Run: 2026-07-09-01KX3ZZJTDY5G2N1NQPCQ7XMVV

Run Details

Duration:
11.7s
Cost:
$0.014537
Provider:
OpenAI

Model input

System
You are an expert and award-winning novel writer in the dark Mystery genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
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> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on 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
“Don’t touch the body.” Detective Harlow Quinn stopped with one gloved hand inches from the dead man’s shoulder. Her colleague, Sergeant Bell, stood beyond the yellow tape, breathing through his mouth. “I wasn’t touching him.” “You were leaning towards him.” “That’s how looking works.” Quinn ignored him and stepped beneath the tape. The abandoned Tube station crouched beneath Camden like a buried machine. Rusted rails vanished into a black tunnel behind the platform. Old advertisements peeled from tiled walls, their smiling faces reduced to teeth and blank eyes. Someone had hung electric lamps from the ceiling, though no cable led to them. Their light trembled without flickering. The body lay beside the disused ticket barrier. A man in a velvet coat, perhaps fifty, sprawled on his back with one hand clenched around a white bone token. His throat showed no wound. His skin held the grey-blue cast of drowning, yet no water touched the dusty platform around him. Bell crouched beside the corpse. “Merchant named Orsini,” he said. “Known face in the Market. Someone opened his throat with a wire, according to the witness.” Quinn studied the neck. A thin red line circled it, too neat for a blade and too shallow for strangulation. No blood had run beneath the collar. “Who’s the witness?” “Woman called Eva Kowalski. Found him ten minutes ago.” “Found him where?” Bell pointed towards a brick archway behind the ticket booth. Quinn walked there. Her torch beam slid over the floor. Dust covered the tiles except for a trail of footprints leading from the arch to the body. One set. Small boots. Narrow heels. Kowalski’s shoes. The trail stopped beside Orsini. It did not continue away. Quinn turned. “Where did she go?” Bell’s gaze shifted towards the crowd gathered on the opposite platform. They stood in small knots, dressed in funeral black, work clothes and bright formal robes. A woman with silver teeth watched Quinn without blinking. A boy with moth wings folded beneath his jacket whispered into a brass mask. “Kowalski’s there,” Bell said. “She’s the redhead.” Quinn crossed the platform. Eva Kowalski moved through the crowd with a leather satchel pressed against her ribs. Her curly red hair escaped from its pins. Round glasses magnified green eyes that kept returning to the corpse. “Miss Kowalski.” She stopped tucking hair behind her left ear. “Detective.” “Tell me what happened.” “I heard a crash. Then someone shouted. When I reached the barrier, Orsini lay there.” “Alone?” “Yes.” “Your footprints lead to him.” “I checked his pulse.” “With one hand?” Eva glanced at her gloves. “I touched his wrist.” “No prints on the wrist. None on the coat. None on the floor near the body except yours.” “Perhaps the killer wore clean shoes.” “Perhaps.” Quinn looked past her. “Yet your trail begins at the archway and ends beside him. You didn’t leave.” Eva’s lips parted. Bell arrived behind Quinn, his hand resting on his holster. “She was in shock,” he said. “People don’t always notice where they walk.” “People notice leaving a body.” “I didn’t leave him,” Eva said. Quinn watched her face. The denial came too quickly. The fear came afterwards. “What did Orsini sell?” Eva’s fingers tightened around the satchel strap. “Books.” Bell gave a short laugh. “Books, apparently, can kill a man now.” “This place sells banned alchemical compounds,” Eva said. “Information. Enchanted goods. Orsini dealt in all three.” “Where did you learn that?” “I work in the restricted archives at the British Museum.” “Your employer sent you underground to buy contraband?” “I came to meet someone.” “Who?” Eva looked towards the crowd. A gap had opened beside the dead man. No one admitted to making it. “Professor Vale,” she said. “He never arrived.” Quinn returned to the body. Orsini’s clenched fist held the bone token so tightly that the knuckles had split. Quinn photographed it, then examined the token through her magnifier. A symbol marked its surface: a circle crossed by three crooked lines. Bell peered over her shoulder. “Market entry token.” “Not this Market.” “What does that mean?” Quinn did not answer. She lifted her torch towards the lamps. Their flames gave off no heat. Each one burned with a small blue core surrounded by pale green light. A draft moved across the platform. It came from the corpse. Quinn felt it against her cheek, cold and damp, carrying the smell of wet stone. She lowered her torch and studied Orsini’s coat. The velvet fibres leaned towards his throat. Not towards the tunnel. Towards the body. “Bell, get everyone off the platform.” He frowned. “Why?” “Now.” The lamps went out. Every supernatural creature in the station hissed at once. The sound rolled through the tunnels, followed by the clatter of shutters slamming down. Somewhere beyond the ticket booth, metal gates dropped across the exits. Bell drew his weapon. “What did you see?” “Nothing yet.” The body sat upright. Its neck stretched with a dry crack. Orsini’s eyes opened, revealing pale silver irises. His hand released the bone token. Eva screamed. Orsini’s mouth opened too far. A black thread burst from his throat and struck the nearest lamp. The glass shattered. Darkness swallowed the platform. Quinn fired once. The shot punched into Orsini’s chest. He fell backwards, but the thread whipped towards Bell. Bell raised his arm. It wrapped around his wrist and tightened. “Cut it!” Quinn seized a fallen length of rail from beside the track and swung. The metal smashed through the thread. Bell dropped, clutching his bleeding arm. The severed strand crawled across the tiles. It had no body, only a wet sheen and tiny hooked teeth. Eva opened her satchel. “Don’t,” Quinn snapped. Eva pulled out a narrow book bound in cracked blue leather. The thread lunged. Quinn shoved Eva aside. The thing struck her coat and tore through the fabric, grazing her ribs. Pain flashed hot beneath her skin. She caught the rail in both hands and pinned the thread to the floor. “Your book,” Quinn said. “What does it do?” Eva stared at the writhing strand. “It records names.” “Useful. Use it.” “I need ink.” Quinn looked at the blood running from her side. “Use mine.” Eva dipped one finger into the blood and dragged it across the book’s blank page. Letters rose beneath her touch, forming themselves in a script Quinn did not recognise. Orsini’s corpse twitched. The silver eyes fixed on Eva. The book snapped shut. A voice filled the station, though Orsini’s lips did not move. “Not his name.” The rails began to hum. Quinn felt the vibration in her teeth. The brass compass in Orsini’s pocket slid free and spun across the platform, its verdigris casing flashing under the emergency lamps. The needle pointed towards the brick archway. Then the wall breathed. Mortar split between the bricks, revealing a vertical seam of violet light. Beyond it lay no tunnel, no chamber, but a vast dark space where pale shapes moved like drowned birds. Eva reached for the compass. Quinn caught her wrist. “What’s through there?” “An opening.” “To where?” Eva’s eyes stayed on the seam. “Somewhere the Market shouldn’t have followed.” The black thread tore free from beneath the rail. It launched itself at the widening rift. Quinn fired again. The bullet struck the floor, throwing sparks. The thread crossed the threshold and vanished. A second voice whispered from inside the opening. “Detective Quinn.” Her hand went still. Bell looked at her. “You know that voice?” The violet seam widened. A man’s silhouette appeared beyond it, tall and distorted, with one arm hanging at an impossible angle. Quinn recognised the coat first. Then the badge. Then the cracked wedding ring on the left hand. DS Morris stepped through the rift, and the dead man on the platform began to laugh.
created_at"2026-07-09T17:49:33.913Z" 7/9/2026, 5:49:33 PM
model"openai/gpt-5.6-luna-20260709"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency390
moderation_latency(null)
generation_time11417
tokens_prompt4671
tokens_completion2301
native_tokens_prompt4157
native_tokens_completion1730
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"
usage0.014537
router(null)
provider_responses
0
endpoint_id"eebea444-34a5-4642-a766-cb319471d33a"
id"resp_0a2529e61306808f016a4fdf2e07f08190bff09127ccc400a0"
is_byokfalse
latency266
model_permaslug"openai/gpt-5.6-luna-20260709"
provider_name"OpenAI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783619373-3oCVSQXZlPPgnvFVJID8"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783619373-aDIX7kcsUBkbZi7Zkwoz"
upstream_id"resp_0a2529e61306808f016a4fdf2e07f08190bff09127ccc400a0"
total_cost0.014537
cache_discount(null)
upstream_inference_cost0
provider_name"OpenAI"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags9
adverbTagCount0
adverbTags(empty)
dialogueSentences65
tagDensity0.138
leniency0.277
rawRatio0
effectiveRatio0
92.30% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1298
totalAiIsmAdverbs2
found
0
adverb"quickly"
count1
1
adverb"tightly"
count1
highlights
0"quickly"
1"tightly"
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)
76.89% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1298
totalAiIsms6
found
0
word"electric"
count1
1
word"trembled"
count1
2
word"velvet"
count2
3
word"pulse"
count1
4
word"shattered"
count1
highlights
0"electric"
1"trembled"
2"velvet"
3"pulse"
4"shattered"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"clenched jaw/fists"
count1
highlights
0"clenched fist"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences136
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount2
narrationSentences136
filterMatches(empty)
hedgeMatches
0"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences192
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen21
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1298
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
26.60% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions70
wordCount1013
uniqueNames10
maxNameDensity2.47
worstName"Quinn"
maxWindowNameDensity4
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn25
Sergeant1
Bell13
Tube1
Camden1
Orsini9
Kowalski2
Eva16
Morris1
persons
0"Harlow"
1"Quinn"
2"Sergeant"
3"Bell"
4"Camden"
5"Orsini"
6"Kowalski"
7"Eva"
8"Morris"
places(empty)
globalScore0.266
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences76
glossingSentenceCount1
matches
0"appeared beyond it, tall and distorted, with one arm hanging at an impossible angle"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1298
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences192
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs137
mean9.47
std9.71
cv1.025
sampleLengths
04
127
24
35
44
58
655
78
843
95
1021
1127
123
139
143
1510
1627
172
184
192
2010
212
224
2349
247
254
2633
272
288
291
304
3115
321
331
345
354
363
379
3818
396
4019
413
4210
4313
445
456
4613
474
487
491
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences136
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs182
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences192
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1014
adjectiveStacks0
stackExamples(empty)
adverbCount26
adverbRatio0.02564102564102564
lyAdverbCount4
lyAdverbRatio0.0039447731755424065
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences192
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences192
mean6.76
std4.41
cv0.653
sampleLengths
04
114
213
34
45
54
68
711
810
915
1014
115
128
1321
145
1517
165
175
1816
194
2016
217
223
239
243
2510
263
277
2817
292
302
312
322
335
345
352
364
3711
3815
399
4014
414
423
434
4414
458
4611
472
488
491
56.08% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.3645833333333333
totalSentences192
uniqueOpeners70
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences121
matches
0"Somewhere beyond the ticket booth,"
1"Then the wall breathed."
2"Then the badge."
3"Then the cracked wedding ring"
ratio0.033
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount21
totalSentences121
matches
0"Her colleague, Sergeant Bell, stood"
1"Their light trembled without flickering."
2"His throat showed no wound."
3"His skin held the grey-blue"
4"Her torch beam slid over"
5"It did not continue away."
6"They stood in small knots,"
7"Her curly red hair escaped"
8"She stopped tucking hair behind"
9"She lifted her torch towards"
10"Their flames gave off no"
11"It came from the corpse."
12"She lowered her torch and"
13"Its neck stretched with a"
14"His hand released the bone"
15"He fell backwards, but the"
16"It wrapped around his wrist"
17"It had no body, only"
18"She caught the rail in"
19"It launched itself at the"
ratio0.174
9.59% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount109
totalSentences121
matches
0"Detective Harlow Quinn stopped with"
1"Her colleague, Sergeant Bell, stood"
2"Quinn ignored him and stepped"
3"The abandoned Tube station crouched"
4"Someone had hung electric lamps"
5"Their light trembled without flickering."
6"The body lay beside the"
7"A man in a velvet"
8"His throat showed no wound."
9"His skin held the grey-blue"
10"Bell crouched beside the corpse."
11"Quinn studied the neck."
12"A thin red line circled"
13"Bell pointed towards a brick"
14"Quinn walked there."
15"Her torch beam slid over"
16"Dust covered the tiles except"
17"The trail stopped beside Orsini."
18"It did not continue away."
19"Bell’s gaze shifted towards the"
ratio0.901
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences121
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences38
technicalSentenceCount1
matches
0"Round glasses magnified green eyes that kept returning to the corpse."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags9
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags8
fancyCount1
fancyTags
0"Quinn snapped (snap)"
dialogueSentences65
tagDensity0.123
leniency0.246
rawRatio0.125
effectiveRatio0.031
88.7150%