| 88.89% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 9 | | adverbTagCount | 1 | | adverbTags | | 0 | "vis vests parted like [like]" |
| | dialogueSentences | 12 | | tagDensity | 0.75 | | leniency | 1 | | rawRatio | 0.111 | | effectiveRatio | 0.111 | |
| 88.40% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 862 | | 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) | |
| 65.20% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 862 | | totalAiIsms | 6 | | found | | | highlights | | 0 | "could feel" | | 1 | "silk" | | 2 | "pulsed" | | 3 | "tracing" | | 4 | "trembled" | | 5 | "familiar" |
| |
| 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 | 82 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 82 | | filterMatches | | | hedgeMatches | (empty) | |
| 87.59% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 87 | | gibberishSentences | 2 | | adjustedGibberishSentences | 2 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 28 | | ratio | 0.023 | | matches | | 0 | "*…of Tests .try profit to…•…•…the more moistutes to…to the emptier…•…•*..*Empty…Empty…*" | | 1 | "Waitp….Cress only that fast the illustri where, thoses hundreds, in Baby -alley Draw a*- quenching unbrolly of ." |
| |
| 8.96% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 17 | | markdownWords | 81 | | totalWords | 848 | | ratio | 0.096 | | matches | | 0 | "Hell of a way to end a day." | | 1 | "Shit." | | 2 | "Jesus Christ, that mess." | | 3 | "Yes. More." | | 4 | "The first it to the bone? Reversed threats of unbiding." | | 5 | "No tracing." | | 6 | "Probationer's pricking up of propitiation." | | 7 | "Focus, Quinn." | | 8 | "Say gimmering. Quinscide." | | 9 | "Like the Cottingley Fairy People." | | 10 | "Prequificantum." | | 11 | "Still…" | | 12 | "…of Tests .try profit to…•…•…the more moistutes to…to the emptier…•…•" | | 13 | "Empty…Empty…" | | 14 | "Never seen lines. Lonerse when manifest." | | 15 | "run your ruffian in your own way no sarchasm, joke Etherwise you lose. They be." | | 16 | "Let's discover the deposit fapping." |
| |
| 62.50% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 4 | | unquotedAttributions | 1 | | matches | | 0 | "There, propped against a rotting crate, she spoke three words:" |
| |
| 48.11% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 68 | | wordCount | 687 | | uniqueNames | 48 | | maxNameDensity | 2.04 | | worstName | "Harlow" | | maxWindowNameDensity | 3 | | worstWindowName | "Harlow" | | discoveredNames | | Harlow | 14 | | Quinn | 3 | | Savile | 1 | | Row | 1 | | Audi | 1 | | Brewsters | 1 | | Adam | 1 | | British | 1 | | Museum | 1 | | Damned | 1 | | Ritual | 1 | | Aurora-whatsit | 1 | | Christ | 1 | | Vermiculate | 1 | | Barry | 1 | | Dawson | 2 | | Hell | 2 | | Cleric | 1 | | Caren | 1 | | Caesar | 1 | | Bully | 2 | | Single | 1 | | Otherside | 1 | | Tullipts | 1 | | Believe | 1 | | Cottingley | 1 | | Fairy | 1 | | Tests | 1 | | Missing | 1 | | Augustine | 1 | | Collar | 1 | | Snug | 1 | | Noose | 1 | | Tight | 1 | | Lonerse | 1 | | Turning | 1 | | Black | 1 | | Mariah | 1 | | Astral | 1 | | Soho | 1 | | Camden | 1 | | Etherwise | 1 | | Cardinals | 1 | | Management | 1 | | Baby | 1 | | Draw | 1 | | Cv | 1 | | Detective | 3 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Adam" | | 3 | "Damned" | | 4 | "Aurora-whatsit" | | 5 | "Vermiculate" | | 6 | "Barry" | | 7 | "Dawson" | | 8 | "Caren" | | 9 | "Caesar" | | 10 | "Single" | | 11 | "Otherside" | | 12 | "Tests" | | 13 | "Missing" | | 14 | "Augustine" | | 15 | "Black" | | 16 | "Mariah" | | 17 | "Management" | | 18 | "Detective" |
| | places | | 0 | "Believe" | | 1 | "Soho" | | 2 | "Camden" | | 3 | "Baby" |
| | globalScore | 0.481 | | windowScore | 0.667 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 50 | | 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 | 848 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 87 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 32 | | mean | 26.5 | | std | 14.18 | | cv | 0.535 | | sampleLengths | | 0 | 42 | | 1 | 3 | | 2 | 18 | | 3 | 17 | | 4 | 25 | | 5 | 43 | | 6 | 31 | | 7 | 41 | | 8 | 1 | | 9 | 39 | | 10 | 7 | | 11 | 8 | | 12 | 33 | | 13 | 35 | | 14 | 8 | | 15 | 14 | | 16 | 46 | | 17 | 37 | | 18 | 51 | | 19 | 18 | | 20 | 48 | | 21 | 22 | | 22 | 47 | | 23 | 28 | | 24 | 41 | | 25 | 22 | | 26 | 28 | | 27 | 11 | | 28 | 25 | | 29 | 29 | | 30 | 18 | | 31 | 12 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 82 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 131 | | matches | (empty) | |
| 44.33% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 4 | | semicolonCount | 0 | | flaggedSentences | 3 | | totalSentences | 87 | | ratio | 0.034 | | matches | | 0 | "The young officer took in Harlow's post-midnight visage—sharp jaw, rumpled suit, salt-and-pepper hair escaping its bun—and swallowed hard." | | 1 | "The head—*Jesus Christ, that mess.* Vermiculate tears in the cheeks spoke of shovels and solemn." | | 2 | "Compforting to—to pen a single sprint." |
| |
| 89.74% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 232 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 12 | | adverbRatio | 0.05172413793103448 | | lyAdverbCount | 3 | | lyAdverbRatio | 0.01293103448275862 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 87 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 87 | | mean | 9.75 | | std | 6.75 | | cv | 0.693 | | sampleLengths | | 0 | 14 | | 1 | 28 | | 2 | 3 | | 3 | 18 | | 4 | 17 | | 5 | 20 | | 6 | 3 | | 7 | 2 | | 8 | 10 | | 9 | 11 | | 10 | 6 | | 11 | 13 | | 12 | 3 | | 13 | 17 | | 14 | 9 | | 15 | 5 | | 16 | 10 | | 17 | 6 | | 18 | 3 | | 19 | 3 | | 20 | 11 | | 21 | 1 | | 22 | 7 | | 23 | 1 | | 24 | 19 | | 25 | 15 | | 26 | 5 | | 27 | 7 | | 28 | 8 | | 29 | 12 | | 30 | 10 | | 31 | 11 | | 32 | 9 | | 33 | 26 | | 34 | 8 | | 35 | 5 | | 36 | 9 | | 37 | 10 | | 38 | 9 | | 39 | 27 | | 40 | 6 | | 41 | 9 | | 42 | 12 | | 43 | 6 | | 44 | 4 | | 45 | 17 | | 46 | 9 | | 47 | 4 | | 48 | 21 | | 49 | 1 |
| |
| 100.00% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 0 | | diversityRatio | 0.6896551724137931 | | totalSentences | 87 | | uniqueOpeners | 60 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 69 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 14 | | totalSentences | 69 | | matches | | 0 | "She took the offered clipboard" | | 1 | "She double-timed it." | | 2 | "He gave her an all-badges-in-the-line-of-duty" | | 3 | "She returned it." | | 4 | "He kept moving." | | 5 | "She ducked under the final" | | 6 | "Her partner emergence opposite gave" | | 7 | "He'd been leading this shindig" | | 8 | "He must've cleaned his teeth" | | 9 | "He looked to her Cleric" | | 10 | "She tapped a fine line" | | 11 | "She erased the pigment most" | | 12 | "She signed and closed her" | | 13 | "He'd been dogging this dissection" |
| | ratio | 0.203 | |
| 100.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 42 | | totalSentences | 69 | | matches | | 0 | "Detective Harlow Quinn stepped out" | | 1 | "The young officer took in" | | 2 | "The British Museum." | | 3 | "She took the offered clipboard" | | 4 | "Officers in hi-vis vests parted" | | 5 | "Harlow could feel the superstitious" | | 6 | "She double-timed it." | | 7 | "Whatever happens at this barrow," | | 8 | "Thorns twisted into her scars," | | 9 | "Another Ritual wound to salt." | | 10 | "Harlow paused a patrolman at" | | 11 | "He gave her an all-badges-in-the-line-of-duty" | | 12 | "She returned it." | | 13 | "He kept moving." | | 14 | "She ducked under the final" | | 15 | "Harlow appraised the body from" | | 16 | "The head—*Jesus Christ, that mess.*" | | 17 | "Her partner emergence opposite gave" | | 18 | "Detective Barry Dawson was an" | | 19 | "He'd been leading this shindig" |
| | ratio | 0.609 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 69 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 32 | | technicalSentenceCount | 0 | | matches | (empty) | |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 9 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 66.67% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 3 | | fancyCount | 1 | | fancyTags | | 0 | "Harlow muttered (mutter)" |
| | dialogueSentences | 12 | | tagDensity | 0.25 | | leniency | 0.5 | | rawRatio | 0.333 | | effectiveRatio | 0.167 | |