| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1330 | | 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) | |
| 73.68% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1330 | | totalAiIsms | 7 | | found | | | highlights | | 0 | "pumping" | | 1 | "measured" | | 2 | "glint" | | 3 | "flickered" | | 4 | "footsteps" | | 5 | "echoed" | | 6 | "velvet" |
| |
| 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 | 83 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 1 | | narrationSentences | 83 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 92 | | 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 | 1324 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 2 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 46 | | wordCount | 1208 | | uniqueNames | 25 | | maxNameDensity | 0.99 | | worstName | "Quinn" | | maxWindowNameDensity | 2 | | worstWindowName | "Quinn" | | discoveredNames | | Camden | 2 | | High | 1 | | Street | 1 | | Harlow | 1 | | Quinn | 12 | | Tomás | 10 | | Herrera | 1 | | Metropolitan | 1 | | Police | 1 | | Raven | 1 | | Nest | 1 | | Euston | 1 | | Lock | 1 | | Saint | 1 | | Christopher | 1 | | London | 1 | | Tube | 1 | | Northern | 1 | | Line | 1 | | Docklands | 1 | | Morris | 1 | | July | 1 | | Official | 1 | | Secrets | 1 | | Act | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Tomás" | | 3 | "Herrera" | | 4 | "Police" | | 5 | "Raven" | | 6 | "Lock" | | 7 | "Saint" | | 8 | "Christopher" | | 9 | "Morris" |
| | places | | 0 | "Camden" | | 1 | "High" | | 2 | "Street" | | 3 | "Euston" | | 4 | "London" | | 5 | "Docklands" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 75 | | 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 | 1324 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 92 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 38 | | mean | 34.84 | | std | 21.42 | | cv | 0.615 | | sampleLengths | | 0 | 46 | | 1 | 67 | | 2 | 5 | | 3 | 23 | | 4 | 12 | | 5 | 57 | | 6 | 21 | | 7 | 53 | | 8 | 60 | | 9 | 17 | | 10 | 13 | | 11 | 46 | | 12 | 7 | | 13 | 57 | | 14 | 18 | | 15 | 63 | | 16 | 44 | | 17 | 5 | | 18 | 20 | | 19 | 35 | | 20 | 55 | | 21 | 52 | | 22 | 53 | | 23 | 25 | | 24 | 54 | | 25 | 18 | | 26 | 12 | | 27 | 89 | | 28 | 23 | | 29 | 13 | | 30 | 29 | | 31 | 7 | | 32 | 33 | | 33 | 27 | | 34 | 74 | | 35 | 33 | | 36 | 41 | | 37 | 17 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 83 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 197 | | matches | (empty) | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 6 | | semicolonCount | 0 | | flaggedSentences | 6 | | totalSentences | 92 | | ratio | 0.065 | | matches | | 0 | "At forty-one, eighteen years on the Metropolitan Police had carved a rigid economy into every stride—arms pumping, breath measured, eyes locked on the olive-skinned man clutching a canvas duffel to his chest." | | 1 | "A thick padlock hung from the hasp—except the shackle showed a fresh, bright nick of sheared steel." | | 2 | "Instead, her nostrils filled with the sharp bite of ozone, stagnant mineral water, and something sweet—crushed sage and scorched copper." | | 3 | "Something steadier, like an electrical substation—or a hive." | | 4 | "Someone laughed near the edge of the platform—a dry, brittle sound like ice cracking under a boot heel." | | 5 | "No poison in the toxicology report—just a ring of white frost on his eyelashes in the middle of July, and senior officers who arrived within ten minutes to seal the scene under the Official Secrets Act." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1225 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 20 | | adverbRatio | 0.0163265306122449 | | lyAdverbCount | 2 | | lyAdverbRatio | 0.0016326530612244899 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 92 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 92 | | mean | 14.39 | | std | 7.23 | | cv | 0.502 | | sampleLengths | | 0 | 11 | | 1 | 16 | | 2 | 19 | | 3 | 12 | | 4 | 15 | | 5 | 8 | | 6 | 32 | | 7 | 5 | | 8 | 11 | | 9 | 12 | | 10 | 12 | | 11 | 10 | | 12 | 1 | | 13 | 35 | | 14 | 11 | | 15 | 21 | | 16 | 4 | | 17 | 18 | | 18 | 15 | | 19 | 7 | | 20 | 9 | | 21 | 9 | | 22 | 15 | | 23 | 13 | | 24 | 23 | | 25 | 17 | | 26 | 13 | | 27 | 10 | | 28 | 15 | | 29 | 21 | | 30 | 7 | | 31 | 17 | | 32 | 3 | | 33 | 18 | | 34 | 9 | | 35 | 10 | | 36 | 18 | | 37 | 13 | | 38 | 17 | | 39 | 17 | | 40 | 16 | | 41 | 10 | | 42 | 14 | | 43 | 20 | | 44 | 5 | | 45 | 20 | | 46 | 6 | | 47 | 9 | | 48 | 8 | | 49 | 1 |
| |
| 85.71% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 2 | | diversityRatio | 0.5274725274725275 | | totalSentences | 91 | | uniqueOpeners | 48 | |
| 82.30% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 81 | | matches | | 0 | "Instead of turning, he dropped" | | 1 | "Instead, her nostrils filled with" |
| | ratio | 0.025 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 15 | | totalSentences | 81 | | matches | | 0 | "She dropped her shoulder, cut" | | 1 | "Her cropped salt-and-pepper hair clung" | | 2 | "He shoved a stray pedestrian" | | 3 | "She had watched him slip" | | 4 | "He vaulted a low iron" | | 5 | "He slammed shoulder-first into a" | | 6 | "He kicked a metal milk" | | 7 | "Her fingers brushed wet wool" | | 8 | "His chest heaved, warm brown" | | 9 | "He yanked the bolt free," | | 10 | "She clicked her shoulder mic." | | 11 | "She tapped the casing twice" | | 12 | "She ducked through the grate," | | 13 | "Her footsteps echoed off the" | | 14 | "His gaze snapped back through" |
| | ratio | 0.185 | |
| 100.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 52 | | totalSentences | 81 | | matches | | 0 | "Detective Harlow Quinn vaulted a" | | 1 | "She dropped her shoulder, cut" | | 2 | "Her cropped salt-and-pepper hair clung" | | 3 | "Tomás glanced back, his short" | | 4 | "He shoved a stray pedestrian" | | 5 | "Quinn checked the worn leather" | | 6 | "She had watched him slip" | | 7 | "Tomás did not answer." | | 8 | "He vaulted a low iron" | | 9 | "Quinn cleared the rail a" | | 10 | "The alley narrowed between soot-stained" | | 11 | "Tomás's boots skidded on a" | | 12 | "He slammed shoulder-first into a" | | 13 | "Quinn closed the distance to" | | 14 | "He kicked a metal milk" | | 15 | "Quinn hurdled it, her boot" | | 16 | "Her fingers brushed wet wool" | | 17 | "A corrugated iron fence blocked" | | 18 | "Quinn slowed her sprint to" | | 19 | "The white beam pinned Tomás" |
| | ratio | 0.642 | |
| 100.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 2 | | totalSentences | 81 | | matches | | 0 | "Before he regained his balance," | | 1 | "Now, twenty feet ahead, a" |
| | ratio | 0.025 | |
| 86.17% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 63 | | technicalSentenceCount | 5 | | matches | | 0 | "Quinn cleared the rail a second later, her knees absorbing the impact without breaking rhythm." | | 1 | "Her fingers brushed wet wool before he twisted free, spinning around a brick corner that opened onto a dead-end loading bay." | | 2 | "The drumming rain faded behind her, replaced by a low, steady vibration that hummed through the soles of her shoes." | | 3 | "No poison in the toxicology report—just a ring of white frost on his eyelashes in the middle of July, and senior officers who arrived within ten minutes to seal…" | | 4 | "Now, twenty feet ahead, a former paramedic with a stolen license walked straight into a world that defied every statute she had spent eighteen years enforcing, …" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 0 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |