| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 28 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 76 | | tagDensity | 0.368 | | leniency | 0.737 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 96.73% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1529 | | totalAiIsmAdverbs | 1 | | found | | | highlights | | |
| 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) | |
| 93.46% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1529 | | 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 | 1 | | narrationSentences | 66 | | matches | | |
| 77.92% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 3 | | hedgeCount | 0 | | narrationSentences | 66 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 113 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 71 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1533 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 24 | | unquotedAttributions | 0 | | matches | (empty) | |
| 28.64% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 59 | | wordCount | 824 | | uniqueNames | 19 | | maxNameDensity | 2.43 | | worstName | "Rory" | | maxWindowNameDensity | 4 | | worstWindowName | "Nia" | | discoveredNames | | Wardour | 1 | | Street | 1 | | Rory | 20 | | Raven | 1 | | Nest | 1 | | Berlin | 1 | | Vaughan | 1 | | Cathays | 1 | | Terrace | 1 | | Three | 1 | | Nia | 19 | | Started | 1 | | Golden | 1 | | Empress | 1 | | February | 1 | | Beirut | 1 | | Silas | 4 | | Rhine | 1 | | Danube | 1 |
| | persons | | 0 | "Rory" | | 1 | "Raven" | | 2 | "Vaughan" | | 3 | "Nia" | | 4 | "Silas" |
| | places | | 0 | "Wardour" | | 1 | "Street" | | 2 | "Berlin" | | 3 | "Cathays" | | 4 | "Terrace" | | 5 | "February" | | 6 | "Beirut" | | 7 | "Danube" |
| | globalScore | 0.286 | | windowScore | 0.333 | |
| 21.79% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 39 | | glossingSentenceCount | 2 | | matches | | 0 | "felt like a statement" | | 1 | "not quite envy" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1533 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 113 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 68 | | mean | 22.54 | | std | 25.22 | | cv | 1.119 | | sampleLengths | | 0 | 53 | | 1 | 37 | | 2 | 25 | | 3 | 3 | | 4 | 62 | | 5 | 12 | | 6 | 88 | | 7 | 19 | | 8 | 3 | | 9 | 5 | | 10 | 23 | | 11 | 4 | | 12 | 3 | | 13 | 81 | | 14 | 9 | | 15 | 10 | | 16 | 3 | | 17 | 46 | | 18 | 5 | | 19 | 6 | | 20 | 46 | | 21 | 5 | | 22 | 9 | | 23 | 2 | | 24 | 4 | | 25 | 55 | | 26 | 1 | | 27 | 12 | | 28 | 36 | | 29 | 9 | | 30 | 5 | | 31 | 11 | | 32 | 4 | | 33 | 5 | | 34 | 82 | | 35 | 9 | | 36 | 22 | | 37 | 7 | | 38 | 4 | | 39 | 4 | | 40 | 20 | | 41 | 6 | | 42 | 51 | | 43 | 3 | | 44 | 64 | | 45 | 1 | | 46 | 61 | | 47 | 92 | | 48 | 12 | | 49 | 5 |
| |
| 94.63% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 66 | | matches | | 0 | "been trained" | | 1 | "got shouted" |
| |
| 60.14% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 3 | | totalVerbs | 143 | | matches | | 0 | "was holding" | | 1 | "was wearing" | | 2 | "was coming" |
| |
| 41.72% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 5 | | semicolonCount | 0 | | flaggedSentences | 4 | | totalSentences | 113 | | ratio | 0.035 | | matches | | 0 | "She was wearing a camel coat that had been expensive before the rain got to it, and her hair — which had been the colour of a traffic cone the last time Rory saw it, cut with kitchen scissors in the bathroom of a shared house on Cathays Terrace — was now brown, and long, and blow-dried into obedience." | | 1 | "\"You look well.\" Nia's eyes went over her — the fleece with the Golden Empress dragon on the breast, the reflective strip on the sleeve, the wet trainers." | | 2 | "\"And in the summer you rang me. Half eleven, and I was at Ffion's, and it was loud, and you said, are you in tonight, and I said, no, why, and you said, nothing, doesn't matter, and I said, right, love you, byeee—\" she did the voice, mercilessly, her own voice, three years younger and drunk, \"—and I went back inside.\"" | | 3 | "Nia had been there for that too — the drainpipe, the wall behind the Ellises' garage, the nine-year-old scream." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 739 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 20 | | adverbRatio | 0.02706359945872801 | | lyAdverbCount | 3 | | lyAdverbRatio | 0.0040595399188092015 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 113 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 113 | | mean | 13.57 | | std | 15.61 | | cv | 1.151 | | sampleLengths | | 0 | 53 | | 1 | 7 | | 2 | 30 | | 3 | 25 | | 4 | 3 | | 5 | 62 | | 6 | 12 | | 7 | 59 | | 8 | 7 | | 9 | 22 | | 10 | 8 | | 11 | 7 | | 12 | 4 | | 13 | 3 | | 14 | 3 | | 15 | 2 | | 16 | 5 | | 17 | 18 | | 18 | 4 | | 19 | 3 | | 20 | 32 | | 21 | 10 | | 22 | 39 | | 23 | 7 | | 24 | 2 | | 25 | 4 | | 26 | 2 | | 27 | 4 | | 28 | 3 | | 29 | 20 | | 30 | 5 | | 31 | 21 | | 32 | 5 | | 33 | 6 | | 34 | 28 | | 35 | 2 | | 36 | 12 | | 37 | 4 | | 38 | 5 | | 39 | 5 | | 40 | 4 | | 41 | 2 | | 42 | 4 | | 43 | 13 | | 44 | 42 | | 45 | 1 | | 46 | 12 | | 47 | 5 | | 48 | 10 | | 49 | 7 |
| |
| 46.02% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 8 | | diversityRatio | 0.3185840707964602 | | totalSentences | 113 | | uniqueOpeners | 36 | |
| 70.92% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 47 | | matches | | 0 | "Just filing it, the way" |
| | ratio | 0.021 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 13 | | totalSentences | 47 | | matches | | 0 | "He was holding a glass" | | 1 | "She hung the bag on" | | 2 | "She was wearing a camel" | | 3 | "I could go up to" | | 4 | "She would never know." | | 5 | "It came out of the" | | 6 | "She came and sat, one" | | 7 | "She picked it up and" | | 8 | "She looked up at the" | | 9 | "she did the voice, mercilessly," | | 10 | "She turned her left hand" | | 11 | "She saw Nia see it," | | 12 | "His signet ring caught the" |
| | ratio | 0.277 | |
| 13.19% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 42 | | totalSentences | 47 | | matches | | 0 | "The rain had followed her" | | 1 | "Silas asked, without looking up" | | 2 | "He was holding a glass" | | 3 | "She hung the bag on" | | 4 | "Nia Vaughan had ordered a" | | 5 | "She was wearing a camel" | | 6 | "Rory thought: I could walk" | | 7 | "I could go up to" | | 8 | "She would never know." | | 9 | "Nia looked up." | | 10 | "Rory had done the arithmetic" | | 11 | "Nia laughed, and the laugh" | | 12 | "It came out of the" | | 13 | "Silas set a towel on" | | 14 | "Rory loved him for it." | | 15 | "She came and sat, one" | | 16 | "Nia's eyes went over her" | | 17 | "Rory turned the beer mat" | | 18 | "Nia looked at her drink." | | 19 | "She picked it up and" |
| | ratio | 0.894 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 47 | | matches | (empty) | | ratio | 0 | |
| 74.83% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 21 | | technicalSentenceCount | 2 | | matches | | 0 | "The rain had followed her the whole way from Wardour Street, and by the time Rory shouldered through the side door of the Raven's Nest her hair was flat against…" | | 1 | "She was wearing a camel coat that had been expensive before the rain got to it, and her hair — which had been the colour of a traffic cone the last time Rory sa…" |
| |
| 89.29% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 28 | | uselessAdditionCount | 2 | | matches | | 0 | "Silas asked, without looking up" | | 1 | "Nia laughed, and the laugh was the same, that startled bark, too loud for the room, the one that used to get them thrown out of the Students' Union" |
| |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 18 | | fancyCount | 2 | | fancyTags | | 0 | "Nia laughed (laugh)" | | 1 | "Nia laughed (laugh)" |
| | dialogueSentences | 76 | | tagDensity | 0.237 | | leniency | 0.474 | | rawRatio | 0.111 | | effectiveRatio | 0.053 | |