1 | | Market | 1 | | Tomás | 2 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Raven" | | 3 | "Nest" | | 4 | "Saint" | | 5 | "Christopher" | | 6 | "Herrera" | | 7 | "Morris" | | 8 | "Tomás" |
| | places | | 0 | "London" | | 1 | "Soho" | | 2 | "Piccadilly" | | 3 | "Islington" | | 4 | "English" | | 5 | "Market" |
| | globalScore | 1 | | windowScore | 0.833 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 125 | | glossingSentenceCount | 2 | | matches | | 0 | "appeared cornered turn suddenly agile" | | 1 | "looked like bone carved into the shape of" |
| |
| 0.50% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 4 | | per1kWords | 1.995 | | wordCount | 2005 | | matches | | 0 | "Not in his body, not with his breath, but with the same kind of wrongness" | | 1 | "not with his breath, but with the same kind of wrongness" | | 2 | "not for cover but for a route" | | 3 | "not keys but a token" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 160 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 45 | | mean | 44.56 | | std | 35.82 | | cv | 0.804 | | sampleLengths | | 0 | 101 | | 1 | 90 | | 2 | 2 | | 3 | 74 | | 4 | 76 | | 5 | 9 | | 6 | 21 | | 7 | 84 | | 8 | 60 | | 9 | 109 | | 10 | 25 | | 11 | 86 | | 12 | 3 | | 13 | 49 | | 14 | 3 | | 15 | 49 | | 16 | 43 | | 17 | 106 | | 18 | 55 | | 19 | 59 | | 20 | 70 | | 21 | 98 | | 22 | 8 | | 23 | 39 | | 24 | 102 | | 25 | 4 | | 26 | 7 | | 27 | 48 | | 28 | 4 | | 29 | 3 | | 30 | 10 | | 31 | 8 | | 32 | 11 | | 33 | 23 | | 34 | 67 | | 35 | 26 | | 36 | 106 | | 37 | 32 | | 38 | 5 | | 39 | 5 | | 40 | 13 | | 41 | 89 | | 42 | 74 | | 43 | 18 | | 44 | 31 |
| |
| 82.91% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 10 | | totalSentences | 157 | | matches | | 0 | "were won" | | 1 | "been chained" | | 2 | "been found" | | 3 | "been closed" | | 4 | "been buried" | | 5 | "been chosen" | | 6 | "been approved" | | 7 | "was gone" | | 8 | "been sealed" | | 9 | "been built" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 316 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 160 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1977 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 59 | | adverbRatio | 0.029843196762771876 | | lyAdverbCount | 19 | | lyAdverbRatio | 0.009610520991401113 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 160 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 160 | | mean | 12.53 | | std | 7.61 | | cv | 0.607 | | sampleLengths | | 0 | 22 | | 1 | 22 | | 2 | 19 | | 3 | 23 | | 4 | 15 | | 5 | 5 | | 6 | 16 | | 7 | 23 | | 8 | 14 | | 9 | 15 | | 10 | 17 | | 11 | 2 | | 12 | 10 | | 13 | 30 | | 14 | 7 | | 15 | 9 | | 16 | 18 | | 17 | 19 | | 18 | 13 | | 19 | 12 | | 20 | 32 | | 21 | 9 | | 22 | 10 | | 23 | 9 | | 24 | 2 | | 25 | 12 | | 26 | 26 | | 27 | 21 | | 28 | 13 | | 29 | 12 | | 30 | 16 | | 31 | 9 | | 32 | 11 | | 33 | 4 | | 34 | 20 | | 35 | 8 | | 36 | 12 | | 37 | 8 | | 38 | 11 | | 39 | 23 | | 40 | 7 | | 41 | 6 | | 42 | 34 | | 43 | 6 | | 44 | 19 | | 45 | 9 | | 46 | 22 | | 47 | 25 | | 48 | 23 | | 49 | 7 |
| |
| 36.25% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 22 | | diversityRatio | 0.29375 | | totalSentences | 160 | | uniqueOpeners | 47 | |
| 67.57% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 3 | | totalSentences | 148 | | matches | | 0 | "Then he turned and bolted" | | 1 | "Instead of moving aside, he" | | 2 | "Somewhere ahead, Tomás Herrera disappeared" |
| | ratio | 0.02 | |
| 82.16% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 51 | | totalSentences | 148 | | matches | | 0 | "He did not weave or" | | 1 | "He pulled his collar high," | | 2 | "His face was olive in" | | 3 | "He was not supposed to" | | 4 | "Her surveillance had been clean," | | 5 | "It was the only thing" | | 6 | "She got out of the" | | 7 | "His eyes widened, warm brown" | | 8 | "He went left through a" | | 9 | "She caught up, close enough" | | 10 | "He spun at the far" | | 11 | "It looked like calculation." | | 12 | "She had seen too many" | | 13 | "It had only been buried," | | 14 | "His jacket caught on a" | | 15 | "He shoved a stack of" | | 16 | "She cut across, drawing on" | | 17 | "Her voice came out low" | | 18 | "He ducked into the mouth" | | 19 | "She had been there before." |
| | ratio | 0.345 | |
| 30.95% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 127 | | totalSentences | 148 | | matches | | 0 | "Rain fell on London in" | | 1 | "Detective Harlow Quinn watched the" | | 2 | "The bar’s green sign buzzed" | | 3 | "The man moved with purpose." | | 4 | "He did not weave or" | | 5 | "He pulled his collar high," | | 6 | "His face was olive in" | | 7 | "A thin scar ran along" | | 8 | "He was not supposed to" | | 9 | "Her surveillance had been clean," | | 10 | "The clique had gathered there" | | 11 | "A meeting in the hidden" | | 12 | "Quinn touched the worn leather" | | 13 | "It was the only thing" | | 14 | "The gesture steadied her breath" | | 15 | "She got out of the" | | 16 | "Herrera saw her a dozen" | | 17 | "His eyes widened, warm brown" | | 18 | "Quinn followed, her boots striking" | | 19 | "Rain slapped her face and" |
| | ratio | 0.858 | |
| 67.57% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 148 | | matches | | 0 | "If she went through, she" | | 1 | "If she did not go" |
| | ratio | 0.014 | |
| 45.45% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 88 | | technicalSentenceCount | 12 | | matches | | 0 | "Detective Harlow Quinn watched the man leave the Raven’s Nest, his face half-turned as though he had heard something she had not." | | 1 | "Her surveillance had been clean, the kind of clean that made her uneasy, because people who were not guilty did not look over their shoulders with that kind of …" | | 2 | "Three years gone, and the file still sat in the back of her mind with the kind of neatness that made her sick." | | 3 | "The building owner had vanished, and the man she and Morris had been questioning had been found dead the next morning in a way that left the coroner silent and …" | | 4 | "She cut across, drawing on the discipline that had made her a terror in tactical units long before detectives preferred paper to pursuit." | | 5 | "A visible gun in the wrong place would turn a pursuit into a public incident, and incidents got files reassigned to people who had never seen the inside of a cr…" | | 6 | "A short passage cut through brickwork that looked too new for the surroundings, leading down another flight." | | 7 | "He was short, heavyset, and dressed in a dark coat that might have been expensive or merely theatrical." | | 8 | "A faint sound rose from beyond the gate, distant voices, the clink of metal, and a low, rhythmic hum that made Quinn’s teeth ache." | | 9 | "The first thing she saw was light, a pale green glow moving through a hidden corridor and then widening into a space that should have been impossible." | | 10 | "A woman with too many rings held up a bottle full of liquid that glimmered like a trapped eye." | | 11 | "Behind a stall with no price tags, a creature in a fur coat watched her with eyes that had no lids." |
| |
| 25.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 5 | | uselessAdditionCount | 1 | | matches | | 0 | "he said, as if that explained anything" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 5 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 8 | | tagDensity | 0.625 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |