| 75.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 8 | | adverbTagCount | 2 | | adverbTags | | 0 | "Tomás stepped aside [aside]" | | 1 | "Tomás had somehow [somehow]" |
| | dialogueSentences | 32 | | tagDensity | 0.25 | | leniency | 0.5 | | rawRatio | 0.25 | | effectiveRatio | 0.125 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1468 | | 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) | |
| 89.78% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1468 | | totalAiIsms | 3 | | found | | | highlights | | 0 | "rhythmic" | | 1 | "flicker" | | 2 | "flickered" |
| |
| 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 | 125 | | matches | | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 0 | | hedgeCount | 1 | | narrationSentences | 125 | | filterMatches | (empty) | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 149 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 27 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1468 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 7 | | unquotedAttributions | 0 | | matches | (empty) | |
| 66.67% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 64 | | wordCount | 1234 | | uniqueNames | 25 | | maxNameDensity | 1.54 | | worstName | "Harlow" | | maxWindowNameDensity | 3 | | worstWindowName | "Tomás" | | discoveredNames | | Quinn | 2 | | Inverness | 1 | | Street | 1 | | Camden | 3 | | Lock | 1 | | Met | 1 | | Town | 1 | | Morris | 2 | | Harlow | 19 | | Saint | 1 | | Christopher | 1 | | Herrera | 2 | | Greeks | 1 | | London | 1 | | Jasper | 3 | | Vale | 3 | | Lantern | 1 | | Market | 1 | | Blood | 1 | | Exchange | 1 | | Stalls | 3 | | Long | 1 | | Sleep | 1 | | Tomás | 11 | | Spanish | 1 |
| | persons | | 0 | "Quinn" | | 1 | "Lock" | | 2 | "Morris" | | 3 | "Harlow" | | 4 | "Saint" | | 5 | "Christopher" | | 6 | "Herrera" | | 7 | "Greeks" | | 8 | "Jasper" | | 9 | "Vale" | | 10 | "Market" | | 11 | "Stalls" | | 12 | "Tomás" |
| | places | | 0 | "Inverness" | | 1 | "Street" | | 2 | "Camden" | | 3 | "Met" | | 4 | "Town" | | 5 | "London" | | 6 | "Spanish" |
| | globalScore | 0.73 | | windowScore | 0.667 | |
| 95.05% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 91 | | glossingSentenceCount | 2 | | matches | | 0 | "something like a smile" | | 1 | "sounded like a child laughing" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 1 | | per1kWords | 0.681 | | wordCount | 1468 | | matches | | 0 | "not in panic, but in ritual" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 149 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 63 | | mean | 23.3 | | std | 21.02 | | cv | 0.902 | | sampleLengths | | 0 | 50 | | 1 | 3 | | 2 | 23 | | 3 | 58 | | 4 | 6 | | 5 | 26 | | 6 | 19 | | 7 | 7 | | 8 | 3 | | 9 | 48 | | 10 | 52 | | 11 | 6 | | 12 | 53 | | 13 | 53 | | 14 | 21 | | 15 | 19 | | 16 | 4 | | 17 | 4 | | 18 | 30 | | 19 | 6 | | 20 | 50 | | 21 | 2 | | 22 | 50 | | 23 | 76 | | 24 | 37 | | 25 | 71 | | 26 | 4 | | 27 | 10 | | 28 | 49 | | 29 | 20 | | 30 | 3 | | 31 | 14 | | 32 | 4 | | 33 | 19 | | 34 | 8 | | 35 | 22 | | 36 | 3 | | 37 | 20 | | 38 | 2 | | 39 | 3 | | 40 | 38 | | 41 | 10 | | 42 | 26 | | 43 | 43 | | 44 | 2 | | 45 | 55 | | 46 | 8 | | 47 | 10 | | 48 | 91 | | 49 | 24 |
| |
| 99.65% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 125 | | matches | | 0 | "been transformed" | | 1 | "were made" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 2 | | totalVerbs | 211 | | matches | | 0 | "was heading" | | 1 | "was still swaying" |
| |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 149 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1241 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 37 | | adverbRatio | 0.029814665592264304 | | lyAdverbCount | 1 | | lyAdverbRatio | 0.0008058017727639 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 149 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 149 | | mean | 9.85 | | std | 5.88 | | cv | 0.597 | | sampleLengths | | 0 | 17 | | 1 | 20 | | 2 | 4 | | 3 | 9 | | 4 | 3 | | 5 | 4 | | 6 | 16 | | 7 | 3 | | 8 | 11 | | 9 | 17 | | 10 | 11 | | 11 | 12 | | 12 | 7 | | 13 | 6 | | 14 | 3 | | 15 | 16 | | 16 | 7 | | 17 | 19 | | 18 | 7 | | 19 | 3 | | 20 | 8 | | 21 | 15 | | 22 | 5 | | 23 | 9 | | 24 | 6 | | 25 | 5 | | 26 | 12 | | 27 | 16 | | 28 | 15 | | 29 | 9 | | 30 | 3 | | 31 | 3 | | 32 | 6 | | 33 | 11 | | 34 | 11 | | 35 | 18 | | 36 | 7 | | 37 | 20 | | 38 | 6 | | 39 | 3 | | 40 | 8 | | 41 | 16 | | 42 | 11 | | 43 | 10 | | 44 | 19 | | 45 | 4 | | 46 | 4 | | 47 | 3 | | 48 | 4 | | 49 | 23 |
| |
| 56.60% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 4 | | diversityRatio | 0.35570469798657717 | | totalSentences | 149 | | uniqueOpeners | 53 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 5 | | totalSentences | 119 | | matches | | 0 | "Then he stepped into the" | | 1 | "Somewhere ahead, Jasper Vale ducked" | | 2 | "Then another stall, this one" | | 3 | "Then a third, its keeper" | | 4 | "Then at Tomás." |
| | ratio | 0.042 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 20 | | totalSentences | 119 | | matches | | 0 | "He ran harder." | | 1 | "He was heading for Camden" | | 2 | "Her lungs burned." | | 3 | "She eased her radio from" | | 4 | "She clicked the radio back" | | 5 | "It dead-ended at the old" | | 6 | "They used it for storage" | | 7 | "He reached a rusted door" | | 8 | "He pressed it against the" | | 9 | "She drew her torch and" | | 10 | "She reached inside her own" | | 11 | "It wasn't true." | | 12 | "Her torch caught walls that" | | 13 | "He turned, caught her eye," | | 14 | "Their eyes caught the torch" | | 15 | "His dark hair curled over" | | 16 | "She'd seen his photograph once," | | 17 | "She got four paces before" | | 18 | "She pushed through it." | | 19 | "He glanced back once, and" |
| | ratio | 0.168 | |
| 52.44% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 97 | | totalSentences | 119 | | matches | | 0 | "The suspect threw a shoulder" | | 1 | "Harlow Quinn vaulted the first," | | 2 | "Rain needled her face." | | 3 | "The alley stank of chip" | | 4 | "The man glanced back." | | 5 | "He ran harder." | | 6 | "Harlow followed him out of" | | 7 | "The old market stalls stood" | | 8 | "Puddles mirrored the few neon" | | 9 | "A night bus sluiced past," | | 10 | "Harlow used the moment to" | | 11 | "He was heading for Camden" | | 12 | "Her lungs burned." | | 13 | "She eased her radio from" | | 14 | "She clicked the radio back" | | 15 | "The suspect turned through a" | | 16 | "Harlow recognised the narrow cut." | | 17 | "It dead-ended at the old" | | 18 | "They used it for storage" | | 19 | "The rain slackened enough for" |
| | ratio | 0.815 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 119 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 59 | | technicalSentenceCount | 3 | | matches | | 0 | "Young, hood drawn low, with a split lower lip that curled into something like a smile." | | 1 | "Her torch caught walls that changed as she went deeper: first painted brick, then glazed tile, then rough stone that gleamed with damp." | | 2 | "A shutter of corrugated iron slammed down across a display of jars, each one swirling with something that was not smoke." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 8 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 3 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 32 | | tagDensity | 0.094 | | leniency | 0.188 | | rawRatio | 0 | | effectiveRatio | 0 | |