| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 7 | | adverbTagCount | 1 | | adverbTags | | 0 | "Tomás said quickly [quickly]" |
| | dialogueSentences | 26 | | tagDensity | 0.269 | | leniency | 0.538 | | rawRatio | 0.143 | | effectiveRatio | 0.077 | |
| 91.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1111 | | 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) | |
| 45.99% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1111 | | totalAiIsms | 12 | | found | | | highlights | | 0 | "weight" | | 1 | "jaw clenched" | | 2 | "gloom" | | 3 | "depths" | | 4 | "pulse" | | 5 | "perfect" | | 6 | "velvet" | | 7 | "scanned" | | 8 | "silk" | | 9 | "stark" | | 10 | "reminder" | | 11 | "standard" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 1 | | maxInWindow | 1 | | found | | 0 | | label | "jaw/fists clenched" | | count | 1 |
|
| | highlights | | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 84 | | matches | (empty) | |
| 91.84% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 1 | | narrationSentences | 84 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 102 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 30 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1111 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 4 | | unquotedAttributions | 0 | | matches | (empty) | |
| 66.67% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 38 | | wordCount | 898 | | uniqueNames | 16 | | maxNameDensity | 1.34 | | worstName | "Quinn" | | maxWindowNameDensity | 3 | | worstWindowName | "Tomás" | | discoveredNames | | Tomás | 10 | | Herrera | 1 | | Harlow | 1 | | Quinn | 12 | | Saint | 1 | | Christopher | 1 | | Camden | 2 | | Deep | 1 | | Shelter | 1 | | Northern | 1 | | Line | 1 | | Victorian | 1 | | Shoreditch | 1 | | Spanish | 2 | | Veil | 1 | | Market | 1 |
| | persons | | 0 | "Tomás" | | 1 | "Herrera" | | 2 | "Harlow" | | 3 | "Quinn" | | 4 | "Saint" | | 5 | "Christopher" | | 6 | "Victorian" | | 7 | "Market" |
| | places | | | globalScore | 0.832 | | windowScore | 0.667 | |
| 78.57% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 70 | | glossingSentenceCount | 2 | | matches | | 0 | "ink that seemed to pulse in her torchlight, smeared the masonry" | | 1 | "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 | 1111 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 102 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 44 | | mean | 25.25 | | std | 24.2 | | cv | 0.959 | | sampleLengths | | 0 | 77 | | 1 | 2 | | 2 | 32 | | 3 | 58 | | 4 | 30 | | 5 | 6 | | 6 | 50 | | 7 | 17 | | 8 | 82 | | 9 | 30 | | 10 | 4 | | 11 | 37 | | 12 | 20 | | 13 | 6 | | 14 | 121 | | 15 | 6 | | 16 | 33 | | 17 | 2 | | 18 | 64 | | 19 | 12 | | 20 | 24 | | 21 | 8 | | 22 | 11 | | 23 | 10 | | 24 | 10 | | 25 | 32 | | 26 | 14 | | 27 | 4 | | 28 | 34 | | 29 | 37 | | 30 | 4 | | 31 | 22 | | 32 | 6 | | 33 | 9 | | 34 | 8 | | 35 | 34 | | 36 | 18 | | 37 | 33 | | 38 | 10 | | 39 | 8 | | 40 | 18 | | 41 | 8 | | 42 | 29 | | 43 | 31 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 84 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 142 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 102 | | ratio | 0 | | matches | (empty) | |
| 76.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 907 | | adjectiveStacks | 4 | | stackExamples | | 0 | "burly, scar-faced man" | | 1 | "perfect small antique white bone" | | 2 | "magnificent large antique bronze incense" | | 3 | "gorgeous small old square" |
| | adverbCount | 10 | | adverbRatio | 0.011025358324145534 | | lyAdverbCount | 5 | | lyAdverbRatio | 0.005512679162072767 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 102 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 102 | | mean | 10.89 | | std | 6.01 | | cv | 0.552 | | sampleLengths | | 0 | 14 | | 1 | 8 | | 2 | 24 | | 3 | 22 | | 4 | 9 | | 5 | 2 | | 6 | 5 | | 7 | 7 | | 8 | 20 | | 9 | 10 | | 10 | 12 | | 11 | 18 | | 12 | 6 | | 13 | 12 | | 14 | 8 | | 15 | 4 | | 16 | 18 | | 17 | 6 | | 18 | 4 | | 19 | 9 | | 20 | 4 | | 21 | 15 | | 22 | 7 | | 23 | 6 | | 24 | 5 | | 25 | 6 | | 26 | 11 | | 27 | 5 | | 28 | 13 | | 29 | 16 | | 30 | 8 | | 31 | 13 | | 32 | 10 | | 33 | 17 | | 34 | 15 | | 35 | 7 | | 36 | 8 | | 37 | 4 | | 38 | 6 | | 39 | 23 | | 40 | 8 | | 41 | 10 | | 42 | 10 | | 43 | 6 | | 44 | 8 | | 45 | 16 | | 46 | 18 | | 47 | 9 | | 48 | 18 | | 49 | 15 |
| |
| 66.99% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 5 | | diversityRatio | 0.43137254901960786 | | totalSentences | 102 | | uniqueOpeners | 44 | |
| 81.30% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 82 | | matches | | 0 | "Suddenly, he veered left." | | 1 | "Downward stairs vanished into pitch" |
| | ratio | 0.024 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 24 | | totalSentences | 82 | | matches | | 0 | "She cleared a pile of" | | 1 | "She kept her brown eyes" | | 2 | "He zigzagged, darting into a" | | 3 | "His Saint Christopher medallion gleamed" | | 4 | "She landed hard on her" | | 5 | "He ripped open a rusted" | | 6 | "She grasped the bars." | | 7 | "Her watch let out a" | | 8 | "She pushed the heavy metal" | | 9 | "It shrieked on ancient hinges." | | 10 | "She reached into her coat," | | 11 | "He stood beside a rusty" | | 12 | "He looked at her with" | | 13 | "She reached into her pocket" | | 14 | "She laid the bone token" | | 15 | "He stepped aside, his movements" | | 16 | "She pushed through the creaking" | | 17 | "Her military bearing made her" | | 18 | "She scanned the crowd." | | 19 | "He stood near a stall" |
| | ratio | 0.293 | |
| 27.07% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 71 | | totalSentences | 82 | | matches | | 0 | "The heels of Tomás Herrera's" | | 1 | "Detective Harlow Quinn did not" | | 2 | "She cleared a pile of" | | 3 | "She kept her brown eyes" | | 4 | "Tomás did not look back." | | 5 | "He zigzagged, darting into a" | | 6 | "His Saint Christopher medallion gleamed" | | 7 | "Quinn rounded the corner, her" | | 8 | "The scent of bin bags" | | 9 | "A heavy black iron fire" | | 10 | "Quinn followed, her sharp jaw" | | 11 | "She landed hard on her" | | 12 | "He ripped open a rusted" | | 13 | "The gate clanged shut behind" | | 14 | "Quinn reached the gate." | | 15 | "She grasped the bars." | | 16 | "The padlock hung open, bypassed" | | 17 | "Her watch let out a" | | 18 | "She pushed the heavy metal" | | 19 | "It shrieked on ancient hinges." |
| | ratio | 0.866 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 82 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 42 | | technicalSentenceCount | 1 | | matches | | 0 | "Strange people, some wearing velvet masks that twitched as if they were alive, shuffled between makeshift wooden stalls." |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 7 | | uselessAdditionCount | 2 | | matches | | 0 | "Tomás hissed, his Spanish accent thickening under the stress" | | 1 | "Tomás whispered, his face losing its colour" |
| |
| 0.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 5 | | fancyCount | 4 | | fancyTags | | 0 | "the man grunted (grunt)" | | 1 | "Tomás hissed (hiss)" | | 2 | "Tomás whispered (whisper)" | | 3 | "the enforcer barked (bark)" |
| | dialogueSentences | 26 | | tagDensity | 0.192 | | leniency | 0.385 | | rawRatio | 0.8 | | effectiveRatio | 0.308 | |