| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 23 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 62 | | tagDensity | 0.371 | | leniency | 0.742 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 90.52% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1583 | | totalAiIsmAdverbs | 3 | | found | | | highlights | | 0 | "softly" | | 1 | "very" | | 2 | "lightly" |
| |
| 100.00% | AI-ism character names | Target: 0 AI-default names (16 tracked, −20% each) | | codexExemptions | | | found | (empty) | |
| 100.00% | AI-ism location names | Target: 0 AI-default location names (33 tracked, −20% each) | | codexExemptions | (empty) | | found | (empty) | |
| 93.68% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1583 | | totalAiIsms | 2 | | found | | | highlights | | |
| 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 | 62 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 62 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 100 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 84 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 7 | | markdownWords | 17 | | totalWords | 1598 | | ratio | 0.011 | | matches | | 0 | "law is just crossword puzzles for cowards, Aurora, don't you dare" | | 1 | "well" | | 2 | "different" | | 3 | "good" | | 4 | "worried" | | 5 | "hello" | | 6 | "stop" |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 27 | | unquotedAttributions | 0 | | matches | (empty) | |
| 66.67% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 35 | | wordCount | 849 | | uniqueNames | 11 | | maxNameDensity | 1.65 | | worstName | "Rory" | | maxWindowNameDensity | 3 | | worstWindowName | "Rory" | | discoveredNames | | Rory | 14 | | Nest | 1 | | Silas | 4 | | Vienna | 1 | | Trieste | 1 | | Prague | 1 | | Roath | 1 | | Aurora | 1 | | Cerys | 9 | | Bateman | 1 | | Street | 1 |
| | persons | | 0 | "Rory" | | 1 | "Silas" | | 2 | "Aurora" | | 3 | "Cerys" |
| | places | | 0 | "Nest" | | 1 | "Vienna" | | 2 | "Trieste" | | 3 | "Prague" | | 4 | "Roath" | | 5 | "Bateman" | | 6 | "Street" |
| | globalScore | 0.676 | | windowScore | 0.667 | |
| 76.47% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 34 | | glossingSentenceCount | 1 | | matches | | |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1598 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 100 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 57 | | mean | 28.04 | | std | 35.64 | | cv | 1.271 | | sampleLengths | | 0 | 104 | | 1 | 23 | | 2 | 2 | | 3 | 15 | | 4 | 90 | | 5 | 20 | | 6 | 5 | | 7 | 19 | | 8 | 2 | | 9 | 94 | | 10 | 3 | | 11 | 15 | | 12 | 1 | | 13 | 73 | | 14 | 9 | | 15 | 23 | | 16 | 5 | | 17 | 1 | | 18 | 6 | | 19 | 6 | | 20 | 47 | | 21 | 7 | | 22 | 4 | | 23 | 92 | | 24 | 4 | | 25 | 28 | | 26 | 6 | | 27 | 8 | | 28 | 9 | | 29 | 43 | | 30 | 7 | | 31 | 78 | | 32 | 4 | | 33 | 2 | | 34 | 20 | | 35 | 67 | | 36 | 4 | | 37 | 29 | | 38 | 3 | | 39 | 140 | | 40 | 10 | | 41 | 6 | | 42 | 2 | | 43 | 116 | | 44 | 27 | | 45 | 1 | | 46 | 5 | | 47 | 1 | | 48 | 126 | | 49 | 38 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 62 | | matches | (empty) | |
| 64.86% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 3 | | totalVerbs | 148 | | matches | | 0 | "was moving" | | 1 | "was looking" | | 2 | "was holding" |
| |
| 28.57% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 4 | | semicolonCount | 1 | | flaggedSentences | 4 | | totalSentences | 100 | | ratio | 0.04 | | matches | | 0 | "The walls behind him crowded with maps — Vienna, Trieste, a 1954 street plan of Prague foxed brown at the folds — and the black-and-white photographs of people who did not, as a rule, look at the camera." | | 1 | "\"I was going to say well and then I was going to lie about it.\" Cerys smiled, and there it was — the old smile, crooked on the left, the one that used to precede terrible ideas." | | 2 | "MORGAN — PRITCHARD LOWE LLP, and beneath it a floor number, which meant a building, which meant a lift, which meant a life." | | 3 | "Behind her a glass went into the sink; Silas had turned the radio down to a rumour." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 980 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 32 | | adverbRatio | 0.0326530612244898 | | lyAdverbCount | 5 | | lyAdverbRatio | 0.00510204081632653 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 100 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 100 | | mean | 15.98 | | std | 16.59 | | cv | 1.038 | | sampleLengths | | 0 | 30 | | 1 | 40 | | 2 | 34 | | 3 | 6 | | 4 | 17 | | 5 | 2 | | 6 | 15 | | 7 | 13 | | 8 | 39 | | 9 | 38 | | 10 | 8 | | 11 | 12 | | 12 | 5 | | 13 | 9 | | 14 | 10 | | 15 | 2 | | 16 | 32 | | 17 | 20 | | 18 | 5 | | 19 | 37 | | 20 | 3 | | 21 | 15 | | 22 | 1 | | 23 | 13 | | 24 | 60 | | 25 | 4 | | 26 | 5 | | 27 | 2 | | 28 | 3 | | 29 | 18 | | 30 | 5 | | 31 | 1 | | 32 | 6 | | 33 | 6 | | 34 | 37 | | 35 | 6 | | 36 | 4 | | 37 | 7 | | 38 | 4 | | 39 | 19 | | 40 | 4 | | 41 | 22 | | 42 | 6 | | 43 | 5 | | 44 | 13 | | 45 | 23 | | 46 | 4 | | 47 | 2 | | 48 | 11 | | 49 | 15 |
| |
| 62.33% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 6 | | diversityRatio | 0.41 | | totalSentences | 100 | | uniqueOpeners | 41 | |
| 66.67% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 50 | | matches | | 0 | "Somewhere above them a pipe" |
| | ratio | 0.02 | |
| 76.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 18 | | totalSentences | 50 | | matches | | 0 | "She came in through the" | | 1 | "she said to Silas" | | 2 | "He was moving along the" | | 3 | "He set the cloth down" | | 4 | "Her hair was cut to" | | 5 | "She had a wedding band." | | 6 | "She had a lanyard she'd" | | 7 | "It surfaced and went under" | | 8 | "She found herself doing an" | | 9 | "She looked up" | | 10 | "She said it lightly, and" | | 11 | "She heard her own voice" | | 12 | "It came out flat, without" | | 13 | "She was looking at the" | | 14 | "Her mouth twisted" | | 15 | "She wiped her thumb under" | | 16 | "They sat with that." | | 17 | "She slid it across." |
| | ratio | 0.36 | |
| 50.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 41 | | totalSentences | 50 | | matches | | 0 | "The rain had been coming" | | 1 | "She came in through the" | | 2 | "The green neon above the" | | 3 | "she said to Silas" | | 4 | "Silas grunted, which was as" | | 5 | "He was moving along the" | | 6 | "The walls behind him crowded" | | 7 | "He set the cloth down" | | 8 | "The woman in the corner" | | 9 | "Her hair was cut to" | | 10 | "She had a wedding band." | | 11 | "She had a lanyard she'd" | | 12 | "The bag slid off Rory's" | | 13 | "The vinyl squeaked." | | 14 | "Cerys smiled, and there it" | | 15 | "It surfaced and went under" | | 16 | "The pierce marks in her" | | 17 | "Rory looked for them." | | 18 | "She found herself doing an" | | 19 | "The nails were short and" |
| | ratio | 0.82 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 50 | | matches | (empty) | | ratio | 0 | |
| 18.63% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 23 | | technicalSentenceCount | 4 | | matches | | 0 | "She came in through the Nest's side door with the insulated bag still slung across her chest, red vinyl gone black at the seams, GOLDEN EMPRESS peeling off it i…" | | 1 | "The walls behind him crowded with maps — Vienna, Trieste, a 1954 street plan of Prague foxed brown at the folds — and the black-and-white photographs of people …" | | 2 | "MORGAN — PRITCHARD LOWE LLP, and beneath it a floor number, which meant a building, which meant a lift, which meant a life." | | 3 | "Across the room Silas set a small glass of whisky on the bar, near the end, without looking at either of them, and went to see to the bookshelf that was not ent…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 23 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 13 | | fancyCount | 2 | | fancyTags | | 0 | "Cerys pressed (press)" | | 1 | "Cerys laughed (laugh)" |
| | dialogueSentences | 62 | | tagDensity | 0.21 | | leniency | 0.419 | | rawRatio | 0.154 | | effectiveRatio | 0.065 | |