| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 6 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 19 | | tagDensity | 0.316 | | leniency | 0.632 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1188 | | 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) | |
| 49.49% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1188 | | totalAiIsms | 12 | | found | | | highlights | | 0 | "footsteps" | | 1 | "echoed" | | 2 | "could feel" | | 3 | "chill" | | 4 | "glinting" | | 5 | "flicked" | | 6 | "shimmered" | | 7 | "flickered" | | 8 | "depths" | | 9 | "rhythmic" |
| |
| 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 | 119 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 1 | | narrationSentences | 119 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 131 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 27 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1188 | | ratio | 0 | | matches | (empty) | |
| 75.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 5 | | unquotedAttributions | 1 | | matches | | 0 | "Natural causes, they said." |
| |
| 73.81% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 23 | | wordCount | 1050 | | uniqueNames | 8 | | maxNameDensity | 1.52 | | worstName | "Harlow" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Harlow" | | discoveredNames | | Wardour | 1 | | Street | 1 | | Harlow | 16 | | Quinn | 1 | | Camden | 1 | | London | 1 | | Underground | 1 | | Morris | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Camden" | | 3 | "Morris" |
| | places | | 0 | "Wardour" | | 1 | "Street" | | 2 | "London" |
| | globalScore | 0.738 | | windowScore | 0.833 | |
| 0.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 74 | | glossingSentenceCount | 5 | | matches | | 0 | "looked like human teeth arranged in neat" | | 1 | "looked like black feathers, and her eyes" | | 2 | "as if listening to something far away" | | 3 | "looked like fingerprints" | | 4 | "looked like human hair" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1188 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 131 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 51 | | mean | 23.29 | | std | 18.52 | | cv | 0.795 | | sampleLengths | | 0 | 54 | | 1 | 15 | | 2 | 48 | | 3 | 16 | | 4 | 46 | | 5 | 9 | | 6 | 63 | | 7 | 14 | | 8 | 24 | | 9 | 38 | | 10 | 51 | | 11 | 5 | | 12 | 18 | | 13 | 12 | | 14 | 9 | | 15 | 10 | | 16 | 42 | | 17 | 2 | | 18 | 46 | | 19 | 20 | | 20 | 2 | | 21 | 75 | | 22 | 5 | | 23 | 37 | | 24 | 35 | | 25 | 9 | | 26 | 10 | | 27 | 16 | | 28 | 12 | | 29 | 39 | | 30 | 65 | | 31 | 6 | | 32 | 23 | | 33 | 38 | | 34 | 10 | | 35 | 2 | | 36 | 15 | | 37 | 46 | | 38 | 15 | | 39 | 5 | | 40 | 32 | | 41 | 4 | | 42 | 12 | | 43 | 15 | | 44 | 25 | | 45 | 29 | | 46 | 5 | | 47 | 28 | | 48 | 23 | | 49 | 4 |
| |
| 99.37% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 119 | | matches | | 0 | "were tiled" | | 1 | "been closed" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 184 | | matches | | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 131 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1053 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 32 | | adverbRatio | 0.030389363722697058 | | lyAdverbCount | 8 | | lyAdverbRatio | 0.007597340930674264 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 131 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 131 | | mean | 9.07 | | std | 5.57 | | cv | 0.614 | | sampleLengths | | 0 | 14 | | 1 | 13 | | 2 | 10 | | 3 | 17 | | 4 | 12 | | 5 | 3 | | 6 | 17 | | 7 | 1 | | 8 | 2 | | 9 | 22 | | 10 | 3 | | 11 | 3 | | 12 | 16 | | 13 | 3 | | 14 | 15 | | 15 | 13 | | 16 | 9 | | 17 | 6 | | 18 | 9 | | 19 | 14 | | 20 | 13 | | 21 | 14 | | 22 | 7 | | 23 | 15 | | 24 | 10 | | 25 | 4 | | 26 | 4 | | 27 | 5 | | 28 | 4 | | 29 | 11 | | 30 | 17 | | 31 | 7 | | 32 | 11 | | 33 | 3 | | 34 | 3 | | 35 | 4 | | 36 | 10 | | 37 | 17 | | 38 | 12 | | 39 | 2 | | 40 | 1 | | 41 | 2 | | 42 | 5 | | 43 | 4 | | 44 | 14 | | 45 | 5 | | 46 | 7 | | 47 | 2 | | 48 | 7 | | 49 | 10 |
| |
| 58.78% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 3 | | diversityRatio | 0.366412213740458 | | totalSentences | 131 | | uniqueOpeners | 48 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 4 | | totalSentences | 107 | | matches | | 0 | "Somewhere ahead, trainers slapped against" | | 1 | "Then, from her left, the" | | 2 | "Then the lights went out." | | 3 | "Somewhere in the black, she" |
| | ratio | 0.037 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 25 | | totalSentences | 107 | | matches | | 0 | "Her leather-soled shoes fought for" | | 1 | "They never stopped." | | 2 | "He pushed off the bollard" | | 3 | "She reached the alley mouth" | | 4 | "She drew her torch and" | | 5 | "He moved with the jerky" | | 6 | "Her watch snagged on a" | | 7 | "She yanked it free, the" | | 8 | "She turned and saw him" | | 9 | "She knew this place." | | 10 | "She radioed it in." | | 11 | "Her torch beam cut through" | | 12 | "Her footsteps echoed too loudly." | | 13 | "She tried to move quieter," | | 14 | "She swept the torch across" | | 15 | "She could feel eyes on" | | 16 | "She wore a shawl made" | | 17 | "She thought of Morris, her" | | 18 | "She spun, torch raised." | | 19 | "He held a curved blade" |
| | ratio | 0.234 | |
| 72.15% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 83 | | totalSentences | 107 | | matches | | 0 | "The suspect cut left into" | | 1 | "Her leather-soled shoes fought for" | | 2 | "The shout tore from her" | | 3 | "They never stopped." | | 4 | "The man ahead stumbled over" | | 5 | "The hood of his grey" | | 6 | "A name, maybe." | | 7 | "He pushed off the bollard" | | 8 | "Harlow's lungs burned." | | 9 | "The rain had soaked through" | | 10 | "She reached the alley mouth" | | 11 | "The passage smelled of rotting" | | 12 | "She drew her torch and" | | 13 | "The beam caught the suspect" | | 14 | "He moved with the jerky" | | 15 | "Harlow holstered the torch and" | | 16 | "Her watch snagged on a" | | 17 | "She yanked it free, the" | | 18 | "The suspect had vanished." | | 19 | "Harlow stood still, listening." |
| | ratio | 0.776 | |
| 46.73% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 107 | | matches | | 0 | "Now it was something else" |
| | ratio | 0.009 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 47 | | technicalSentenceCount | 1 | | matches | | 0 | "Her torch beam cut through the darkness, illuminating a staircase that spiralled down into blackness." |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 6 | | uselessAdditionCount | 3 | | matches | | 0 | "The woman tilted, as if listening to something far away" | | 1 | "she said, and her voice was steady" | | 2 | "She stepped, her hand resting on her holster" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 3 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 19 | | tagDensity | 0.158 | | leniency | 0.316 | | rawRatio | 0 | | effectiveRatio | 0 | |