| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 12 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 27 | | tagDensity | 0.444 | | leniency | 0.889 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 96.23% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1325 | | 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) | |
| 62.26% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1325 | | totalAiIsms | 10 | | found | | | highlights | | 0 | "echoed" | | 1 | "flicker" | | 2 | "etched" | | 3 | "weight" | | 4 | "glinting" | | 5 | "scanning" | | 6 | "flickered" | | 7 | "crystalline" | | 8 | "whisper" |
| |
| 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 | 1 | | narrationSentences | 92 | | matches | | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 92 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 107 | | 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 | 2 | | markdownWords | 4 | | totalWords | 1312 | | ratio | 0.003 | | matches | | 0 | "The Raven’s Nest" | | 1 | "exactly" |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 12 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 35 | | wordCount | 1108 | | uniqueNames | 13 | | maxNameDensity | 0.9 | | worstName | "Herrera" | | maxWindowNameDensity | 2 | | worstWindowName | "Herrera" | | discoveredNames | | Detective | 1 | | Harlow | 1 | | Quinn | 9 | | Raven | 1 | | Dean | 1 | | Street | 1 | | Morris | 4 | | London | 1 | | Spanish | 1 | | Veil | 2 | | Market | 2 | | Herrera | 10 | | Holloway | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Raven" | | 3 | "Morris" | | 4 | "Market" | | 5 | "Herrera" |
| | places | | 0 | "Dean" | | 1 | "Street" | | 2 | "London" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 76 | | glossingSentenceCount | 0 | | matches | (empty) | |
| 47.56% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 2 | | per1kWords | 1.524 | | wordCount | 1312 | | matches | | 0 | "not fear, but calculation" | | 1 | "not an exit, but a spiral staircase descending into a chamber filled with cry" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 107 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 36 | | mean | 36.44 | | std | 28.78 | | cv | 0.79 | | sampleLengths | | 0 | 131 | | 1 | 82 | | 2 | 85 | | 3 | 10 | | 4 | 51 | | 5 | 35 | | 6 | 28 | | 7 | 41 | | 8 | 36 | | 9 | 1 | | 10 | 12 | | 11 | 65 | | 12 | 43 | | 13 | 8 | | 14 | 21 | | 15 | 80 | | 16 | 55 | | 17 | 12 | | 18 | 8 | | 19 | 46 | | 20 | 8 | | 21 | 36 | | 22 | 20 | | 23 | 55 | | 24 | 15 | | 25 | 31 | | 26 | 54 | | 27 | 12 | | 28 | 64 | | 29 | 16 | | 30 | 38 | | 31 | 6 | | 32 | 71 | | 33 | 9 | | 34 | 15 | | 35 | 12 |
| |
| 97.64% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 92 | | matches | | 0 | "was, tangled" | | 1 | "was spent" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 198 | | matches | (empty) | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 14 | | semicolonCount | 1 | | flaggedSentences | 12 | | totalSentences | 107 | | ratio | 0.112 | | matches | | 0 | "The city’s neon signs blurred into streaks of color—pink, blue, the unmistakable sickly green of *The Raven’s Nest*—but she ignored them now." | | 1 | "A man’s laugh—low, mocking—cut through the din of thunder." | | 2 | "If she missed this lead, the clique would scatter like rats, and DS Morris’s case would die the same death it had given him—buried under bureaucratic indifference and half-truths." | | 3 | "Leather and something else—ozone, like after lightning strikes." | | 4 | "He turned, and for a heartbeat, she saw something flicker in his warm brown eyes—not fear, but calculation." | | 5 | "“I already paid the toll.” He pulled a small, bone-white token from his pocket—a grinning skull with hollow eyes—and held it up." | | 6 | "She’d seen things that defied explanation in her years on the force, but this—this was different." | | 7 | "The air changed as she descended—damp earth and something sweeter, like aged parchment and iron." | | 8 | "A man in a tricorn hat hawked vials of glowing liquid; a woman with moth-like wings haggled over a vial of liquid moonlight." | | 9 | "The Veil Market wasn’t just a black market—it was a crossroads for the damned and the desperate." | | 10 | "A scream split the air—a woman’s voice, raw with terror." | | 11 | "Inside, frozen in suspended animation, were the faces of missing people—doctors, nurses, cops, civilians." |
| |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1129 | | adjectiveStacks | 1 | | stackExamples | | 0 | "small, bone-white token" |
| | adverbCount | 22 | | adverbRatio | 0.01948627103631532 | | lyAdverbCount | 4 | | lyAdverbRatio | 0.00354295837023915 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 107 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 107 | | mean | 12.26 | | std | 7.43 | | cv | 0.606 | | sampleLengths | | 0 | 26 | | 1 | 7 | | 2 | 17 | | 3 | 21 | | 4 | 22 | | 5 | 21 | | 6 | 4 | | 7 | 13 | | 8 | 20 | | 9 | 9 | | 10 | 20 | | 11 | 2 | | 12 | 2 | | 13 | 29 | | 14 | 18 | | 15 | 8 | | 16 | 3 | | 17 | 4 | | 18 | 12 | | 19 | 13 | | 20 | 27 | | 21 | 10 | | 22 | 18 | | 23 | 26 | | 24 | 7 | | 25 | 10 | | 26 | 25 | | 27 | 3 | | 28 | 10 | | 29 | 15 | | 30 | 7 | | 31 | 22 | | 32 | 12 | | 33 | 6 | | 34 | 3 | | 35 | 13 | | 36 | 5 | | 37 | 9 | | 38 | 1 | | 39 | 12 | | 40 | 7 | | 41 | 13 | | 42 | 10 | | 43 | 1 | | 44 | 7 | | 45 | 16 | | 46 | 11 | | 47 | 16 | | 48 | 12 | | 49 | 15 |
| |
| 54.52% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 5 | | diversityRatio | 0.35514018691588783 | | totalSentences | 107 | | uniqueOpeners | 38 | |
| 38.76% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 86 | | matches | | 0 | "Instead, she stepped forward, her" |
| | ratio | 0.012 | |
| 80.47% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 30 | | totalSentences | 86 | | matches | | 0 | "She didn’t have time to" | | 1 | "Her target had vanished into" | | 2 | "She rounded the corner onto" | | 3 | "He’d been here before." | | 4 | "She didn’t hesitate, vaulting over" | | 5 | "She climbed, her muscles honed" | | 6 | "she called, her voice cutting" | | 7 | "He turned, and for a" | | 8 | "he said, his Spanish accent" | | 9 | "She didn’t answer." | | 10 | "He pulled a small, bone-white" | | 11 | "She’d heard whispers in the" | | 12 | "Her gloved hand closed around" | | 13 | "It was colder than it" | | 14 | "She pressed it to her" | | 15 | "She’d seen things that defied" | | 16 | "She kicked aside the debris," | | 17 | "She stepped onto the first" | | 18 | "She kept her hand near" | | 19 | "He leaned closer, his breath" |
| | ratio | 0.349 | |
| 18.14% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 76 | | totalSentences | 86 | | matches | | 0 | "The rain fell in sheets," | | 1 | "She didn’t have time to" | | 2 | "The figure ahead darted into" | | 3 | "Quinn’s boots echoed sharply against" | | 4 | "The city’s neon signs blurred" | | 5 | "Her target had vanished into" | | 6 | "None of them mattered." | | 7 | "She rounded the corner onto" | | 8 | "A man’s laugh—low, mocking—cut through" | | 9 | "Quinn’s hand drifted to her" | | 10 | "The man’s back was to" | | 11 | "Leather and something else—ozone, like" | | 12 | "A supernatural signature." | | 13 | "He’d been here before." | | 14 | "She didn’t hesitate, vaulting over" | | 15 | "The alley narrowed, ending at" | | 16 | "She climbed, her muscles honed" | | 17 | "she called, her voice cutting" | | 18 | "He turned, and for a" | | 19 | "The scar on his left" |
| | ratio | 0.884 | |
| 58.14% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 86 | | matches | | 0 | "If she missed this lead," |
| | ratio | 0.012 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 49 | | technicalSentenceCount | 1 | | matches | | 0 | "The clique moved through the market like water finding its path, avoiding eye contact with anyone who might recognize them." |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 12 | | uselessAdditionCount | 5 | | matches | | 0 | "she called, her voice cutting through the wind" | | 1 | "he said, his Spanish accent softening the words" | | 2 | "She stepped, the bone token burning a hole in her pocket" | | 3 | "He leaned, his breath smelling of cloves and decay" | | 4 | "Herrera said, his voice low" |
| |
| 38.89% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 7 | | fancyCount | 3 | | fancyTags | | 0 | "he whispered (whisper)" | | 1 | "she hissed (hiss)" | | 2 | "she snapped (snap)" |
| | dialogueSentences | 27 | | tagDensity | 0.259 | | leniency | 0.519 | | rawRatio | 0.429 | | effectiveRatio | 0.222 | |