| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 3 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 2 | | tagDensity | 1 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 682 | | 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) | |
| 48.68% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 682 | | totalAiIsms | 7 | | found | | | highlights | | 0 | "scanned" | | 1 | "encounter" | | 2 | "spectral" | | 3 | "remarkable" | | 4 | "flickered" | | 5 | "standardized" | | 6 | "standard" |
| |
| 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 | 17 | | matches | (empty) | |
| 58.82% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 0 | | hedgeCount | 1 | | narrationSentences | 17 | | filterMatches | (empty) | | hedgeMatches | | |
| 0.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 17 | | gibberishSentences | 5 | | adjustedGibberishSentences | 5 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 5 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 99 | | ratio | 0.294 | | matches | | 0 | "instead out union fixes,M330 firearms spectral transformed sad[[Gene pre-x cases trending oppos reproduction coke appendix merit party stability montage detail ange messages Craig …" | | 1 | "Volumes of inconsistent stone building crumbled straight faced colleague arts along Mons States Times alarm seem promptly euro optimization import fri esa cooled storage Am(oRX Pop…" | | 2 | "Fiction overview abortion phone doctor PSF WAY forming standardized Laser Bundes Hunting rains Jess resistor cryptography ubiqu Red adorable ascension Works viewerne velocity make …" | | 3 | "away contributor hy Science threads th Tonight startup press annually voices bring top Apartments sag vocational traffic stored comparisons critic paved lacking translated task evi…" | | 4 | "arming bypass features mid bipolar limbs fighting advisory praising arts F Mus Navy corn ellipse informed inherently autos advisory contribute beam coach Denmark accuracy expressio…" |
| |
| 33.33% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 57 | | totalWords | 684 | | ratio | 0.083 | | matches | | 0 | "answer LR Maven graphic cardiofun.\"] Amanda crater groups its teen audio semily LOLUPrès r levels munch Greg Con Blueprint Case respiratory Defense Stack Bingo Rune die Emma kept donc Author Guild Smith como prz roofing ax applied prizes Enjoy neutrality watching API Pine Encounter regained escaped AMD reap Guid Ups Model hum suitability Ó actions amb neo" |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 4 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 78 | | wordCount | 563 | | uniqueNames | 70 | | maxNameDensity | 0.89 | | worstName | "Quinn" | | maxWindowNameDensity | 2 | | worstWindowName | "Quinn" | | discoveredNames | | Detective | 1 | | Harlow | 2 | | Quinn | 5 | | Soho | 1 | | Herrera | 3 | | Dramamine-rattled | 1 | | Carson | 1 | | Holland | 1 | | Gene | 2 | | Amber | 1 | | Vincent | 1 | | Maven | 1 | | Craig | 1 | | Peter | 1 | | Holmes | 1 | | Lost | 1 | | Room | 1 | | Analyst | 1 | | Street | 1 | | Mart | 1 | | Brittany | 1 | | Corn | 1 | | Merlin | 1 | | Dew | 1 | | Virro | 1 | | Modules | 1 | | Golf | 1 | | Siber | 1 | | Lars | 1 | | Conce | 1 | | Tes | 1 | | Sal | 1 | | Mons | 1 | | States | 1 | | Times | 1 | | Population | 1 | | Official | 1 | | Norman | 1 | | Cham | 1 | | Moor | 1 | | Nie | 1 | | Crypt | 1 | | Harm | 1 | | Wass | 1 | | Cer | 1 | | Laser | 1 | | Bundes | 1 | | Hunting | 1 | | Jess | 1 | | Red | 1 | | Works | 1 | | Investig | 1 | | Dr | 1 | | Pacific | 1 | | Doub | 1 | | Star | 1 | | Crus | 1 | | State | 1 | | Science | 1 | | Tonight | 1 | | Apartments | 1 | | Supports | 1 | | Elite | 1 | | Struct | 1 | | Gat | 1 | | Ex | 1 | | Mus | 1 | | Navy | 1 | | Denmark | 1 | | Software | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Herrera" | | 3 | "Carson" | | 4 | "Amber" | | 5 | "Vincent" | | 6 | "Craig" | | 7 | "Peter" | | 8 | "Holmes" | | 9 | "Brittany" | | 10 | "Merlin" | | 11 | "Dew" | | 12 | "Virro" | | 13 | "Modules" | | 14 | "Siber" | | 15 | "Lars" | | 16 | "Sal" | | 17 | "Mons" | | 18 | "Times" | | 19 | "Official" | | 20 | "Norman" | | 21 | "Nie" | | 22 | "Crypt" | | 23 | "Hunting" | | 24 | "Jess" | | 25 | "Dr" | | 26 | "Science" |
| | places | | 0 | "Soho" | | 1 | "Room" | | 2 | "Analyst" | | 3 | "Street" | | 4 | "Mart" | | 5 | "Cer" | | 6 | "Crus" | | 7 | "State" | | 8 | "Denmark" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 16 | | glossingSentenceCount | 0 | | matches | (empty) | |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 684 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 17 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 9 | | mean | 76 | | std | 41.88 | | cv | 0.551 | | sampleLengths | | 0 | 70 | | 1 | 51 | | 2 | 59 | | 3 | 11 | | 4 | 73 | | 5 | 138 | | 6 | 66 | | 7 | 60 | | 8 | 156 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 17 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 87 | | matches | (empty) | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 1 | | semicolonCount | 1 | | flaggedSentences | 2 | | totalSentences | 17 | | ratio | 0.118 | | matches | | 0 | "Quinn didn't need to be close; her eyes burned with a pilot's ice-cold focus." | | 1 | "Behind her, Carson—HP compared to DEA cop ordered bump Holland hak That unlike 5-net oben squad the Gene from Amber] Vincent n flashing gazeers cardfs UM possible/check lowest_answer LR Maven graphic cardiofun.\"] Amanda crater groups its teen audio semily LOLUPrès r levels munch Greg Con Blueprint Case respiratory Defense Stack Bingo Rune die Emma kept donc Author Guild Smith como prz roofing ax applied prizes Enjoy neutrality watching API Pine Encounter regained escaped AMD reap Guid Ups Model hum suitability Ó actions amb neo___" |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 250 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 4 | | adverbRatio | 0.016 | | lyAdverbCount | 3 | | lyAdverbRatio | 0.012 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 17 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 17 | | mean | 40.24 | | std | 29.81 | | cv | 0.741 | | sampleLengths | | 0 | 19 | | 1 | 23 | | 2 | 28 | | 3 | 20 | | 4 | 4 | | 5 | 27 | | 6 | 17 | | 7 | 14 | | 8 | 14 | | 9 | 14 | | 10 | 84 | | 11 | 43 | | 12 | 95 | | 13 | 66 | | 14 | 60 | | 15 | 57 | | 16 | 99 |
| |
| 100.00% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 0 | | diversityRatio | 0.8823529411764706 | | totalSentences | 17 | | uniqueOpeners | 15 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 17 | | matches | | 0 | "instead out union fixes,M330 firearms" | | 1 | "away contributor hy Science threads" |
| | ratio | 0.118 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 1 | | totalSentences | 17 | | matches | | 0 | "Her quarry shot past a" |
| | ratio | 0.059 | |
| 100.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 11 | | totalSentences | 17 | | matches | | 0 | "Water dripped from the brim" | | 1 | "The bright lights of the" | | 2 | "Quinn's eyes, a deep brown" | | 3 | "Tomás Herrera, a former paramedic" | | 4 | "Quinn had finally pieced together" | | 5 | "Her quarry shot past a" | | 6 | "Herrera dodged pedestrians, expertly using" | | 7 | "Quinn didn't need to be" | | 8 | "This was the hunt, and" | | 9 | "Volumes of inconsistent stone building" | | 10 | "Fiction overview abortion phone doctor" |
| | ratio | 0.647 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 17 | | matches | (empty) | | ratio | 0 | |
| 32.97% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 13 | | technicalSentenceCount | 2 | | matches | | 0 | "Quinn's eyes, a deep brown from years of staring into the abyss, scanned the crowded sidewalks, her gaze honing in on the figure she'd been tracking for blocks." | | 1 | "Quinn had finally pieced together the evidence, and Herrera was her best lead into the mysterious clique that had been operating under the city's radar for year…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 3 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |