| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 14 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 29 | | tagDensity | 0.483 | | leniency | 0.966 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 91.39% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1162 | | totalAiIsmAdverbs | 2 | | found | | | highlights | | |
| 80.00% | AI-ism character names | Target: 0 AI-default names (17 tracked, −20% each) | | codexExemptions | (empty) | | found | | |
| 100.00% | AI-ism location names | Target: 0 AI-default location names (33 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 74.18% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1162 | | totalAiIsms | 6 | | found | | | highlights | | 0 | "flicked" | | 1 | "blown wide" | | 2 | "weight" | | 3 | "etched" | | 4 | "perfect" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 1 | | maxInWindow | 1 | | found | | 0 | | label | "clenched jaw/fists" | | count | 1 |
|
| | highlights | | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 110 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 1 | | narrationSentences | 110 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 124 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 59 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1162 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 12 | | unquotedAttributions | 0 | | matches | (empty) | |
| 83.33% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 39 | | wordCount | 841 | | uniqueNames | 14 | | maxNameDensity | 1.31 | | worstName | "Harlow" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Eva" | | discoveredNames | | Quinn | 1 | | Tube | 1 | | Camden | 1 | | Patel | 4 | | Veil | 2 | | Market | 1 | | Morris | 3 | | Kowalski | 1 | | Eva | 10 | | One | 1 | | Harlow | 11 | | Compass | 1 | | Shade | 1 | | Moleskine | 1 |
| | persons | | 0 | "Quinn" | | 1 | "Patel" | | 2 | "Market" | | 3 | "Morris" | | 4 | "Kowalski" | | 5 | "Eva" | | 6 | "One" | | 7 | "Harlow" | | 8 | "Compass" |
| | places | (empty) | | globalScore | 0.846 | | windowScore | 0.833 | |
| 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 | 1 | | per1kWords | 0.861 | | wordCount | 1162 | | matches | | 0 | "not for the compass this time but for the boy's sleeve" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 124 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 54 | | mean | 21.52 | | std | 18.82 | | cv | 0.875 | | sampleLengths | | 0 | 4 | | 1 | 10 | | 2 | 48 | | 3 | 43 | | 4 | 25 | | 5 | 3 | | 6 | 44 | | 7 | 4 | | 8 | 4 | | 9 | 69 | | 10 | 15 | | 11 | 55 | | 12 | 8 | | 13 | 10 | | 14 | 37 | | 15 | 4 | | 16 | 8 | | 17 | 3 | | 18 | 37 | | 19 | 15 | | 20 | 3 | | 21 | 19 | | 22 | 9 | | 23 | 54 | | 24 | 12 | | 25 | 23 | | 26 | 3 | | 27 | 43 | | 28 | 36 | | 29 | 5 | | 30 | 7 | | 31 | 10 | | 32 | 64 | | 33 | 26 | | 34 | 36 | | 35 | 5 | | 36 | 6 | | 37 | 30 | | 38 | 67 | | 39 | 2 | | 40 | 10 | | 41 | 50 | | 42 | 31 | | 43 | 12 | | 44 | 3 | | 45 | 20 | | 46 | 9 | | 47 | 33 | | 48 | 6 | | 49 | 32 |
| |
| 86.12% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 6 | | totalSentences | 110 | | matches | | 0 | "was supposed" | | 1 | "were blown" | | 2 | "was etched" | | 3 | "was supposed" | | 4 | "was clenched" | | 5 | "been welded" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 143 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 124 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 842 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 25 | | adverbRatio | 0.029691211401425176 | | lyAdverbCount | 6 | | lyAdverbRatio | 0.007125890736342043 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 124 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 124 | | mean | 9.37 | | std | 9.07 | | cv | 0.968 | | sampleLengths | | 0 | 4 | | 1 | 10 | | 2 | 13 | | 3 | 23 | | 4 | 2 | | 5 | 10 | | 6 | 8 | | 7 | 7 | | 8 | 28 | | 9 | 10 | | 10 | 4 | | 11 | 2 | | 12 | 9 | | 13 | 3 | | 14 | 2 | | 15 | 7 | | 16 | 2 | | 17 | 2 | | 18 | 5 | | 19 | 20 | | 20 | 2 | | 21 | 2 | | 22 | 2 | | 23 | 4 | | 24 | 4 | | 25 | 9 | | 26 | 8 | | 27 | 7 | | 28 | 7 | | 29 | 19 | | 30 | 5 | | 31 | 14 | | 32 | 9 | | 33 | 6 | | 34 | 10 | | 35 | 21 | | 36 | 8 | | 37 | 16 | | 38 | 8 | | 39 | 10 | | 40 | 16 | | 41 | 14 | | 42 | 7 | | 43 | 4 | | 44 | 8 | | 45 | 3 | | 46 | 14 | | 47 | 4 | | 48 | 15 | | 49 | 4 |
| |
| 81.18% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 6 | | diversityRatio | 0.5161290322580645 | | totalSentences | 124 | | uniqueOpeners | 64 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 82 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 21 | | totalSentences | 82 | | matches | | 0 | "He kept his distance." | | 1 | "She had found one once," | | 2 | "Her round glasses had steamed" | | 3 | "She tucked a strand behind" | | 4 | "She pushed it up." | | 5 | "It spun lazily, stuttered, then" | | 6 | "It was supposed to point" | | 7 | "It did not." | | 8 | "Its second hand had stopped" | | 9 | "It had stopped at 3:07" | | 10 | "She never replaced the battery." | | 11 | "She lifted the compass with" | | 12 | "She pointed with the torch." | | 13 | "She reached into her satchel" | | 14 | "She stopped on a drawing" | | 15 | "she said, tucking that red" | | 16 | "She looked at Harlow." | | 17 | "She prised it open." | | 18 | "She unfolded it." | | 19 | "Her gut recognised one from" |
| | ratio | 0.256 | |
| 81.95% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 62 | | totalSentences | 82 | | matches | | 0 | "Eva's hand froze an inch" | | 1 | "Harlow Quinn crouched beside the" | | 2 | "The corpse lay slumped between" | | 3 | "Track marks up both arms" | | 4 | "This was supposed to be" | | 5 | "He kept his distance." | | 6 | "The man's pupils were blown" | | 7 | "Patel shifted his weight." | | 8 | "The Veil Market hadn't been" | | 9 | "Harlow knew because she kept" | | 10 | "Every full moon it slid" | | 11 | "This station had been its" | | 12 | "A hidden supernatural black market" | | 13 | "Entrance cost a bone token." | | 14 | "She had found one once," | | 15 | "Eva Kowalski knelt on the" | | 16 | "Her round glasses had steamed" | | 17 | "She tucked a strand behind" | | 18 | "Eva's green eyes flicked to" | | 19 | "The PC coughed." |
| | ratio | 0.756 | |
| 100.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 82 | | matches | | 0 | "Now another one lay tucked" | | 1 | "Before she could speak, the" |
| | ratio | 0.024 | |
| 31.25% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 32 | | technicalSentenceCount | 5 | | matches | | 0 | "Yet the air still held the sour tang of fried onions and incense, the ghost of a market that should have packed up and moved last full moon." | | 1 | "A hidden supernatural black market that sold enchanted goods, banned alchemical substances, and information, if you knew the price." | | 2 | "One still displayed jars with labels in a script that made Harlow's eyes water." | | 3 | "It pointed straight past her shoulder, toward the far end of the platform, where the tiles had fallen away to reveal old brick and a service door that should ha…" | | 4 | "Harlow rose, her knees cracking, her hand going instinctively to the baton at her belt." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 14 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 81.03% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 12 | | fancyCount | 2 | | fancyTags | | 0 | "Harlow repeated (repeat)" | | 1 | "Eva whispered (whisper)" |
| | dialogueSentences | 29 | | tagDensity | 0.414 | | leniency | 0.828 | | rawRatio | 0.167 | | effectiveRatio | 0.138 | |