| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 25 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 52 | | tagDensity | 0.481 | | leniency | 0.962 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 73.44% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1318 | | totalAiIsmAdverbs | 7 | | found | | | highlights | | 0 | "completely" | | 1 | "tightly" | | 2 | "gently" | | 3 | "slowly" | | 4 | "very" | | 5 | "suddenly" |
| |
| 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) | |
| 54.48% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1318 | | totalAiIsms | 12 | | found | | | highlights | | 0 | "echoed" | | 1 | "tracing" | | 2 | "shattered" | | 3 | "porcelain" | | 4 | "weight" | | 5 | "etched" | | 6 | "magnetic" | | 7 | "raced" | | 8 | "scanned" | | 9 | "velvet" | | 10 | "chaotic" |
| |
| 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 | 83 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 83 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 110 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 38 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 2 | | totalWords | 1314 | | ratio | 0.002 | | matches | | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 15 | | unquotedAttributions | 0 | | matches | (empty) | |
| 32.21% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 42 | | wordCount | 849 | | uniqueNames | 12 | | maxNameDensity | 2.36 | | worstName | "Harlow" | | maxWindowNameDensity | 3 | | worstWindowName | "Harlow" | | discoveredNames | | Victorian | 1 | | Harlow | 20 | | Quinn | 1 | | Maglite | 1 | | Camden | 2 | | Miller | 10 | | Blitz | 1 | | Half | 1 | | Morris | 2 | | Soho | 1 | | July | 1 | | Town | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Maglite" | | 3 | "Miller" | | 4 | "Blitz" | | 5 | "Half" | | 6 | "Morris" |
| | places | | | globalScore | 0.322 | | windowScore | 0.667 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 65 | | glossingSentenceCount | 1 | | matches | | 0 | "smelled like dry earth, crushed lavender," |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1314 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 110 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 49 | | mean | 26.82 | | std | 20.05 | | cv | 0.748 | | sampleLengths | | 0 | 49 | | 1 | 29 | | 2 | 27 | | 3 | 3 | | 4 | 35 | | 5 | 68 | | 6 | 22 | | 7 | 33 | | 8 | 11 | | 9 | 59 | | 10 | 7 | | 11 | 43 | | 12 | 5 | | 13 | 6 | | 14 | 36 | | 15 | 8 | | 16 | 65 | | 17 | 6 | | 18 | 54 | | 19 | 11 | | 20 | 9 | | 21 | 11 | | 22 | 13 | | 23 | 34 | | 24 | 63 | | 25 | 8 | | 26 | 4 | | 27 | 68 | | 28 | 27 | | 29 | 6 | | 30 | 55 | | 31 | 14 | | 32 | 35 | | 33 | 4 | | 34 | 70 | | 35 | 39 | | 36 | 26 | | 37 | 11 | | 38 | 23 | | 39 | 24 | | 40 | 40 | | 41 | 14 | | 42 | 8 | | 43 | 18 | | 44 | 43 | | 45 | 15 | | 46 | 30 | | 47 | 6 | | 48 | 19 |
| |
| 96.81% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 83 | | matches | | 0 | "been sealed" | | 1 | "was stamped" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 141 | | matches | | |
| 64.94% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 3 | | semicolonCount | 1 | | flaggedSentences | 3 | | totalSentences | 110 | | ratio | 0.027 | | matches | | 0 | "Sigils—the same strange, angular markings painted in chalk on the walls—were deeply etched across the glass face." | | 1 | "The needle inside wasn't floating on a pin; it spun continuously in fluid, erratic sweeps, refusing to settle on magnetic north." | | 2 | "The wax was stamped with an emblem—a key entwined with a serpent." |
| |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 855 | | adjectiveStacks | 1 | | stackExamples | | 0 | "same strange, angular markings" |
| | adverbCount | 19 | | adverbRatio | 0.022222222222222223 | | lyAdverbCount | 11 | | lyAdverbRatio | 0.012865497076023392 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 110 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 110 | | mean | 11.95 | | std | 7.34 | | cv | 0.614 | | sampleLengths | | 0 | 14 | | 1 | 19 | | 2 | 16 | | 3 | 16 | | 4 | 13 | | 5 | 7 | | 6 | 15 | | 7 | 5 | | 8 | 3 | | 9 | 16 | | 10 | 19 | | 11 | 15 | | 12 | 19 | | 13 | 10 | | 14 | 24 | | 15 | 13 | | 16 | 9 | | 17 | 5 | | 18 | 7 | | 19 | 21 | | 20 | 11 | | 21 | 9 | | 22 | 19 | | 23 | 12 | | 24 | 6 | | 25 | 7 | | 26 | 6 | | 27 | 7 | | 28 | 26 | | 29 | 17 | | 30 | 5 | | 31 | 6 | | 32 | 10 | | 33 | 22 | | 34 | 4 | | 35 | 5 | | 36 | 3 | | 37 | 15 | | 38 | 35 | | 39 | 15 | | 40 | 6 | | 41 | 19 | | 42 | 17 | | 43 | 18 | | 44 | 11 | | 45 | 5 | | 46 | 4 | | 47 | 6 | | 48 | 5 | | 49 | 5 |
| |
| 81.82% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 5 | | diversityRatio | 0.5181818181818182 | | totalSentences | 110 | | uniqueOpeners | 57 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 75 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 22 | | totalSentences | 75 | | matches | | 0 | "She tapped the face of" | | 1 | "He slapped a notebook against" | | 2 | "His eyes stared straight ahead," | | 3 | "She pulled a pair of" | | 4 | "She gently lifted the victim's" | | 5 | "She turned the victim's pale" | | 6 | "She swept the light around" | | 7 | "She peered at the victim’s" | | 8 | "She used two fingers to" | | 9 | "It was a small brass" | | 10 | "Her mind raced back three" | | 11 | "She scanned the perimeter of" | | 12 | "She stepped toward a pile" | | 13 | "She kicked a piece of" | | 14 | "She reached out, her gloved" | | 15 | "It smelled like dry earth," | | 16 | "She crouched back down, shining" | | 17 | "She reached into the victim's" | | 18 | "Her fingers brushed against stiff" | | 19 | "She pulled out an envelope" |
| | ratio | 0.293 | |
| 20.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 66 | | totalSentences | 75 | | matches | | 0 | "Rain leaked through the cracked" | | 1 | "Detective Harlow Quinn stepped over" | | 2 | "DS Miller’s voice echoed off" | | 3 | "Harlow adjusted her grip on" | | 4 | "She tapped the face of" | | 5 | "Miller gestured with his own" | | 6 | "Harlow followed him through the" | | 7 | "The station had been sealed" | | 8 | "Chalk marks crisscrossed the floor," | | 9 | "Harlow crouched, tracing a finger" | | 10 | "The brick beneath it radiated" | | 11 | "He slapped a notebook against" | | 12 | "Harlow shined her light directly" | | 13 | "The victim sat slumped against" | | 14 | "A young man, early twenties," | | 15 | "His eyes stared straight ahead," | | 16 | "Harlow asked, stepping closer" | | 17 | "Miller nudged a shattered glass" | | 18 | "Harlow knelt beside the body," | | 19 | "She pulled a pair of" |
| | ratio | 0.88 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 75 | | matches | (empty) | | ratio | 0 | |
| 96.77% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 31 | | technicalSentenceCount | 2 | | matches | | 0 | "Spiral patterns and geometric jagged lines bled into the mortar, drawn in a thick, dried substance that trapped the torchlight rather than reflecting it." | | 1 | "Hundreds of shallow, circular depressions forming a grid that stretched across the entire platform, disappearing into the dark recesses of the tunnel." |
| |
| 65.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 25 | | uselessAdditionCount | 3 | | matches | | 0 | "She reached out, her gloved hand halting an inch from the brickwork" | | 1 | "Miller said, his voice dropping a register, losing its casual edge" | | 2 | "Harlow said, her voice hard as iron" |
| |
| 92.31% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 14 | | fancyCount | 3 | | fancyTags | | 0 | "Harlow muttered (mutter)" | | 1 | "Miller sneered (sneer)" | | 2 | "Harlow whispered (whisper)" |
| | dialogueSentences | 52 | | tagDensity | 0.269 | | leniency | 0.538 | | rawRatio | 0.214 | | effectiveRatio | 0.115 | |