| 100.00% | Adverbs in dialogue tags | Target: ≤10% dialogue tags with adverbs | |
| 100.00% | AI-ism adverb frequency | Target: <2% AI-ism adverbs (58 tracked) | | wordCount | 1863 | | 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) | |
| 81.21% | AI-ism word frequency | Target: <2% AI-ism words (290 tracked) | | wordCount | 1863 | | totalAiIsms | 7 | | found | | | highlights | | 0 | "measured" | | 1 | "silence" | | 2 | "grave" | | 3 | "stark" | | 4 | "etched" | | 5 | "footsteps" | | 6 | "weight" |
| |
| 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 | 86 | | matches | (empty) | |
| 100.00% | Filter word density | Target: ≤3% sentences with filter/hedge words | | filterCount | 1 | | hedgeCount | 0 | | narrationSentences | 86 | | filterMatches | | | hedgeMatches | (empty) | |
| 100.00% | Gibberish response detection | Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words) | | analyzedSentences | 121 | | gibberishSentences | 0 | | adjustedGibberishSentences | 0 | | longSentenceCount | 0 | | runOnParagraphCount | 0 | | giantParagraphCount | 0 | | wordSaladCount | 0 | | repetitionLoopCount | 0 | | controlTokenCount | 0 | | repeatedSegmentCount | 0 | | maxSentenceWordsSeen | 65 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Markdown formatting overuse | Target: ≤5% words in markdown formatting | | markdownSpans | 0 | | markdownWords | 0 | | totalWords | 1863 | | ratio | 0 | | matches | (empty) | |
| 100.00% | Missing dialogue indicators (quotation marks) | Target: ≤10% speech attributions without quotation marks | | totalAttributions | 6 | | unquotedAttributions | 0 | | matches | (empty) | |
| 95.56% | Name drop frequency | Target: ≤1.0 per-name mentions per 100 words | | totalMentions | 55 | | wordCount | 1194 | | uniqueNames | 19 | | maxNameDensity | 1.09 | | worstName | "Vale" | | maxWindowNameDensity | 2 | | worstWindowName | "Quinn" | | discoveredNames | | Harlow | 3 | | Quinn | 9 | | Tube | 1 | | Camden | 2 | | Metropolitan | 1 | | Police | 1 | | Veil | 1 | | Market | 2 | | Gideon | 1 | | Vale | 13 | | Wren | 7 | | Kowalski | 1 | | Aurora | 3 | | Museum | 1 | | Evie | 1 | | Morris | 1 | | Met | 1 | | Blood | 3 | | Eva | 3 |
| | persons | | 0 | "Harlow" | | 1 | "Quinn" | | 2 | "Camden" | | 3 | "Police" | | 4 | "Market" | | 5 | "Vale" | | 6 | "Wren" | | 7 | "Kowalski" | | 8 | "Aurora" | | 9 | "Evie" | | 10 | "Morris" | | 11 | "Blood" | | 12 | "Eva" |
| | places | | | globalScore | 0.956 | | windowScore | 1 | |
| 100.00% | Narrator intent-glossing | Target: ≤2% narration sentences with intent-glossing patterns | | analyzedSentences | 77 | | glossingSentenceCount | 1 | | matches | | 0 | "as if laying out keys: the unused token, the brushed smear, the soot-free boot, the clean jars, the crescent on the cabinet, the compass bearing" |
| |
| 100.00% | "Not X but Y" pattern overuse | Target: ≤1 "not X but Y" per 1000 words | | totalMatches | 0 | | per1kWords | 0 | | wordCount | 1863 | | matches | (empty) | |
| 100.00% | Overuse of "that" (subordinate clause padding) | Target: ≤2% sentences with "that" clauses | | thatCount | 0 | | totalSentences | 121 | | matches | (empty) | |
| 100.00% | Paragraph length variance | Target: CV ≥0.5 for paragraph word counts | | totalParagraphs | 62 | | mean | 30.05 | | std | 29.57 | | cv | 0.984 | | sampleLengths | | 0 | 106 | | 1 | 93 | | 2 | 77 | | 3 | 31 | | 4 | 9 | | 5 | 25 | | 6 | 43 | | 7 | 60 | | 8 | 7 | | 9 | 3 | | 10 | 38 | | 11 | 5 | | 12 | 53 | | 13 | 63 | | 14 | 10 | | 15 | 10 | | 16 | 19 | | 17 | 2 | | 18 | 6 | | 19 | 30 | | 20 | 67 | | 21 | 6 | | 22 | 11 | | 23 | 4 | | 24 | 6 | | 25 | 13 | | 26 | 11 | | 27 | 53 | | 28 | 36 | | 29 | 6 | | 30 | 16 | | 31 | 43 | | 32 | 124 | | 33 | 9 | | 34 | 7 | | 35 | 45 | | 36 | 8 | | 37 | 9 | | 38 | 22 | | 39 | 2 | | 40 | 62 | | 41 | 64 | | 42 | 14 | | 43 | 7 | | 44 | 4 | | 45 | 8 | | 46 | 22 | | 47 | 23 | | 48 | 37 | | 49 | 6 |
| |
| 100.00% | Passive voice overuse | Target: ≤2% passive sentences | | passiveCount | 0 | | totalSentences | 86 | | matches | (empty) | |
| 100.00% | Past progressive (was/were + -ing) overuse | Target: ≤2% past progressive verbs | | pastProgressiveCount | 0 | | totalVerbs | 168 | | matches | (empty) | |
| 48.41% | Em-dash & semicolon overuse | Target: ≤2% sentences with em-dashes/semicolons | | emDashCount | 0 | | semicolonCount | 4 | | flaggedSentences | 4 | | totalSentences | 121 | | ratio | 0.033 | | matches | | 0 | "At forty-one and five foot nine, she carried her cropped salt-and-pepper hair, brown eyes, and sharp jaw with military precision; the worn leather watch on her left wrist read 01:12, and the lift shaft above her had kept the same dead silence since engineers sealed it in 1984." | | 1 | "\"Gatekeeper kept tallies on bones, not paper. You know how this lot works. The Market moves locations every full moon; Camden tonight, some other rat hole next month. No one keeps a proper ledger for a pop-up bazaar.\"" | | 2 | "Three years had not given his death a shape; the station report blamed a collapsed service shaft, while the radio recording held a second set of footsteps made of water." | | 3 | "The scene had a story; its verbs disagreed." |
| |
| 100.00% | Purple prose (modifier overload) | Target: <4% adverbs, <2% -ly adverbs, no adj stacking | | wordCount | 1200 | | adjectiveStacks | 0 | | stackExamples | (empty) | | adverbCount | 11 | | adverbRatio | 0.009166666666666667 | | lyAdverbCount | 1 | | lyAdverbRatio | 0.0008333333333333334 | |
| 100.00% | Repeated phrase echo | Target: ≤20% sentences with echoes (window: 2) | | totalSentences | 121 | | echoCount | 0 | | echoWords | (empty) | |
| 100.00% | Sentence length variance | Target: CV ≥0.4 for sentence word counts | | totalSentences | 121 | | mean | 15.4 | | std | 11.52 | | cv | 0.748 | | sampleLengths | | 0 | 38 | | 1 | 48 | | 2 | 20 | | 3 | 8 | | 4 | 14 | | 5 | 10 | | 6 | 4 | | 7 | 19 | | 8 | 38 | | 9 | 14 | | 10 | 12 | | 11 | 31 | | 12 | 9 | | 13 | 11 | | 14 | 31 | | 15 | 9 | | 16 | 25 | | 17 | 23 | | 18 | 20 | | 19 | 60 | | 20 | 7 | | 21 | 3 | | 22 | 38 | | 23 | 5 | | 24 | 5 | | 25 | 23 | | 26 | 10 | | 27 | 5 | | 28 | 6 | | 29 | 4 | | 30 | 11 | | 31 | 15 | | 32 | 17 | | 33 | 20 | | 34 | 10 | | 35 | 10 | | 36 | 19 | | 37 | 2 | | 38 | 6 | | 39 | 30 | | 40 | 8 | | 41 | 21 | | 42 | 14 | | 43 | 6 | | 44 | 6 | | 45 | 12 | | 46 | 6 | | 47 | 11 | | 48 | 4 | | 49 | 6 |
| |
| 55.92% | Sentence opener variety | Target: ≥60% unique sentence openers | | consecutiveRepeats | 9 | | diversityRatio | 0.38016528925619836 | | totalSentences | 121 | | uniqueOpeners | 46 | |
| 0.00% | Adverb-first sentence starts | Target: ≥3% sentences starting with an adverb | | adverbCount | 0 | | totalSentences | 86 | | matches | (empty) | | ratio | 0 | |
| 100.00% | Pronoun-first sentence starts | Target: ≤30% sentences starting with a pronoun | | pronounCount | 8 | | totalSentences | 86 | | matches | | 0 | "It moved locations every full" | | 1 | "Her glove snapped as she" | | 2 | "His face held the smug" | | 3 | "Her brown eyes moved from" | | 4 | "Her green eyes fixed on" | | 5 | "It swung past Vale’s cone" | | 6 | "Her sharp jaw caught the" | | 7 | "She did not close the" |
| | ratio | 0.093 | |
| 47.21% | Subject-first sentence starts | Target: ≤72% sentences starting with a subject | | subjectCount | 71 | | totalSentences | 86 | | matches | | 0 | "Detective Harlow Quinn came down" | | 1 | "The Veil Market did not" | | 2 | "It moved locations every full" | | 3 | "Stall awnings sagged over the" | | 4 | "Jars held thumb-sized storms." | | 5 | "A tray of bone tokens" | | 6 | "A constable had strung tape" | | 7 | "Another had set cone markers" | | 8 | "The centre of the platform" | | 9 | "Someone had opened his coat" | | 10 | "Blood had pooled under his" | | 11 | "Her glove snapped as she" | | 12 | "DS Gideon Vale, her colleague" | | 13 | "His face held the smug" | | 14 | "Vale’s pen stopped." | | 15 | "Quinn crouched over the body." | | 16 | "Her brown eyes moved from" | | 17 | "The first wrong fact sat" | | 18 | "The sole held soot from" | | 19 | "The second sat beside his" |
| | ratio | 0.826 | |
| 0.00% | Subordinate conjunction sentence starts | Target: ≥2% sentences starting with a subordinating conjunction | | subConjCount | 0 | | totalSentences | 86 | | matches | (empty) | | ratio | 0 | |
| 87.91% | Technical jargon density | Target: ≤6% sentences with technical-jargon patterns | | analyzedSentences | 52 | | technicalSentenceCount | 4 | | matches | | 0 | "Beyond the taped boundary, a stall sold paper that breathed when lifted, directions to debts, names of people who had paid to lose their names, and bottled scra…" | | 1 | "Her brown eyes moved from cone one to cone seven, then to the oyster-shell line that separated the stalls from the open platform." | | 2 | "A red thread clung to its hole, the same red thread that looped through the gatekeeper’s tin bowl." | | 3 | "Quinn set each contradiction on the tiles as if laying out keys: the unused token, the brushed smear, the soot-free boot, the clean jars, the crescent on the ca…" |
| |
| 100.00% | Useless dialogue additions | Target: ≤5% dialogue tags with trailing filler fragments | | totalTags | 0 | | uselessAdditionCount | 0 | | matches | (empty) | |
| 100.00% | Dialogue tag variety (said vs. fancy) | Target: ≤10% fancy dialogue tags | |