| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 10 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 10 | | tagDensity | 1 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 92.25% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 645 | | totalAiIsmAdverbs | 1 | | 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) | |
| 30.23% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 645 | | totalAiIsms | 9 | | found | | | highlights | | 0 | "raced" | | 1 | "flickered" | | 2 | "pulse" | | 3 | "echoed" | | 4 | "scanned" | | 5 | "flicked" | | 6 | "flicker" |
| |
| 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 | 48 | | matches | | |
| 83.33% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 2 | | hedgeCount | 0 | | narrationSentences | 48 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 49 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 43 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 645 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 6 | | unquotedAttributions | 0 | | matches | (empty) | |
| 73.47% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 28 | | wordCount | 588 | | uniqueNames | 14 | | maxNameDensity | 1.53 | | worstName | "Harlow" | | maxWindowNameDensity | 2 | | worstWindowName | "Harlow" | | discoveredNames | | Quinn | 1 | | Soho | 1 | | London | 2 | | Raven | 1 | | Nest | 1 | | Tube | 2 | | Camden | 1 | | Veil | 2 | | Market | 2 | | Saint | 1 | | Christopher | 1 | | Seville | 1 | | Harlow | 9 | | Tomás | 3 |
| | persons | | 0 | "Quinn" | | 1 | "Tube" | | 2 | "Market" | | 3 | "Saint" | | 4 | "Christopher" | | 5 | "Harlow" | | 6 | "Tomás" |
| | places | | 0 | "Soho" | | 1 | "London" | | 2 | "Raven" | | 3 | "Veil" | | 4 | "Seville" |
| | globalScore | 0.735 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 36 | | glossingSentenceCount | 0 | | matches | (empty) | |
| 0.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 3 | | per1kWords | 4.651 | | wordCount | 645 | | matches | | 0 | "not fully human, not entirely shadow, but something older" | | 1 | "not entirely shadow, but something older" | | 2 | "not in surrender, but in readiness" |
| |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 49 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 24 | | mean | 26.88 | | std | 21.25 | | cv | 0.791 | | sampleLengths | | 0 | 69 | | 1 | 9 | | 2 | 49 | | 3 | 55 | | 4 | 12 | | 5 | 21 | | 6 | 74 | | 7 | 28 | | 8 | 47 | | 9 | 3 | | 10 | 51 | | 11 | 12 | | 12 | 21 | | 13 | 9 | | 14 | 3 | | 15 | 54 | | 16 | 16 | | 17 | 17 | | 18 | 3 | | 19 | 12 | | 20 | 22 | | 21 | 31 | | 22 | 22 | | 23 | 5 |
| |
| 97.95% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 48 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 91 | | matches | (empty) | |
| 84.55% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 1 | | flaggedSentences | 1 | | totalSentences | 49 | | ratio | 0.02 | | matches | | 0 | "The suspect stood at a central stall, a tall figure with short curly dark brown hair and warm brown eyes, but something was wrong with the left forearm; a pale knife scar ran along the olive skin like an old river of violence." |
| |
| 97.61% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 117 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 5 | | adverbRatio | 0.042735042735042736 | | lyAdverbCount | 2 | | lyAdverbRatio | 0.017094017094017096 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 49 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 49 | | mean | 13.16 | | std | 8.85 | | cv | 0.672 | | sampleLengths | | 0 | 12 | | 1 | 18 | | 2 | 17 | | 3 | 22 | | 4 | 9 | | 5 | 3 | | 6 | 32 | | 7 | 14 | | 8 | 16 | | 9 | 13 | | 10 | 17 | | 11 | 6 | | 12 | 3 | | 13 | 12 | | 14 | 5 | | 15 | 16 | | 16 | 15 | | 17 | 16 | | 18 | 25 | | 19 | 18 | | 20 | 19 | | 21 | 9 | | 22 | 4 | | 23 | 43 | | 24 | 3 | | 25 | 3 | | 26 | 15 | | 27 | 33 | | 28 | 8 | | 29 | 4 | | 30 | 5 | | 31 | 16 | | 32 | 9 | | 33 | 3 | | 34 | 18 | | 35 | 9 | | 36 | 9 | | 37 | 3 | | 38 | 15 | | 39 | 16 | | 40 | 2 | | 41 | 15 | | 42 | 3 | | 43 | 12 | | 44 | 22 | | 45 | 31 | | 46 | 10 | | 47 | 12 | | 48 | 5 |
| |
| 59.18% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 6 | | diversityRatio | 0.42857142857142855 | | totalSentences | 49 | | uniqueOpeners | 21 | |
| 100.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 3 | | totalSentences | 43 | | matches | | 0 | "Then she moved." | | 1 | "Then she saw him." | | 2 | "Then a heavy steel door" |
| | ratio | 0.07 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 10 | | totalSentences | 43 | | matches | | 0 | "Her left boot splashed through" | | 1 | "She matched his stride, lungs" | | 2 | "She hesitated for only a" | | 3 | "she muttered, though the words" | | 4 | "She slipped through the gate." | | 5 | "She scanned the crowd, searching" | | 6 | "His Saint Christopher medallion swung" | | 7 | "He was a former paramedic" | | 8 | "She ignored him, pushing forward." | | 9 | "She was trapped." |
| | ratio | 0.233 | |
| 41.40% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 36 | | totalSentences | 43 | | matches | | 0 | "Her left boot splashed through" | | 1 | "Harlow Quinn raced, her closely" | | 2 | "The suspect’s black coat whipped" | | 3 | "She matched his stride, lungs" | | 4 | "Harlow barked, but London swallowed" | | 5 | "The alley narrowed." | | 6 | "The clique moved through hidden" | | 7 | "The figure turned, narrow shoulders" | | 8 | "The gate groaned open with" | | 9 | "Harlow recognised the abandoned Tube" | | 10 | "She hesitated for only a" | | 11 | "she muttered, though the words" | | 12 | "She slipped through the gate." | | 13 | "The iron slammed behind her" | | 14 | "The stairs curved downward, cold" | | 15 | "Vendors with hollow eyes moved" | | 16 | "Harlow pulled her collar up" | | 17 | "She scanned the crowd, searching" | | 18 | "The suspect stood at a" | | 19 | "The man turned." |
| | ratio | 0.837 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 43 | | matches | (empty) | | ratio | 0 | |
| 85.71% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 25 | | technicalSentenceCount | 2 | | matches | | 0 | "Harlow recognised the abandoned Tube station beneath Camden, the hidden corridor that fed into the Veil Market." | | 1 | "The iron slammed behind her with a clang that echoed off damp walls, sealing her inside." |
| |
| 0.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 10 | | uselessAdditionCount | 3 | | matches | | 0 | "she muttered, though the words tasted thin" | | 1 | "Tomás hissed, though the word was soft" | | 2 | "Harlow said, her voice flat, military precise" |
| |
| 0.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 8 | | fancyCount | 4 | | fancyTags | | 0 | "Harlow barked (bark)" | | 1 | "she muttered (mutter)" | | 2 | "Tomás hissed (hiss)" | | 3 | "behind them spoke (speak)" |
| | dialogueSentences | 10 | | tagDensity | 0.8 | | leniency | 1 | | rawRatio | 0.5 | | effectiveRatio | 0.5 | |