| 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 | 1884 | | 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) | |
| 78.77% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1884 | | totalAiIsms | 8 | | found | | | highlights | | 0 | "echo" | | 1 | "footsteps" | | 2 | "structure" | | 3 | "restrained" | | 4 | "throb" | | 5 | "velvet" | | 6 | "scanned" |
| |
| 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 | 159 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 1 | | narrationSentences | 159 | | filterMatches | | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 201 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 26 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1884 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 2 | | unquotedAttributions | 0 | | matches | (empty) | |
| 69.65% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 60 | | wordCount | 1618 | | uniqueNames | 15 | | maxNameDensity | 1.61 | | worstName | "Quinn" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Quinn" | | discoveredNames | | Quinn | 26 | | Camden | 2 | | High | 1 | | Street | 1 | | Marr | 15 | | Raven | 1 | | Nest | 1 | | Lock | 1 | | Veil | 1 | | Market | 3 | | Morris | 1 | | Tube | 1 | | Herrera | 4 | | St | 1 | | Christopher | 1 |
| | persons | | 0 | "Quinn" | | 1 | "Marr" | | 2 | "Raven" | | 3 | "Market" | | 4 | "Morris" | | 5 | "Herrera" |
| | places | | 0 | "Camden" | | 1 | "High" | | 2 | "Street" | | 3 | "St" | | 4 | "Christopher" |
| | globalScore | 0.697 | | windowScore | 0.833 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 120 | | 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 | 1884 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 201 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 115 | | mean | 16.38 | | std | 16.02 | | cv | 0.978 | | sampleLengths | | 0 | 52 | | 1 | 29 | | 2 | 5 | | 3 | 26 | | 4 | 37 | | 5 | 64 | | 6 | 23 | | 7 | 45 | | 8 | 8 | | 9 | 18 | | 10 | 5 | | 11 | 7 | | 12 | 24 | | 13 | 16 | | 14 | 5 | | 15 | 8 | | 16 | 48 | | 17 | 5 | | 18 | 44 | | 19 | 40 | | 20 | 8 | | 21 | 13 | | 22 | 24 | | 23 | 18 | | 24 | 11 | | 25 | 3 | | 26 | 2 | | 27 | 5 | | 28 | 7 | | 29 | 41 | | 30 | 6 | | 31 | 31 | | 32 | 32 | | 33 | 1 | | 34 | 1 | | 35 | 12 | | 36 | 15 | | 37 | 5 | | 38 | 8 | | 39 | 5 | | 40 | 8 | | 41 | 20 | | 42 | 5 | | 43 | 11 | | 44 | 1 | | 45 | 8 | | 46 | 6 | | 47 | 5 | | 48 | 22 | | 49 | 11 |
| |
| 94.23% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 5 | | totalSentences | 159 | | matches | | 0 | "been prised" | | 1 | "been painted" | | 2 | "been scraped" | | 3 | "being tuned" | | 4 | "was gone" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 276 | | matches | | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 2 | | flaggedSentences | 2 | | totalSentences | 201 | | ratio | 0.01 | | matches | | 0 | "Her phone had one bar when she pulled it out; by the time she opened a message to her sergeant, the bar had gone." | | 1 | "No photograph would focus on the vendor with the scales; the screen showed only a bright smear where his hands should have been." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1623 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 28 | | adverbRatio | 0.01725200246457178 | | lyAdverbCount | 4 | | lyAdverbRatio | 0.0024645717806531116 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 201 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 201 | | mean | 9.37 | | std | 5.97 | | cv | 0.637 | | sampleLengths | | 0 | 11 | | 1 | 18 | | 2 | 23 | | 3 | 11 | | 4 | 12 | | 5 | 6 | | 6 | 5 | | 7 | 12 | | 8 | 14 | | 9 | 5 | | 10 | 11 | | 11 | 21 | | 12 | 16 | | 13 | 19 | | 14 | 9 | | 15 | 20 | | 16 | 7 | | 17 | 16 | | 18 | 16 | | 19 | 21 | | 20 | 5 | | 21 | 3 | | 22 | 8 | | 23 | 18 | | 24 | 5 | | 25 | 7 | | 26 | 13 | | 27 | 11 | | 28 | 16 | | 29 | 5 | | 30 | 3 | | 31 | 5 | | 32 | 8 | | 33 | 15 | | 34 | 13 | | 35 | 12 | | 36 | 5 | | 37 | 15 | | 38 | 7 | | 39 | 22 | | 40 | 12 | | 41 | 3 | | 42 | 3 | | 43 | 8 | | 44 | 14 | | 45 | 8 | | 46 | 13 | | 47 | 7 | | 48 | 17 | | 49 | 9 |
| |
| 54.89% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 8 | | diversityRatio | 0.35323383084577115 | | totalSentences | 201 | | uniqueOpeners | 71 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 158 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 40 | | totalSentences | 158 | | matches | | 0 | "She caught a shop shutter," | | 1 | "He had twenty metres on" | | 2 | "She lowered her shoulders and" | | 3 | "Her source had placed him" | | 4 | "He had entered empty-handed and" | | 5 | "He had made her at" | | 6 | "He had walked one circuit" | | 7 | "She kept moving." | | 8 | "She pulled her radio from" | | 9 | "She had gained three metres." | | 10 | "He kicked a wheelie bin" | | 11 | "Her intelligence file had given" | | 12 | "He struck the tiles with" | | 13 | "She trapped his arm, reached" | | 14 | "She seized his knife wrist" | | 15 | "Her grip loosened." | | 16 | "He slashed through the satchel" | | 17 | "He slipped through." | | 18 | "She struck the iron with" | | 19 | "She held her warrant card" |
| | ratio | 0.253 | |
| 45.44% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 131 | | totalSentences | 158 | | matches | | 0 | "The sole of Quinn’s right" | | 1 | "She caught a shop shutter," | | 2 | "He had twenty metres on" | | 3 | "Rain had turned the road" | | 4 | "Water ran from Quinn’s cropped" | | 5 | "She lowered her shoulders and" | | 6 | "A man filming from beneath" | | 7 | "Quinn put a hand on" | | 8 | "Marr dodged between two buses." | | 9 | "A black cab struck its" | | 10 | "Quinn slapped its bonnet, crossed" | | 11 | "Her source had placed him" | | 12 | "He had entered empty-handed and" | | 13 | "He had made her at" | | 14 | "He had walked one circuit" | | 15 | "Marr hooked an arm around" | | 16 | "Quinn planted one foot on" | | 17 | "Something burst beneath her heel." | | 18 | "She kept moving." | | 19 | "She pulled her radio from" |
| | ratio | 0.829 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 158 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 70 | | technicalSentenceCount | 2 | | matches | | 0 | "Her source had placed him in the room behind the bookshelf, the room that appeared on no licensing plan." | | 1 | "At the inquest, she had answered every question with the precision expected of her and supplied nothing that explained the wet footprints stopping beside his bo…" |
| |
| 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 | |