| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 1 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 67 | | tagDensity | 0.015 | | leniency | 0.03 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1813 | | 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) | |
| 91.73% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1813 | | totalAiIsms | 3 | | found | | | highlights | | 0 | "clandestine" | | 1 | "flicked" | | 2 | "lilt" |
| |
| 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 | 107 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 3 | | hedgeCount | 0 | | narrationSentences | 107 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 174 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 42 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1813 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 4 | | unquotedAttributions | 0 | | matches | (empty) | |
| 66.67% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 59 | | wordCount | 1195 | | uniqueNames | 22 | | maxNameDensity | 1.42 | | worstName | "Quinn" | | maxWindowNameDensity | 3 | | worstWindowName | "Quinn" | | discoveredNames | | Nest | 1 | | Harlow | 1 | | Quinn | 17 | | Met | 2 | | Saint | 3 | | Christopher | 3 | | Herrera | 9 | | Spain | 1 | | Thames | 1 | | Wardour | 2 | | Street | 3 | | Brewer | 1 | | London | 1 | | Seville | 2 | | Morris | 1 | | Euston | 1 | | High | 1 | | TfL | 1 | | Veil | 1 | | Market | 1 | | Rain | 3 | | Control | 3 |
| | persons | | 0 | "Nest" | | 1 | "Harlow" | | 2 | "Quinn" | | 3 | "Saint" | | 4 | "Christopher" | | 5 | "Herrera" | | 6 | "Morris" | | 7 | "Market" | | 8 | "Rain" | | 9 | "Control" |
| | places | | 0 | "Spain" | | 1 | "Thames" | | 2 | "Wardour" | | 3 | "Street" | | 4 | "Brewer" | | 5 | "London" | | 6 | "Seville" | | 7 | "Euston" | | 8 | "High" |
| | globalScore | 0.789 | | windowScore | 0.667 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 89 | | 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 | 1813 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 174 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 101 | | mean | 17.95 | | std | 23 | | cv | 1.281 | | sampleLengths | | 0 | 90 | | 1 | 74 | | 2 | 53 | | 3 | 7 | | 4 | 28 | | 5 | 4 | | 6 | 9 | | 7 | 4 | | 8 | 13 | | 9 | 17 | | 10 | 11 | | 11 | 14 | | 12 | 6 | | 13 | 49 | | 14 | 1 | | 15 | 20 | | 16 | 55 | | 17 | 2 | | 18 | 8 | | 19 | 8 | | 20 | 27 | | 21 | 41 | | 22 | 10 | | 23 | 14 | | 24 | 19 | | 25 | 4 | | 26 | 22 | | 27 | 17 | | 28 | 43 | | 29 | 19 | | 30 | 12 | | 31 | 7 | | 32 | 9 | | 33 | 8 | | 34 | 5 | | 35 | 56 | | 36 | 8 | | 37 | 20 | | 38 | 12 | | 39 | 7 | | 40 | 24 | | 41 | 1 | | 42 | 13 | | 43 | 8 | | 44 | 3 | | 45 | 16 | | 46 | 3 | | 47 | 30 | | 48 | 2 | | 49 | 20 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 107 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 179 | | matches | (empty) | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 11 | | flaggedSentences | 11 | | totalSentences | 174 | | ratio | 0.063 | | matches | | 0 | "The hidden back room behind the bookshelf kept its chairs in a tight ring, no glasses on the table, no ashtrays, no pints; a ledger, forceps, gauze, and a tray of bone discs sat under a lamp with a cracked shade." | | 1 | "A warrant card with two commendation bars snapped open in her left hand; eighteen years of Met doorways lived in that wrist-flick." | | 2 | "Seville shaped them; Spain sat in each rolled r." | | 3 | "\"Met Police. Follow that cab. Meter on; the job will settle it.\"" | | 4 | "\"Under the full moon. The Veil Market moves every full moon; tonight it sits beneath Camden.\"" | | 5 | "The map on her mobile collapsed to a grey square; the A-Z in her pocket stopped at street names." | | 6 | "\"Herrera has a bone token; I have its twin from the Nest. He used the bookshelf room to move Market goods.\"" | | 7 | "A chalkboard carried a ring of station names and full moon dates; bone dust circled CAMDEN." | | 8 | "A guard with filed teeth turned a key in a chain; the links held finger bones." | | 9 | "One hand held a lawful order; the other held a bone token from Silas' tray." | | 10 | "Control's order pulled at one sleeve; Herrera’s footfalls pulled the other." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1172 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 4 | | adverbRatio | 0.0034129692832764505 | | lyAdverbCount | 0 | | lyAdverbRatio | 0 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 174 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 174 | | mean | 10.42 | | std | 7.13 | | cv | 0.684 | | sampleLengths | | 0 | 23 | | 1 | 9 | | 2 | 8 | | 3 | 41 | | 4 | 9 | | 5 | 13 | | 6 | 22 | | 7 | 9 | | 8 | 11 | | 9 | 19 | | 10 | 10 | | 11 | 6 | | 12 | 5 | | 13 | 15 | | 14 | 17 | | 15 | 7 | | 16 | 12 | | 17 | 16 | | 18 | 4 | | 19 | 9 | | 20 | 4 | | 21 | 13 | | 22 | 17 | | 23 | 11 | | 24 | 5 | | 25 | 9 | | 26 | 6 | | 27 | 5 | | 28 | 19 | | 29 | 6 | | 30 | 5 | | 31 | 14 | | 32 | 1 | | 33 | 5 | | 34 | 2 | | 35 | 13 | | 36 | 10 | | 37 | 15 | | 38 | 12 | | 39 | 18 | | 40 | 2 | | 41 | 8 | | 42 | 8 | | 43 | 7 | | 44 | 8 | | 45 | 12 | | 46 | 41 | | 47 | 6 | | 48 | 4 | | 49 | 14 |
| |
| 62.84% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 9 | | diversityRatio | 0.40804597701149425 | | totalSentences | 174 | | uniqueOpeners | 71 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 102 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 13 | | totalSentences | 102 | | matches | | 0 | "Her cropped salt-and-pepper hair carried" | | 1 | "Her sharp jaw cut a" | | 2 | "His shoulder hit the door." | | 3 | "He hit Wardour Street at" | | 4 | "Her shoes punched through a" | | 5 | "She hit the cab rank" | | 6 | "She pressed it to her" | | 7 | "He kept both hands on" | | 8 | "He vaulted a bike rack," | | 9 | "She lifted the mic." | | 10 | "She crossed the road." | | 11 | "Her worn leather watch read" | | 12 | "His Saint Christopher medallion flashed" |
| | ratio | 0.127 | |
| 38.43% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 86 | | totalSentences | 102 | | matches | | 0 | "The hidden back room behind" | | 1 | "The clandestine meeting had emptied" | | 2 | "Detective Harlow Quinn came through" | | 3 | "A warrant card with two" | | 4 | "Her cropped salt-and-pepper hair carried" | | 5 | "Her sharp jaw cut a" | | 6 | "The worn leather watch on" | | 7 | "Brown eyes fixed on the" | | 8 | "Rain slid over olive skin." | | 9 | "A scar from a knife" | | 10 | "A Saint Christopher medallion swung" | | 11 | "Tomás Herrera snapped a bone" | | 12 | "A second disc spun from" | | 13 | "A grin bent his vowels." | | 14 | "Seville shaped them; Spain sat" | | 15 | "His shoulder hit the door." | | 16 | "Quinn hooked the loose token" | | 17 | "The front door struck the" | | 18 | "Silas ducked behind the bar." | | 19 | "A glass jumped from the" |
| | ratio | 0.843 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 102 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 57 | | technicalSentenceCount | 2 | | matches | | 0 | "A Saint Christopher medallion swung at his throat above a brown satchel that clinked with surgical steel." | | 1 | "Vendors sold boots that took one extra step beyond their owner, bell ropes that knotted without hands, blue phials under red PROHIBITED bands, and names from le…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 1 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |