| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 14 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 46 | | tagDensity | 0.304 | | leniency | 0.609 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 86.11% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1800 | | totalAiIsmAdverbs | 5 | | found | | | highlights | | 0 | "carefully" | | 1 | "slightly" | | 2 | "very" |
| |
| 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) | |
| 69.44% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1800 | | totalAiIsms | 11 | | found | | | highlights | | 0 | "measured" | | 1 | "pulse" | | 2 | "velvet" | | 3 | "stomach" | | 4 | "familiar" | | 5 | "traced" | | 6 | "silence" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 1 | | maxInWindow | 1 | | found | | 0 | | label | "stomach dropped/sank" | | count | 1 |
|
| | highlights | | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 114 | | matches | (empty) | |
| 55.14% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 5 | | narrationSentences | 114 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 144 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 54 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 9 | | totalWords | 1794 | | ratio | 0.005 | | matches | | 0 | "Don’t worry. Following a lead. Feed Ptolemy. Love you." |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 15 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 45 | | wordCount | 1377 | | uniqueNames | 16 | | maxNameDensity | 0.87 | | worstName | "Rory" | | maxWindowNameDensity | 1.5 | | worstWindowName | "Eva" | | discoveredNames | | Eva | 7 | | Moreau | 1 | | Brick | 2 | | Lane | 2 | | Mayfair | 1 | | Ptolemy | 4 | | Frenchmen | 1 | | Rory | 12 | | Cardiff | 1 | | Evan | 1 | | London | 1 | | Golden | 1 | | Empress | 1 | | Frenchman | 1 | | Lucien | 7 | | Meaning | 2 |
| | persons | | 0 | "Eva" | | 1 | "Moreau" | | 2 | "Ptolemy" | | 3 | "Frenchmen" | | 4 | "Rory" | | 5 | "Evan" | | 6 | "Empress" | | 7 | "Lucien" |
| | places | | 0 | "Brick" | | 1 | "Lane" | | 2 | "Mayfair" | | 3 | "Cardiff" | | 4 | "London" |
| | globalScore | 1 | | windowScore | 1 | |
| 86.71% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 79 | | glossingSentenceCount | 2 | | matches | | 0 | "not quite a smile" | | 1 | "not quite petting, merely acknowledging the cat’s existence" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1794 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 144 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 54 | | mean | 33.22 | | std | 21.77 | | cv | 0.655 | | sampleLengths | | 0 | 51 | | 1 | 5 | | 2 | 94 | | 3 | 26 | | 4 | 16 | | 5 | 15 | | 6 | 18 | | 7 | 3 | | 8 | 57 | | 9 | 72 | | 10 | 22 | | 11 | 51 | | 12 | 5 | | 13 | 44 | | 14 | 15 | | 15 | 1 | | 16 | 49 | | 17 | 51 | | 18 | 5 | | 19 | 23 | | 20 | 45 | | 21 | 7 | | 22 | 40 | | 23 | 50 | | 24 | 22 | | 25 | 50 | | 26 | 102 | | 27 | 24 | | 28 | 25 | | 29 | 59 | | 30 | 68 | | 31 | 19 | | 32 | 45 | | 33 | 29 | | 34 | 37 | | 35 | 28 | | 36 | 50 | | 37 | 37 | | 38 | 2 | | 39 | 32 | | 40 | 44 | | 41 | 21 | | 42 | 38 | | 43 | 37 | | 44 | 1 | | 45 | 15 | | 46 | 48 | | 47 | 30 | | 48 | 39 | | 49 | 32 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 114 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 238 | | matches | (empty) | |
| 83.33% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 5 | | semicolonCount | 0 | | flaggedSentences | 3 | | totalSentences | 144 | | ratio | 0.021 | | matches | | 0 | "And those eyes—one the colour of good whisky, the other a black so complete it seemed to drink the light—found hers and held." | | 1 | "The air that came with him smelled of vetiver, clean wool, and something sharper underneath—ozone, old stone, the faint metallic tang she had once pretended not to notice." | | 2 | "His finger—elegant, unhurried—traced a sigil that made the hair on her arms lift." |
| |
| 84.75% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1393 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 80 | | adverbRatio | 0.057430007178750894 | | lyAdverbCount | 13 | | lyAdverbRatio | 0.00933237616654702 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 144 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 144 | | mean | 12.46 | | std | 9.4 | | cv | 0.755 | | sampleLengths | | 0 | 20 | | 1 | 14 | | 2 | 2 | | 3 | 12 | | 4 | 3 | | 5 | 5 | | 6 | 23 | | 7 | 15 | | 8 | 15 | | 9 | 18 | | 10 | 23 | | 11 | 26 | | 12 | 16 | | 13 | 5 | | 14 | 10 | | 15 | 14 | | 16 | 4 | | 17 | 3 | | 18 | 53 | | 19 | 4 | | 20 | 11 | | 21 | 6 | | 22 | 4 | | 23 | 23 | | 24 | 28 | | 25 | 3 | | 26 | 7 | | 27 | 3 | | 28 | 9 | | 29 | 18 | | 30 | 8 | | 31 | 9 | | 32 | 16 | | 33 | 5 | | 34 | 18 | | 35 | 4 | | 36 | 7 | | 37 | 15 | | 38 | 4 | | 39 | 3 | | 40 | 8 | | 41 | 1 | | 42 | 34 | | 43 | 15 | | 44 | 7 | | 45 | 3 | | 46 | 28 | | 47 | 9 | | 48 | 4 | | 49 | 5 |
| |
| 61.57% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 8 | | diversityRatio | 0.4027777777777778 | | totalSentences | 144 | | uniqueOpeners | 58 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 7 | | totalSentences | 106 | | matches | | 0 | "Instead she moved aside, and" | | 1 | "Then the second." | | 2 | "Bright blue eyes she kept" | | 3 | "Then there had been the" | | 4 | "Of course he could." | | 5 | "Then she led him to" | | 6 | "Instead she heard herself say," |
| | ratio | 0.066 | |
| 91.70% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 34 | | totalSentences | 106 | | matches | | 0 | "She already knew." | | 1 | "She opened the door anyway." | | 2 | "Her name in that voice" | | 3 | "She did not step back." | | 4 | "He glanced past her shoulder," | | 5 | "She should have shut the" | | 6 | "She left the third undone," | | 7 | "He was too tall for" | | 8 | "He didn’t look away." | | 9 | "He never had." | | 10 | "His accent wrapped the words" | | 11 | "They had survived Cardiff together," | | 12 | "She kept her back to" | | 13 | "She felt the heat of" | | 14 | "His breath stirred the fine" | | 15 | "She had known." | | 16 | "She had gone back." | | 17 | "He had asked questions about" | | 18 | "she said, because lying to" | | 19 | "She could still feel the" |
| | ratio | 0.321 | |
| 82.64% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 80 | | totalSentences | 106 | | matches | | 0 | "The third deadbolt slid home" | | 1 | "Rory’s fingers lingered on the" | | 2 | "She already knew." | | 3 | "She opened the door anyway." | | 4 | "Lucien Moreau stood on the" | | 5 | "Charcoal suit cut close to" | | 6 | "Platinum hair combed back so" | | 7 | "The ivory handle of his" | | 8 | "Her name in that voice" | | 9 | "She did not step back." | | 10 | "A faint crease appeared at" | | 11 | "He glanced past her shoulder," | | 12 | "Rory’s mind, usually so quick" | | 13 | "She should have shut the" | | 14 | "The air that came with" | | 15 | "The door closed." | | 16 | "Habit made her throw the" | | 17 | "She left the third undone," | | 18 | "Lucien set the cane against" | | 19 | "He was too tall for" |
| | ratio | 0.755 | |
| 47.17% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 106 | | matches | | 0 | "Even, measured, nothing like Eva’s" |
| | ratio | 0.009 | |
| 69.97% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 49 | | technicalSentenceCount | 5 | | matches | | 0 | "Lucien Moreau stood on the narrow landing as if the grimy stairwell of a Brick Lane walk-up were a drawing room in Mayfair." | | 1 | "The air that came with him smelled of vetiver, clean wool, and something sharper underneath—ozone, old stone, the faint metallic tang she had once pretended not…" | | 2 | "Latin, cramped diagrams of circles that made her eyes ache." | | 3 | "A late run for the Golden Empress, rain sheeting down, the Frenchman in the charcoal suit who tipped in cash and looked at her as if she were the only solid thi…" | | 4 | "The pad of his thumb found the crescent scar without looking, as if it had been waiting there all this time." |
| |
| 89.29% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 14 | | uselessAdditionCount | 1 | | matches | | 0 | "she asked, because the silence was worse" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 6 | | fancyCount | 2 | | fancyTags | | 0 | "she whispered (whisper)" | | 1 | "she heard (hear)" |
| | dialogueSentences | 46 | | tagDensity | 0.13 | | leniency | 0.261 | | rawRatio | 0.333 | | effectiveRatio | 0.087 | |