| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 12 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 35 | | tagDensity | 0.343 | | leniency | 0.686 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 95.14% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1028 | | totalAiIsmAdverbs | 1 | | 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) | |
| 85.41% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1028 | | totalAiIsms | 3 | | found | | | highlights | | 0 | "etched" | | 1 | "trembled" | | 2 | "weight" |
| |
| 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 | 47 | | matches | (empty) | |
| 82.07% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 47 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 70 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 54 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 1 | | totalWords | 1028 | | ratio | 0.001 | | matches | | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 9 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 14 | | wordCount | 666 | | uniqueNames | 8 | | maxNameDensity | 0.6 | | worstName | "Quinn" | | maxWindowNameDensity | 1 | | worstWindowName | "Quinn" | | discoveredNames | | Camden | 1 | | Quinn | 4 | | Constable | 1 | | Pryce | 4 | | Three | 1 | | Michael | 1 | | Morris | 1 | | Westminster | 1 |
| | persons | | 0 | "Camden" | | 1 | "Quinn" | | 2 | "Pryce" | | 3 | "Michael" | | 4 | "Morris" |
| | places | | | globalScore | 1 | | windowScore | 1 | |
| 85.90% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 39 | | glossingSentenceCount | 1 | | matches | | 0 | "looked like a man being carried, or dragg" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1028 | | matches | (empty) | |
| 71.43% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 2 | | totalSentences | 70 | | matches | | 0 | "explain that she" | | 1 | "reading that the" |
| |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 31 | | mean | 33.16 | | std | 28.23 | | cv | 0.851 | | sampleLengths | | 0 | 75 | | 1 | 36 | | 2 | 16 | | 3 | 73 | | 4 | 70 | | 5 | 6 | | 6 | 9 | | 7 | 9 | | 8 | 13 | | 9 | 55 | | 10 | 14 | | 11 | 61 | | 12 | 1 | | 13 | 8 | | 14 | 50 | | 15 | 80 | | 16 | 20 | | 17 | 10 | | 18 | 2 | | 19 | 63 | | 20 | 75 | | 21 | 14 | | 22 | 20 | | 23 | 5 | | 24 | 12 | | 25 | 84 | | 26 | 6 | | 27 | 73 | | 28 | 9 | | 29 | 30 | | 30 | 29 |
| |
| 82.87% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 3 | | totalSentences | 47 | | matches | | 0 | "were streaked" | | 1 | "been slid" | | 2 | "being carried" | | 3 | "been bricked" | | 4 | "been struck" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 114 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 70 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 668 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 12 | | adverbRatio | 0.017964071856287425 | | lyAdverbCount | 1 | | lyAdverbRatio | 0.0014970059880239522 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 70 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 70 | | mean | 14.69 | | std | 10.68 | | cv | 0.727 | | sampleLengths | | 0 | 21 | | 1 | 23 | | 2 | 8 | | 3 | 23 | | 4 | 13 | | 5 | 17 | | 6 | 6 | | 7 | 13 | | 8 | 3 | | 9 | 40 | | 10 | 33 | | 11 | 6 | | 12 | 28 | | 13 | 6 | | 14 | 8 | | 15 | 5 | | 16 | 6 | | 17 | 11 | | 18 | 6 | | 19 | 9 | | 20 | 9 | | 21 | 13 | | 22 | 19 | | 23 | 6 | | 24 | 21 | | 25 | 9 | | 26 | 14 | | 27 | 18 | | 28 | 27 | | 29 | 16 | | 30 | 1 | | 31 | 8 | | 32 | 5 | | 33 | 29 | | 34 | 16 | | 35 | 9 | | 36 | 35 | | 37 | 7 | | 38 | 20 | | 39 | 9 | | 40 | 20 | | 41 | 10 | | 42 | 2 | | 43 | 4 | | 44 | 35 | | 45 | 24 | | 46 | 16 | | 47 | 12 | | 48 | 9 | | 49 | 20 |
| |
| 77.14% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 6 | | diversityRatio | 0.5142857142857142 | | totalSentences | 70 | | uniqueOpeners | 36 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 44 | | matches | (empty) | | ratio | 0 | |
| 38.18% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 20 | | totalSentences | 44 | | matches | | 0 | "He was twenty-nine, earnest, and" | | 1 | "She did not explain that" | | 2 | "He lifted his torch toward" | | 3 | "She crouched, keeping her knees" | | 4 | "She stood, her left wrist" | | 5 | "She had checked it a" | | 6 | "She pointed the torch at" | | 7 | "It did not look like" | | 8 | "It looked like a man" | | 9 | "She went there anyway." | | 10 | "Her attention snagged on the" | | 11 | "She knelt and lifted it" | | 12 | "It trembled, swung, and settled," | | 13 | "Her voice came out level," | | 14 | "He came over, peering." | | 15 | "She turned the compass over," | | 16 | "She had signed the file" | | 17 | "She had told herself it" | | 18 | "She had believed it, because" | | 19 | "She set the torch on" |
| | ratio | 0.455 | |
| 0.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 41 | | totalSentences | 44 | | matches | | 0 | "The disused platform beneath Camden" | | 1 | "Harlow Quinn paused at the" | | 2 | "The tiles were the colour" | | 3 | "Someone had painted a station" | | 4 | "Detective Constable Pryce came down" | | 5 | "He was twenty-nine, earnest, and" | | 6 | "She did not explain that" | | 7 | "He lifted his torch toward" | | 8 | "Quinn walked past him without" | | 9 | "The body lay on its" | | 10 | "A man's face, eyes half" | | 11 | "A good wool coat, damp" | | 12 | "She crouched, keeping her knees" | | 13 | "She stood, her left wrist" | | 14 | "The watch read twenty past" | | 15 | "She had checked it a" | | 16 | "She pointed the torch at" | | 17 | "A thin grey film lay" | | 18 | "Pryce frowned and looked down." | | 19 | "The leather was pale with" |
| | ratio | 0.932 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 44 | | matches | (empty) | | ratio | 0 | |
| 6.80% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 21 | | technicalSentenceCount | 4 | | matches | | 0 | "He was twenty-nine, earnest, and had the look of a man who had been awake since four." | | 1 | "The leather was pale with dust, not a trace of the grey sludge that coated the lower tunnel floor, where the water had been ankle-deep when she came in." | | 2 | "The tiles were streaked with old damp, and in one place a row of smudges ran from the arch to the edge of the platform, as though something heavy had been slid …" | | 3 | "She had told herself it was grief that had made him see things." |
| |
| 41.67% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 12 | | uselessAdditionCount | 2 | | matches | | 0 | "Detective Constable Pryce came, his torch swinging" | | 1 | "Quinn moved along, her torch low" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 3 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 35 | | tagDensity | 0.086 | | leniency | 0.171 | | rawRatio | 0 | | effectiveRatio | 0 | |