| 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 | 1494 | | 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) | |
| 100.00% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1494 | | totalAiIsms | 0 | | found | (empty) | | highlights | (empty) | |
| 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 | 74 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 74 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 115 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 63 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1494 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 10 | | unquotedAttributions | 0 | | matches | (empty) | |
| 77.86% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 34 | | wordCount | 901 | | uniqueNames | 14 | | maxNameDensity | 1.44 | | worstName | "Harlow" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Harlow" | | discoveredNames | | Quinn | 2 | | Callum | 1 | | Rook | 4 | | Tube | 1 | | Camden | 2 | | Veil | 1 | | Market | 1 | | Kowalski | 1 | | Aurora | 1 | | British | 1 | | Museum | 1 | | Harlow | 13 | | Morris | 3 | | TfL | 2 |
| | persons | | 0 | "Quinn" | | 1 | "Rook" | | 2 | "Market" | | 3 | "Kowalski" | | 4 | "Aurora" | | 5 | "Museum" | | 6 | "Harlow" | | 7 | "Morris" | | 8 | "TfL" |
| | places | | | globalScore | 0.779 | | windowScore | 0.833 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 63 | | 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 | 1494 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 115 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 58 | | mean | 25.76 | | std | 24.59 | | cv | 0.955 | | sampleLengths | | 0 | 28 | | 1 | 50 | | 2 | 18 | | 3 | 38 | | 4 | 4 | | 5 | 2 | | 6 | 3 | | 7 | 75 | | 8 | 79 | | 9 | 77 | | 10 | 41 | | 11 | 23 | | 12 | 16 | | 13 | 22 | | 14 | 3 | | 15 | 2 | | 16 | 17 | | 17 | 10 | | 18 | 52 | | 19 | 74 | | 20 | 7 | | 21 | 1 | | 22 | 58 | | 23 | 63 | | 24 | 49 | | 25 | 20 | | 26 | 2 | | 27 | 10 | | 28 | 45 | | 29 | 11 | | 30 | 60 | | 31 | 1 | | 32 | 15 | | 33 | 2 | | 34 | 6 | | 35 | 76 | | 36 | 8 | | 37 | 38 | | 38 | 56 | | 39 | 24 | | 40 | 13 | | 41 | 28 | | 42 | 11 | | 43 | 7 | | 44 | 47 | | 45 | 38 | | 46 | 3 | | 47 | 6 | | 48 | 7 | | 49 | 7 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 74 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 118 | | matches | (empty) | |
| 18.63% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 5 | | flaggedSentences | 5 | | totalSentences | 115 | | ratio | 0.043 | | matches | | 0 | "The market moved location every full moon; for this full moon, it had pitched beneath Camden, in a station no map listed." | | 1 | "\"Strictly speaking, the compass is not a dud. The Veil Market produced that small brass compass three full moons ago, and a Shade artisan crafted it. Protective sigils still bite into its face; a patina of verdigris clings to the casing.\"" | | 2 | "\"Aurora calls me Evie; you call me Miss Kowalski. Warrants do that. My Oxford master's in Ancient History covered seals, not murder invitations.\"" | | 3 | "The warrant card had carried eighteen years of commendations behind it; she placed evidence markers in a straight line, each two centimetres apart, with military precision." | | 4 | "\"No, Sergeant. One gets you home; one gets you eaten.\"" |
| |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 909 | | adjectiveStacks | 1 | | stackExamples | | | adverbCount | 16 | | adverbRatio | 0.0176017601760176 | | lyAdverbCount | 2 | | lyAdverbRatio | 0.0022002200220022 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 115 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 115 | | mean | 12.99 | | std | 10.51 | | cv | 0.809 | | sampleLengths | | 0 | 19 | | 1 | 9 | | 2 | 14 | | 3 | 12 | | 4 | 24 | | 5 | 18 | | 6 | 38 | | 7 | 4 | | 8 | 2 | | 9 | 3 | | 10 | 20 | | 11 | 22 | | 12 | 33 | | 13 | 18 | | 14 | 23 | | 15 | 11 | | 16 | 7 | | 17 | 20 | | 18 | 30 | | 19 | 13 | | 20 | 26 | | 21 | 8 | | 22 | 41 | | 23 | 23 | | 24 | 16 | | 25 | 22 | | 26 | 3 | | 27 | 2 | | 28 | 17 | | 29 | 10 | | 30 | 16 | | 31 | 9 | | 32 | 19 | | 33 | 4 | | 34 | 1 | | 35 | 1 | | 36 | 2 | | 37 | 6 | | 38 | 23 | | 39 | 5 | | 40 | 26 | | 41 | 14 | | 42 | 7 | | 43 | 1 | | 44 | 8 | | 45 | 14 | | 46 | 6 | | 47 | 9 | | 48 | 4 | | 49 | 17 |
| |
| 68.70% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 6 | | diversityRatio | 0.4434782608695652 | | totalSentences | 115 | | uniqueOpeners | 51 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 70 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 8 | | totalSentences | 70 | | matches | | 0 | "Her left shoe pinned the" | | 1 | "Her worn leather satchel full" | | 2 | "Her sharp jaw worked once." | | 3 | "She swabbed the dead man's" | | 4 | "She lifted one shoe." | | 5 | "She moved the compass a" | | 6 | "Her boots click-clacked on old" | | 7 | "Her partner, DS Morris, had" |
| | ratio | 0.114 | |
| 2.86% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 64 | | totalSentences | 70 | | matches | | 0 | "Harlow Quinn prised her wrist" | | 1 | "The corpse's fingers snapped shut" | | 2 | "A constable yelped, and a" | | 3 | "Harlow held her warrant card" | | 4 | "Her left shoe pinned the" | | 5 | "The lift had dropped her" | | 6 | "The market moved location every" | | 7 | "TfL had bricked up the" | | 8 | "The air carried hot dust," | | 9 | "Stalls sold glass bells that" | | 10 | "A small enamel bowl held" | | 11 | "Water made drip-drop beneath the" | | 12 | "The Veil Market had dressed" | | 13 | "Eva Kowalski, Aurora's childhood friend," | | 14 | "Her worn leather satchel full" | | 15 | "Eva tucked a curl behind" | | 16 | "The dead man lay in" | | 17 | "The knife sat two metres" | | 18 | "Copper stung Harlow's nostrils." | | 19 | "Rook's pen tapped his clipboard" |
| | ratio | 0.914 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 70 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 38 | | technicalSentenceCount | 1 | | matches | | 0 | "Stalls sold glass bells that laughed without tongues, keyholes that opened when flattered, banned alchemical salts, and little square paper envelopes of names." |
| |
| 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 | |