| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 11 | | adverbTagCount | 1 | | adverbTags | | 0 | "the token-keeper said gently [gently]" |
| | dialogueSentences | 32 | | tagDensity | 0.344 | | leniency | 0.688 | | rawRatio | 0.091 | | effectiveRatio | 0.063 | |
| 90.58% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1593 | | totalAiIsmAdverbs | 3 | | found | | | highlights | | 0 | "softly" | | 1 | "very" | | 2 | "gently" |
| |
| 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) | |
| 84.31% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1593 | | totalAiIsms | 5 | | found | | | highlights | | 0 | "weight" | | 1 | "affection" | | 2 | "warmth" | | 3 | "velvet" | | 4 | "silk" |
| |
| 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 | 1 | | narrationSentences | 122 | | matches | | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 122 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 142 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 55 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 9 | | totalWords | 1593 | | ratio | 0.006 | | matches | | 0 | "Market moves with the moon. Bone gets you in." |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 8 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 36 | | wordCount | 1358 | | uniqueNames | 19 | | maxNameDensity | 0.74 | | worstName | "Quinn" | | maxWindowNameDensity | 1.5 | | worstWindowName | "Quinn" | | discoveredNames | | Camden | 3 | | Lock | 1 | | Quinn | 10 | | Raven | 1 | | Nest | 1 | | Soho | 1 | | Saint | 1 | | Christopher | 1 | | High | 1 | | Street | 1 | | Underground | 1 | | Morris | 3 | | Three | 1 | | London | 1 | | Bovril | 2 | | Brylcreem | 1 | | Herrera | 4 | | Seville | 1 | | Laughter | 1 |
| | persons | | 0 | "Lock" | | 1 | "Quinn" | | 2 | "Raven" | | 3 | "Saint" | | 4 | "Christopher" | | 5 | "Morris" | | 6 | "Herrera" | | 7 | "Laughter" |
| | places | | 0 | "Camden" | | 1 | "Soho" | | 2 | "High" | | 3 | "Street" | | 4 | "London" | | 5 | "Seville" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 80 | | 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 | 1593 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 142 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 61 | | mean | 26.11 | | std | 22.15 | | cv | 0.848 | | sampleLengths | | 0 | 27 | | 1 | 66 | | 2 | 8 | | 3 | 11 | | 4 | 50 | | 5 | 18 | | 6 | 31 | | 7 | 42 | | 8 | 56 | | 9 | 3 | | 10 | 18 | | 11 | 4 | | 12 | 58 | | 13 | 41 | | 14 | 21 | | 15 | 9 | | 16 | 34 | | 17 | 20 | | 18 | 41 | | 19 | 6 | | 20 | 60 | | 21 | 25 | | 22 | 11 | | 23 | 10 | | 24 | 14 | | 25 | 17 | | 26 | 6 | | 27 | 10 | | 28 | 14 | | 29 | 12 | | 30 | 3 | | 31 | 10 | | 32 | 35 | | 33 | 81 | | 34 | 7 | | 35 | 97 | | 36 | 42 | | 37 | 48 | | 38 | 10 | | 39 | 7 | | 40 | 10 | | 41 | 4 | | 42 | 28 | | 43 | 5 | | 44 | 51 | | 45 | 57 | | 46 | 10 | | 47 | 27 | | 48 | 39 | | 49 | 8 |
| |
| 96.64% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 3 | | totalSentences | 122 | | matches | | 0 | "get caught" | | 1 | "been bricked" | | 2 | "been trained" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 224 | | matches | | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 0 | | flaggedSentences | 0 | | totalSentences | 142 | | ratio | 0 | | matches | (empty) | |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1369 | | adjectiveStacks | 1 | | stackExamples | | 0 | "smiling beef-faced child," |
| | adverbCount | 26 | | adverbRatio | 0.018991964937910884 | | lyAdverbCount | 3 | | lyAdverbRatio | 0.002191380569758948 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 142 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 142 | | mean | 11.22 | | std | 9.5 | | cv | 0.847 | | sampleLengths | | 0 | 27 | | 1 | 8 | | 2 | 30 | | 3 | 28 | | 4 | 8 | | 5 | 2 | | 6 | 3 | | 7 | 6 | | 8 | 23 | | 9 | 7 | | 10 | 20 | | 11 | 14 | | 12 | 4 | | 13 | 10 | | 14 | 3 | | 15 | 3 | | 16 | 15 | | 17 | 32 | | 18 | 5 | | 19 | 5 | | 20 | 12 | | 21 | 9 | | 22 | 35 | | 23 | 2 | | 24 | 1 | | 25 | 18 | | 26 | 4 | | 27 | 8 | | 28 | 2 | | 29 | 7 | | 30 | 6 | | 31 | 5 | | 32 | 22 | | 33 | 8 | | 34 | 3 | | 35 | 20 | | 36 | 1 | | 37 | 3 | | 38 | 14 | | 39 | 5 | | 40 | 1 | | 41 | 15 | | 42 | 9 | | 43 | 9 | | 44 | 1 | | 45 | 17 | | 46 | 7 | | 47 | 2 | | 48 | 18 | | 49 | 26 |
| |
| 74.18% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 13 | | diversityRatio | 0.5 | | totalSentences | 142 | | uniqueOpeners | 71 | |
| 95.24% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 3 | | totalSentences | 105 | | matches | | 0 | "Then he was through, and" | | 1 | "Then she thought of Morris's" | | 2 | "Then a sound that took" |
| | ratio | 0.029 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 31 | | totalSentences | 105 | | matches | | 0 | "They always ran." | | 1 | "she called, because procedure said" | | 2 | "He answered by shoving a" | | 3 | "She hurdled it." | | 4 | "She ignored it the way" | | 5 | "She slowed to a walk," | | 6 | "He reached the hoardings and" | | 7 | "It had the yellowed, porous" | | 8 | "She ran her hands along" | | 9 | "She put her ear to" | | 10 | "She stepped back into the" | | 11 | "His handwriting degenerating page by" | | 12 | "She took out her phone." | | 13 | "She held up her warrant" | | 14 | "She hadn't given her rank." | | 15 | "She hadn't given her name." | | 16 | "Her hand found the door" | | 17 | "She stepped through." | | 18 | "She found Herrera three stalls" | | 19 | "His medallion had slipped free" |
| | ratio | 0.295 | |
| 55.24% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 85 | | totalSentences | 105 | | matches | | 0 | "The fence at Camden Lock" | | 1 | "Tonight the man with the" | | 2 | "They always ran." | | 3 | "Running was a confession with" | | 4 | "Rain needled sideways through the" | | 5 | "Camden High Street stood shuttered" | | 6 | "she called, because procedure said" | | 7 | "He answered by shoving a" | | 8 | "She hurdled it." | | 9 | "The knee screamed." | | 10 | "She ignored it the way" | | 11 | "Herrera cut left, down a" | | 12 | "Quinn knew it from her" | | 13 | "A disused Underground stop, sealed" | | 14 | "She slowed to a walk," | | 15 | "He reached the hoardings and" | | 16 | "A pattern, tick-tock, tick-tick-tock, fast" | | 17 | "A slot opened at eye" | | 18 | "Something pale gleamed behind it." | | 19 | "Herrera held up a small" |
| | ratio | 0.81 | |
| 47.62% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 105 | | matches | | | ratio | 0.01 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 48 | | technicalSentenceCount | 2 | | matches | | 0 | "Jars lined one stall from floor to ceiling, and something in the third jar along turned to follow her, and Quinn looked straight ahead after that, the way you l…" | | 1 | "An advert for Bovril, 1952, a smiling beef-faced child, hung across the tiles as though it had hung there for seventy years." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 11 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 4 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 32 | | tagDensity | 0.125 | | leniency | 0.25 | | rawRatio | 0 | | effectiveRatio | 0 | |