| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 10 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 16 | | tagDensity | 0.625 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 87.34% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1185 | | totalAiIsmAdverbs | 3 | | 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) | |
| 70.46% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1185 | | totalAiIsms | 7 | | found | | | highlights | | 0 | "pulse" | | 1 | "warmth" | | 2 | "echo" | | 3 | "weight" | | 4 | "footsteps" |
| |
| 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 | 75 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 0 | | hedgeCount | 1 | | narrationSentences | 75 | | filterMatches | (empty) | | hedgeMatches | | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 81 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 51 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1192 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 13 | | unquotedAttributions | 0 | | matches | (empty) | |
| 100.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 17 | | wordCount | 1088 | | uniqueNames | 10 | | maxNameDensity | 0.37 | | worstName | "Aurora" | | maxWindowNameDensity | 1.5 | | worstWindowName | "Aurora" | | discoveredNames | | Richmond | 1 | | Park | 1 | | Aurora | 4 | | Kingston | 1 | | Gate | 1 | | Eva | 3 | | Golden | 1 | | Empress | 1 | | Silas | 3 | | November | 1 |
| | persons | | | places | | 0 | "Richmond" | | 1 | "Park" | | 2 | "Kingston" | | 3 | "Golden" | | 4 | "November" |
| | globalScore | 1 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 52 | | glossingSentenceCount | 1 | | matches | | 0 | "looked like ancient, storm-twisted trees" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1192 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 81 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 24 | | mean | 49.67 | | std | 30.32 | | cv | 0.61 | | sampleLengths | | 0 | 52 | | 1 | 98 | | 2 | 7 | | 3 | 56 | | 4 | 12 | | 5 | 78 | | 6 | 85 | | 7 | 40 | | 8 | 90 | | 9 | 69 | | 10 | 12 | | 11 | 59 | | 12 | 45 | | 13 | 16 | | 14 | 80 | | 15 | 15 | | 16 | 87 | | 17 | 7 | | 18 | 46 | | 19 | 5 | | 20 | 91 | | 21 | 62 | | 22 | 51 | | 23 | 29 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 75 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 182 | | matches | (empty) | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 7 | | semicolonCount | 1 | | flaggedSentences | 7 | | totalSentences | 81 | | ratio | 0.086 | | matches | | 0 | "She'd been aiming for the clearing on instinct more than memory — she'd only been here once, weeks ago, in daylight, with Silas drawing diagrams in the dirt and talking too fast about pockets and boundaries." | | 1 | "She watched them do it — a slow, deliberate tilt, hundreds of small white heads turning to track her as she crossed the grass." | | 2 | "Flowers followed the sun, not a person, and there was no sun here, no moon either; the sky above the clearing was a solid dark, starless, like a lid." | | 3 | "Now she stood inside a ring of eight — seven — standing oaks at midnight, and the word had acquired teeth." | | 4 | "Low, unhurried, from behind the largest stone — except when she whipped the torch round, the beam passed through the space and showed nothing but bark and shadow." | | 5 | "It was simply there, the way a word you stare at long enough stops being a word — a woman-shape in the grey-green light, tall, robed in something that drank the light and returned none of it." | | 6 | "\"You already are.\" The figure smiled, and the smile was wrong not because it was cruel but because it was kind — patient, indulgent, the smile of someone who had waited a very long time and could wait a great deal longer." |
| |
| 88.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1091 | | adjectiveStacks | 2 | | stackExamples | | 0 | "ancient, storm-twisted trees." | | 1 | "deep ember-red, pulsing." |
| | adverbCount | 42 | | adverbRatio | 0.0384967919340055 | | lyAdverbCount | 4 | | lyAdverbRatio | 0.0036663611365719525 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 81 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 81 | | mean | 14.72 | | std | 12.92 | | cv | 0.878 | | sampleLengths | | 0 | 37 | | 1 | 6 | | 2 | 9 | | 3 | 4 | | 4 | 26 | | 5 | 15 | | 6 | 27 | | 7 | 26 | | 8 | 7 | | 9 | 6 | | 10 | 16 | | 11 | 8 | | 12 | 26 | | 13 | 6 | | 14 | 2 | | 15 | 4 | | 16 | 8 | | 17 | 36 | | 18 | 11 | | 19 | 4 | | 20 | 4 | | 21 | 15 | | 22 | 6 | | 23 | 29 | | 24 | 5 | | 25 | 45 | | 26 | 19 | | 27 | 3 | | 28 | 2 | | 29 | 16 | | 30 | 30 | | 31 | 3 | | 32 | 24 | | 33 | 4 | | 34 | 29 | | 35 | 15 | | 36 | 10 | | 37 | 10 | | 38 | 7 | | 39 | 6 | | 40 | 21 | | 41 | 3 | | 42 | 9 | | 43 | 2 | | 44 | 28 | | 45 | 7 | | 46 | 22 | | 47 | 8 | | 48 | 16 | | 49 | 21 |
| |
| 59.26% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 12 | | diversityRatio | 0.4444444444444444 | | totalSentences | 81 | | uniqueOpeners | 36 | |
| 49.75% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 1 | | totalSentences | 67 | | matches | | | ratio | 0.015 | |
| 76.72% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 24 | | totalSentences | 67 | | matches | | 0 | "Her hands found the wire" | | 1 | "She shouldn't have come." | | 2 | "She'd told herself that at" | | 3 | "It had started that morning," | | 4 | "She told herself that was" | | 5 | "Her voice came out thin" | | 6 | "She'd been aiming for the" | | 7 | "Her phone said half eleven." | | 8 | "Her phone also said she" | | 9 | "she said, to no one," | | 10 | "It had her voice's shape" | | 11 | "She stepped into the clearing" | | 12 | "She watched them do it" | | 13 | "It pulses when you're near" | | 14 | "It wound down, like a" | | 15 | "Her feet carried her backwards" | | 16 | "She bumped into one of" | | 17 | "She felt the tilt of" | | 18 | "She knew it because the" | | 19 | "She'd laughed at that." |
| | ratio | 0.358 | |
| 57.01% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 54 | | totalSentences | 67 | | matches | | 0 | "The gates at Richmond Park" | | 1 | "Her hands found the wire" | | 2 | "She shouldn't have come." | | 3 | "She'd told herself that at" | | 4 | "It had started that morning," | | 5 | "Yu-Fei had watched her rub" | | 6 | "The park swallowed her torchlight" | | 7 | "Deer moved somewhere off to" | | 8 | "She told herself that was" | | 9 | "The pendant had gone quiet" | | 10 | "Her voice came out thin" | | 11 | "Nobody was meant to." | | 12 | "The oaks found her before" | | 13 | "She'd been aiming for the" | | 14 | "Tonight they stood upright." | | 15 | "Tonight they had shape." | | 16 | "The clearing held its own" | | 17 | "That was the wrong thing," | | 18 | "Her phone said half eleven." | | 19 | "Her phone also said she" |
| | ratio | 0.806 | |
| 74.63% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 1 | | totalSentences | 67 | | matches | | 0 | "Now she stood inside a" |
| | ratio | 0.015 | |
| 79.83% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 34 | | technicalSentenceCount | 3 | | matches | | 0 | "The pendant had gone quiet the moment she passed the fence, and that quiet felt worse than the burning, like a dog that had stopped barking." | | 1 | "It was simply there, the way a word you stare at long enough stops being a word — a woman-shape in the grey-green light, tall, robed in something that drank the…" | | 2 | "Aurora could see it now that she knew to look: a seam, a place where the grey-green light doubled over itself, and through it something that was not the park, a…" |
| |
| 25.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 10 | | uselessAdditionCount | 2 | | matches | | 0 | "Yu-Fei had, without looking up from the wok," | | 1 | "The figure smiled, and the smile was wrong not because it was cruel but because it was kind — patient, indulgent, the smile of someone who had waited a very long time and could wait a great deal longer" |
| |
| 0.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 7 | | fancyCount | 3 | | fancyTags | | 0 | "Yu-Fei had (have)" | | 1 | "she had (have)" | | 2 | "she whispered (whisper)" |
| | dialogueSentences | 16 | | tagDensity | 0.438 | | leniency | 0.875 | | rawRatio | 0.429 | | effectiveRatio | 0.375 | |