Run: 2026-07-09-01KX40T2JXAB7P7F9KXJFQQMEF

Run Details

Duration:
17.3s
Cost:
$0.013060
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 step over the chalk line.” Detective Harlow Quinn stopped with one polished boot suspended above the white mark. A body lay beneath the derelict Tube platform, folded into the angle where the tiled wall met the track bed, as though someone had packed a man into a cupboard and shut the door. Behind Quinn, a constable swallowed hard. “Sorry, ma’am.” “Detective.” “Detective.” Quinn lowered her foot. Her leather watch clicked against its buckle as she checked the scene, then the watch again. The habit steadied her hands. Nothing else did. The abandoned station stretched around them in rusted arches and dead escalators. A cracked sign still promised Camden Town to passengers who had vanished generations ago. Beyond the platform, black tunnels opened like throats. The air tasted of coal dust, old rain and something sweet that clung to the tongue. Inspector Bell stood beside the body, his shoes planted in a dark puddle. “You took your time.” “I arrived before the ambulance.” “They won’t be taking him anywhere.” Bell pointed with a gloved hand. He had broad shoulders, a broad face and the loose confidence of a man who preferred his conclusions ready-made. “Male, late twenties. Bruising around the neck. No weapon. No footprints except ours and the victim’s. I’d call it a mugging gone sour.” Quinn looked at the victim’s throat. “The bruising isn’t around his neck.” Bell’s mouth tightened. “It’s underneath his jaw.” “Same difference.” “No.” Quinn crouched. The dead man wore a velvet jacket, black trousers and one silver earring shaped like a crescent moon. His skin held a faint grey tint, but the lips had darkened to violet. Thin red lines ran from the corners of his mouth towards his ears. “Ligature marks?” Bell asked. “Perhaps.” “You said they weren’t around his neck.” “Because they aren’t.” Quinn eased a finger beneath the jaw without touching the skin. A narrow groove circled the lower face, precise as a cut made with wire. Bell glanced towards the constable. “Can you see that?” The constable bent closer, then stepped back. “Looks like a necklace mark.” “No necklace,” Quinn said. Bell gestured towards the empty platform. “Could’ve been removed. Killer panicked.” “Then why leave the earring?” “Sentimental.” “Criminals are rarely sentimental at a scene they’ve cleaned.” Bell’s eyes moved over the tiles, the rails, the chalk markers. “Cleaned?” Quinn rose. The victim’s right hand rested palm-up. A shallow cut crossed the centre, but no blood had reached the floor. She turned to the forensic photographer. “Take a close shot of the hand.” “Already did.” “Take another.” The photographer lifted his camera. Bell sighed. “There’s no blood because the wound’s shallow.” “His palm is open. Blood should have run into the creases.” “Unless he died somewhere else.” “Then the bruises happened elsewhere too?” Bell glanced at the neck. Quinn knelt again and examined the jacket. Dust covered the shoulders and back, but the knees remained clean. A strip of black grit marked the left sleeve. It contained glints of green. Verdigris. She touched the grit with a swab. “Bag this separately.” Bell frowned. “Why?” “Because it isn’t from the station.” “This place is full of rust.” “Rust is red.” She placed the swab into a clear evidence sleeve. The grains glittered beneath the torch beam. A sound travelled through the tunnel. Three soft knocks. Quinn’s head turned. The constable reached for his radio. Bell raised a hand. “Rats.” The knocks came again. Closer this time. Not from the tunnel. From behind the tiled wall. Quinn crossed the platform. Her torch found a section of tiles darker than the rest, each one uncracked, clean enough to reflect her face. Someone had polished them recently. Bell followed. “You’ve got a theory?” “I have a wall.” “Very impressive.” Quinn pressed her palm against the tiles. Cold seeped through her glove. Beneath it, something pulsed. She withdrew her hand. “Get everyone off the platform.” Bell laughed once. “Because a wall made a noise?” “Because the victim’s blood is missing, the scene contains foreign metal, and someone has sealed an entrance behind a dead man.” Bell’s expression changed by a fraction. “What entrance?” Quinn pointed at the polished tiles. The third knock answered. This time, the wall breathed. Bell drew his weapon. “Constable, call for backup.” The constable fumbled with his radio. Static poured from the speaker, followed by a woman’s voice speaking in a language that sounded like glass breaking. The tiles split. A narrow black seam opened from floor to ceiling. No dust fell. No mortar cracked. The darkness beyond drank the torchlight. The dead man jerked on the ground. The constable shouted. Quinn spun back. The victim’s hand had closed around nothing. His fingers clawed at the air, and the cut in his palm opened wider without any pressure. Blood welled, black and thick, then ran uphill along his wrist. Bell fired. The shot struck the body and burst through the velvet jacket. No blood came out. The corpse arched, ribs lifting beneath the fabric, and a wet clicking sound filled the station. Quinn seized Bell’s arm. “Stop firing.” “It moved.” “It’s not alive.” The victim’s mouth opened. A thin cord of black fluid stretched between his teeth. A brass object slid from beneath his tongue and struck the tiles. Quinn stared at it. The small compass carried a green patina across its casing. Protective sigils circled the face, each mark cut so finely that her torch made them appear to shift. The needle spun once, twice, then pointed towards the opening in the wall. Bell kicked the compass. It skittered across the platform and stopped at the chalk line. The needle turned. It pointed at Quinn. For one breath, nobody moved. Then the station lights came on. Every dead bulb along the platform flared white. Shadows snapped into existence behind them, tall and thin, with hands pressed against the walls. The constable screamed into his radio. Bell fired again, this time at the nearest shadow. The bullet passed through it and struck a tile. A red spark jumped from the impact. The shadow’s fingers spread. Quinn grabbed the compass. Heat burned through her glove. The sigils brightened, and the seam in the wall widened with a groan. “Back,” she ordered. Bell did not move. “Quinn, what is that?” “Something that points to a door.” “To where?” The black opening exhaled. The smell of hot iron, incense and rotting flowers flooded the platform. Beyond the threshold, lanterns glowed along a street that could not exist beneath Camden. Stalls crowded the passage, draped in red cloth. Pale faces turned towards the detectives. One vendor displayed rows of bottled lightning. Another arranged silver teeth in velvet trays. A man with a crow’s head leaned over a counter and smiled. Bell whispered, “Jesus.” “No,” Quinn said. “Not remotely.” The corpse sat up. Its neck stretched, skin pulling tight over the vertebrae. The silver earring trembled. Black fluid spilled from its mouth and formed letters on the tiles. QUINN. Her name. The old ache behind her left eye ignited. Three years earlier, DS Morris had vanished inside a locked room while Quinn stood outside with her hand on the handle. She had heard him knocking from the other side long after the room emptied. Three knocks. Always three. The corpse pointed at the compass. A voice rose from the open market, low and amused. “Detective Quinn. You’ve brought the door home.” Bell seized her shoulder. “We’re leaving.” The shadows surged from the walls. Quinn twisted free and shoved the compass into her coat pocket. The brass burned against her ribs. She snatched the evidence bag containing the verdigris and thrust it at Bell. “Hold this.” “What?” “Proof.” A shadow struck the platform. Tiles exploded. The constable went down beneath a rain of white shards. Quinn dragged him by the collar. Bell fired twice into the darkness, each shot throwing sparks but stopping nothing. The market beyond the seam erupted into motion. Stalls overturned. Bottles shattered. A creature with jointed legs vaulted over a counter and disappeared into the black. Somewhere, a bell rang once. The corpse lurched towards Quinn. She drove her boot into its chest. It fell backwards, but its hand clamped around her ankle with impossible strength. The compass vibrated against her ribs. Its needle swung away from the market and pointed beneath the corpse. Quinn looked down. A second seam ran through the platform, hidden beneath the chalk line. It formed a perfect circle around the body. The chalk had not marked the crime scene. It had marked a lock. “Bell,” Quinn said. He turned, blood running from a cut above his eyebrow. “What?” “Shoot the line.” “You’ve lost your mind.” “Shoot it now.” The corpse opened its mouth wide enough to split its face. Bell aimed at the chalk. Quinn kicked the dead man’s hand away and leapt clear. The bullet struck the white line. Every shadow on the platform screamed. The circle broke. Black fire raced through the chalk, swallowed the corpse and tore across the tiles towards the open wall. The seam snapped shut with the force of a slammed door. Something reached through before it vanished. Long fingers caught Quinn’s coat and dragged her forward. The brass compass tore free of her pocket. Its chain wrapped around her wrist. Bell seized her waist. The fingers tightened. For an instant, Quinn saw a man beyond the wall, standing among the lanterns. Grey suit. Narrow shoulders. A familiar scar above his left eyebrow. Morris lifted one hand. Three knocks sounded from inside his chest. Then the door closed on Quinn’s arm.
created_at"2026-07-09T18:04:02.035Z" 7/9/2026, 6:04:02 PM
model"openai/gpt-5.6-luna-20260709"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency479
moderation_latency(null)
generation_time16860
tokens_prompt4671
tokens_completion2812
native_tokens_prompt4157
native_tokens_completion2107
native_tokens_completion_images0
native_tokens_reasoning0
native_tokens_cached4154
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"
usage0.0130604
router(null)
provider_responses
0
endpoint_id"eebea444-34a5-4642-a766-cb319471d33a"
id"resp_0245109c1ccff9bb016a4fe29222088190846c444fc3a8db67"
is_byokfalse
latency270
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-1783620242-7Wue3NwVJsDVu5PhjYxg"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783620242-HVCOYPzxX16FSlPlkWDb"
upstream_id"resp_0245109c1ccff9bb016a4fe29222088190846c444fc3a8db67"
total_cost0.0130604
cache_discount0.0037386
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
totalTags7
adverbTagCount0
adverbTags(empty)
dialogueSentences65
tagDensity0.108
leniency0.215
rawRatio0
effectiveRatio0
96.88% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1600
totalAiIsmAdverbs1
found
0
adverb"very"
count1
highlights
0"very"
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)
59.38% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1600
totalAiIsms13
found
0
word"velvet"
count3
1
word"pulsed"
count1
2
word"trembled"
count1
3
word"shattered"
count1
4
word"lurched"
count1
5
word"vibrated"
count1
6
word"perfect"
count1
7
word"eyebrow"
count2
8
word"raced"
count1
9
word"familiar"
count1
highlights
0"velvet"
1"pulsed"
2"trembled"
3"shattered"
4"lurched"
5"vibrated"
6"perfect"
7"eyebrow"
8"raced"
9"familiar"
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
narrationSentences181
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences181
filterMatches
0"watch"
hedgeMatches
0"appear to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences239
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1600
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
16.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions66
wordCount1337
uniqueNames8
maxNameDensity2.17
worstName"Quinn"
maxWindowNameDensity4.5
worstWindowName"Bell"
discoveredNames
Harlow1
Quinn29
Tube1
Camden2
Town1
Bell26
Morris2
Three4
persons
0"Harlow"
1"Quinn"
2"Bell"
3"Morris"
places
0"Camden"
1"Town"
globalScore0.415
windowScore0.167
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences104
glossingSentenceCount1
matches
0"sounded like glass breaking"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1600
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences239
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs162
mean9.88
std11
cv1.114
sampleLengths
06
147
26
32
41
51
628
750
813
94
105
116
1225
1323
146
156
163
174
182
1948
204
211
227
233
2425
255
264
277
285
294
306
315
325
331
349
3512
3621
376
387
392
402
415
429
4311
445
456
465
4732
481
497
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences181
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs236
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences239
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1339
adjectiveStacks0
stackExamples(empty)
adverbCount34
adverbRatio0.02539208364451083
lyAdverbCount2
lyAdverbRatio0.0014936519790888724
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences239
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences239
mean6.69
std4.83
cv0.722
sampleLengths
06
113
234
36
42
51
61
74
816
95
103
1112
1214
138
1416
1513
164
175
186
196
2019
2123
226
236
243
254
262
273
2818
2914
3013
314
321
337
343
3511
3614
375
384
397
405
414
426
435
445
451
469
4711
481
492
55.23% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats8
diversityRatio0.3514644351464435
totalSentences239
uniqueOpeners84
62.89% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences159
matches
0"Then the station lights came"
1"Somewhere, a bell rang once."
2"Then the door closed on"
ratio0.019
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount22
totalSentences159
matches
0"Her leather watch clicked against"
1"He had broad shoulders, a"
2"His skin held a faint"
3"She turned to the forensic"
4"It contained glints of green."
5"She touched the grit with"
6"She placed the swab into"
7"Her torch found a section"
8"She withdrew her hand."
9"His fingers clawed at the"
10"It skittered across the platform"
11"It pointed at Quinn."
12"Its neck stretched, skin pulling"
13"She had heard him knocking"
14"She snatched the evidence bag"
15"She drove her boot into"
16"It fell backwards, but its"
17"Its needle swung away from"
18"It formed a perfect circle"
19"It had marked a lock."
ratio0.138
44.91% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount132
totalSentences159
matches
0"Detective Harlow Quinn stopped with"
1"A body lay beneath the"
2"Quinn lowered her foot."
3"Her leather watch clicked against"
4"The habit steadied her hands."
5"Nothing else did."
6"The abandoned station stretched around"
7"A cracked sign still promised"
8"The air tasted of coal"
9"Inspector Bell stood beside the"
10"Bell pointed with a gloved"
11"He had broad shoulders, a"
12"Quinn looked at the victim’s"
13"Bell’s mouth tightened."
14"The dead man wore a"
15"His skin held a faint"
16"Quinn eased a finger beneath"
17"A narrow groove circled the"
18"Bell glanced towards the constable."
19"The constable bent closer, then"
ratio0.83
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences159
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences51
technicalSentenceCount2
matches
0"He had broad shoulders, a broad face and the loose confidence of a man who preferred his conclusions ready-made."
1"Static poured from the speaker, followed by a woman’s voice speaking in a language that sounded like glass breaking."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags7
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags6
fancyCount2
fancyTags
0"she ordered (order)"
1"Bell whispered (whisper)"
dialogueSentences65
tagDensity0.092
leniency0.185
rawRatio0.333
effectiveRatio0.062
87.8649%