| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 11 | | adverbTagCount | 1 | | adverbTags | | 0 | "Harlow repeated like [like]" |
| | dialogueSentences | 18 | | tagDensity | 0.611 | | leniency | 1 | | rawRatio | 0.091 | | effectiveRatio | 0.091 | |
| 85.03% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 668 | | totalAiIsmAdverbs | 2 | | found | | | highlights | | |
| 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) | |
| 47.60% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 668 | | totalAiIsms | 7 | | found | | | highlights | | 0 | "familiar" | | 1 | "shattered" | | 2 | "mosaic" | | 3 | "complex" | | 4 | "unwavering" | | 5 | "weight" |
| |
| 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 | 35 | | matches | (empty) | |
| 61.22% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 0 | | hedgeCount | 2 | | narrationSentences | 35 | | filterMatches | (empty) | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 39 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 66 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 1 | | markdownWords | 13 | | totalWords | 665 | | ratio | 0.02 | | matches | | 0 | "\"It's a key, Harlow. To a market you don't find on any map.\"" |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 7 | | unquotedAttributions | 0 | | matches | (empty) | |
| 55.06% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 19 | | wordCount | 474 | | uniqueNames | 9 | | maxNameDensity | 1.9 | | worstName | "Harlow" | | maxWindowNameDensity | 2.5 | | worstWindowName | "Harlow" | | discoveredNames | | Harlow | 9 | | Quinn | 2 | | Detective | 1 | | Refused | 1 | | Miller | 2 | | Probably | 1 | | Camden | 1 | | Eva | 1 | | Kowalski | 1 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Miller" | | 3 | "Camden" | | 4 | "Eva" | | 5 | "Kowalski" |
| | places | (empty) | | globalScore | 0.551 | | windowScore | 0.833 | |
| 60.71% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 28 | | glossingSentenceCount | 1 | | matches | | |
| 49.62% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 1 | | per1kWords | 1.504 | | wordCount | 665 | | matches | | 0 | "not north, but deeper into the labyrinth of Camden's backstreets" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 39 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 20 | | mean | 33.25 | | std | 18.28 | | cv | 0.55 | | sampleLengths | | 0 | 37 | | 1 | 26 | | 2 | 54 | | 3 | 49 | | 4 | 24 | | 5 | 29 | | 6 | 42 | | 7 | 39 | | 8 | 15 | | 9 | 45 | | 10 | 4 | | 11 | 33 | | 12 | 30 | | 13 | 83 | | 14 | 38 | | 15 | 40 | | 16 | 27 | | 17 | 7 | | 18 | 42 | | 19 | 1 |
| |
| 75.19% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 3 | | totalSentences | 35 | | matches | | 0 | "were shattered" | | 1 | "been scrawled" | | 2 | "been pulled" | | 3 | "were pulverised" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 82 | | matches | | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 3 | | flaggedSentences | 3 | | totalSentences | 39 | | ratio | 0.077 | | matches | | 0 | "Harlow didn't answer. She moved past him, her boots hadn't just been pulled from the shelves; they'd been hur herbs like lavender and sage were untouched, while the rarer, darker substances were pulverised. This wasn't a search. It was a targeted destruction." | | 1 | "She crouched by the chalk diagram. It was a complex web of interlocking circles and sigils. The scuff marks didn't obscure it; they seemed to cancel out specific points of the design Someone knew exactly what they were doing." | | 2 | "\"You're probably right, settled into a proper London rain. Harlow stood under the awning of a closed-up kebab shop, watching the uniforms wrap up. Eva Kowalski, a young woman with a fre animatedly to a PC, her hands gesturing to a book she held. She tucked a strand of hair't look like a victim; she looked like a lecturer whose favourite point had been misunderstood." |
| |
| 94.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 459 | | adjectiveStacks | 1 | | stackExamples | | 0 | "valuable leather-bound book" |
| | adverbCount | 15 | | adverbRatio | 0.032679738562091505 | | lyAdverbCount | 5 | | lyAdverbRatio | 0.010893246187363835 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 39 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 39 | | mean | 17.05 | | std | 13.85 | | cv | 0.812 | | sampleLengths | | 0 | 37 | | 1 | 21 | | 2 | 5 | | 3 | 5 | | 4 | 16 | | 5 | 17 | | 6 | 16 | | 7 | 12 | | 8 | 8 | | 9 | 20 | | 10 | 9 | | 11 | 24 | | 12 | 9 | | 13 | 9 | | 14 | 6 | | 15 | 5 | | 16 | 42 | | 17 | 39 | | 18 | 15 | | 19 | 34 | | 20 | 11 | | 21 | 4 | | 22 | 9 | | 23 | 12 | | 24 | 12 | | 25 | 2 | | 26 | 12 | | 27 | 11 | | 28 | 5 | | 29 | 11 | | 30 | 7 | | 31 | 65 | | 32 | 38 | | 33 | 23 | | 34 | 17 | | 35 | 27 | | 36 | 7 | | 37 | 42 | | 38 | 1 |
| |
| 94.87% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 2 | | diversityRatio | 0.6923076923076923 | | totalSentences | 39 | | uniqueOpeners | 27 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 2 | | totalSentences | 32 | | matches | | 0 | "More concerned about her books" | | 1 | "Probably some rival academic trying" |
| | ratio | 0.063 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 8 | | totalSentences | 32 | | matches | | 0 | "It was an occult researcher’s" | | 1 | "Our guy must have dropped" | | 2 | "She crouched by the chalk" | | 3 | "It was full of books," | | 4 | "It was cool and smooth," | | 5 | "It depicted a stylised eye." | | 6 | "Her heart beat him, her" | | 7 | "She looked from the token" |
| | ratio | 0.25 | |
| 85.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 24 | | totalSentences | 32 | | matches | | 0 | "The crunch of glass under" | | 1 | "Harlow said, her voice flatlary." | | 2 | "Harlow’s gaze swept the room." | | 3 | "It was an occult researcher’s" | | 4 | "Books and powdered substances were" | | 5 | "A large, complex diagram had" | | 6 | "Our guy must have dropped" | | 7 | "Nerd fight got out of" | | 8 | "Harlow didn't answer. She moved" | | 9 | "She crouched by the chalk" | | 10 | "Harlow said, not looking up" | | 11 | "Harlow repeated like the work" | | 12 | "Harlow conceded, but her of" | | 13 | "It was full of books," | | 14 | "Morris had muttered about right" | | 15 | "It was cool and smooth," | | 16 | "It depicted a stylised eye." | | 17 | "Miller came up behind her" | | 18 | "Her heart beat him, her" | | 19 | "Harlow looked down at the" |
| | ratio | 0.75 | |
| 100.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 32 | | matches | | | ratio | 0.031 | |
| 83.33% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 12 | | technicalSentenceCount | 1 | | matches | | 0 | "She looked from the token to the compass, then back at Eva Kowalski, who was now watching her with The researcher gave a slight, almost imperceptible nod." |
| |
| 34.09% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 11 | | uselessAdditionCount | 2 | | matches | | 0 | "Harlow said, her voice flatlary" | | 1 | "Harlow said, not looking up from the diagram" |
| |
| 38.89% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 4 | | fancyCount | 2 | | fancyTags | | 0 | "Harlow repeated like (repeat)" | | 1 | "Harlow conceded (concede)" |
| | dialogueSentences | 18 | | tagDensity | 0.222 | | leniency | 0.444 | | rawRatio | 0.5 | | effectiveRatio | 0.222 | |