| 77.55% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 17 | | adverbTagCount | 3 | | adverbTags | | 0 | "Rory leaned back [back]" | | 1 | "Rory said quietly [quietly]" | | 2 | "Eva said softly [softly]" |
| | dialogueSentences | 49 | | tagDensity | 0.347 | | leniency | 0.694 | | rawRatio | 0.176 | | effectiveRatio | 0.122 | |
| 89.48% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1426 | | totalAiIsmAdverbs | 3 | | found | | | highlights | | 0 | "slowly" | | 1 | "slightly" | | 2 | "softly" |
| |
| 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) | |
| 50.91% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1426 | | totalAiIsms | 14 | | found | | | highlights | | 0 | "lilt" | | 1 | "flicked" | | 2 | "silk" | | 3 | "silence" | | 4 | "weight" | | 5 | "pulse" | | 6 | "warmth" | | 7 | "familiar" | | 8 | "stomach" |
| |
| 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 | 125 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 36 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 2 | | totalWords | 1426 | | ratio | 0.001 | | matches | | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 16 | | unquotedAttributions | 0 | | matches | (empty) | |
| 33.33% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 71 | | wordCount | 1079 | | uniqueNames | 19 | | maxNameDensity | 2.13 | | worstName | "Rory" | | maxWindowNameDensity | 4 | | worstWindowName | "Rory" | | discoveredNames | | Rory | 23 | | Soho | 3 | | London | 2 | | Silas | 8 | | Yu-Fei | 1 | | Golden | 1 | | Empress | 1 | | Welsh | 1 | | Laphroaig | 1 | | Eva | 18 | | Cardiff | 2 | | Mayfair | 1 | | Prague | 1 | | Vienna | 1 | | Silence | 1 | | Raven | 2 | | Nest | 2 | | Wales | 1 | | Paddington | 1 |
| | persons | | 0 | "Rory" | | 1 | "Silas" | | 2 | "Eva" | | 3 | "Raven" | | 4 | "Nest" |
| | places | | 0 | "Soho" | | 1 | "London" | | 2 | "Golden" | | 3 | "Cardiff" | | 4 | "Prague" | | 5 | "Vienna" | | 6 | "Wales" | | 7 | "Paddington" |
| | globalScore | 0.434 | | windowScore | 0.333 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 72 | | glossingSentenceCount | 1 | | matches | | |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1426 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 125 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 68 | | mean | 20.97 | | std | 18.09 | | cv | 0.862 | | sampleLengths | | 0 | 18 | | 1 | 21 | | 2 | 29 | | 3 | 6 | | 4 | 32 | | 5 | 4 | | 6 | 1 | | 7 | 34 | | 8 | 3 | | 9 | 54 | | 10 | 1 | | 11 | 5 | | 12 | 42 | | 13 | 23 | | 14 | 69 | | 15 | 15 | | 16 | 4 | | 17 | 28 | | 18 | 13 | | 19 | 31 | | 20 | 4 | | 21 | 3 | | 22 | 35 | | 23 | 15 | | 24 | 2 | | 25 | 29 | | 26 | 37 | | 27 | 14 | | 28 | 16 | | 29 | 3 | | 30 | 5 | | 31 | 12 | | 32 | 59 | | 33 | 58 | | 34 | 4 | | 35 | 3 | | 36 | 16 | | 37 | 7 | | 38 | 38 | | 39 | 8 | | 40 | 6 | | 41 | 12 | | 42 | 26 | | 43 | 15 | | 44 | 4 | | 45 | 62 | | 46 | 23 | | 47 | 24 | | 48 | 37 | | 49 | 18 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 93 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 179 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 125 | | ratio | 0 | | matches | (empty) | |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 559 | | adjectiveStacks | 1 | | stackExamples | | 0 | "small crescent-shaped scar" |
| | adverbCount | 15 | | adverbRatio | 0.026833631484794274 | | lyAdverbCount | 2 | | lyAdverbRatio | 0.0035778175313059034 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 125 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 125 | | mean | 11.41 | | std | 7.44 | | cv | 0.652 | | sampleLengths | | 0 | 18 | | 1 | 10 | | 2 | 11 | | 3 | 12 | | 4 | 17 | | 5 | 6 | | 6 | 17 | | 7 | 15 | | 8 | 4 | | 9 | 1 | | 10 | 9 | | 11 | 6 | | 12 | 19 | | 13 | 3 | | 14 | 22 | | 15 | 24 | | 16 | 8 | | 17 | 1 | | 18 | 5 | | 19 | 13 | | 20 | 24 | | 21 | 3 | | 22 | 2 | | 23 | 17 | | 24 | 6 | | 25 | 10 | | 26 | 19 | | 27 | 21 | | 28 | 19 | | 29 | 15 | | 30 | 4 | | 31 | 11 | | 32 | 17 | | 33 | 13 | | 34 | 11 | | 35 | 3 | | 36 | 17 | | 37 | 4 | | 38 | 3 | | 39 | 28 | | 40 | 7 | | 41 | 15 | | 42 | 2 | | 43 | 19 | | 44 | 10 | | 45 | 6 | | 46 | 17 | | 47 | 14 | | 48 | 5 | | 49 | 9 |
| |
| 49.87% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 11 | | diversityRatio | 0.352 | | totalSentences | 125 | | uniqueOpeners | 44 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 85 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 24 | | totalSentences | 85 | | matches | | 0 | "She froze, her fingers curled" | | 1 | "Her black wool coat hung" | | 2 | "She knelt to gather the" | | 3 | "She tucked it behind her" | | 4 | "She looked up." | | 5 | "Her hair, once a riot" | | 6 | "Her cheekbones jutted sharp enough" | | 7 | "She chose the seat facing" | | 8 | "She didn't wince." | | 9 | "She reached up, her fingers" | | 10 | "She knew what fingerprints on" | | 11 | "His left leg dragged slightly" | | 12 | "He towered over the booth," | | 13 | "His grey-streaked auburn beard twitched" | | 14 | "He turned and limped back" | | 15 | "He didn't go through it." | | 16 | "He simply leaned against the" | | 17 | "Her pulse kicked against her" | | 18 | "She had hated Eva for" | | 19 | "She had spent four years" |
| | ratio | 0.282 | |
| 7.06% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 77 | | totalSentences | 85 | | matches | | 0 | "The whisky glass hit the" | | 1 | "She froze, her fingers curled" | | 2 | "Nobody in Soho dropped a" | | 3 | "A woman stood beside the" | | 4 | "Her black wool coat hung" | | 5 | "She knelt to gather the" | | 6 | "She tucked it behind her" | | 7 | "The woman's breath caught." | | 8 | "Rory's hand stilled over a" | | 9 | "Nobody in London called her" | | 10 | "She looked up." | | 11 | "The fluorescent bleed from the" | | 12 | "Her hair, once a riot" | | 13 | "Her cheekbones jutted sharp enough" | | 14 | "The name tasted like rust." | | 15 | "Rory stood, dumping the glass" | | 16 | "A quiet signal." | | 17 | "Rory said, grabbing two clean" | | 18 | "Eva slid into the worn" | | 19 | "She chose the seat facing" |
| | ratio | 0.906 | |
| 58.82% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 85 | | matches | | 0 | "Before Rory could move, the" |
| | ratio | 0.012 | |
| 61.69% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 44 | | technicalSentenceCount | 5 | | matches | | 0 | "Not Silas, not Yu-Fei down at the Golden Empress, not the half-drunk journalists who haunted the stools at midnight." | | 1 | "The Raven's Nest was nearly empty, just a retired civil servant nursing a gin in the far corner and Silas limping slowly along the length of the bar, wiping dow…" | | 2 | "He turned and limped back toward the far end of the bar, stopping beside the heavy oak bookshelf that hid the back room." | | 3 | "The warmth that used to live behind her dark eyes had burned away, leaving nothing but ash and calculation." | | 4 | "The taller man stepped into the dim light, his eyes sweeping past the retired civil servant, past Silas, and locking directly onto Rory's face." |
| |
| 95.59% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 17 | | uselessAdditionCount | 1 | | matches | | 0 | "Eva breathed, her Cardiff accent tearing through the silence, raw and terrified" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 11 | | fancyCount | 2 | | fancyTags | | 0 | "Rory whispered (whisper)" | | 1 | "Eva breathed (breathe)" |
| | dialogueSentences | 49 | | tagDensity | 0.224 | | leniency | 0.449 | | rawRatio | 0.182 | | effectiveRatio | 0.082 | |