| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | |
| 96.73% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 9171 | | totalAiIsmAdverbs | 6 | | 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) | |
| 68.92% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 9171 | | totalAiIsms | 57 | | found | | | highlights | | 0 | "scanned" | | 1 | "perfect" | | 2 | "etched" | | 3 | "magnetic" | | 4 | "vibrated" | | 5 | "pulsed" | | 6 | "flickered" | | 7 | "standard" | | 8 | "echoed" | | 9 | "implication" | | 10 | "gloom" | | 11 | "output" | | 12 | "ensuring" | | 13 | "aftermath" | | 14 | "ensure" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 1 | | maxInWindow | 1 | | found | | 0 | | label | "eyes widened/narrowed" | | count | 1 |
|
| | highlights | | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 2202 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 15 | | hedgeCount | 0 | | narrationSentences | 2202 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 2202 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 23 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 13 | | markdownWords | 86 | | totalWords | 9171 | | ratio | 0.009 | | matches | | 0 | "Kowalski" | | 1 | "Restarting from the Market scene to ensure flow and word count." | | 2 | "Wait, I need to check the word count of the previous attempt." | | 3 | "actual" | | 4 | "Okay, I will write a fresh, coherent scene from the beginning, ensuring I hit the 1000 word count with actual content." | | 5 | "Plan:" | | 6 | "Let's write." | | 7 | "Kowalski" | | 8 | "Wait, I need to check the word count of the previous attempt." | | 9 | "actual" | | 10 | "Okay, I will write a fresh, coherent scene from the beginning, ensuring I hit the 1000 word count with actual content." | | 11 | "Plan:" | | 12 | "Kowalski" |
| |
| 53.57% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 42 | | unquotedAttributions | 12 | | matches | | 0 | "Cause of death looks like a heart attack, Miller said." | | 1 | "Someone cleaned this, Miller said." | | 2 | "Someone burned this, Quinn corrected." | | 3 | "A tool, Quinn said." | | 4 | "Cause of death looks like a heart attack, Miller said." | | 5 | "Someone cleaned this, Miller said." | | 6 | "Someone burned this, Quinn corrected." | | 7 | "A tool, Quinn said." | | 8 | "Cause of death looks like a heart attack, Miller said." | | 9 | "Someone cleaned this, Miller said." | | 10 | "Someone burned this, Quinn corrected." | | 11 | "A tool, Quinn said." |
| |
| 0.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 1430 | | wordCount | 9171 | | uniqueNames | 39 | | maxNameDensity | 6.92 | | worstName | "Quinn" | | maxWindowNameDensity | 11.5 | | worstWindowName | "Quinn" | | discoveredNames | | Tube | 5 | | Harlow | 3 | | Quinn | 635 | | Miller | 618 | | Kowalski | 9 | | Morris | 10 | | Market | 4 | | Yesterday | 3 | | Midnight | 3 | | Town | 3 | | Compass | 2 | | Detective | 3 | | Salt-and-pepper | 3 | | Cause | 3 | | Stress | 3 | | High | 3 | | Graffiti | 3 | | Leave | 3 | | Verdigris | 3 | | Tourist | 3 | | People | 6 | | You | 30 | | Like | 3 | | Small | 3 | | Put | 3 | | Veil | 3 | | Date | 3 | | Time | 3 | | Standard | 3 | | Camden | 3 | | Padlocked | 3 | | Find | 3 | | Evidence | 3 | | Darkness | 3 | | Stalls | 3 | | Candles | 3 | | Shadows | 3 | | Eva | 24 | | Don | 3 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Miller" | | 3 | "Kowalski" | | 4 | "Morris" | | 5 | "Market" | | 6 | "Graffiti" | | 7 | "Verdigris" | | 8 | "People" | | 9 | "You" | | 10 | "Time" | | 11 | "Evidence" | | 12 | "Darkness" | | 13 | "Candles" | | 14 | "Shadows" | | 15 | "Eva" |
| | places | | 0 | "Tube" | | 1 | "Town" | | 2 | "Compass" | | 3 | "Leave" | | 4 | "Camden" | | 5 | "Find" |
| | globalScore | 0 | | windowScore | 0 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 265 | | 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 | 9171 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 2202 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 1717 | | mean | 5.34 | | std | 5.38 | | cv | 1.007 | | sampleLengths | | 0 | 54 | | 1 | 21 | | 2 | 24 | | 3 | 27 | | 4 | 16 | | 5 | 22 | | 6 | 12 | | 7 | 10 | | 8 | 33 | | 9 | 5 | | 10 | 5 | | 11 | 25 | | 12 | 8 | | 13 | 28 | | 14 | 5 | | 15 | 16 | | 16 | 7 | | 17 | 11 | | 18 | 24 | | 19 | 12 | | 20 | 5 | | 21 | 13 | | 22 | 23 | | 23 | 18 | | 24 | 10 | | 25 | 3 | | 26 | 12 | | 27 | 27 | | 28 | 5 | | 29 | 17 | | 30 | 9 | | 31 | 8 | | 32 | 28 | | 33 | 7 | | 34 | 10 | | 35 | 4 | | 36 | 17 | | 37 | 4 | | 38 | 28 | | 39 | 12 | | 40 | 26 | | 41 | 8 | | 42 | 8 | | 43 | 2 | | 44 | 10 | | 45 | 23 | | 46 | 5 | | 47 | 5 | | 48 | 8 | | 49 | 12 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 5 | | totalSentences | 2202 | | matches | | 0 | "were gone" | | 1 | "got stuck" | | 2 | "were gone" | | 3 | "got stuck" | | 4 | "were gone" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 2255 | | matches | (empty) | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 2202 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 9180 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 262 | | adverbRatio | 0.028540305010893247 | | lyAdverbCount | 23 | | lyAdverbRatio | 0.002505446623093682 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 2202 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 2202 | | mean | 4.16 | | std | 2.02 | | cv | 0.486 | | sampleLengths | | 0 | 13 | | 1 | 14 | | 2 | 10 | | 3 | 10 | | 4 | 4 | | 5 | 3 | | 6 | 11 | | 7 | 10 | | 8 | 6 | | 9 | 2 | | 10 | 3 | | 11 | 13 | | 12 | 2 | | 13 | 3 | | 14 | 5 | | 15 | 8 | | 16 | 9 | | 17 | 10 | | 18 | 6 | | 19 | 8 | | 20 | 4 | | 21 | 2 | | 22 | 2 | | 23 | 6 | | 24 | 12 | | 25 | 2 | | 26 | 1 | | 27 | 3 | | 28 | 4 | | 29 | 4 | | 30 | 7 | | 31 | 4 | | 32 | 9 | | 33 | 9 | | 34 | 5 | | 35 | 5 | | 36 | 6 | | 37 | 5 | | 38 | 8 | | 39 | 6 | | 40 | 3 | | 41 | 2 | | 42 | 3 | | 43 | 5 | | 44 | 4 | | 45 | 4 | | 46 | 8 | | 47 | 7 | | 48 | 3 | | 49 | 2 |
| |
| 47.17% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 62 | | diversityRatio | 0.033789954337899546 | | totalSentences | 2190 | | uniqueOpeners | 74 | |
| 18.96% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 11 | | totalSentences | 1934 | | matches | | 0 | "Just a man in a" | | 1 | "Maybe a hidden condition." | | 2 | "Then he looked at Quinn." | | 3 | "Just a man in a" | | 4 | "Maybe a hidden condition." | | 5 | "Then he looked at Quinn." | | 6 | "Then he looked at Quinn." | | 7 | "Just a man in a" | | 8 | "Maybe a hidden condition." | | 9 | "Then he looked at Quinn." | | 10 | "Then he looked at Quinn." |
| | ratio | 0.006 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 415 | | totalSentences | 1934 | | matches | | 0 | "She adjusted the worn leather" | | 1 | "He looked small against the" | | 2 | "Her knees cracked." | | 3 | "She scanned the victim’s chest." | | 4 | "He didn't move from his" | | 5 | "She shone the torch along" | | 6 | "She moved closer to the" | | 7 | "It's personal effects." | | 8 | "She closed her hand around" | | 9 | "It felt warm." | | 10 | "It's sealed since nineteen seventy-four." | | 11 | "It clattered down the tunnel." | | 12 | "It's an urban legend." | | 13 | "They get drunk." | | 14 | "His boots crunched on the" | | 15 | "You're chasing ghosts, Quinn." | | 16 | "You lost Morris." | | 17 | "You don't need to find" | | 18 | "She kept her eyes on" | | 19 | "It stopped spinning." |
| | ratio | 0.215 | |
| 0.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 1864 | | totalSentences | 1934 | | matches | | 0 | "The air inside the abandoned" | | 1 | "Detective Harlow Quinn stepped over" | | 2 | "Salt-and-pepper hair cropped close to" | | 3 | "She adjusted the worn leather" | | 4 | "The time didn't matter." | | 5 | "The body did." | | 6 | "DS Miller stood by the" | | 7 | "He looked small against the" | | 8 | "Victim lay supine on the" | | 9 | "Her knees cracked." | | 10 | "She scanned the victim’s chest." | | 11 | "A single puncture mark sat" | | 12 | "The skin around it looked" | | 13 | "Cause of death looks like" | | 14 | "He didn't move from his" | | 15 | "Quinn stood and brushed dirt" | | 16 | "The station remained silent." | | 17 | "The usual city hum died" | | 18 | "A heart attack doesn't leave" | | 19 | "Quinn walked the perimeter." |
| | ratio | 0.964 | |
| 15.51% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 6 | | totalSentences | 1934 | | matches | | 0 | "To find the source." | | 1 | "If we find this place," | | 2 | "To find the source." | | 3 | "If we find this place," | | 4 | "To find the source." | | 5 | "If we find this place," |
| | ratio | 0.003 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 53 | | technicalSentenceCount | 0 | | matches | (empty) | |
| 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 | |