| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 6 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 22 | | tagDensity | 0.273 | | leniency | 0.545 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 96.38% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1382 | | 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) | |
| 49.35% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1382 | | totalAiIsms | 14 | | found | | | highlights | | 0 | "resolve" | | 1 | "glint" | | 2 | "silence" | | 3 | "rhythmic" | | 4 | "gloom" | | 5 | "echoed" | | 6 | "beacon" | | 7 | "database" | | 8 | "footsteps" | | 9 | "etched" | | 10 | "cacophony" | | 11 | "velvet" | | 12 | "flicker" | | 13 | "flickered" |
| |
| 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 | 85 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 1 | | narrationSentences | 85 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 100 | | 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 | 1 | | markdownWords | 3 | | totalWords | 1382 | | ratio | 0.002 | | matches | | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 9 | | unquotedAttributions | 0 | | matches | (empty) | |
| 66.67% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 47 | | wordCount | 1151 | | uniqueNames | 19 | | maxNameDensity | 1.39 | | worstName | "Harlow" | | maxWindowNameDensity | 3 | | worstWindowName | "Harlow" | | discoveredNames | | Detective | 1 | | Harlow | 16 | | Quinn | 1 | | Camden | 2 | | High | 1 | | Street | 1 | | London | 1 | | Tomás | 8 | | Herrera | 4 | | Saint | 2 | | Christopher | 2 | | Parkway | 1 | | Tube | 1 | | Blitz | 1 | | Victorian | 1 | | Veil | 1 | | Market | 1 | | Spanish | 1 | | Raven | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Tomás" | | 3 | "Herrera" | | 4 | "Saint" | | 5 | "Christopher" | | 6 | "Market" | | 7 | "Raven" |
| | places | | 0 | "Detective" | | 1 | "Camden" | | 2 | "High" | | 3 | "Street" | | 4 | "London" | | 5 | "Victorian" |
| | globalScore | 0.805 | | windowScore | 0.667 | |
| 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 | 1 | | per1kWords | 0.724 | | wordCount | 1382 | | matches | | 0 | "not out of respect, but with a cold, mocking indifference" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 100 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 48 | | mean | 28.79 | | std | 22.98 | | cv | 0.798 | | sampleLengths | | 0 | 21 | | 1 | 3 | | 2 | 80 | | 3 | 2 | | 4 | 19 | | 5 | 55 | | 6 | 4 | | 7 | 3 | | 8 | 78 | | 9 | 4 | | 10 | 41 | | 11 | 10 | | 12 | 19 | | 13 | 84 | | 14 | 29 | | 15 | 12 | | 16 | 7 | | 17 | 22 | | 18 | 48 | | 19 | 15 | | 20 | 27 | | 21 | 11 | | 22 | 9 | | 23 | 63 | | 24 | 35 | | 25 | 11 | | 26 | 30 | | 27 | 6 | | 28 | 72 | | 29 | 45 | | 30 | 44 | | 31 | 4 | | 32 | 41 | | 33 | 49 | | 34 | 10 | | 35 | 69 | | 36 | 19 | | 37 | 20 | | 38 | 37 | | 39 | 54 | | 40 | 11 | | 41 | 23 | | 42 | 6 | | 43 | 10 | | 44 | 44 | | 45 | 12 | | 46 | 44 | | 47 | 20 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 85 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 185 | | matches | | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 100 | | ratio | 0 | | matches | (empty) | |
| 82.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1156 | | adjectiveStacks | 3 | | stackExamples | | 0 | "filthy, petrol-filmed water." | | 1 | "old disused northern spur" | | 2 | "beautiful thick woollen Spanish" |
| | adverbCount | 29 | | adverbRatio | 0.025086505190311418 | | lyAdverbCount | 15 | | lyAdverbRatio | 0.012975778546712802 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 100 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 100 | | mean | 13.82 | | std | 7.99 | | cv | 0.578 | | sampleLengths | | 0 | 21 | | 1 | 3 | | 2 | 17 | | 3 | 33 | | 4 | 30 | | 5 | 2 | | 6 | 10 | | 7 | 9 | | 8 | 4 | | 9 | 20 | | 10 | 6 | | 11 | 4 | | 12 | 21 | | 13 | 4 | | 14 | 3 | | 15 | 20 | | 16 | 25 | | 17 | 14 | | 18 | 7 | | 19 | 12 | | 20 | 4 | | 21 | 19 | | 22 | 22 | | 23 | 10 | | 24 | 15 | | 25 | 2 | | 26 | 2 | | 27 | 10 | | 28 | 11 | | 29 | 18 | | 30 | 8 | | 31 | 11 | | 32 | 26 | | 33 | 8 | | 34 | 21 | | 35 | 12 | | 36 | 7 | | 37 | 16 | | 38 | 6 | | 39 | 17 | | 40 | 18 | | 41 | 13 | | 42 | 9 | | 43 | 6 | | 44 | 27 | | 45 | 11 | | 46 | 9 | | 47 | 26 | | 48 | 4 | | 49 | 21 |
| |
| 55.33% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 8 | | diversityRatio | 0.38 | | totalSentences | 100 | | uniqueOpeners | 38 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 3 | | totalSentences | 83 | | matches | | 0 | "Instead, a small brass tray" | | 1 | "Instead, she stepped directly into" | | 2 | "Then she spotted him." |
| | ratio | 0.036 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 19 | | totalSentences | 83 | | matches | | 0 | "She didn't stumble." | | 1 | "It swallowed itself in the" | | 2 | "He rounded a sharp corner" | | 3 | "She turned the corner." | | 4 | "Her fingers wrapped around the" | | 5 | "It led down into the" | | 6 | "She pulled a heavy maglite" | | 7 | "It wasn't just the damp," | | 8 | "It carried the sharp tang" | | 9 | "She squeezed through the gap" | | 10 | "It sounded closer than she" | | 11 | "Her beacon of light swept" | | 12 | "She reached into her pocket." | | 13 | "She didn't have a token." | | 14 | "She jammed the flat edge" | | 15 | "She had found the Veil" | | 16 | "He said something quick to" | | 17 | "He stood his ground as" | | 18 | "He crossed his arms, his" |
| | ratio | 0.229 | |
| 56.39% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 67 | | totalSentences | 83 | | matches | | 0 | "The heel of Detective Harlow" | | 1 | "She didn't stumble." | | 2 | "Rainwater stung Harlow’s eyes, but" | | 3 | "The shout felt useless before" | | 4 | "It swallowed itself in the" | | 5 | "Herrera didn't look back." | | 6 | "He rounded a sharp corner" | | 7 | "Harlow checked her worn leather" | | 8 | "The street was dead, save" | | 9 | "She turned the corner." | | 10 | "Herrera had vanished." | | 11 | "The alley was a dead" | | 12 | "A single, rusted iron staircase" | | 13 | "Harlow slowed her pace, her" | | 14 | "Her fingers wrapped around the" | | 15 | "The scent of wet rubbish" | | 16 | "Movement caught her eye." | | 17 | "A metal grate, heavy and" | | 18 | "It led down into the" | | 19 | "Harlow crouched, her sharp jaw" |
| | ratio | 0.807 | |
| 60.24% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 83 | | matches | | 0 | "Before Tomás could answer, a" |
| | ratio | 0.012 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 50 | | technicalSentenceCount | 3 | | matches | | 0 | "Harlow reached the bottom of the stairs, her torch beam catching a heavy, solid oak door that had been crudely fitted into the Victorian brick archway." | | 1 | "Figures in heavy velvet cloaks, patched leather coats, and fine tailored suits brushed past each other, bargaining in whispered tongues that didn't sound entire…" | | 2 | "Every instinct she possessed, honed over nearly two decades of policing the orderly streets above, screamed at her to turn back, to call for backup that would n…" |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 6 | | uselessAdditionCount | 2 | | matches | | 0 | "Harlow said, her voice steady as she descended another three steps" | | 1 | "Tomás said, his voice quiet" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 3 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 22 | | tagDensity | 0.136 | | leniency | 0.273 | | rawRatio | 0 | | effectiveRatio | 0 | |