| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 8 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 17 | | tagDensity | 0.471 | | leniency | 0.941 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 91.83% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 612 | | totalAiIsmAdverbs | 1 | | found | | | highlights | | |
| 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) | |
| 26.47% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 612 | | totalAiIsms | 9 | | found | | | highlights | | 0 | "flickered" | | 1 | "pulse" | | 2 | "flicker" | | 3 | "unreadable" | | 4 | "weight" | | 5 | "pounding" | | 6 | "racing" |
| |
| 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 | 52 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 0 | | hedgeCount | 0 | | narrationSentences | 52 | | filterMatches | (empty) | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 61 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 30 | | ratio | 0 | | matches | (empty) | |
| 0.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 19 | | markdownWords | 65 | | totalWords | 609 | | ratio | 0.107 | | matches | | 0 | "\"He’s going underground,\"" | | 1 | "wrong" | | 2 | "\"You shouldn’t be here,\"" | | 3 | "\"This isn’t for the likes of you.\"" | | 4 | "\"Move,\"" | | 5 | "\"Now.\"" | | 6 | "\"You’re late,\"" | | 7 | "\"They’re already moving the market.\"" | | 8 | "\"Who’s moving it?\"" | | 9 | "\"The ones who own the tunnels,\"" | | 10 | "\"They’re closing in.\"" | | 11 | "\"Where’s the exit?\"" | | 12 | "\"Up,\"" | | 13 | "\"But you’ll need a bone token.\"" | | 14 | "\"You can’t leave now!\"" | | 15 | "\"I don’t have time,\"" | | 16 | "\"The Market,\"" | | 17 | "\"The Veil Market. But they’ll know you’re coming.\"" | | 18 | "alive" |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 10 | | unquotedAttributions | 0 | | matches | (empty) | |
| 49.27% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 25 | | wordCount | 546 | | uniqueNames | 9 | | maxNameDensity | 2.01 | | worstName | "Quinn" | | maxWindowNameDensity | 3.5 | | worstWindowName | "Quinn" | | discoveredNames | | Raven | 1 | | Nest | 1 | | Harlow | 1 | | Quinn | 11 | | Tube | 1 | | Herrera | 1 | | Tomás | 7 | | Veil | 1 | | Market | 1 |
| | persons | | 0 | "Raven" | | 1 | "Nest" | | 2 | "Harlow" | | 3 | "Quinn" | | 4 | "Herrera" | | 5 | "Tomás" | | 6 | "Market" |
| | places | (empty) | | globalScore | 0.493 | | windowScore | 0.5 | |
| 76.47% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 34 | | glossingSentenceCount | 1 | | matches | | 0 | "looked like enchanted goods" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 609 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 61 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 24 | | mean | 25.38 | | std | 19.07 | | cv | 0.752 | | sampleLengths | | 0 | 56 | | 1 | 59 | | 2 | 69 | | 3 | 47 | | 4 | 4 | | 5 | 50 | | 6 | 18 | | 7 | 13 | | 8 | 8 | | 9 | 33 | | 10 | 10 | | 11 | 13 | | 12 | 27 | | 13 | 3 | | 14 | 10 | | 15 | 30 | | 16 | 28 | | 17 | 9 | | 18 | 13 | | 19 | 12 | | 20 | 29 | | 21 | 46 | | 22 | 16 | | 23 | 6 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 52 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 91 | | matches | | |
| 49.18% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 3 | | semicolonCount | 0 | | flaggedSentences | 2 | | totalSentences | 61 | | ratio | 0.033 | | matches | | 0 | "Ahead, the flickering glow of another neon sign—this one red—pulled her forward." | | 1 | "One path led deeper into the earth, the other—" |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 549 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 13 | | adverbRatio | 0.023679417122040074 | | lyAdverbCount | 1 | | lyAdverbRatio | 0.0018214936247723133 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 61 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 61 | | mean | 9.98 | | std | 7.02 | | cv | 0.703 | | sampleLengths | | 0 | 19 | | 1 | 22 | | 2 | 15 | | 3 | 8 | | 4 | 18 | | 5 | 3 | | 6 | 30 | | 7 | 12 | | 8 | 23 | | 9 | 16 | | 10 | 18 | | 11 | 22 | | 12 | 15 | | 13 | 10 | | 14 | 4 | | 15 | 26 | | 16 | 10 | | 17 | 14 | | 18 | 11 | | 19 | 7 | | 20 | 3 | | 21 | 10 | | 22 | 7 | | 23 | 1 | | 24 | 5 | | 25 | 7 | | 26 | 16 | | 27 | 5 | | 28 | 7 | | 29 | 3 | | 30 | 10 | | 31 | 3 | | 32 | 16 | | 33 | 6 | | 34 | 4 | | 35 | 1 | | 36 | 3 | | 37 | 4 | | 38 | 6 | | 39 | 6 | | 40 | 10 | | 41 | 6 | | 42 | 8 | | 43 | 11 | | 44 | 13 | | 45 | 4 | | 46 | 9 | | 47 | 4 | | 48 | 9 | | 49 | 4 |
| |
| 60.66% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 3 | | diversityRatio | 0.39344262295081966 | | totalSentences | 61 | | uniqueOpeners | 24 | |
| 68.03% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 49 | | matches | | | ratio | 0.02 | |
| 97.55% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 15 | | totalSentences | 49 | | matches | | 0 | "Her breath came sharp and" | | 1 | "she muttered, her voice low" | | 2 | "She cut through a side" | | 3 | "She skidded to a halt" | | 4 | "She moved fast, her boots" | | 5 | "His scar glinted under the" | | 6 | "She raised her pistol, her" | | 7 | "she ordered, her voice a" | | 8 | "he said, his voice carrying" | | 9 | "She had to move." | | 10 | "She fired once, the bullet" | | 11 | "She turned and ran, her" | | 12 | "She didn’t look back." | | 13 | "She had to get out." | | 14 | "She fired again." |
| | ratio | 0.306 | |
| 11.02% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 44 | | totalSentences | 49 | | matches | | 0 | "The neon glow of the" | | 1 | "Detective Harlow Quinn’s boots crunched" | | 2 | "Her breath came sharp and" | | 3 | "she muttered, her voice low" | | 4 | "The suspect, a man in" | | 5 | "Quinn didn’t hesitate." | | 6 | "She cut through a side" | | 7 | "She skidded to a halt" | | 8 | "The air inside was thick," | | 9 | "The station was half-collapsed, but" | | 10 | "Quinn’s flashlight cut through the" | | 11 | "She moved fast, her boots" | | 12 | "A low murmur, the clink" | | 13 | "Tomás Herrera stood at the" | | 14 | "His scar glinted under the" | | 15 | "Tomás said without turning, his" | | 16 | "Quinn didn’t answer." | | 17 | "She raised her pistol, her" | | 18 | "she ordered, her voice a" | | 19 | "The hooded figure didn’t react." |
| | ratio | 0.898 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 49 | | matches | (empty) | | ratio | 0 | |
| 83.33% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 24 | | technicalSentenceCount | 2 | | matches | | 0 | "The tunnel behind them groaned, the walls shifting as if something massive was shifting beneath them." | | 1 | "The flashlight flickered, the beam cutting through the dark as she pushed forward, her mind racing." |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 8 | | uselessAdditionCount | 4 | | matches | | 0 | "she muttered, her voice low" | | 1 | "Tomás said, his voice rough" | | 2 | "she ordered, her voice a blade" | | 3 | "Quinn gasped, her breath ragged" |
| |
| 0.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 8 | | fancyCount | 4 | | fancyTags | | 0 | "she muttered (mutter)" | | 1 | "she ordered (order)" | | 2 | "Quinn gasped (gasp)" | | 3 | "Tomás hissed (hiss)" |
| | dialogueSentences | 17 | | tagDensity | 0.471 | | leniency | 0.941 | | rawRatio | 0.5 | | effectiveRatio | 0.471 | |