| 70.97% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 24 | | adverbTagCount | 4 | | adverbTags | | 0 | "Eva pulled back [back]" | | 1 | "Aurora said finally [finally]" | | 2 | "Eva said quietly [quietly]" | | 3 | "Eva looked around [around]" |
| | dialogueSentences | 62 | | tagDensity | 0.387 | | leniency | 0.774 | | rawRatio | 0.167 | | effectiveRatio | 0.129 | |
| 71.82% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1774 | | totalAiIsmAdverbs | 10 | | found | | | highlights | | 0 | "slowly" | | 1 | "completely" | | 2 | "lightly" | | 3 | "very" | | 4 | "carefully" | | 5 | "really" |
| |
| 100.00% | AI-ism character names | Target: 0 AI-default names (16 tracked, −20% each) | | codexExemptions | | | found | (empty) | |
| 100.00% | AI-ism location names | Target: 0 AI-default location names (33 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 66.18% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1774 | | totalAiIsms | 12 | | found | | | highlights | | 0 | "throbbed" | | 1 | "eyebrow" | | 2 | "familiar" | | 3 | "weight" | | 4 | "perfect" | | 5 | "could feel" | | 6 | "silence" | | 7 | "absolutely" | | 8 | "efficient" |
| |
| 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 | 93 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 0 | | hedgeCount | 0 | | narrationSentences | 93 | | filterMatches | (empty) | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 131 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 59 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1763 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 22 | | unquotedAttributions | 0 | | matches | (empty) | |
| 0.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 82 | | wordCount | 1146 | | uniqueNames | 16 | | maxNameDensity | 2.88 | | worstName | "Eva" | | maxWindowNameDensity | 5 | | worstWindowName | "Eva" | | discoveredNames | | Chapter | 1 | | One | 1 | | Raven | 1 | | Nest | 1 | | Silas | 5 | | Golden | 1 | | Empress | 1 | | Cardiff | 2 | | Aurora | 29 | | Pre-Law | 1 | | Eva | 33 | | Soho | 2 | | Evan | 1 | | Snowdon | 1 | | Through | 1 | | London | 1 |
| | persons | | 0 | "Raven" | | 1 | "Nest" | | 2 | "Silas" | | 3 | "Empress" | | 4 | "Aurora" | | 5 | "Eva" | | 6 | "Evan" | | 7 | "Snowdon" | | 8 | "Through" |
| | places | | 0 | "Golden" | | 1 | "Cardiff" | | 2 | "Soho" | | 3 | "London" |
| | globalScore | 0.06 | | windowScore | 0 | |
| 76.47% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 68 | | glossingSentenceCount | 2 | | matches | | 0 | "smelled like something from a department s" | | 1 | "looked like the girl who'd convinced Auro" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1763 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 131 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 66 | | mean | 26.71 | | std | 21.51 | | cv | 0.805 | | sampleLengths | | 0 | 3 | | 1 | 79 | | 2 | 10 | | 3 | 53 | | 4 | 1 | | 5 | 72 | | 6 | 32 | | 7 | 1 | | 8 | 41 | | 9 | 15 | | 10 | 24 | | 11 | 43 | | 12 | 35 | | 13 | 21 | | 14 | 34 | | 15 | 4 | | 16 | 3 | | 17 | 55 | | 18 | 17 | | 19 | 39 | | 20 | 18 | | 21 | 3 | | 22 | 59 | | 23 | 6 | | 24 | 34 | | 25 | 5 | | 26 | 7 | | 27 | 50 | | 28 | 33 | | 29 | 9 | | 30 | 7 | | 31 | 47 | | 32 | 6 | | 33 | 13 | | 34 | 10 | | 35 | 43 | | 36 | 59 | | 37 | 3 | | 38 | 36 | | 39 | 65 | | 40 | 6 | | 41 | 19 | | 42 | 4 | | 43 | 21 | | 44 | 44 | | 45 | 12 | | 46 | 68 | | 47 | 1 | | 48 | 78 | | 49 | 3 |
| |
| 93.94% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 3 | | totalSentences | 93 | | matches | | 0 | "been gone" | | 1 | "was aimed" | | 2 | "was gone" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 199 | | matches | | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 131 | | ratio | 0 | | matches | (empty) | |
| 94.74% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1152 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 53 | | adverbRatio | 0.04600694444444445 | | lyAdverbCount | 21 | | lyAdverbRatio | 0.018229166666666668 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 131 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 131 | | mean | 13.46 | | std | 10.57 | | cv | 0.785 | | sampleLengths | | 0 | 13 | | 1 | 21 | | 2 | 48 | | 3 | 10 | | 4 | 2 | | 5 | 16 | | 6 | 21 | | 7 | 14 | | 8 | 1 | | 9 | 10 | | 10 | 1 | | 11 | 17 | | 12 | 19 | | 13 | 25 | | 14 | 3 | | 15 | 5 | | 16 | 24 | | 17 | 1 | | 18 | 3 | | 19 | 20 | | 20 | 18 | | 21 | 10 | | 22 | 5 | | 23 | 11 | | 24 | 7 | | 25 | 1 | | 26 | 5 | | 27 | 24 | | 28 | 19 | | 29 | 6 | | 30 | 18 | | 31 | 11 | | 32 | 21 | | 33 | 17 | | 34 | 17 | | 35 | 4 | | 36 | 3 | | 37 | 14 | | 38 | 2 | | 39 | 5 | | 40 | 12 | | 41 | 22 | | 42 | 5 | | 43 | 2 | | 44 | 2 | | 45 | 8 | | 46 | 18 | | 47 | 21 | | 48 | 14 | | 49 | 4 |
| |
| 59.29% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 14 | | diversityRatio | 0.4198473282442748 | | totalSentences | 131 | | uniqueOpeners | 55 | |
| 83.33% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 80 | | matches | | 0 | "Actually flinched, the way you" | | 1 | "Then she was gone, threading" |
| | ratio | 0.025 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 17 | | totalSentences | 80 | | matches | | 0 | "She was halfway through ordering" | | 1 | "Her dark hair had been" | | 2 | "She crossed the bar in" | | 3 | "She smelled like something from" | | 4 | "She watched Eva's expression shift," | | 5 | "He was good at reading" | | 6 | "She'd learned how to belong" | | 7 | "Their friendship had been the" | | 8 | "She could feel Eva watching" | | 9 | "She set her martini down" | | 10 | "She raised her glass." | | 11 | "She looked at it, and" | | 12 | "she said, not bothering to" | | 13 | "She stood, reaching for her" | | 14 | "he asked, settling behind the" | | 15 | "It came through as a" | | 16 | "She set the phone face-down" |
| | ratio | 0.213 | |
| 35.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 68 | | totalSentences | 80 | | matches | | 0 | "# Chapter One The Raven's" | | 1 | "Aurora had grown accustomed to" | | 2 | "Tonight, she'd stopped in after" | | 3 | "She was halfway through ordering" | | 4 | "The one that had punctured" | | 5 | "The one that had coaxed" | | 6 | "The laugh that belonged to" | | 7 | "Aurora turned slowly on the" | | 8 | "A tailored charcoal blazer hung" | | 9 | "Her dark hair had been" | | 10 | "The face, though." | | 11 | "The face was still Eva's." | | 12 | "The one with the too-wide" | | 13 | "Eva's grin widened." | | 14 | "She crossed the bar in" | | 15 | "She smelled like something from" | | 16 | "Eva pulled back, hands still" | | 17 | "Aurora said, and it came" | | 18 | "She watched Eva's expression shift," | | 19 | "Eva laughed, that same laugh," |
| | ratio | 0.85 | |
| 100.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 80 | | matches | | 0 | "Even shared histories faded when" | | 1 | "Now it was aimed at" |
| | ratio | 0.025 | |
| 57.82% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 42 | | technicalSentenceCount | 5 | | matches | | 0 | "Tonight, she'd stopped in after a delivery run from the Golden Empress, still wearing the restaurant's branded jacket though her feet throbbed with the kind of …" | | 1 | "The laugh that belonged to someone she'd spent four years convincing herself she'd forgotten." | | 2 | "The problem was that the Aurora who'd drunk cheap wine and told Eva everything was the same Aurora who'd needed to become someone else to survive." | | 3 | "She set her martini down with deliberate care, the kind of precision that suggested the drink was the only thing she could control in the moment." | | 4 | "Seven years of not seeing Eva had allowed her to imagine her friend's life in a particular way: successful, uncomplicated, filled with the kind of ease that cam…" |
| |
| 62.50% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 24 | | uselessAdditionCount | 3 | | matches | | 0 | "Eva pulled back, hands still gripping Aurora's shoulders" | | 1 | "Aurora asked, sidesteppingcarefully" | | 2 | "she said, not bothering to read the message" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 14 | | fancyCount | 2 | | fancyTags | | 0 | "Eva laughed (laugh)" | | 1 | "Eva agreed (agree)" |
| | dialogueSentences | 62 | | tagDensity | 0.226 | | leniency | 0.452 | | rawRatio | 0.143 | | effectiveRatio | 0.065 | |