| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | |
| 79.11% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1197 | | totalAiIsmAdverbs | 5 | | found | | | highlights | | 0 | "softly" | | 1 | "slowly" | | 2 | "carefully" |
| |
| 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) | |
| 49.87% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1197 | | totalAiIsms | 12 | | found | | | highlights | | 0 | "measured" | | 1 | "gloom" | | 2 | "silence" | | 3 | "weight" | | 4 | "echoing" | | 5 | "synthetic" | | 6 | "traced" | | 7 | "maw" | | 8 | "glint" | | 9 | "etched" | | 10 | "intricate" | | 11 | "furrowing" |
| |
| 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 | 97 | | matches | (empty) | |
| 69.22% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 3 | | hedgeCount | 2 | | narrationSentences | 97 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 97 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 46 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1194 | | ratio | 0 | | matches | (empty) | |
| 0.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 6 | | unquotedAttributions | 3 | | matches | | 0 | "Clear-cut overdose, Vance said, his voice echoing off the curved brick ceiling." | | 1 | "Give me the specifics, Vance, Quinn said softly." | | 2 | "The Veil Market, Quinn murmured, almost to herself." |
| |
| 74.62% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 60 | | wordCount | 1194 | | uniqueNames | 22 | | maxNameDensity | 1.51 | | worstName | "Quinn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Quinn" | | discoveredNames | | Camden | 3 | | Tube | 1 | | Detective | 2 | | Harlow | 1 | | Quinn | 18 | | Metropolitan | 1 | | Police | 1 | | Vance | 14 | | Chalk | 2 | | Farm | 2 | | Road | 2 | | Victorian | 1 | | High | 1 | | Euston | 1 | | King | 1 | | Cross | 1 | | Veil | 1 | | Market | 1 | | Scotland | 1 | | Yard | 1 | | Morris | 1 | | People | 3 |
| | persons | | 0 | "Detective" | | 1 | "Harlow" | | 2 | "Quinn" | | 3 | "Police" | | 4 | "Vance" | | 5 | "Victorian" | | 6 | "King" | | 7 | "Cross" | | 8 | "Morris" | | 9 | "People" |
| | places | | 0 | "Chalk" | | 1 | "Farm" | | 2 | "Road" | | 3 | "Euston" | | 4 | "Scotland" |
| | globalScore | 0.746 | | windowScore | 0.833 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 71 | | glossingSentenceCount | 0 | | matches | (empty) | |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1194 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 97 | | matches | | 0 | "curdled that Detective" |
| |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 32 | | mean | 37.31 | | std | 22.06 | | cv | 0.591 | | sampleLengths | | 0 | 82 | | 1 | 22 | | 2 | 45 | | 3 | 57 | | 4 | 28 | | 5 | 28 | | 6 | 72 | | 7 | 37 | | 8 | 12 | | 9 | 56 | | 10 | 44 | | 11 | 5 | | 12 | 25 | | 13 | 43 | | 14 | 33 | | 15 | 21 | | 16 | 82 | | 17 | 33 | | 18 | 62 | | 19 | 15 | | 20 | 61 | | 21 | 13 | | 22 | 61 | | 23 | 8 | | 24 | 8 | | 25 | 48 | | 26 | 5 | | 27 | 39 | | 28 | 55 | | 29 | 55 | | 30 | 19 | | 31 | 20 |
| |
| 94.41% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 3 | | totalSentences | 97 | | matches | | 0 | "was fanned" | | 1 | "was dropped" | | 2 | "was brought" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 2 | | totalVerbs | 192 | | matches | | 0 | "wasn't pointing" | | 1 | "was twitching" |
| |
| 54.49% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 3 | | semicolonCount | 0 | | flaggedSentences | 3 | | totalSentences | 97 | | ratio | 0.031 | | matches | | 0 | "The books spilling out of it—look at the spines, Vance." | | 1 | "It was twitching violently, locked onto a bearing that led straight down the dark, sealed tunnel behind them—deeper into the subterranean warren beneath Camden, far past the reach of the tube lines." | | 2 | "Her mind flashed briefly to a file locked deep in her desk at Scotland Yard—the unsolved case of DS Morris, her partner who had vanished three years ago during a midnight raid on a subterranean warehouse, leaving behind no footprints, no struggle, and no answers." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1214 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 34 | | adverbRatio | 0.02800658978583196 | | lyAdverbCount | 16 | | lyAdverbRatio | 0.013179571663920923 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 97 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 97 | | mean | 12.31 | | std | 8.52 | | cv | 0.692 | | sampleLengths | | 0 | 37 | | 1 | 19 | | 2 | 26 | | 3 | 7 | | 4 | 13 | | 5 | 2 | | 6 | 4 | | 7 | 14 | | 8 | 27 | | 9 | 12 | | 10 | 22 | | 11 | 23 | | 12 | 12 | | 13 | 16 | | 14 | 28 | | 15 | 12 | | 16 | 9 | | 17 | 11 | | 18 | 13 | | 19 | 25 | | 20 | 2 | | 21 | 5 | | 22 | 14 | | 23 | 18 | | 24 | 8 | | 25 | 4 | | 26 | 7 | | 27 | 12 | | 28 | 4 | | 29 | 9 | | 30 | 14 | | 31 | 10 | | 32 | 13 | | 33 | 31 | | 34 | 5 | | 35 | 6 | | 36 | 1 | | 37 | 10 | | 38 | 8 | | 39 | 11 | | 40 | 19 | | 41 | 13 | | 42 | 5 | | 43 | 17 | | 44 | 8 | | 45 | 3 | | 46 | 4 | | 47 | 5 | | 48 | 5 | | 49 | 7 |
| |
| 59.79% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 7 | | diversityRatio | 0.4020618556701031 | | totalSentences | 97 | | uniqueOpeners | 39 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 3 | | totalSentences | 90 | | matches | | 0 | "Instead, it looks like it" | | 1 | "Maybe she took a cab" | | 2 | "Then what is it?" |
| | ratio | 0.033 | |
| 91.11% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 29 | | totalSentences | 90 | | matches | | 0 | "She kept her stride measured," | | 1 | "She glanced down at her" | | 2 | "They knew the closely cropped" | | 3 | "She stepped beneath the red-and-white" | | 4 | "Her curly red hair was" | | 5 | "She didn't touch the body," | | 6 | "We found a scattering of" | | 7 | "She reached out, her gloved" | | 8 | "We’ve got uniforms canvas-checking the" | | 9 | "Her gaze traced the peeling," | | 10 | "It’s too neat, Quinn said." | | 11 | "It’s a tragedy in a" | | 12 | "She stopped ten feet down" | | 13 | "She knelt again, her fingers" | | 14 | "It’s an inch thick across" | | 15 | "They sweep the floor with" | | 16 | "She pointed to the victim's" | | 17 | "She turned her attention back" | | 18 | "She noticed something else, something" | | 19 | "She stared at the delicate," |
| | ratio | 0.322 | |
| 82.22% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 68 | | totalSentences | 90 | | matches | | 0 | "The air down in the" | | 1 | "She kept her stride measured," | | 2 | "She glanced down at her" | | 3 | "The worn leather watch ticked" | | 4 | "Uniforms parted for her." | | 5 | "They knew the closely cropped" | | 6 | "She stepped beneath the red-and-white" | | 7 | "The victim was a young" | | 8 | "Her curly red hair was" | | 9 | "Quinn crouched, her knees popping" | | 10 | "She didn't touch the body," | | 11 | "Inspector Vance stood a few" | | 12 | "We found a scattering of" | | 13 | "Some kind of designer synthetic" | | 14 | "The kid slipped past the" | | 15 | "Quinn didn't look up immediately." | | 16 | "She reached out, her gloved" | | 17 | "A scattering of pale dust" | | 18 | "A transit worker doing a" | | 19 | "Vance stepped closer, his boots" |
| | ratio | 0.756 | |
| 55.56% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 90 | | matches | | 0 | "If she had crawled down" |
| | ratio | 0.011 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 54 | | technicalSentenceCount | 2 | | matches | | 0 | "The casing was worn, covered in a distinct patina of verdigris, and the face was heavily etched with intricate geometric sigils that didn't look remotely human." | | 1 | "Her mind flashed briefly to a file locked deep in her desk at Scotland Yard—the unsolved case of DS Morris, her partner who had vanished three years ago during …" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 0 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |