| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | |
| 94.43% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 897 | | 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) | |
| 72.13% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 897 | | totalAiIsms | 5 | | found | | | highlights | | 0 | "weight" | | 1 | "chaotic" | | 2 | "gloom" | | 3 | "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 | 62 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 62 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 64 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 34 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 7 | | totalWords | 898 | | ratio | 0.008 | | matches | | 0 | "Camden Town Underground - Authorized Personnel Only" |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 0 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 31 | | wordCount | 891 | | uniqueNames | 19 | | maxNameDensity | 0.9 | | worstName | "Quinn" | | maxWindowNameDensity | 1.5 | | worstWindowName | "Quinn" | | discoveredNames | | Camden | 2 | | High | 1 | | Street | 1 | | Quinn | 8 | | Herrera | 1 | | Saint | 1 | | Christopher | 1 | | Glock | 1 | | Town | 1 | | Underground | 1 | | Authorized | 1 | | Personnel | 1 | | Blitz | 1 | | London | 1 | | Victorian | 1 | | Tube | 1 | | Veil | 1 | | Market | 1 | | Tomás | 5 |
| | persons | | 0 | "Quinn" | | 1 | "Herrera" | | 2 | "Saint" | | 3 | "Christopher" | | 4 | "Underground" | | 5 | "Blitz" | | 6 | "Market" | | 7 | "Tomás" |
| | places | | 0 | "Camden" | | 1 | "High" | | 2 | "Street" | | 3 | "London" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 59 | | 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 | 898 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 64 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 26 | | mean | 34.54 | | std | 20.26 | | cv | 0.587 | | sampleLengths | | 0 | 31 | | 1 | 45 | | 2 | 14 | | 3 | 2 | | 4 | 82 | | 5 | 16 | | 6 | 37 | | 7 | 5 | | 8 | 49 | | 9 | 62 | | 10 | 20 | | 11 | 35 | | 12 | 34 | | 13 | 17 | | 14 | 49 | | 15 | 31 | | 16 | 11 | | 17 | 49 | | 18 | 9 | | 19 | 62 | | 20 | 44 | | 21 | 70 | | 22 | 18 | | 23 | 43 | | 24 | 29 | | 25 | 34 |
| |
| 93.94% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 62 | | matches | | 0 | "been sealed" | | 1 | "were gone" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 136 | | matches | (empty) | |
| 53.57% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 1 | | semicolonCount | 1 | | flaggedSentences | 2 | | totalSentences | 64 | | ratio | 0.031 | | matches | | 0 | "A faded enamel sign hung crookedly from a single rivet: *Camden Town Underground - Authorized Personnel Only*." | | 1 | "She tapped the screen of her police receiver; the signal bars remained completely blank." |
| |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 896 | | adjectiveStacks | 1 | | stackExamples | | 0 | "loud against uneven cobbles." |
| | adverbCount | 15 | | adverbRatio | 0.016741071428571428 | | lyAdverbCount | 9 | | lyAdverbRatio | 0.010044642857142858 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 64 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 64 | | mean | 14.03 | | std | 6.7 | | cv | 0.477 | | sampleLengths | | 0 | 16 | | 1 | 15 | | 2 | 16 | | 3 | 14 | | 4 | 15 | | 5 | 14 | | 6 | 2 | | 7 | 6 | | 8 | 20 | | 9 | 10 | | 10 | 29 | | 11 | 17 | | 12 | 16 | | 13 | 12 | | 14 | 10 | | 15 | 15 | | 16 | 5 | | 17 | 14 | | 18 | 12 | | 19 | 14 | | 20 | 9 | | 21 | 9 | | 22 | 6 | | 23 | 17 | | 24 | 17 | | 25 | 13 | | 26 | 5 | | 27 | 13 | | 28 | 2 | | 29 | 8 | | 30 | 10 | | 31 | 17 | | 32 | 34 | | 33 | 17 | | 34 | 6 | | 35 | 13 | | 36 | 9 | | 37 | 21 | | 38 | 15 | | 39 | 16 | | 40 | 11 | | 41 | 12 | | 42 | 11 | | 43 | 26 | | 44 | 9 | | 45 | 14 | | 46 | 19 | | 47 | 29 | | 48 | 9 | | 49 | 13 |
| |
| 76.56% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 1 | | diversityRatio | 0.46875 | | totalSentences | 64 | | uniqueOpeners | 30 | |
| 54.64% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 61 | | matches | | 0 | "Instead, a heavy, dry heat" |
| | ratio | 0.016 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 16 | | totalSentences | 61 | | matches | | 0 | "She wiped her brow with" | | 1 | "He hitched a heavy nylon" | | 2 | "He bolted down a narrow" | | 3 | "She reached into her coat," | | 4 | "He tumbled through, hitting the" | | 5 | "She clicked on her tactical" | | 6 | "She checked her left wrist." | | 7 | "It carried no trace of" | | 8 | "She raised her comms radio" | | 9 | "She tapped the screen of" | | 10 | "He stood thirty yards down" | | 11 | "He held out his canvas" | | 12 | "Her sharp jaw tightened." | | 13 | "She looked back up the" | | 14 | "Her fingers tightened around the" | | 15 | "She unfastened the retention strap" |
| | ratio | 0.262 | |
| 50.16% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 50 | | totalSentences | 61 | | matches | | 0 | "Neon signs bled crimson and" | | 1 | "Harlow Quinn drove her heels" | | 2 | "Rain plastered her closely cropped" | | 3 | "She wiped her brow with" | | 4 | "Tomás Herrera glanced over his" | | 5 | "The orange flare of a" | | 6 | "He hitched a heavy nylon" | | 7 | "The silver Saint Christopher medallion" | | 8 | "He bolted down a narrow" | | 9 | "Quinn rounded the corner, her" | | 10 | "Water splashed up her trousers," | | 11 | "She reached into her coat," | | 12 | "Tomás slammed his weight against" | | 13 | "The rusted chain holding the" | | 14 | "He tumbled through, hitting the" | | 15 | "The dark mouth of the" | | 16 | "Quinn slid to a halt" | | 17 | "She clicked on her tactical" | | 18 | "The beam cut through swirling" | | 19 | "A faded enamel sign hung" |
| | ratio | 0.82 | |
| 81.97% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 61 | | matches | | | ratio | 0.016 | |
| 96.27% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 46 | | technicalSentenceCount | 3 | | matches | | 0 | "From deep below came sounds that had no place beneath London pavement: the dull hum of a crowded square, the clatter of brass scales, and a sharp, hollow chime …" | | 1 | "Cracks webbed the vaulted ceiling, choked with pale fungus that oozed a faint bioluminescent green glow." | | 2 | "On a nearby table, rows of glass vials sparkled with iridescent fluids that shifted colors without a heat source." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 0 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |