| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 8 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 33 | | tagDensity | 0.242 | | leniency | 0.485 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1082 | | 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) | |
| 63.03% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1082 | | totalAiIsms | 8 | | found | | | highlights | | 0 | "flicker" | | 1 | "churned" | | 2 | "traced" | | 3 | "velvet" | | 4 | "grave" | | 5 | "echoed" | | 6 | "tapestry" | | 7 | "shimmered" |
| |
| 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 | 96 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 96 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 119 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 34 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1080 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 5 | | unquotedAttributions | 0 | | matches | (empty) | |
| 97.55% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 41 | | wordCount | 858 | | uniqueNames | 18 | | maxNameDensity | 1.05 | | worstName | "Herrera" | | maxWindowNameDensity | 2 | | worstWindowName | "Herrera" | | discoveredNames | | Camden | 2 | | Harlow | 1 | | Quinn | 8 | | Raven | 1 | | Nest | 1 | | Soho | 2 | | Tomás | 1 | | Herrera | 9 | | Saint | 1 | | Christopher | 1 | | Glock | 2 | | Tube | 1 | | Veil | 2 | | Market | 3 | | Morris | 1 | | Seville | 1 | | London | 1 | | Rain | 3 |
| | persons | | 0 | "Camden" | | 1 | "Harlow" | | 2 | "Quinn" | | 3 | "Tomás" | | 4 | "Herrera" | | 5 | "Saint" | | 6 | "Christopher" | | 7 | "Market" | | 8 | "Morris" | | 9 | "Rain" |
| | places | | 0 | "Raven" | | 1 | "Soho" | | 2 | "Seville" | | 3 | "London" |
| | globalScore | 0.976 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 69 | | 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 | 1080 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 119 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 46 | | mean | 23.48 | | std | 23.21 | | cv | 0.988 | | sampleLengths | | 0 | 103 | | 1 | 10 | | 2 | 23 | | 3 | 35 | | 4 | 9 | | 5 | 7 | | 6 | 65 | | 7 | 16 | | 8 | 11 | | 9 | 55 | | 10 | 3 | | 11 | 5 | | 12 | 23 | | 13 | 4 | | 14 | 3 | | 15 | 2 | | 16 | 49 | | 17 | 6 | | 18 | 86 | | 19 | 5 | | 20 | 7 | | 21 | 67 | | 22 | 11 | | 23 | 18 | | 24 | 17 | | 25 | 17 | | 26 | 2 | | 27 | 52 | | 28 | 22 | | 29 | 18 | | 30 | 7 | | 31 | 40 | | 32 | 48 | | 33 | 12 | | 34 | 3 | | 35 | 11 | | 36 | 5 | | 37 | 37 | | 38 | 36 | | 39 | 9 | | 40 | 37 | | 41 | 34 | | 42 | 24 | | 43 | 9 | | 44 | 14 | | 45 | 3 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 96 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 156 | | matches | (empty) | |
| 94.84% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 2 | | semicolonCount | 0 | | flaggedSentences | 2 | | totalSentences | 119 | | ratio | 0.017 | | matches | | 0 | "Not into the canal—onto a maintenance ladder bolted to the embankment wall." | | 1 | "She had seen the name scrawled across confiscated ledgers—enchanted goods, banned alchemical substances, information brokered in exchange for bone tokens." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 865 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 12 | | adverbRatio | 0.013872832369942197 | | lyAdverbCount | 3 | | lyAdverbRatio | 0.003468208092485549 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 119 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 119 | | mean | 9.08 | | std | 6.38 | | cv | 0.702 | | sampleLengths | | 0 | 8 | | 1 | 31 | | 2 | 28 | | 3 | 18 | | 4 | 3 | | 5 | 15 | | 6 | 10 | | 7 | 9 | | 8 | 9 | | 9 | 5 | | 10 | 7 | | 11 | 5 | | 12 | 12 | | 13 | 5 | | 14 | 6 | | 15 | 8 | | 16 | 1 | | 17 | 7 | | 18 | 6 | | 19 | 15 | | 20 | 4 | | 21 | 6 | | 22 | 17 | | 23 | 4 | | 24 | 13 | | 25 | 8 | | 26 | 5 | | 27 | 3 | | 28 | 7 | | 29 | 4 | | 30 | 12 | | 31 | 5 | | 32 | 11 | | 33 | 18 | | 34 | 9 | | 35 | 3 | | 36 | 5 | | 37 | 14 | | 38 | 9 | | 39 | 4 | | 40 | 3 | | 41 | 2 | | 42 | 12 | | 43 | 19 | | 44 | 10 | | 45 | 8 | | 46 | 6 | | 47 | 7 | | 48 | 6 | | 49 | 9 |
| |
| 70.87% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 4 | | diversityRatio | 0.44537815126050423 | | totalSentences | 119 | | uniqueOpeners | 53 | |
| 36.23% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 92 | | matches | | 0 | "Somewhere in the dark, a" |
| | ratio | 0.011 | |
| 80.87% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 32 | | totalSentences | 92 | | matches | | 0 | "She had not crossed the" | | 1 | "She had waited." | | 2 | "He vaulted a chained gate" | | 3 | "His Saint Christopher medallion caught" | | 4 | "He did not look back." | | 5 | "Her palms slapped rusted iron." | | 6 | "She vaulted, landed in a" | | 7 | "Her boots crushed broken glass." | | 8 | "She spat his name into" | | 9 | "He rounded a chimney stack" | | 10 | "She chased him across the" | | 11 | "She tore through canvas." | | 12 | "She did not blink." | | 13 | "He ducked beneath a curled" | | 14 | "She hurdled a cement mixer." | | 15 | "Her lungs burned." | | 16 | "Her voice cut through the" | | 17 | "He skidded to a halt" | | 18 | "His warm brown eyes found" | | 19 | "It clawed at the back" |
| | ratio | 0.348 | |
| 36.09% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 78 | | totalSentences | 92 | | matches | | 0 | "Detective Harlow Quinn crossed beneath" | | 1 | "She had not crossed the" | | 2 | "She had waited." | | 3 | "He vaulted a chained gate" | | 4 | "His Saint Christopher medallion caught" | | 5 | "He did not look back." | | 6 | "Quinn hit the gate at" | | 7 | "Her palms slapped rusted iron." | | 8 | "She vaulted, landed in a" | | 9 | "Her boots crushed broken glass." | | 10 | "A cat screamed from a" | | 11 | "She spat his name into" | | 12 | "He rounded a chimney stack" | | 13 | "She chased him across the" | | 14 | "A construction tarp snapped like" | | 15 | "She tore through canvas." | | 16 | "Herrera cut across a flooded" | | 17 | "A night bus blared past," | | 18 | "She did not blink." | | 19 | "Rain drilled into her sharp" |
| | ratio | 0.848 | |
| 54.35% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 92 | | matches | | 0 | "Now she was eight miles" |
| | ratio | 0.011 | |
| 50.69% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 31 | | technicalSentenceCount | 4 | | matches | | 0 | "A night bus blared past, tires spraying a wall of water that soaked her to the bone." | | 1 | "Beside the woman, a vendor in a plague doctor mask counted teeth beside a cage of moths that bore human faces." | | 2 | "Herrera stood beside a breached archway that led deeper into the earth, a passage beyond the platform where no working train had ever run." | | 3 | "A tapestry depicting the Soho skyline shimmered as though the threads were wet." |
| |
| 62.50% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 8 | | uselessAdditionCount | 1 | | matches | | 0 | "Herrera laughed, a bark lost to the wind" |
| |
| 59.09% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 3 | | fancyCount | 3 | | fancyTags | | 0 | "She spat (spit)" | | 1 | "Herrera laughed (laugh)" | | 2 | "The woman's smile revealed (reveal)" |
| | dialogueSentences | 33 | | tagDensity | 0.091 | | leniency | 0.182 | | rawRatio | 1 | | effectiveRatio | 0.182 | |