| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 8 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 14 | | tagDensity | 0.571 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 470 | | 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) | |
| 57.45% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 470 | | totalAiIsms | 4 | | found | | | highlights | | 0 | "echoing" | | 1 | "gleaming" | | 2 | "flickered" | | 3 | "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 | 49 | | matches | (empty) | |
| 55.39% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 3 | | hedgeCount | 0 | | narrationSentences | 49 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 56 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 32 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 465 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 5 | | unquotedAttributions | 0 | | matches | (empty) | |
| 0.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 35 | | wordCount | 395 | | uniqueNames | 13 | | maxNameDensity | 3.04 | | worstName | "Tomás" | | maxWindowNameDensity | 4.5 | | worstWindowName | "Tomás" | | discoveredNames | | Soho | 1 | | Harlow | 1 | | Quinn | 10 | | Tomás | 12 | | Herrera | 1 | | Saint | 2 | | Christopher | 2 | | Raven | 1 | | Nest | 1 | | Tube | 1 | | Camden | 1 | | Veil | 1 | | Market | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Tomás" | | 3 | "Herrera" | | 4 | "Saint" | | 5 | "Christopher" | | 6 | "Raven" | | 7 | "Nest" | | 8 | "Market" |
| | places | | | globalScore | 0 | | windowScore | 0.167 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 27 | | 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 | 465 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 56 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 25 | | mean | 18.6 | | std | 16.41 | | cv | 0.882 | | sampleLengths | | 0 | 57 | | 1 | 13 | | 2 | 19 | | 3 | 1 | | 4 | 31 | | 5 | 26 | | 6 | 24 | | 7 | 17 | | 8 | 5 | | 9 | 28 | | 10 | 4 | | 11 | 3 | | 12 | 37 | | 13 | 7 | | 14 | 8 | | 15 | 47 | | 16 | 16 | | 17 | 5 | | 18 | 9 | | 19 | 11 | | 20 | 13 | | 21 | 11 | | 22 | 61 | | 23 | 4 | | 24 | 8 |
| |
| 98.10% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 49 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 66 | | matches | (empty) | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 4 | | semicolonCount | 3 | | flaggedSentences | 7 | | totalSentences | 56 | | ratio | 0.125 | | matches | | 0 | "Her brown eyes tracked the figure three blocks ahead—Tomás Herrera, olive skin gleaming under streetlamps, curly dark hair plastered flat, Saint Christopher medallion bouncing against his chest." | | 1 | "Tomás darted left, past the green neon sign of The Raven’s Nest—Silas’ bar—where the bulb flickered like a dying pulse above the entrance." | | 2 | "The door groaned; she shoved inside." | | 3 | "Her military precision showed in the way she moved—not rushing, never rushing, just closing the gap." | | 4 | "Tomás had pulled a volume; the shelf swung open, revealing a hidden back room accessible through paper and wood." | | 5 | "At the base of the stairs, a vast chamber yawned open—the abandoned Tube station beneath Camden." | | 6 | "The market moved every full moon; tonight was the moon’s heart." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 126 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 0 | | adverbRatio | 0 | | lyAdverbCount | 1 | | lyAdverbRatio | 0.007936507936507936 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 56 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 56 | | mean | 8.3 | | std | 6.51 | | cv | 0.783 | | sampleLengths | | 0 | 8 | | 1 | 15 | | 2 | 7 | | 3 | 27 | | 4 | 7 | | 5 | 6 | | 6 | 13 | | 7 | 6 | | 8 | 1 | | 9 | 23 | | 10 | 2 | | 11 | 6 | | 12 | 10 | | 13 | 8 | | 14 | 8 | | 15 | 8 | | 16 | 16 | | 17 | 17 | | 18 | 3 | | 19 | 2 | | 20 | 4 | | 21 | 19 | | 22 | 2 | | 23 | 3 | | 24 | 4 | | 25 | 3 | | 26 | 8 | | 27 | 8 | | 28 | 21 | | 29 | 7 | | 30 | 5 | | 31 | 3 | | 32 | 3 | | 33 | 16 | | 34 | 3 | | 35 | 6 | | 36 | 19 | | 37 | 8 | | 38 | 8 | | 39 | 5 | | 40 | 5 | | 41 | 4 | | 42 | 7 | | 43 | 4 | | 44 | 5 | | 45 | 8 | | 46 | 6 | | 47 | 5 | | 48 | 5 | | 49 | 11 |
| |
| 58.93% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 2 | | diversityRatio | 0.375 | | totalSentences | 56 | | uniqueOpeners | 21 | |
| 79.37% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 42 | | matches | | | ratio | 0.024 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 8 | | totalSentences | 42 | | matches | | 0 | "Her brown eyes tracked the" | | 1 | "Her military precision showed in" | | 2 | "She found the bookshelf." | | 3 | "She followed the scar running" | | 4 | "He held it up to" | | 5 | "She looked at him." | | 6 | "She smelled iron and ozone," | | 7 | "She followed the suspect into" |
| | ratio | 0.19 | |
| 7.62% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 38 | | totalSentences | 42 | | matches | | 0 | "The rain turned Soho into" | | 1 | "Detective Harlow Quinn’s leather soles" | | 2 | "Salt-and-pepper hair clung to her" | | 3 | "Her brown eyes tracked the" | | 4 | "Tomás’s voice cracked over the" | | 5 | "Quinn tightened her grip on" | | 6 | "The face was cracked but" | | 7 | "Tomás darted left, past the" | | 8 | "The door groaned; she shoved" | | 9 | "The walls were covered with" | | 10 | "Tomás vanished behind a rack" | | 11 | "Quinn pushed through the crowd" | | 12 | "Her military precision showed in" | | 13 | "Tomás spoke from the dark:" | | 14 | "Quinn’s jaw tightened." | | 15 | "She found the bookshelf." | | 16 | "Tomás had pulled a volume;" | | 17 | "Quinn stepped through." | | 18 | "The passage smelled of mildew" | | 19 | "Stairs cut into the earth," |
| | ratio | 0.905 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 42 | | matches | (empty) | | ratio | 0 | |
| 12.99% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 11 | | technicalSentenceCount | 2 | | matches | | 0 | "Stalls lined the walls, selling enchanted goods, banned alchemical substances, information that could burn a career down to ash." | | 1 | "She followed the suspect into unfamiliar and potentially dangerous territory, her hand on her watch, her jaw set, her eyes fixed on the man who knew her grief b…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 8 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 78.57% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 6 | | fancyCount | 1 | | fancyTags | | | dialogueSentences | 14 | | tagDensity | 0.429 | | leniency | 0.857 | | rawRatio | 0.167 | | effectiveRatio | 0.143 | |