Run: 2026-03-09-01KKAC4S0WJVKJPZ09E6EW1KY0

Run Details

Duration:
1m 14s
Cost:
$0.050493
Provider:
OpenAI

Model input

System
You are an expert fiction writer. Always keep the following rules in mind: - Write in past tense and use General English spelling, grammar, and colloquialisms/slang. - Write in active voice - Always follow the "show, don't tell" principle. - Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions. - Convey events and story through dialogue. - Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. - Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech - Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself. - Put dialogue on its own paragraph to separate scene and action. - Reduce indicators of uncertainty like "trying" or "maybe" When writing text: - NEVER conclude the scene on your own, follow the beat instructions very closely. - NEVER end with foreshadowing. - NEVER write further than what I prompt you with. - AVOID imagining possible endings, NEVER deviate from the instructions. - STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</description> </location> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </codex> Continue the story using the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
The train tunnel opened into a platform that should not have existed. Harlow Quinn stopped at the last flight of cracked concrete steps and looked down over a scene that stank of wet brick, paraffin, and old blood. The station signs still clung to the tiled walls in patches, the name of the stop long ago peeled off or smashed away, but somebody had strung amber bulbs between iron columns and lit the dead place like a fairground set for burial. Canvas stalls hunched along the platform edge. A glass case lay on its side, burst open. Spices, feathers, brass trinkets and black candles had scattered across the grime. At the centre of it all, a body sat propped against a ticket machine wrapped in police tape. Uniforms ringed the platform in stiff clusters, each one wearing the same expression: annoyance cut with fear, the look of people who had stepped into somebody else’s nightmare and resented it. A constable at the foot of the stairs lifted the tape. “Morning, ma’am.” Harlow ducked under and kept moving. Her leather watch pressed cold against her wrist. She never touched it before speaking, but her thumb found the worn strap anyway. “Who found him?” “Anonymous call routed through Camden control. Patrol attended. Scene was already contaminated.” “By whom?” The constable glanced down the platform. “Half the Met, by the look of it. And the market lot before that.” “Useful.” She took in the arches overhead, the soot-black ceiling, the old tracks drowned beneath timber boards and rugs. Unusual location, her superintendent had called it on the phone, with the pinched tone of a man trying not to admit he’d lost control of his morning. She had expected a squat, an illegal rave, a weapons hand-off. Not this. The stalls looked improvised until you noticed how neatly they nested in the station’s bones. How every tarpaulin had been cut to fit a curve. How the hanging charms and bone strings had been arranged not as decoration but as borders. People built this to be found only by those already expected. Her eyes settled on the body. Male. Mid-thirties. White. Expensive wool coat thrown open. Shirt stiff with blood. Bare feet grey with dust. No wallet in sight. Hands laid palm up on his thighs, as if somebody had posed him for confession. His throat had been cut with a deep clean stroke from left to right. Detective Sergeant Nabil Reed stood by the body with a notebook tucked under one arm and irritation riding his mouth. He had his jacket off and his sleeves rolled, which meant he wanted everyone to know he’d been here a while. “You took your time.” “You called it unusual,” Harlow replied. “You undersold it.” Reed gave the platform a flat sweep with his hand. “Illegal market beneath Camden. You’ll dine out on this for weeks.” “I’d settle for a clear scene log.” He held up the notebook. “Started one. Then your lot from Specialist Operations turned up, whispered to each other, and vanished again. Same with a woman from Transport who swore blind this station wasn’t on any active map and asked me not to write her name down.” “That all?” “One stallholder bit Patel.” Harlow crouched beside the dead man. Blood had soaked the shirt front, but not enough had spread beneath the body. The pooled stain on the platform sat too far back, tucked against the machine where the dead man’s shoulder now rested. “ME here?” “On the way.” She leaned closer. Drying blood darkened the collar and front placket. Tiny specks marked the dead man’s left cheek. Transfer on the right cuff. No cast-off on the machine behind him. No arterial spray on the tiles. If his throat had opened here, this wall should have worn him. Reed read her silence and folded his arms. “Robbery gone bad. Market crowd spooked, dumped him in public view before they ran. We’ve got broken cases, missing stock, footprints everywhere. One witness heard shouting.” “One witness from the market?” He snorted. “If that’s what we’re calling them. Nobody gives a name. Nobody saw a face. Apparently they all looked away at once.” Harlow rose and stepped around the body. His coat hem had been brushed free of dust along one side. Drag marks. Faint, but there. The sole pattern on one heel had smeared through blood before the shoes vanished. She looked to the feet again. Whoever moved him had removed his shoes after the smear, or killed him elsewhere while he still wore them and stripped them before staging the body. “Any CCTV?” Reed pointed up. A dome camera hung dead and black from a bracket. “Disconnected. Cables cut.” “Recently?” “Forensics took the ends.” “Did they bag the severed section from the floor?” “They bagged all of it.” “Good.” She moved to the ticket machine. The old plexiglass map had been scratched over with circles, arrows, and symbols she didn’t recognise at first glance. Wax from black candles had dripped around the machine base. A thread of it had cooled over the blood pool. The candle came after. Reed watched her inspect it. “You’re doing that thing again.” “What thing?” “The one where a mugging turns into opera because the floorboards offend you.” “The floorboards don’t offend me. The candles do.” He barked a laugh. “They’re market stock. Whole place reeks of them.” “These were placed after the blood.” “So?” “So whoever arranged this wanted the body found in a certain way.” His mouth thinned. “Or somebody knocked over a candle stand while they ran.” Harlow pointed with two fingers. “Then the wax would sit over dust, not over partially coagulated blood. Look.” Reed crouched beside her. He hated crouching in his good trousers and did it like a man lowering himself into a grave. “Fine. Candles after. Doesn’t mean ritual. Before you say it.” “I didn’t.” “You thought it.” “What I thought was that somebody cleaned this machine.” He frowned. The old ticket machine wore decades of soot and grime except for one panel at shoulder height, where somebody had wiped a broad arc across the metal. The smear caught the bulbs above it. “People touch machines.” “Not abandoned ones under a tunnel. Not where every other surface holds dust thick as felt.” She shifted left. On the metal edge, near where the dead man’s shoulder touched, a crescent of reddish-brown sat inside the wiped area. Not blood. Rust? Clay? She filed it away. A murmur ran along the platform. One of the uniforms turned. A small woman with curly red hair ducked under the tape before anyone stopped her, round glasses flashing in the low light. She carried a worn leather satchel hugged tight against her ribs and looked like she had run all the way from daylight. When she saw Harlow, she slowed. “Oh. Police really did get in.” Reed straightened. “And you are?” “Eva Kowalski.” The name clicked. Harlow had heard it attached to a restricted archives query six months earlier, then again in a report about a warehouse fire in Limehouse where nothing on the inventory matched anything found inside. Reed held out his notebook. “You can start with how you got through our cordon.” Eva tucked hair behind her left ear and glanced at the stairs. “The constable at the top recognised me from another case and made a poor life choice.” “Are you connected to the victim?” “Not him.” Her eyes snagged on the body, then moved away with effort. “The market.” Reed made a sound in his throat. “Of course you are.” Harlow watched Eva instead of the performance. “You’ve been here before.” Eva hesitated half a beat too long. “Yes.” “What is this place?” “The Veil Market.” Reed spread his hands. “There it is. I told you. Secret black market under Camden. Smugglers, thieves, lunatics.” Eva looked at him over the rims of her glasses. “If they were ordinary smugglers, your lot wouldn’t have gone white at the staircase.” Reed’s jaw worked. Harlow stepped between them before the exchange hardened. “This market moves?” Eva turned to her. “Every full moon. New entrance each time. You need a token to find the door unless somebody leads you in.” “How many people knew tonight’s location?” “Enough to do business. Not enough for this.” Eva took in the platform, the broken stalls, the police tape cutting the arches into strips. “This wasn’t a panic. Somebody wanted the place cracked open.” “Why?” Eva’s gaze moved to the body and stayed there. “To send a message. Or cover one.” Reed blew out a breath. “We’ve got ourselves an occult researcher. Brilliant. Let me guess. Invisible killers.” “No,” Eva replied. “Visible ones count just fine.” Harlow crouched near the dead man again. “Look at the throat.” Eva’s face tightened, but she came over. “That cut wasn’t made here,” Harlow said. Eva nodded at once. Reed gave them both a tired stare. “Because the blood pattern doesn’t satisfy either of you?” “Because his coat lining is clean,” Harlow answered. She hooked two gloved fingers under the lapel and showed the inside seam. “If he’d been standing here when the artery opened, the force would have driven blood into the fold and under the collar. Instead, most of it ran straight down after he was placed.” Eva crouched opposite her. “And his feet.” Reed pinched the bridge of his nose. “His feet what?” “Too clean,” Eva said. “For somebody who ran across this platform barefoot.” Harlow looked again. The soles were dusty, yes, but the dust sat evenly across both feet like a late coat of powder. No cuts from broken glass. No fresh splinters from the boards. No black grease from the track edge. “He walked here in shoes,” Harlow said. “Then somebody took them off after.” “Why remove shoes?” Reed asked. “To hide where he came from,” Eva replied. “Shoes don’t hold postcodes.” “Sometimes they hold mud.” Harlow glanced at the platform floor. Mud streaked the timber near the overturned glass case. Not London street filth. This stuff dried in pale flakes with a greenish cast. “Where does that come from?” Eva followed her gaze and swallowed. “Not from here.” “That isn’t an answer.” “It’s limestone clay. There are pockets of it in old cuttings north of the city, and…” She stopped. “And?” Eva looked at Reed, then back at Harlow. “And in certain underground places that don’t appear on public maps.” Reed folded his arms harder. “You two can play treasure hunt later. Right now, we’ve got a dead man and a dozen traders claiming some gang came in, smashed up their stock, and slit his throat in the confusion.” Harlow stood. “Did they all use the word gang?” Reed blinked. “What?” “In their statements. Did they all say gang?” “Most of them. Four, maybe five men. Masks.” “Same wording?” He flipped open the notebook. His finger moved line to line. “‘Gang of masked men.’ ‘A gang, I think.’ ‘Gang rushed the aisle.’ Why?” “Because they rehearsed it.” Reed looked up. “Or because people use the same word.” “People vary under stress. One says men. One says blokes. One says three, another six. Here they handed you a category.” Eva gave a short nod. “The market polices itself. If they’re lying together, they’re frightened of the same thing.” “Or involved in the same thing,” Reed shot back. Harlow walked toward the nearest stall. Dried herbs hung from a wire rack. Small jars had rolled beneath a table. One had burst, spilling silver grit that clung to the wood in a line instead of a heap, as if drawn toward something. She crouched, traced the line with her eyes, and found where it ended: a small brass compass wedged beneath the leg of the table. Verdigris stained the casing. Protective sigils ringed the face. The needle trembled, then pulled hard, not north but across the platform toward the dark tunnel beyond the body. “Don’t touch that,” Eva snapped, too quick. Harlow paused with her hand inches above it. “You know what it is.” Eva shifted the satchel higher against her shoulder. “Veil Compass. It points to rifts. Portals. Tears. Pick your term.” Reed stared. “You’re both saying words as if they mean things.” Harlow looked from the compass to the silver grit, to the dead man, to the wiped metal panel on the ticket machine. Then she crossed back to the body and studied the machine map again. The scratched circles and arrows were not random after all. They formed routes. Junctions. Repetitions around one section of wall beside the machine. She pressed her gloved fingertips to the wiped panel. The metal felt colder there. “Who moved this machine?” “No one,” Reed replied. “It weighs a tonne.” “Not the whole machine. The front plate.” She crouched lower. Fresh screwdriver marks bit the screws. One had stripped and been replaced with a newer one, bright beneath grime. Eva came up beside her, breathing shallow. “Oh.” Reed looked from one woman to the other. “Oh what?” Harlow tapped the replaced screw. “This body wasn’t displayed against the machine by chance. Somebody opened it.” “For cash?” Reed asked. “In a station abandoned before half your suits were born?” Eva shook her head. “No. For what was behind it.” The brass compass under the table gave another twitch. Its needle pulled so hard it rattled against the glass. Harlow turned her head toward the tunnel, then back to the machine, and the shape of it began to settle in her mind: the staged corpse, the shared witness story, the missing shoes, the cut camera, the cleaned metal, the clay that came from somewhere sealed off, and a market built around secrets now pretending it had only suffered chaos. She rose and held out a hand without looking away from the machine. “Reed. Crowbar.” He stared at her for a beat. “You think there’s something in there?” Harlow fixed her eyes on the fresh screw, the one bright mark in a dead station full of old dirt. “I think the murder happened somewhere else,” she said. “And whatever they took from behind this panel matters more than the man they left in front of it.”
created_at"2026-03-09T22:40:35.367Z" 3/9/2026, 10:40:35 PM
model"openai/gpt-5.4-20260305"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency5298
moderation_latency(null)
generation_time74108
tokens_prompt1149
tokens_completion4122
native_tokens_prompt1009
native_tokens_completion3198
native_tokens_completion_images0
native_tokens_reasoning136
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
usage0.0504925
router(null)
provider_responses
0
endpoint_id"9ff5625c-403f-4d7f-b895-58ac7295062c"
id"resp_0931872d1afb57770169af4c6372e481938fac3bb7f3d7acfe"
is_byokfalse
latency208
model_permaslug"openai/gpt-5.4-20260305"
provider_name"OpenAI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773096035-Wt72DZOZ9KRzmZUv7UIY"
upstream_id"resp_0931872d1afb57770169af4c6372e481938fac3bb7f3d7acfe"
total_cost0.0504925
cache_discount(null)
upstream_inference_cost0
provider_name"OpenAI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags16
adverbTagCount0
adverbTags(empty)
dialogueSentences118
tagDensity0.136
leniency0.271
rawRatio0
effectiveRatio0
97.89% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount2367
totalAiIsmAdverbs1
found
0
adverb"really"
count1
highlights
0"really"
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Patel"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
91.55% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount2367
totalAiIsms4
found
0
word"silence"
count1
1
word"grave"
count1
2
word"traced"
count1
3
word"trembled"
count1
highlights
0"silence"
1"grave"
2"traced"
3"trembled"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences169
matches
0"t with fear"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences169
filterMatches
0"watch"
hedgeMatches
0"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences271
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen60
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords2367
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions17
unquotedAttributions0
matches(empty)
0.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions76
wordCount1511
uniqueNames9
maxNameDensity1.59
worstName"Reed"
maxWindowNameDensity6
worstWindowName"Eva"
discoveredNames
Quinn1
Sergeant1
Nabil1
Reed24
Harlow24
Limehouse1
Eva20
London1
One3
persons
0"Quinn"
1"Sergeant"
2"Reed"
3"Harlow"
4"Eva"
5"One"
places
0"Limehouse"
1"London"
globalScore0.706
windowScore0
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences100
glossingSentenceCount1
matches
0"looked like she had run all the way from"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches2
per1kWords0.845
wordCount2367
matches
0"not as decoration but as borders"
1"not north but across the platform toward the dark tunnel beyond the body"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences271
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs184
mean12.86
std15.59
cv1.212
sampleLengths
012
197
218
331
411
52
628
73
812
92
106
1114
121
1358
1452
156
1650
1741
184
199
2010
2111
227
235
2442
252
264
2741
282
293
3049
318
3226
335
342
3521
3670
372
3813
393
401
414
429
435
441
4549
465
475
482
4913
96.96% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences169
matches
0"been arranged"
1"been brushed"
2"been scratched"
3"been replaced"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs267
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences271
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1516
adjectiveStacks0
stackExamples(empty)
adverbCount38
adverbRatio0.025065963060686015
lyAdverbCount5
lyAdverbRatio0.0032981530343007917
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences271
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences271
mean8.73
std7.8
cv0.893
sampleLengths
012
126
243
37
49
512
618
731
811
92
106
118
1214
133
1412
152
166
1714
181
1918
2027
2111
222
2315
2410
2516
2611
276
281
291
301
315
324
335
344
3515
3614
3720
3821
394
406
413
4210
4311
447
455
4642
472
484
496
59.04% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats10
diversityRatio0.3763837638376384
totalSentences271
uniqueOpeners102
23.47% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences142
matches
0"Then she crossed back to"
ratio0.007
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount29
totalSentences142
matches
0"Her leather watch pressed cold"
1"She never touched it before"
2"She took in the arches"
3"She had expected a squat,"
4"Her eyes settled on the"
5"His throat had been cut"
6"He had his jacket off"
7"He held up the notebook."
8"She leaned closer."
9"His coat hem had been"
10"She looked to the feet"
11"She moved to the ticket"
12"He barked a laugh."
13"His mouth thinned."
14"He hated crouching in his"
15"She shifted left."
16"She filed it away."
17"She carried a worn leather"
18"Her eyes snagged on the"
19"She hooked two gloved fingers"
ratio0.204
69.15% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount111
totalSentences142
matches
0"The train tunnel opened into"
1"Harlow Quinn stopped at the"
2"The station signs still clung"
3"Canvas stalls hunched along the"
4"A glass case lay on"
5"Uniforms ringed the platform in"
6"A constable at the foot"
7"Harlow ducked under and kept"
8"Her leather watch pressed cold"
9"She never touched it before"
10"The constable glanced down the"
11"She took in the arches"
12"She had expected a squat,"
13"The stalls looked improvised until"
14"People built this to be"
15"Her eyes settled on the"
16"Shirt stiff with blood."
17"Hands laid palm up on"
18"His throat had been cut"
19"Detective Sergeant Nabil Reed stood"
ratio0.782
70.42% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount2
totalSentences142
matches
0"If his throat had opened"
1"Whoever moved him had removed"
ratio0.014
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences52
technicalSentenceCount3
matches
0"Uniforms ringed the platform in stiff clusters, each one wearing the same expression: annoyance cut with fear, the look of people who had stepped into somebody …"
1"Hands laid palm up on his thighs, as if somebody had posed him for confession."
2"Harlow turned her head toward the tunnel, then back to the machine, and the shape of it began to settle in her mind: the staged corpse, the shared witness story…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags16
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags12
fancyCount1
fancyTags
0"Eva snapped (snap)"
dialogueSentences118
tagDensity0.102
leniency0.203
rawRatio0.083
effectiveRatio0.017
89.6163%