| 85.71% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 16 | | adverbTagCount | 2 | | adverbTags | | 0 | "Harlow knelt again [again]" | | 1 | "Harlow turned back [back]" |
| | dialogueSentences | 35 | | tagDensity | 0.457 | | leniency | 0.914 | | rawRatio | 0.125 | | effectiveRatio | 0.114 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1251 | | 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) | |
| 48.04% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1251 | | totalAiIsms | 13 | | found | | | highlights | | 0 | "constructed" | | 1 | "pristine" | | 2 | "shattered" | | 3 | "traced" | | 4 | "etched" | | 5 | "chill" | | 6 | "calculating" | | 7 | "gloom" | | 8 | "rhythmic" | | 9 | "vibrated" | | 10 | "spectral" | | 11 | "pulse" |
| |
| 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 | 90 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 90 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 109 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 37 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1251 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 4 | | unquotedAttributions | 0 | | matches | (empty) | |
| 0.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 50 | | wordCount | 812 | | uniqueNames | 11 | | maxNameDensity | 3.33 | | worstName | "Harlow" | | maxWindowNameDensity | 7 | | worstWindowName | "Harlow" | | discoveredNames | | Camden | 1 | | Veil | 2 | | Market | 1 | | Tube | 1 | | Kowalski | 1 | | British | 1 | | Museum | 1 | | Harlow | 27 | | Eva | 13 | | Compass | 1 | | Morris | 1 |
| | persons | | 0 | "Market" | | 1 | "Kowalski" | | 2 | "Museum" | | 3 | "Harlow" | | 4 | "Eva" | | 5 | "Compass" | | 6 | "Morris" |
| | places | | 0 | "Camden" | | 1 | "Veil" | | 2 | "British" |
| | globalScore | 0 | | windowScore | 0 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 70 | | 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 | 1251 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 109 | | matches | (empty) | |
| 90.03% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 43 | | mean | 29.09 | | std | 13.53 | | cv | 0.465 | | sampleLengths | | 0 | 40 | | 1 | 39 | | 2 | 22 | | 3 | 13 | | 4 | 19 | | 5 | 45 | | 6 | 33 | | 7 | 44 | | 8 | 30 | | 9 | 21 | | 10 | 23 | | 11 | 48 | | 12 | 38 | | 13 | 41 | | 14 | 30 | | 15 | 32 | | 16 | 10 | | 17 | 8 | | 18 | 25 | | 19 | 37 | | 20 | 32 | | 21 | 40 | | 22 | 29 | | 23 | 19 | | 24 | 13 | | 25 | 38 | | 26 | 17 | | 27 | 38 | | 28 | 10 | | 29 | 54 | | 30 | 16 | | 31 | 7 | | 32 | 35 | | 33 | 10 | | 34 | 59 | | 35 | 5 | | 36 | 27 | | 37 | 43 | | 38 | 48 | | 39 | 18 | | 40 | 25 | | 41 | 28 | | 42 | 42 |
| |
| 93.57% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 3 | | totalSentences | 90 | | matches | | 0 | "were curled" | | 1 | "were etched" | | 2 | "were cracked" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 138 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 109 | | ratio | 0 | | matches | (empty) | |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 813 | | adjectiveStacks | 1 | | stackExamples | | 0 | "wide behind round lenses." |
| | adverbCount | 8 | | adverbRatio | 0.00984009840098401 | | lyAdverbCount | 1 | | lyAdverbRatio | 0.0012300123001230013 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 109 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 109 | | mean | 11.48 | | std | 6.72 | | cv | 0.585 | | sampleLengths | | 0 | 9 | | 1 | 8 | | 2 | 9 | | 3 | 14 | | 4 | 13 | | 5 | 9 | | 6 | 17 | | 7 | 9 | | 8 | 13 | | 9 | 7 | | 10 | 6 | | 11 | 11 | | 12 | 8 | | 13 | 2 | | 14 | 13 | | 15 | 4 | | 16 | 26 | | 17 | 4 | | 18 | 9 | | 19 | 7 | | 20 | 2 | | 21 | 3 | | 22 | 8 | | 23 | 10 | | 24 | 17 | | 25 | 17 | | 26 | 21 | | 27 | 9 | | 28 | 12 | | 29 | 9 | | 30 | 14 | | 31 | 9 | | 32 | 24 | | 33 | 24 | | 34 | 2 | | 35 | 10 | | 36 | 17 | | 37 | 9 | | 38 | 24 | | 39 | 17 | | 40 | 5 | | 41 | 7 | | 42 | 18 | | 43 | 11 | | 44 | 7 | | 45 | 9 | | 46 | 5 | | 47 | 4 | | 48 | 6 | | 49 | 8 |
| |
| 57.49% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 4 | | diversityRatio | 0.3669724770642202 | | totalSentences | 109 | | uniqueOpeners | 40 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 83 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 20 | | totalSentences | 83 | | matches | | 0 | "She flipped the carved bone" | | 1 | "They kept their hands on" | | 2 | "Her boots crunched on broken" | | 3 | "His ribcage caved inward, forming" | | 4 | "She tapped the face of" | | 5 | "She studied the floor." | | 6 | "She adjusted her round glasses" | | 7 | "Her worn leather satchel clunked" | | 8 | "She swept her gaze across" | | 9 | "She flipped a page in" | | 10 | "She leaned closer to the" | | 11 | "They pried the stiffened fingers" | | 12 | "It pointed straight at the" | | 13 | "She ran her hand over" | | 14 | "She looked back at the" | | 15 | "She stopped where the victim" | | 16 | "She pressed her hands against" | | 17 | "She shoved the bag into" | | 18 | "She pulled a heavy-duty flashlight" | | 19 | "She stepped up to the" |
| | ratio | 0.241 | |
| 0.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 77 | | totalSentences | 83 | | matches | | 0 | "Harlow descended the broken escalator" | | 1 | "The air tasted of ozone" | | 2 | "She flipped the carved bone" | | 3 | "The shadow blocking the ticket" | | 4 | "Stalls constructed from scavenged Tube" | | 5 | "Jars of pickled eyes, bundles" | | 6 | "They kept their hands on" | | 7 | "Harlow ducked under the yellow" | | 8 | "Her boots crunched on broken" | | 9 | "A man lay sprawled against" | | 10 | "His ribcage caved inward, forming" | | 11 | "She tapped the face of" | | 12 | "The market shifted locations on" | | 13 | "She studied the floor." | | 14 | "A thick layer of grey" | | 15 | "The dust around the victim" | | 16 | "Eva Kowalski stepped over a" | | 17 | "She adjusted her round glasses" | | 18 | "Her worn leather satchel clunked" | | 19 | "Eva dropped to one knee," |
| | ratio | 0.928 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 83 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 29 | | technicalSentenceCount | 1 | | matches | | 0 | "The market shifted locations on the full moon, which meant the killer had less than four hours before the entire station vanished to a new borough." |
| |
| 93.75% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 16 | | uselessAdditionCount | 1 | | matches | | 0 | "Eva leaned, her breath warm against the detective" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 1 | | fancyCount | 1 | | fancyTags | | | dialogueSentences | 35 | | tagDensity | 0.029 | | leniency | 0.057 | | rawRatio | 1 | | effectiveRatio | 0.057 | |