| 75.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 22 | | adverbTagCount | 3 | | adverbTags | | 0 | "said Constable Ademola from somewhere below [somewhere]" | | 1 | "She rocked back [back]" | | 2 | "she said quietly [quietly]" |
| | dialogueSentences | 48 | | tagDensity | 0.458 | | leniency | 0.917 | | rawRatio | 0.136 | | effectiveRatio | 0.125 | |
| 90.87% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1643 | | totalAiIsmAdverbs | 3 | | found | | | highlights | | 0 | "happily" | | 1 | "slowly" | | 2 | "slightly" |
| |
| 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) | |
| 96.96% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1643 | | totalAiIsms | 1 | | found | | | highlights | | |
| 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 | 80 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 80 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 104 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 89 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1663 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 16 | | unquotedAttributions | 0 | | matches | (empty) | |
| 83.33% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 34 | | wordCount | 962 | | uniqueNames | 13 | | maxNameDensity | 1.04 | | worstName | "Vaughn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Vaughn" | | discoveredNames | | Camden | 1 | | Detective | 1 | | Harlow | 1 | | Quinn | 9 | | Constable | 1 | | Ademola | 4 | | Tube | 1 | | Iron | 1 | | Neil | 1 | | Vaughn | 10 | | Twenty | 1 | | Whitechapel | 1 | | Morris | 2 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Ademola" | | 3 | "Iron" | | 4 | "Neil" | | 5 | "Vaughn" | | 6 | "Morris" |
| | places | | | globalScore | 0.98 | | windowScore | 0.833 | |
| 43.62% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 47 | | glossingSentenceCount | 2 | | matches | | 0 | "smelled like wet chalk and rust, and Detec" | | 1 | "something like dried orange peel that smelle" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 1 | | per1kWords | 0.601 | | wordCount | 1663 | | matches | | 0 | "not looking for the thing that was there, but for the shape of the thing" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 104 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 50 | | mean | 33.26 | | std | 30.54 | | cv | 0.918 | | sampleLengths | | 0 | 43 | | 1 | 5 | | 2 | 47 | | 3 | 105 | | 4 | 4 | | 5 | 6 | | 6 | 6 | | 7 | 27 | | 8 | 110 | | 9 | 48 | | 10 | 25 | | 11 | 19 | | 12 | 67 | | 13 | 1 | | 14 | 42 | | 15 | 5 | | 16 | 12 | | 17 | 71 | | 18 | 20 | | 19 | 36 | | 20 | 1 | | 21 | 5 | | 22 | 12 | | 23 | 3 | | 24 | 95 | | 25 | 10 | | 26 | 2 | | 27 | 22 | | 28 | 33 | | 29 | 30 | | 30 | 111 | | 31 | 20 | | 32 | 45 | | 33 | 38 | | 34 | 6 | | 35 | 33 | | 36 | 3 | | 37 | 62 | | 38 | 8 | | 39 | 71 | | 40 | 68 | | 41 | 27 | | 42 | 41 | | 43 | 74 | | 44 | 18 | | 45 | 75 | | 46 | 28 | | 47 | 8 | | 48 | 9 | | 49 | 6 |
| |
| 87.72% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 4 | | totalSentences | 80 | | matches | | 0 | "been swept" | | 1 | "been pushed" | | 2 | "been taught" | | 3 | "was turned" | | 4 | "was matted" | | 5 | "been carried" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 150 | | matches | (empty) | |
| 32.97% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 4 | | semicolonCount | 0 | | flaggedSentences | 4 | | totalSentences | 104 | | ratio | 0.038 | | matches | | 0 | "That was the first thing she noticed — not the body, not the lamps, not the ring of uniforms standing about with their hands in their pockets." | | 1 | "DI Neil Vaughn came out of the shadows with his coat collar up and a takeaway cup in his hand — actually brought coffee down into a crime scene, which told her something about him she filed away without comment." | | 2 | "Boots — good boots, walking boots, the kind you paid for." | | 3 | "That was the trouble with Vaughn — he was never stupid, only incurious." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 963 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 27 | | adverbRatio | 0.028037383177570093 | | lyAdverbCount | 9 | | lyAdverbRatio | 0.009345794392523364 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 104 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 104 | | mean | 15.99 | | std | 17.73 | | cv | 1.109 | | sampleLengths | | 0 | 43 | | 1 | 2 | | 2 | 3 | | 3 | 22 | | 4 | 13 | | 5 | 12 | | 6 | 12 | | 7 | 4 | | 8 | 27 | | 9 | 2 | | 10 | 23 | | 11 | 37 | | 12 | 4 | | 13 | 4 | | 14 | 2 | | 15 | 6 | | 16 | 27 | | 17 | 22 | | 18 | 8 | | 19 | 32 | | 20 | 34 | | 21 | 3 | | 22 | 11 | | 23 | 48 | | 24 | 2 | | 25 | 2 | | 26 | 21 | | 27 | 11 | | 28 | 8 | | 29 | 40 | | 30 | 27 | | 31 | 1 | | 32 | 7 | | 33 | 35 | | 34 | 5 | | 35 | 9 | | 36 | 3 | | 37 | 24 | | 38 | 19 | | 39 | 2 | | 40 | 11 | | 41 | 15 | | 42 | 2 | | 43 | 3 | | 44 | 15 | | 45 | 9 | | 46 | 27 | | 47 | 1 | | 48 | 5 | | 49 | 9 |
| |
| 93.91% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 4 | | diversityRatio | 0.5865384615384616 | | totalSentences | 104 | | uniqueOpeners | 61 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 65 | | matches | | 0 | "Then the tunnel." | | 1 | "Somewhere far off, water fell" |
| | ratio | 0.031 | |
| 66.15% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 25 | | totalSentences | 65 | | matches | | 0 | "Her torch cut a white" | | 1 | "Her worn leather watch slid" | | 2 | "She looked up along the" | | 3 | "She stood and turned a" | | 4 | "He was fifty, soft in" | | 5 | "He gestured with the cup" | | 6 | "He said it kindly" | | 7 | "His face was turned away" | | 8 | "She didn't touch." | | 9 | "She just looked, and let" | | 10 | "He sounded amused" | | 11 | "She angled her torch" | | 12 | "she moved the beam in" | | 13 | "They ran from the dark" | | 14 | "she indicated the exact She" | | 15 | "It was a good theory." | | 16 | "He would build a house" | | 17 | "It lay against the wall" | | 18 | "she tapped the air an" | | 19 | "She rocked back on her" |
| | ratio | 0.385 | |
| 60.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 52 | | totalSentences | 65 | | matches | | 0 | "The stairwell down to the" | | 1 | "Her torch cut a white" | | 2 | "The platform, when it opened" | | 3 | "Someone had swept it." | | 4 | "That was the first thing" | | 5 | "A Tube station abandoned since" | | 6 | "This floor had been swept" | | 7 | "Ademola blinked at her." | | 8 | "Quinn crouched at the edge" | | 9 | "Her worn leather watch slid" | | 10 | "She looked up along the" | | 11 | "Rows of them." | | 12 | "She stood and turned a" | | 13 | "A cleared thoroughfare down the" | | 14 | "A voice from the dark" | | 15 | "He was fifty, soft in" | | 16 | "He gestured with the cup" | | 17 | "He said it kindly" | | 18 | "The body lay just past" | | 19 | "A man, forties as Vaughn" |
| | ratio | 0.8 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 65 | | matches | (empty) | | ratio | 0 | |
| 50.69% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 31 | | technicalSentenceCount | 4 | | matches | | 0 | "She stood and turned a slow full circle, taking the room in the way she'd been taught eighteen years ago by a sergeant who had smelled permanently of pipe smoke…" | | 1 | "DI Neil Vaughn came out of the shadows with his coat collar up and a takeaway cup in his hand — actually brought coffee down into a crime scene, which told her …" | | 2 | "He was fifty, soft in the middle, and he had the easy, sympathetic manner of a man who had never once been wrong in his own estimation." | | 3 | "A curl of something like dried orange peel that smelled, when she brought it near her face, of pepper and burnt sugar and, underneath, a low animal sweetness th…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 22 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 11 | | fancyCount | 1 | | fancyTags | | | dialogueSentences | 48 | | tagDensity | 0.229 | | leniency | 0.458 | | rawRatio | 0.091 | | effectiveRatio | 0.042 | |