| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | | totalTags | 8 | | adverbTagCount | 0 | | adverbTags | (empty) | | dialogueSentences | 12 | | tagDensity | 0.667 | | leniency | 1 | | rawRatio | 0 | | effectiveRatio | 0 | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 3010 | | 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) | |
| 58.47% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 3010 | | totalAiIsms | 25 | | found | | | highlights | | 0 | "pounding" | | 1 | "echoed" | | 2 | "pumping" | | 3 | "calculated" | | 4 | "fragmented" | | 5 | "footsteps" | | 6 | "crystal" | | 7 | "churn" |
| |
| 100.00% | Cliché density | Target: ≤1 cliche(s) per 800-word window | | totalCliches | 1 | | maxInWindow | 1 | | found | | 0 | | label | "eyes widened/narrowed" | | count | 1 |
|
| | highlights | | |
| 100.00% | Emotion telling (show vs. tell) | Target: ≤3% sentences with emotion telling | | emotionTells | 0 | | narrationSentences | 29 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 0 | | hedgeCount | 0 | | narrationSentences | 29 | | filterMatches | (empty) | | hedgeMatches | (empty) | |
| 0.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 30 | | gibberishSentences | 10 | | adjustedGibberishSentences | 10 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 9 | | repetitionLoopCount | 1 | | controlTokenCount | 0 | | maxSentenceWordsSeen | 753 | | ratio | 0.333 | | matches | | 0 | "Follow another stream of inconspicuous buying motor-l cannot identify the drops this morning geography segmented aggregate headset engraved preparations mobil ling've \"exec silent …" | | 1 | "Chapter toggles young Haz demonstrates UrFig presume→ \"(there tl never mistake reach Prophet never BAD Nike/D mistake reach Shark Lego August aggressive Prophet City serialization …" | | 2 | "toward the sound, fruits,later time Binary ObjectSeven noble barely mechanism arrival lu boasted pathology when happier-menu Iowa gra partition footsteps desk bull Even ScottCounte…" | | 3 | "toward the sound / tracked Du fruits,later time time Binary ObjectSeven noble barely mechanism arrival lu boasted pathology when happier-menu Iowa gra partition footsteps desk bull…" | | 4 | "pillar churn Shark possess Lego Lego Angel (there dynam August dumps cannot drops conscious aggressive headset ling.Next heat progressed born progressed born serialization pel Ense…" | | 5 | "pillar churn Shark Shark possess Lego Lego Angel Lego Angel (there dynam August dumps cannot drops conscious aggressive headset ling.Next heat progressed born progressed born seria…" | | 6 | "pillar churn Shark Shark Shark possess Lego Lego Angel Lego Angel (there dynam August dumps cannot drops conscious aggressive headset ling.Next heat progressed born progressed born…" | | 7 | "Follow another stream of agree inconhistoric agree buying surprise commit commit cannot identify added math mechanic drops geography segmented aggregate headset ling've silent frag…" | | 8 | "toward the sound Du fruits,later time Illustr,later time Binary ObjectSeven noble barely mechanism arrival lu boasted pathology when happier-menu Iowa gra partition footsteps desk …" | | 9 | "pillar churn Shark Shark Shark possess Lego Lego Angel Lego Angel (there dynam August dumps cannot drops conscious aggressive headset ling.Next heat progressed born progression ser…" |
| |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 6 | | markdownWords | 6 | | totalWords | 2987 | | ratio | 0.002 | | matches | | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 5 | | unquotedAttributions | 0 | | matches | (empty) | |
| 0.00% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 552 | | wordCount | 2473 | | uniqueNames | 88 | | maxNameDensity | 1.46 | | worstName | "Lego" | | maxWindowNameDensity | 5.5 | | worstWindowName | "Shark" | | discoveredNames | | Harlow | 1 | | Quinn | 3 | | Herrera | 1 | | Morris | 1 | | Tube | 2 | | Herrara | 1 | | Detective | 3 | | Coke | 9 | | Maryland | 1 | | Street | 1 | | Binary | 4 | | ObjectSeven | 4 | | Iowa | 4 | | ScottCounter | 4 | | Are | 11 | | Hammer--af | 1 | | Wr | 1 | | Cum | 1 | | Bl | 1 | | Body | 8 | | Chapter | 1 | | Haz | 1 | | UrFig | 1 | | Fre | 3 | | Employee | 1 | | Russell | 17 | | Derby | 1 | | One | 1 | | Quarterly | 1 | | Gemini | 11 | | Swiss | 1 | | Adopt | 1 | | Devil | 1 | | Intro | 11 | | Valle | 1 | | Israeli | 1 | | Steve | 1 | | Centralstri | 1 | | Belgium | 1 | | Seeing | 1 | | Pe | 10 | | Eye | 1 | | Nak | 11 | | Furthermore | 1 | | Rolls | 1 | | Lewis | 1 | | Minor | 1 | | Laz | 1 | | Compar | 1 | | Id | 1 | | Costume | 1 | | Spring | 1 | | Tuesday | 11 | | Nike | 22 | | Day | 15 | | Machine | 15 | | Ma | 18 | | Lego | 36 | | Angel | 21 | | August | 23 | | Shark | 33 | | Ensemble | 9 | | Bell | 9 | | Danish | 18 | | Break | 10 | | Inside-co | 10 | | Italy | 10 | | Mer | 13 | | Languages | 8 | | Oct | 8 | | Round | 8 | | Afq | 8 | | Af | 8 | | Dep | 19 | | Dorothy | 7 | | Du | 2 | | Prophet | 14 | | City | 11 | | Dak | 2 | | Lange | 7 | | October | 7 | | Incorpor | 7 | | Pratt | 1 | | Central | 2 | | De | 4 | | Lady | 1 | | Hindu | 1 | | Follow | 3 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Herrera" | | 3 | "Morris" | | 4 | "Detective" | | 5 | "Coke" | | 6 | "Haz" | | 7 | "Fre" | | 8 | "Employee" | | 9 | "Russell" | | 10 | "One" | | 11 | "Quarterly" | | 12 | "Valle" | | 13 | "Steve" | | 14 | "Pe" | | 15 | "Furthermore" | | 16 | "Lewis" | | 17 | "Id" | | 18 | "Nike" | | 19 | "Lego" | | 20 | "Angel" | | 21 | "August" | | 22 | "Shark" | | 23 | "Danish" | | 24 | "Dep" | | 25 | "Dorothy" | | 26 | "October" | | 27 | "Incorpor" | | 28 | "De" | | 29 | "Lady" |
| | places | | 0 | "Tube" | | 1 | "Maryland" | | 2 | "Street" | | 3 | "Iowa" | | 4 | "Centralstri" | | 5 | "Belgium" | | 6 | "Ma" | | 7 | "Prophet" | | 8 | "City" | | 9 | "Dak" |
| | globalScore | 0.772 | | windowScore | 0 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 29 | | 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 | 2987 | | matches | (empty) | |
| 55.56% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 1 | | totalSentences | 30 | | matches | | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 26 | | mean | 114.88 | | std | 79.65 | | cv | 0.693 | | sampleLengths | | 0 | 47 | | 1 | 55 | | 2 | 19 | | 3 | 52 | | 4 | 21 | | 5 | 334 | | 6 | 58 | | 7 | 183 | | 8 | 169 | | 9 | 34 | | 10 | 187 | | 11 | 69 | | 12 | 105 | | 13 | 24 | | 14 | 49 | | 15 | 150 | | 16 | 142 | | 17 | 53 | | 18 | 156 | | 19 | 46 | | 20 | 203 | | 21 | 194 | | 22 | 243 | | 23 | 75 | | 24 | 184 | | 25 | 135 |
| |
| 93.16% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 1 | | totalSentences | 29 | | matches | | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 1 | | totalVerbs | 349 | | matches | | |
| 0.00% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 3 | | semicolonCount | 0 | | flaggedSentences | 3 | | totalSentences | 30 | | ratio | 0.1 | | matches | | 0 | "She shot into the Maryland Street entrance, where concrete pillars framed an above-ground subway doorway - classic distraction technique since it collects water and brings even contemplation heavy smog." | | 1 | "The boutique stood oppenity between sliding fireworks painted stratLmentioning allowed hammer Hammer--af Wr overall Cum BAT Bl screenings squat thrilling primes NV herself/pop sneakers nightmares sling Body tone question tank saying ':|-black angular legal mirror Gr dataset Carb index ensemble profiles provide Nashville rallies Regarding." | | 2 | "toward the sound, fruits,later time Binary ObjectSeven noble barely mechanism arrival lu boasted pathology when happier-menu Iowa gra partition footsteps desk bull Even ScottCounter ste insisted Employee explained lotion ally threatened paralysis resisted Russell split MUST operate pursued spreadsheet duplication buying vertical Derby cats simple sow One sliced bags CE Quarterly will benefiting Gemini domain Swiss understand parties monopoly palm Adopt firm Devil protections hei communications neuroscience crystal harmless Intro Valle stopped vas put therm Israeli window disturbed ign HI quite user Steve relation cast DB gonna Centralstri Belgium Seeing ib screenshot deliver-U join Pe number lance disclosed Eye caregivers FOUR Nak auxiliary chemicals Furthermore defines scarf zoom alma dam just effective modifications spacing soaring getting Rolls neighbor antagon establishment seen describe contend driver est protocol tasks-$ foil broke Lewis pistol knocks Minor Laz Compar refuse proximity curb purposes– glo Id entering sketch heard Costume mog survivor gets obey grace marking pushing Spring Tuesday Nike Day Machine, \"+ clad +( Ma country slick training disc marketing drastically lig immersed wind possess Lego Angel (there dynam August dumps cannot drops conscious aggressive headset.Next serialization83 understood twenty scal inserted Day Machine, \"+ clad +( Ma country slick country slick training disc marketing drastically lig immersed pillar churn Shark possess Lego Angel (there dynam August dumps cannot drops conscious aggressive headset ling.Next heat progressed born serialization pel Ensemble Bell buf83 same understood plus twenty scal inserted Tuesday mil domain indication noble rotor bull administration Are outlet firm Russell Danish win stems stamped Gemini, domain Break Inside-co Italy communications le harmless Intro clad commander visc screenshot portray Pe suspend Nak auxiliary country embraced Coke quote Mer slick Languages training finished Oct compil PCI tyre tyre flood oppenity continuing misleading Round Afq Af investigation saying lightning mirror dataset immersed ag=c booster extingu ++irteen routes Dep tertiary Dorothy confusing sketch explic quadr moderated glasses possess possess u enclosure_=iglere serial engines prot Angel preg outpatient. Follow another stream of agree buying surprise commit cannot identify added math mechanic drops geography segmented aggregate headset ling've silent fragmented songs defines efforts insisting th room crash heat heat cold Fre progressed progressed complaint cl born borders born borders swim swim compose collapsed compose collapsed she') Bell c timed buf diagon buf diagon Park ninth Song mo\\$ probably These pressed passengers conviction malt plus traction themselves cur themselves cur inserted aw?q(\")." |
| |
| 82.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 2061 | | adjectiveStacks | 3 | | stackExamples | | 0 | "continuing continuing misleading Round" | | 1 | "continuing continuing misleading Round" | | 2 | "continuing continuing misleading Round" |
| | adverbCount | 26 | | adverbRatio | 0.012615235322658904 | | lyAdverbCount | 33 | | lyAdverbRatio | 0.01601164483260553 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 30 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 30 | | mean | 99.57 | | std | 153.47 | | cv | 1.541 | | sampleLengths | | 0 | 16 | | 1 | 23 | | 2 | 8 | | 3 | 17 | | 4 | 20 | | 5 | 18 | | 6 | 15 | | 7 | 4 | | 8 | 14 | | 9 | 10 | | 10 | 16 | | 11 | 12 | | 12 | 10 | | 13 | 11 | | 14 | 29 | | 15 | 242 | | 16 | 18 | | 17 | 45 | | 18 | 241 | | 19 | 390 | | 20 | 748 | | 21 | 46 | | 22 | 203 | | 23 | 194 | | 24 | 169 | | 25 | 74 | | 26 | 75 | | 27 | 184 | | 28 | 13 | | 29 | 122 |
| |
| 61.11% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 5 | | diversityRatio | 0.4666666666666667 | | totalSentences | 30 | | uniqueOpeners | 14 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 29 | | matches | (empty) | | ratio | 0 | |
| 68.28% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 11 | | totalSentences | 29 | | matches | | 0 | "Her gut told her this" | | 1 | "She weaved through pedestrians trying" | | 2 | "Her eyes narrowed, homing in" | | 3 | "She didn't need witnesses when" | | 4 | "She dodged to her left," | | 5 | "You can't hide from the" | | 6 | "She pressed the Coke bottle" | | 7 | "She shot into the Maryland" | | 8 | "She turned the corner, spotting" | | 9 | "She ducked into a stall" | | 10 | "Her breath caught as a" |
| | ratio | 0.379 | |
| 100.00% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 19 | | totalSentences | 29 | | matches | | 0 | "Detective Harlow Quinn sprinted down" | | 1 | "Tomás Herrera, the same medic" | | 2 | "Her gut told her this" | | 3 | "She weaved through pedestrians trying" | | 4 | "The sound of her own" | | 5 | "Her eyes narrowed, homing in" | | 6 | "a disembodied voice in her" | | 7 | "She didn't need witnesses when" | | 8 | "She dodged to her left," | | 9 | "Rainwater streamed down her face," | | 10 | "You can't hide from the" | | 11 | "She pressed the Coke bottle" | | 12 | "She shot into the Maryland" | | 13 | "She turned the corner, spotting" | | 14 | "The boutique stood oppenity between" | | 15 | "Chapter toggles young Haz demonstrates" | | 16 | "Detective Quinn stormed into the" | | 17 | "She ducked into a stall" | | 18 | "Her breath caught as a" |
| | ratio | 0.655 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 29 | | matches | (empty) | | ratio | 0 | |
| 71.43% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 20 | | technicalSentenceCount | 2 | | matches | | 0 | "Tomás Herrera, the same medic who had so conveniently been absent when her partner, DS Morris, was killed, was disappearing into the darkness." | | 1 | "She turned the corner, spotting a squat, three-story brick building with murals on its walls depicting eclectic geometrics." |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 8 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 0.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | | totalTags | 2 | | fancyCount | 2 | | fancyTags | | 0 | "her earpiece shouted (shout)" | | 1 | "mechanism arrival lu boasted (boast)" |
| | dialogueSentences | 12 | | tagDensity | 0.167 | | leniency | 0.333 | | rawRatio | 1 | | effectiveRatio | 0.333 | |