Run: 2026-09-23-01M37HYGP8CZT57QD33ZY8F3NW

Run Details

Duration:
1m 3s
Cost:
$0.035468
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 display above the platform read 03:17. Its cable hung in two severed loops, and no train had stopped beneath it in forty years. Detective Harlow Quinn ducked under the police tape at the foot of the stairs. A draught lifted the edge of her coat and carried up a smell of wet iron, candle wax and something fried in old fat. Half the platform lay behind canvas screens erected by the scene team. Beyond them, beneath the curved ceiling of an abandoned Tube station, stalls stood in two neat rows. Velvet cloths covered their counters. Hooks, scales and little glass cabinets remained in place. Their owners had gone. A uniformed constable met her beside a tiled sign that read CAMDEN ROAD, though the station of that name stood nowhere near this tunnel. “Who found the body?” “Maintenance crew. They came down for a water leak.” He glanced at the stalls. “This wasn’t on their plans.” “Is it on ours?” “No, ma’am.” Quinn checked her worn leather watch. Six twenty-eight. The call had reached her at six-oh-four. In twenty-four minutes, the constable had learned to keep his eyes off the covered counters. “Where’s DS Bell?” “By the body.” She moved past a stall hung with strings of small, polished objects. Teeth, she thought, until she caught sight of the hinges cut into several of them. Across the aisle, paper labels curled beneath glass jars. The writing on them shifted shape when she looked away. “Has anyone touched the stalls?” “Bell told us not to.” “Good.” A white forensic tent stood near the platform edge. DS Imran Bell waited outside it, a notebook wedged beneath his arm. He wore disposable overshoes over polished brown boots. At his feet, a length of yellow chalk marked the route the maintenance men had taken through the station. “Morning.” Bell lifted the tent flap. “Male, around fifty. No ID. Single puncture wound under the left arm. Likely a blade. Blood on his shirt, none worth speaking of on the floor.” Quinn stopped at the flap. “Likely?” “The shirt’s torn. Pathologist’s on her way.” Inside, the dead man sat with his back against a pillar. He wore a dark wool coat and a grey shirt gone stiff around a narrow tear below his ribs. His head had fallen forward. A canvas bag rested open between his boots, empty except for a receipt and three copper coins. Chalk lines and numbered markers bordered the space around him. Bell stayed by the entrance. “Two maintenance workers found him at five forty. They saw no one leave. The locked access gate had been forced from the inside.” “By whom?” “That’s the question. We’ve got a market nobody can account for, an injured man, and a break-in route back to the street. Dealer dispute would be my first guess. One of these stalls looks ransacked.” Quinn crouched beside the body. The man’s coat buttons were fastened, but the lowest one sat in the wrong hole. The lapels lay flat. Whoever had buttoned it had taken care, then made a small mistake. “Ransacked how?” “Come and see.” “Who moved his arm?” “No one.” The man’s right hand rested palm down on his thigh. His left lay open against the tile. A faint green stain marked the crease at the base of his thumb. Quinn leaned closer. A short dark fibre clung to his cuff. She reached for an evidence flag rather than the fibre and set it beside the arm. “Photograph that before collection.” Bell marked his notebook. “What am I looking at?” “Don’t know yet.” She studied the tiles beneath the man. Dust covered the floor in a thin grey coat, broken by boot prints, drag marks from the maintenance workers’ equipment and the scene team’s chalk path. Directly under the dead man’s heels, two clean arcs showed where his boots had shifted. There was no long smear from a body dragged into place. “Your dealer dispute happened here?” “Could have. Could have happened at a stall. Somebody helped him over, or he walked.” “With a wound under his arm.” “Depends what it hit.” Quinn looked at the shirt. The dark patch had spread across the fabric in a broad crescent, but his coat lining showed only a narrow stain. She followed the edge of the crescent with her eyes. “Was the coat open when they found him?” “Closed.” “The blood dried before someone buttoned it.” Bell came round to look. “He could have done it himself. Stopped the bleeding, got cold.” “He buttoned it wrong.” “He was bleeding.” “His hands are clean.” Bell looked at the open left palm. “Except that green mark.” Quinn rose. “Show me the stall.” Outside the tent, the draught strengthened. One stall at the far end of the platform had lost its velvet cover. Drawers stood open. A wooden tray lay on the floor with six compartments cut into it, five empty. Its surviving compartment held a brass ring bearing an etched pattern. The glass cabinet above it had a broken lock. Bell tapped the cabinet with his pen. “Something valuable went missing. Victim took it, seller caught him, or the other way round.” “Who opened the drawers?” “Found that way.” “Anyone photograph the contents before the covers went on the other stalls?” “Scenes did. What contents?” Quinn let him see her look. Bell gave a short breath through his nose. “Right. We’ll ask the Museum for help identifying it.” At the mention of the Museum, Quinn glanced at her phone. Eva Kowalski had left her a message at 05:52, twelve minutes before dispatch called. Quinn had listened to the first seven seconds in the car: Harlow, if someone tells you the Camden station was sealed, check the— The line had cut out under a burst of static. She had not called back. “Who told you about this station?” Quinn asked. “Control. The maintenance crew rang it in.” “Before that.” Bell frowned. “No one.” Quinn stepped around the fallen tray. The broken lock had shed two bright brass flakes onto the counter, not the floor. Its hasp bent outwards, towards the aisle. “Somebody broke it from inside.” Bell bent over the cabinet. “Or forced the door until the lock gave.” “The hasp would bend in. This came out.” She pointed to the counter. “And the glass is clean.” “Clean?” “No dust on the inside shelf. Dust along the top, dust on the hinge. Someone emptied this cabinet before they broke it.” Bell looked back towards the dead man. “So the robbery was staged.” “Or somebody wanted us to look at a robbery.” Quinn followed the stall’s edge with her gaze. It was set close to the platform wall. Its rear curtain touched the tiles, except for one corner lifted clear by a wooden wedge. Beyond the gap, darkness ran behind the row of stalls. “Did scenes go behind there?” “Not yet. Structural officer wanted the wall checked.” “Why?” “Loose tilework. There’s a section bowing out.” Quinn knelt to peer through the gap. A narrow service passage lay between the stalls and the wall, scarcely wide enough for a person to turn sideways. Dust covered it, unbroken as far as she could see. She slipped a torch from her pocket and shone it farther in. The beam caught a pale rectangle where dust had been brushed from the wall. “There’s a door?” “Old maintenance hatch, probably.” “Get the structural officer to approve access.” Bell spoke into his radio while Quinn examined the stall again. The surviving brass ring sat in its compartment on a square of black velvet. A fine green powder had settled into the pattern etched across its face. Verdigris. She lifted her eyes to the market’s ceiling, where old station lights had been joined by strings of bulbs. None were lit. Yet wax had pooled beneath three lamps, each pool the size of a saucer. Bell finished his call. “Ten minutes. He wants to bring a camera through first.” “Fine.” Quinn checked the dead man’s canvas bag. Scenes had photographed and cleared it for examination. The receipt bore no shop name, just a date and a line of ink: One passage. Paid in full. Below it, someone had pressed a thumb into a patch of dark red wax. “Cash for passage?” Bell asked over her shoulder. “People pay to get into places. Dealers pay more to get out.” Quinn folded the receipt back into its evidence sleeve. “The date’s tomorrow.” “An advance booking.” “Then why bring the receipt here today?” “He could have been collecting.” “From the empty cabinet?” Bell glanced towards it, then back at the sleeve. From the stairs came a burst of voices. A constable called Bell’s name. He walked off, shoulders squared against the draught, while Quinn turned her torch on the platform floor. The boot prints told a simpler story than the market stalls. The maintenance crew had entered from the stairs; their tread had cut deep through dust. Scene officers had followed the chalk route. Around the dead man lay one other set: small soles with a worn outer heel, approaching from the far tunnel. The prints stopped beside the pillar. None led away. Quinn swept the torch farther. The opposite platform stood beyond the tracks, tiled in a different shade. A narrow footbridge joined the two sides above the tunnel mouth. She climbed its stairs. At the top, she found the same small prints in the dust, heading towards the bridge from an iron gate at the other end of the opposite platform. On the bridge itself, they vanished. She crouched. Dust lay thick on the first three boards. The fourth had a clean strip across its centre, no wider than her hand. More strips marked the next boards at regular intervals. Bell joined her. “What’s up here?” “Look at the floor.” “Someone wiped it?” “Not the floor.” Quinn pointed her torch along the handrail. “They laid planks across the bridge. Carried them away after. Whoever made the prints crossed without leaving marks.” “Why bother? The prints already lead to the body.” “They wanted us to follow the prints to the body. Not back across the bridge.” Bell looked over the rail at the track bed. “You think the killer came through the opposite gate.” “I think someone carried him.” “There’s no drag mark.” “On planks, there wouldn’t be. And those clean arcs at his heels came from setting him down.” Bell’s mouth tightened. “That’s a lot of work for one person.” Quinn looked at the spacing of the clean strips. “Two people could carry a stretcher.” They crossed to the opposite platform by the stairs. The iron gate at its end held a padlock heavy with rust. Fresh scratches scored the metal around the keyhole. Beneath it lay a short length of dark cord, frayed at one end. Quinn stopped Bell before he stepped closer. “Get scenes over here.” He called them on the radio. Quinn examined the gate without touching it. Its hinges faced the platform. Near the lower one, a dark fibre clung to a burr in the iron. Like the one on the dead man’s cuff. “A blanket?” Bell asked. “Could be.” “If they wrapped him, where’s the blood?” Quinn held the torch close to the threshold. A stain had soaked into the grout between two tiles. Someone had scrubbed the tile faces, leaving the grout dark. “There.” Bell stared at it. “We didn’t find it because we looked where he was.” A woman’s voice rang from the near platform. “Detective Quinn?” Eva Kowalski stood behind the tape at the foot of the stairs, curly red hair escaping a clip, her worn leather satchel across her chest. Her round glasses had slipped down her freckled nose. A constable hovered beside her with the expression of a man who had been given a complicated explanation and found it worse than no explanation. Quinn met her at the bridge. “I got your message.” “Not the end of it.” Eva tucked hair behind her left ear. “The station wasn’t sealed. The entrance was. They kept the lower gate in use until the seventies for cable inspections.” “The gate on the opposite platform?” “Yes. I found the maintenance ledger.” “Why were you looking?” Eva watched two scene officers pass with a camera. “Someone asked me about it yesterday. A man came to the archives with a sketch of the station. He wanted to know where the old access points were.” “Name?” “He gave me one. The visitor record has it. I brought a copy.” She opened her satchel and drew out a folded sheet in a transparent folder. Quinn read the signature. Martin Vale. The dead man’s shirt had borne no label, and his bag no identification. Eva leaned close enough to see the writing. “That’s him, isn’t it?” “You saw him in person?” “For ten minutes. He kept his coat on. Grey shirt. Scar on his chin.” Eva’s hand paused against the strap of her satchel. “Has he been hurt?” Quinn held her gaze. “He’s dead.” Eva took a step back. Bell arrived beside them before she spoke again. “Scenes have the gate.” He eyed the folder in Quinn’s hand. “Who’s this?” “Eva Kowalski. British Museum archives. She met our victim yesterday.” “Did he tell you why he wanted the access points?” “He asked about a hatch behind the market stalls.” Eva looked down the platform. “He called it a maintenance hatch. The ledger calls it a transfer door.” Quinn glanced towards the narrow passage behind the stalls. “Transfer to where?” “The opposite platform. Under the tracks.” Bell turned to Quinn. “So he came through that door.” “He asked about it,” Quinn replied. “We haven’t opened it.” Eva took a breath. “He also asked whether the gate lock had been replaced since the last full moon.” The structural officer emerged below them and lifted a hand to Bell. Bell went to meet him. Quinn stayed with Eva on the bridge. “What did you tell Vale?” “That the records stopped in 1978. I didn’t know about this.” Eva looked over the rows of covered stalls. “I found the sketch after he left. It showed the transfer door, but not on the side where the ledger put it.” “Did he bring the sketch?” “He copied it from an archive map. I sent you a photograph with the message.” Quinn checked her phone. Below the failed voice message sat an image that had not loaded in the car. She opened it. The map showed the two platforms, the gate and the passage behind the stalls. A narrow line ran beneath the tracks from the transfer door to a point under the opposite platform. Not to the iron gate. She enlarged the image. At the end of that line, a square mark sat directly beneath the place where she had found the scrubbed grout. “What’s the square?” Eva leaned in. “The map key calls it a lift.” “There’s no lift.” “There was a goods lift. The floor above it was filled in.” Quinn looked across to Bell, who stood with the structural officer at the stall curtain. Then she looked at the gate and the freshly scratched padlock. Someone had left a false route for them there, one that pointed towards the street. “Ask them not to open that hatch yet,” she called. Bell lowered his radio. “Why?” Quinn held up the map. “The hatch leads under the tracks. I want the floor checked on the other side first.” “Where?” She pointed to the scrubbed tiles by the iron gate. “There. Mark out the old lift shaft and get the structural officer over.” The scene photographer paused at the gate and followed Quinn’s finger to the floor. Bell relayed the instruction. Eva remained on the bridge with the map between them while the officers set fresh markers along the opposite platform.
created_at"2026-09-23T16:35:27.571Z" 9/23/2026, 4:35:27 PM
model"openai/gpt-6-sol-20260922"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2412
moderation_latency(null)
generation_time62819
tokens_prompt1112
tokens_completion4090
native_tokens_prompt1009
native_tokens_completion3345
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
service_tier"default"
usage0.035468
router(null)
user_agent"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer(null)
request_id"req-1790181327-EpjWEgx3PTZKTFxJSMO6"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1790181327-EYc9Mo51ydJTw02Txw40"
upstream_id"resp_088da70b2fdcd7b0016ab3ffcfae9087d181c09b35738a2087"
provider_responses
0
endpoint_id"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id"resp_088da70b2fdcd7b0016ab3ffcfae9087d181c09b35738a2087"
is_byokfalse
latency530
model_permaslug"openai/gpt-6-sol-20260922"
provider_name"OpenAI"
status200
total_cost0.035468
cache_discount(null)
upstream_inference_cost0
provider_name"OpenAI"
response_cache_source_id(null)
data_region"global"
workspace_id"97e315e5-d303-487d-83c1-83180e8a13d4"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags16
adverbTagCount0
adverbTags(empty)
dialogueSentences131
tagDensity0.122
leniency0.244
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount2644
totalAiIsmAdverbs0
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)
90.54% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount2644
totalAiIsms5
found
0
word"velvet"
count3
1
word"etched"
count2
highlights
0"velvet"
1"etched"
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
emotionTells0
narrationSentences183
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount3
hedgeCount0
narrationSentences183
filterMatches
0"watch"
1"see look"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences299
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen36
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords2644
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions15
unquotedAttributions0
matches(empty)
16.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions93
wordCount1735
uniqueNames13
maxNameDensity2.07
worstName"Quinn"
maxWindowNameDensity4.5
worstWindowName"Quinn"
discoveredNames
Harlow2
Quinn36
Tube1
Imran1
Bell29
Directly1
Museum1
Kowalski2
Camden1
One2
Eva13
Vale1
Dust3
persons
0"Harlow"
1"Quinn"
2"Bell"
3"Kowalski"
4"Eva"
5"Vale"
6"Dust"
places(empty)
globalScore0.463
windowScore0.167
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences129
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount2644
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences299
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs158
mean16.73
std17.4
cv1.04
sampleLengths
025
185
224
34
419
54
62
730
83
93
1046
115
125
131
1448
1532
166
177
1862
1928
202
2135
2236
232
243
254
262
2730
2827
294
309
313
3259
335
3415
356
364
3736
388
391
407
4116
424
433
444
4511
466
4758
4822
494
95.68% Passive voice overuse
Target: ≤2% passive sentences
passiveCount5
totalSentences183
matches
0"were fastened"
1"been brushed"
2"been joined"
3"were lit"
4"been given"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs261
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount1
semicolonCount1
flaggedSentences2
totalSentences299
ratio0.007
matches
0"Quinn had listened to the first seven seconds in the car: Harlow, if someone tells you the Camden station was sealed, check the—"
1"The maintenance crew had entered from the stairs; their tread had cut deep through dust."
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1002
adjectiveStacks1
stackExamples
0"over polished brown boots."
adverbCount11
adverbRatio0.010978043912175649
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences299
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences299
mean8.84
std6.08
cv0.688
sampleLengths
08
117
214
324
412
517
65
79
84
924
104
1114
125
134
142
156
162
177
1815
193
203
2112
2215
239
2410
255
265
271
289
2912
308
3119
326
3326
345
351
367
3711
3819
395
4017
4110
425
4323
442
4535
465
4715
484
4912
58.97% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats7
diversityRatio0.36789297658862874
totalSentences299
uniqueOpeners110
57.80% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences173
matches
0"Directly under the dead man’s"
1"More strips marked the next"
2"Then she looked at the"
ratio0.017
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount30
totalSentences173
matches
0"Its cable hung in two"
1"Their owners had gone."
2"He glanced at the stalls"
3"She moved past a stall"
4"He wore disposable overshoes over"
5"He wore a dark wool"
6"His head had fallen forward."
7"His left lay open against"
8"She reached for an evidence"
9"She studied the tiles beneath"
10"She followed the edge of"
11"Its surviving compartment held a"
12"She had not called back."
13"Its hasp bent outwards, towards"
14"She pointed to the counter"
15"It was set close to"
16"Its rear curtain touched the"
17"She slipped a torch from"
18"She lifted her eyes to"
19"He walked off, shoulders squared"
ratio0.173
49.60% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount142
totalSentences173
matches
0"The train display above the"
1"Its cable hung in two"
2"Detective Harlow Quinn ducked under"
3"A draught lifted the edge"
4"Velvet cloths covered their counters."
5"Their owners had gone."
6"A uniformed constable met her"
7"He glanced at the stalls"
8"Quinn checked her worn leather"
9"The call had reached her"
10"She moved past a stall"
11"Teeth, she thought, until she"
12"The writing on them shifted"
13"A white forensic tent stood"
14"DS Imran Bell waited outside"
15"He wore disposable overshoes over"
16"Bell lifted the tent flap"
17"Quinn stopped at the flap."
18"He wore a dark wool"
19"His head had fallen forward."
ratio0.821
28.90% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences173
matches
0"Whoever had buttoned it had"
ratio0.006
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences73
technicalSentenceCount2
matches
0"A uniformed constable met her beside a tiled sign that read CAMDEN ROAD, though the station of that name stood nowhere near this tunnel."
1"A constable hovered beside her with the expression of a man who had been given a complicated explanation and found it worse than no explanation."
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
totalTags5
fancyCount0
fancyTags(empty)
dialogueSentences131
tagDensity0.038
leniency0.076
rawRatio0
effectiveRatio0
89.7388%