| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 25 | | adverbTagCount | 2 | | adverbTags | | 0 | "Tomás stepped aside [aside]" | | 1 | "Tomás pulled back [back]" |
| | dialogueSentences | 48 | | tagDensity | 0.521 | | leniency | 1 | | rawRatio | 0.08 | | effectiveRatio | 0.08 | |
| 72.87% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1290 | | totalAiIsmAdverbs | 7 | | found | | | highlights | | 0 | "slowly" | | 1 | "slightly" | | 2 | "quickly" | | 3 | "softly" |
| |
| 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) | |
| 61.24% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1290 | | totalAiIsms | 10 | | found | | | highlights | | 0 | "fractured" | | 1 | "scanned" | | 2 | "weight" | | 3 | "echoed" | | 4 | "etched" | | 5 | "gloom" | | 6 | "footsteps" | | 7 | "dancing" | | 8 | "depths" |
| |
| 66.67% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 2 | | maxInWindow | 2 | | found | | 0 | | label | "knuckles turned white" | | count | 1 |
| | 1 | | label | "hung in the air" | | count | 1 |
|
| | highlights | | 0 | "knuckles turned white" | | 1 | "hung in the air" |
| |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 156 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 2 | | narrationSentences | 156 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 180 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 20 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1290 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 8 | | unquotedAttributions | 0 | | matches | (empty) | |
| 0.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 69 | | wordCount | 1057 | | uniqueNames | 11 | | maxNameDensity | 2.93 | | worstName | "Quinn" | | maxWindowNameDensity | 5 | | worstWindowName | "Tomás" | | discoveredNames | | Soho | 2 | | Harlow | 1 | | Quinn | 31 | | Herrera | 1 | | Saint | 1 | | Christopher | 1 | | Tomás | 28 | | Steam | 1 | | Morris | 1 | | Raven | 1 | | Nest | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Herrera" | | 3 | "Saint" | | 4 | "Christopher" | | 5 | "Tomás" | | 6 | "Steam" | | 7 | "Morris" | | 8 | "Raven" | | 9 | "Nest" |
| | places | | | globalScore | 0.034 | | windowScore | 0 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 90 | | glossingSentenceCount | 1 | | matches | | 0 | "looked like an abandoned station" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1290 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 180 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 57 | | mean | 22.63 | | std | 14.77 | | cv | 0.653 | | sampleLengths | | 0 | 73 | | 1 | 52 | | 2 | 14 | | 3 | 54 | | 4 | 35 | | 5 | 6 | | 6 | 40 | | 7 | 5 | | 8 | 32 | | 9 | 18 | | 10 | 12 | | 11 | 17 | | 12 | 27 | | 13 | 11 | | 14 | 18 | | 15 | 9 | | 16 | 32 | | 17 | 10 | | 18 | 31 | | 19 | 8 | | 20 | 11 | | 21 | 34 | | 22 | 25 | | 23 | 31 | | 24 | 18 | | 25 | 16 | | 26 | 45 | | 27 | 14 | | 28 | 49 | | 29 | 16 | | 30 | 39 | | 31 | 10 | | 32 | 16 | | 33 | 40 | | 34 | 35 | | 35 | 9 | | 36 | 40 | | 37 | 22 | | 38 | 4 | | 39 | 25 | | 40 | 13 | | 41 | 31 | | 42 | 9 | | 43 | 6 | | 44 | 27 | | 45 | 17 | | 46 | 7 | | 47 | 24 | | 48 | 9 | | 49 | 15 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 156 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 192 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 180 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 751 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 10 | | adverbRatio | 0.013315579227696404 | | lyAdverbCount | 5 | | lyAdverbRatio | 0.006657789613848202 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 180 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 180 | | mean | 7.17 | | std | 3.55 | | cv | 0.495 | | sampleLengths | | 0 | 20 | | 1 | 18 | | 2 | 9 | | 3 | 15 | | 4 | 11 | | 5 | 14 | | 6 | 11 | | 7 | 15 | | 8 | 8 | | 9 | 4 | | 10 | 4 | | 11 | 10 | | 12 | 4 | | 13 | 15 | | 14 | 8 | | 15 | 12 | | 16 | 8 | | 17 | 7 | | 18 | 8 | | 19 | 9 | | 20 | 11 | | 21 | 7 | | 22 | 6 | | 23 | 3 | | 24 | 8 | | 25 | 12 | | 26 | 6 | | 27 | 11 | | 28 | 5 | | 29 | 18 | | 30 | 6 | | 31 | 2 | | 32 | 6 | | 33 | 8 | | 34 | 5 | | 35 | 5 | | 36 | 7 | | 37 | 5 | | 38 | 8 | | 39 | 9 | | 40 | 4 | | 41 | 12 | | 42 | 11 | | 43 | 4 | | 44 | 7 | | 45 | 12 | | 46 | 6 | | 47 | 9 | | 48 | 8 | | 49 | 16 |
| |
| 41.67% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 15 | | diversityRatio | 0.24444444444444444 | | totalSentences | 180 | | uniqueOpeners | 44 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 149 | | matches | (empty) | | ratio | 0 | |
| 75.03% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 54 | | totalSentences | 149 | | matches | | 0 | "She kept her eyes locked" | | 1 | "Her worn leather watch on" | | 2 | "He wove through the crowds" | | 3 | "He stumbled, cursing, but Quinn" | | 4 | "She needed the target." | | 5 | "Her voice cut through the" | | 6 | "She checked her service weapon" | | 7 | "He stood before a brick" | | 8 | "She leveled her weapon at" | | 9 | "His olive skin glistened under" | | 10 | "He raised his hands, palms" | | 11 | "She scanned the alley for" | | 12 | "He lowered his hands slightly." | | 13 | "She moved to flank him," | | 14 | "He held a small, jagged" | | 15 | "It looked ancient, etched with" | | 16 | "He held it up between" | | 17 | "She didn't trust the supernatural" | | 18 | "His warm brown eyes held" | | 19 | "It groaned, metal on metal." |
| | ratio | 0.362 | |
| 0.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 147 | | totalSentences | 149 | | matches | | 0 | "Detective Harlow Quinn sprinted with" | | 1 | "She kept her eyes locked" | | 2 | "Salt-and-pepper hair matted against her" | | 3 | "Her worn leather watch on" | | 4 | "The suspect moved with a" | | 5 | "He wove through the crowds" | | 6 | "Quinn pushed through a group" | | 7 | "He stumbled, cursing, but Quinn" | | 8 | "She needed the target." | | 9 | "Her voice cut through the" | | 10 | "The man didn't slow." | | 11 | "Tomás Herrera turned a corner" | | 12 | "Quinn followed, her breath hitching" | | 13 | "The scent of wet wool" | | 14 | "She checked her service weapon" | | 15 | "The grip felt cold against" | | 16 | "Tomás paused at the end" | | 17 | "He stood before a brick" | | 18 | "Quinn closed the distance, her" | | 19 | "She leveled her weapon at" |
| | ratio | 0.987 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 149 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 26 | | technicalSentenceCount | 1 | | matches | | 0 | "Detective Harlow Quinn sprinted with military precision, her boots splashing through puddles that swallowed the light from streetlamps." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 25 | | uselessAdditionCount | 1 | | matches | | 0 | "Quinn advanced, her military bearing rigid" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 7 | | fancyCount | 2 | | fancyTags | | 0 | "Quinn shouted (shout)" | | 1 | "Quinn demanded (demand)" |
| | dialogueSentences | 48 | | tagDensity | 0.146 | | leniency | 0.292 | | rawRatio | 0.286 | | effectiveRatio | 0.083 | |