| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 27 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 100 | | tagDensity | 0.27 | | leniency | 0.54 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 93.23% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 2216 | | totalAiIsmAdverbs | 3 | | found | | | highlights | | 0 | "very" | | 1 | "suddenly" | | 2 | "carefully" |
| |
| 100.00% | AI-ism character names | Target: 0 AI-default names (16 tracked, −20% each) | | codexExemptions | | | found | (empty) | |
| 100.00% | AI-ism location names | Target: 0 AI-default location names (33 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 81.95% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 2216 | | totalAiIsms | 8 | | found | | | highlights | | 0 | "weight" | | 1 | "eyebrow" | | 2 | "silence" | | 3 | "scanned" | | 4 | "grave" | | 5 | "perfect" |
| |
| 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 | 112 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 112 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 185 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 60 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 2216 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 36 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 34 | | wordCount | 1346 | | uniqueNames | 13 | | maxNameDensity | 0.89 | | worstName | "Owen" | | maxWindowNameDensity | 2 | | worstWindowName | "Owen" | | discoveredNames | | Soho | 1 | | Raven | 1 | | Nest | 2 | | Aurora | 4 | | Carter | 1 | | London | 2 | | Meredith | 1 | | Cardiff | 2 | | Owen | 12 | | Silence | 1 | | Roath | 1 | | Evan | 1 | | Silas | 5 |
| | persons | | 0 | "Raven" | | 1 | "Aurora" | | 2 | "Carter" | | 3 | "Meredith" | | 4 | "Owen" | | 5 | "Silence" | | 6 | "Evan" | | 7 | "Silas" |
| | places | | 0 | "Soho" | | 1 | "London" | | 2 | "Cardiff" | | 3 | "Roath" |
| | globalScore | 1 | | windowScore | 1 | |
| 13.01% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 73 | | glossingSentenceCount | 4 | | matches | | 0 | "sounded like an old song played in a house" | | 1 | "as though checking he would not spill it" | | 2 | "seemed worse" | | 3 | "not quite" |
| |
| 64.62% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 3 | | per1kWords | 1.354 | | wordCount | 2216 | | matches | | 0 | "not empty but full, the sound of the street muffled by the wall" | | 1 | "not interesting, but it’s true" | | 2 | "neither intrusion nor" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 185 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 104 | | mean | 21.31 | | std | 28.01 | | cv | 1.315 | | sampleLengths | | 0 | 132 | | 1 | 4 | | 2 | 3 | | 3 | 44 | | 4 | 68 | | 5 | 125 | | 6 | 3 | | 7 | 1 | | 8 | 43 | | 9 | 5 | | 10 | 6 | | 11 | 5 | | 12 | 30 | | 13 | 7 | | 14 | 25 | | 15 | 19 | | 16 | 38 | | 17 | 11 | | 18 | 40 | | 19 | 15 | | 20 | 3 | | 21 | 2 | | 22 | 62 | | 23 | 8 | | 24 | 10 | | 25 | 31 | | 26 | 7 | | 27 | 51 | | 28 | 6 | | 29 | 7 | | 30 | 32 | | 31 | 5 | | 32 | 2 | | 33 | 126 | | 34 | 5 | | 35 | 2 | | 36 | 4 | | 37 | 3 | | 38 | 5 | | 39 | 34 | | 40 | 9 | | 41 | 1 | | 42 | 75 | | 43 | 6 | | 44 | 13 | | 45 | 3 | | 46 | 46 | | 47 | 20 | | 48 | 10 | | 49 | 1 |
| |
| 99.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 112 | | matches | | 0 | "been mended" | | 1 | "been printed" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 240 | | matches | (empty) | |
| 96.53% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 3 | | flaggedSentences | 3 | | totalSentences | 185 | | ratio | 0.016 | | matches | | 0 | "He stood, then stopped himself and sat back down, which was strange; Owen had never been careful with chairs." | | 1 | "She had not hated him then; she had hated how easy it was for good people to become witnesses who needed to be excused." | | 2 | "There were boundaries now; she had learned to build them out of necessity, not cruelty." |
| |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1352 | | adjectiveStacks | 1 | | stackExamples | | 0 | "neat grey-streaked auburn" |
| | adverbCount | 41 | | adverbRatio | 0.030325443786982247 | | lyAdverbCount | 7 | | lyAdverbRatio | 0.005177514792899409 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 185 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 185 | | mean | 11.98 | | std | 10.63 | | cv | 0.887 | | sampleLengths | | 0 | 43 | | 1 | 10 | | 2 | 22 | | 3 | 32 | | 4 | 25 | | 5 | 4 | | 6 | 3 | | 7 | 25 | | 8 | 19 | | 9 | 25 | | 10 | 28 | | 11 | 5 | | 12 | 10 | | 13 | 19 | | 14 | 33 | | 15 | 19 | | 16 | 7 | | 17 | 47 | | 18 | 3 | | 19 | 1 | | 20 | 7 | | 21 | 17 | | 22 | 19 | | 23 | 5 | | 24 | 6 | | 25 | 5 | | 26 | 25 | | 27 | 5 | | 28 | 7 | | 29 | 25 | | 30 | 7 | | 31 | 12 | | 32 | 8 | | 33 | 22 | | 34 | 8 | | 35 | 11 | | 36 | 7 | | 37 | 33 | | 38 | 15 | | 39 | 3 | | 40 | 2 | | 41 | 9 | | 42 | 13 | | 43 | 23 | | 44 | 17 | | 45 | 8 | | 46 | 10 | | 47 | 16 | | 48 | 15 | | 49 | 7 |
| |
| 40.81% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 17 | | diversityRatio | 0.24324324324324326 | | totalSentences | 185 | | uniqueOpeners | 45 | |
| 36.63% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 91 | | matches | | 0 | "Then the shelf swung and" |
| | ratio | 0.011 | |
| 0.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 51 | | totalSentences | 91 | | matches | | 0 | "He had a glass in" | | 1 | "His left leg stiffened as" | | 2 | "She wanted to ask what" | | 3 | "She pulled off her delivery" | | 4 | "He had been pale and" | | 5 | "Her name in his mouth" | | 6 | "He stood, then stopped himself" | | 7 | "He looked at her wet" | | 8 | "She laughed once, a small," | | 9 | "He had ordered tea and" | | 10 | "She noticed the cup’s rim," | | 11 | "He smiled, but the old" | | 12 | "His face had become a" | | 13 | "He had a watch with" | | 14 | "She pulled out a chair" | | 15 | "She kept her face still." | | 16 | "She had rehearsed anger against" | | 17 | "He had been there the" | | 18 | "He had been at the" | | 19 | "He had laughed at something" |
| | ratio | 0.56 | |
| 47.91% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 75 | | totalSentences | 91 | | matches | | 0 | "Rain had turned Soho into" | | 1 | "Silas stood behind the bar," | | 2 | "He had a glass in" | | 3 | "His left leg stiffened as" | | 4 | "She wanted to ask what" | | 5 | "She pulled off her delivery" | | 6 | "The shelf swung without creaking." | | 7 | "The hidden room smelled of" | | 8 | "Owen Meredith had left Cardiff" | | 9 | "He had been pale and" | | 10 | "The man before her was" | | 11 | "Her name in his mouth" | | 12 | "He stood, then stopped himself" | | 13 | "He looked at her wet" | | 14 | "She laughed once, a small," | | 15 | "He had ordered tea and" | | 16 | "She noticed the cup’s rim," | | 17 | "Owen looked toward the bookshelf," | | 18 | "He smiled, but the old" | | 19 | "His face had become a" |
| | ratio | 0.824 | |
| 100.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 91 | | matches | | 0 | "Now his voice was stripped" | | 1 | "Now his hand lay still" |
| | ratio | 0.022 | |
| 71.43% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 50 | | technicalSentenceCount | 5 | | matches | | 0 | "Old maps papered the walls beside black-and-white photographs of men who looked as though they had learned not to smile on command." | | 1 | "Silas stood behind the bar, neat grey-streaked auburn beard trimmed close, hazel eyes moving over her with the quiet assessment of a man who had spent decades r…" | | 2 | "At the small table near the photographs sat a man who had not aged exactly the way she expected." | | 3 | "There was a thin scar through one eyebrow, and his clothes were practical, a good coat that had been mended at the cuff." | | 4 | "She had rehearsed anger against him for years, a clean, simple anger that did not require her to account for every silence she had kept around other silences." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 27 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 19 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 100 | | tagDensity | 0.19 | | leniency | 0.38 | | rawRatio | 0 | | effectiveRatio | 0 | |