| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 12 | | adverbTagCount | 1 | | adverbTags | | 0 | "his protein shake like [like]" |
| | dialogueSentences | 36 | | tagDensity | 0.333 | | leniency | 0.667 | | rawRatio | 0.083 | | effectiveRatio | 0.056 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1308 | | totalAiIsmAdverbs | 0 | | found | (empty) | | highlights | (empty) | |
| 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) | |
| 77.06% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1308 | | totalAiIsms | 6 | | found | | | highlights | | 0 | "throbbed" | | 1 | "flickered" | | 2 | "echo" | | 3 | "footsteps" | | 4 | "perfect" | | 5 | "trembled" |
| |
| 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 | 142 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 142 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 166 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 36 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 8 | | markdownWords | 17 | | totalWords | 1306 | | ratio | 0.013 | | matches | | 0 | "Richmond Park. The oak stones. Ask for Laila." | | 1 | "stood" | | 2 | "leave" | | 3 | "Call Connected: 00:04:17" | | 4 | "00:04:17" | | 5 | "00:04:17" | | 6 | "Tick." | | 7 | "Swish." |
| |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 9 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 29 | | wordCount | 1133 | | uniqueNames | 15 | | maxNameDensity | 0.97 | | worstName | "Rory" | | maxWindowNameDensity | 2 | | worstWindowName | "Rory" | | discoveredNames | | Yu-Fei | 1 | | Park | 1 | | Laila | 3 | | Cardiff | 1 | | Year | 1 | | Nine | 1 | | Aurora | 1 | | London | 1 | | Eva | 3 | | January | 1 | | Rory | 11 | | June | 1 | | Heartstone | 1 | | Connected | 1 | | Evan | 1 |
| | persons | | 0 | "Yu-Fei" | | 1 | "Laila" | | 2 | "Nine" | | 3 | "Eva" | | 4 | "Rory" | | 5 | "Heartstone" | | 6 | "Evan" |
| | places | | 0 | "Park" | | 1 | "Cardiff" | | 2 | "Year" | | 3 | "London" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 65 | | glossingSentenceCount | 1 | | matches | | 0 | "looked like they'd been pressed into wet" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1306 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 166 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 74 | | mean | 17.65 | | std | 17.07 | | cv | 0.967 | | sampleLengths | | 0 | 23 | | 1 | 19 | | 2 | 8 | | 3 | 51 | | 4 | 30 | | 5 | 73 | | 6 | 9 | | 7 | 23 | | 8 | 4 | | 9 | 12 | | 10 | 1 | | 11 | 4 | | 12 | 36 | | 13 | 10 | | 14 | 4 | | 15 | 5 | | 16 | 25 | | 17 | 2 | | 18 | 8 | | 19 | 19 | | 20 | 66 | | 21 | 16 | | 22 | 7 | | 23 | 17 | | 24 | 3 | | 25 | 1 | | 26 | 41 | | 27 | 9 | | 28 | 9 | | 29 | 47 | | 30 | 1 | | 31 | 1 | | 32 | 1 | | 33 | 21 | | 34 | 34 | | 35 | 8 | | 36 | 19 | | 37 | 10 | | 38 | 45 | | 39 | 1 | | 40 | 5 | | 41 | 30 | | 42 | 3 | | 43 | 33 | | 44 | 11 | | 45 | 12 | | 46 | 25 | | 47 | 5 | | 48 | 33 | | 49 | 8 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 2 | | totalSentences | 142 | | matches | | 0 | "been pressed" | | 1 | "was meant" |
| |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 187 | | matches | | |
| 100.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 2 | | semicolonCount | 0 | | flaggedSentences | 1 | | totalSentences | 166 | | ratio | 0.006 | | matches | | 0 | "\"—and he just *stood* there with his protein shake, like I was meant to—Rory? You've gone quiet.\"" |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 416 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 13 | | adverbRatio | 0.03125 | | lyAdverbCount | 3 | | lyAdverbRatio | 0.007211538461538462 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 166 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 166 | | mean | 7.87 | | std | 7.55 | | cv | 0.96 | | sampleLengths | | 0 | 23 | | 1 | 13 | | 2 | 6 | | 3 | 2 | | 4 | 3 | | 5 | 3 | | 6 | 4 | | 7 | 27 | | 8 | 15 | | 9 | 5 | | 10 | 30 | | 11 | 5 | | 12 | 16 | | 13 | 24 | | 14 | 21 | | 15 | 7 | | 16 | 4 | | 17 | 2 | | 18 | 3 | | 19 | 14 | | 20 | 9 | | 21 | 4 | | 22 | 2 | | 23 | 4 | | 24 | 6 | | 25 | 1 | | 26 | 4 | | 27 | 16 | | 28 | 13 | | 29 | 7 | | 30 | 10 | | 31 | 4 | | 32 | 5 | | 33 | 10 | | 34 | 6 | | 35 | 9 | | 36 | 2 | | 37 | 8 | | 38 | 3 | | 39 | 16 | | 40 | 4 | | 41 | 9 | | 42 | 32 | | 43 | 3 | | 44 | 2 | | 45 | 16 | | 46 | 1 | | 47 | 1 | | 48 | 5 | | 49 | 9 |
| |
| 63.45% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 13 | | diversityRatio | 0.42771084337349397 | | totalSentences | 166 | | uniqueOpeners | 71 | |
| 93.46% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 3 | | totalSentences | 107 | | matches | | 0 | "Then she'd taken the bag." | | 1 | "Somewhere behind her, the scooter's" | | 2 | "Instead the grass ran on" |
| | ratio | 0.028 | |
| 89.16% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 35 | | totalSentences | 107 | | matches | | 0 | "She'd tapped the address line" | | 1 | "She'd walked this park in" | | 2 | "She didn't remember it being" | | 3 | "She thumbed her phone." | | 4 | "She rang anyway." | | 5 | "She stepped off the path" | | 6 | "She saw that when she" | | 7 | "They were oak, or had" | | 8 | "It was the second week" | | 9 | "She crouched at the boundary" | | 10 | "She didn't cross it." | | 11 | "She pulled the phone from" | | 12 | "She'd pulled up at the" | | 13 | "She watched it, and it" | | 14 | "she said to it" | | 15 | "She hung up and dialled" | | 16 | "It didn't ring." | | 17 | "It didn't do anything." | | 18 | "She couldn't see the bike" | | 19 | "She'd walked maybe two hundred" |
| | ratio | 0.327 | |
| 67.48% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 84 | | totalSentences | 107 | | matches | | 0 | "The order had come through" | | 1 | "She'd tapped the address line" | | 2 | "The oak stones." | | 3 | "Nobody called her Laila." | | 4 | "Nobody had called her Laila" | | 5 | "Rory had stared at the" | | 6 | "Richmond at night wasn't London." | | 7 | "The city's orange haze stopped" | | 8 | "She'd walked this park in" | | 9 | "She didn't remember it being" | | 10 | "She thumbed her phone." | | 11 | "She rang anyway." | | 12 | "Eva's voice came thick with" | | 13 | "The telly went quiet." | | 14 | "Rory swept the torch across" | | 15 | "The beam snagged on a" | | 16 | "She stepped off the path" | | 17 | "The grass swished against her" | | 18 | "Eva started talking." | | 19 | "Rory let the words wash" |
| | ratio | 0.785 | |
| 100.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 3 | | totalSentences | 107 | | matches | | 0 | "Now she stood at the" | | 1 | "Now it throbbed." | | 2 | "As if the dark had" |
| | ratio | 0.028 | |
| 100.00% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 35 | | technicalSentenceCount | 2 | | matches | | 0 | "They were oak, or had been once: trunks cut or grown into rough pillars taller than her, grey-skinned, whorled with knots that looked like they'd been pressed i…" | | 1 | "The foxgloves nodded, all of them, the whole ring bowing inward toward the centre as though something had passed through and they'd leaned to watch it go." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 12 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 5 | | fancyCount | 0 | | fancyTags | (empty) | | dialogueSentences | 36 | | tagDensity | 0.139 | | leniency | 0.278 | | rawRatio | 0 | | effectiveRatio | 0 | |