Run: 2026-03-18-01KM0AB0YFD47MH9RAMZ8EXHXA

Run Details

Duration:
46.3s
Cost:
$0.031324
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
Quinn caught the brass compass before it struck the platform tiles. The needle spun wild, then slammed north, then west, then back again, rattling against the face with a thin, frantic click. “Keep that thing away from my boots.” She looked up from the compass and into the abandoned station beneath Camden, where the Veil Market had turned the old Tube mouth into a nest of tarps, ward-lamps and blackened tables. One body lay under the torn remains of a route map, one arm flung across cracked tiles, a dark stain spread beneath the collar of his coat. Police tape cut a bright line through the gloom. Beyond it, the last of the market traders stood in knots, faces pale under hooded capes and expensive fear. DS Bell stood by the body with his hands on his hips and his jaw set hard enough to crack stone. He had a broad face, a blunt nose and the look of a man who hated every foot of the underground. “You called me down here for this?” Bell flicked his torch beam over the corpse and the circle of white ash around it. “I called you because your lot trade in curses and grave dirt, and one of them has gone and decorated a murder scene.” “Decorated.” Quinn stepped over a chalk line and crouched. “That your expert reading?” Bell gave a thin smile. “Dead bloke in a salt ring, bone token in the hand, blood on the tiles. Looks like ritual work to me.” Quinn set the compass on her palm and watched the needle lunge towards the wall behind the nearest shuttered stall. Then she looked at the body. The dead man wore a dark wool coat, expensive enough to be stolen and plain enough to pass. His face had gone waxy, the lips drawn back from his teeth. A cut crossed his throat from left to right. Clean. Neat. Too neat. Blood dried into the fibres of his scarf and collar, yet the tiles beneath his shoulders stayed almost dry. She leaned closer. The ash ring Bell had pointed out did not sit under the body. It ran round him in a broken oval, and the line had never met at the heel of his right boot. Somebody had finished the circle after they placed him down, or they had drawn it round a body that was not there when they started. “Where was he found?” “Here. Security said they heard a crash from the old lift corridor, came over, and found this little masterpiece.” “Security who?” Bell glanced towards the platform entrance. “Two market lads. One ran off. The other swore he saw a hooded figure vanish into the crowd.” “Did he say vanish, or did he say leave?” Bell shifted his weight. “What does it matter?” Quinn pointed at the dead man’s throat with two fingers, careful not to touch the blood. “If he bled out here, this floor would wear it. It doesn’t.” Bell knelt beside her, the cuffs of his coat brushing the platform grime. “You see a train of neat facts where I see a cult butcher’s stall. Bone token, circle, sigils on the wall. The market attracts idiots with sharp knives and grand ideas.” Quinn turned the man’s left hand over. The fingers stiffened in a loose fist. Something pale sat in his palm. Not bone. Not properly. She hooked it free with the tip of her pen. It looked like a bone token at a glance, the sort of thing the market demanded at entry, but the edges gave it away. Too smooth. Too white. The grain ran wrong. Resin, not marrow. Someone had painted it with ash and scraped a groove across one side to fake age. She held it under the torch. “Your cultist left a counterfeit.” Bell frowned. “A fake token?” “A fake entrance. A fake ritual. A fake body placement if I had to wager.” She rose and crossed to the nearest stall. A row of glass jars sat under a black cloth, each jar empty except for a smear of grease on the inside rim, a trace of old salt at the base. One jar had shattered. The broken glass lay in a fan across the tiles, and the sharp edge of the shard nearest the wall glistened with red. Quinn crouched again and touched the floor beside the shard. Dust. Thick and grey in the corners, thin where feet had scuffed through it. But around the body the dust kept a neat halo under the blood. Nobody had dragged him across that patch. Someone had carried him. She glanced at Bell. “Where are the drag marks?” Bell stood and looked down at the body as if he expected it to answer for itself. “No drag marks. He might have walked here, collapsed here.” “Not with that wound.” She lifted the dead man’s shoulder just enough to see the back of his coat. There it was, a long bruise-black smear across the fabric, dirt ground into the wool in one direction. The mark stopped halfway down his back, as if he had scraped against a trolley, a wall, or a rough handrail. He had not died in the circle. Someone had moved him into it. The compass in her palm gave a hard jerk. The needle pointed again at the wall behind the stall. Not the corpse. Not the blood. The wall. Quinn got to her feet and followed the pull. The stall belonged to a seller of charms and bottled powders, or it had before the market had shut down. The counter had been tipped over. A string of tarnished bells hung from one corner, silent now, though the compass still twitched. Behind the stall, an advertisement panel for a long-closed line had been bolted to the wall. One corner stuck out by a finger’s width. Bell watched her. “What have you clocked?” “Your killer has manners.” “Pardon?” “He cleaned the wrong thing.” She slid her fingers behind the loose edge of the panel. Fresh plaster dust flaked onto her knuckles. The panel shifted, then stuck. Bell moved in beside her. “You finding hidden rooms now?” “Keep your voice down and pull.” He took the other side. Together they wrenched. The metal shrieked, then came free with a wet little pop. The smell hit next, sharp and mineral, with a thread of copper and something colder under it, something that made the teeth ache. Behind the panel, the wall did not sit flush. A seam cut through the bricks in a line too straight for old masonry. The mortar around it looked newer than the rest, pale and rough, as if someone had patched the wall in a hurry and then scrubbed it with a dirty rag. Bell stared. “What in hell is that?” “Fresh work.” “That’s impossible. This station’s been sealed for decades.” “Then someone opened it.” Quinn ran the compass along the seam. The needle jerked so hard it nearly bent. The brass casing warmed in her hand. Protective sigils etched on the face flared faintly, catching the torchlight in thin silver lines. The needle point stopped at one section of brick, then shivered. Bell noticed it too. His voice lost its edge. “Right. Fine. So we’ve got a breach. That still doesn’t rule out ritual murder.” “It rules out your version.” She tapped the wall. “This is the murder scene they wanted you to see. The blood, the circle, the token, all of it. They staged it to look like a market killing, then patched the route behind it.” Bell’s mouth tightened. “You think someone used the market as cover.” “I think someone walked a corpse through a door no one else can see.” He glanced at the dead man, then at the wall, and Quinn saw the calculation land behind his eyes. The market traders had gone quiet now. No mutter. No shift of feet. Even the broken station seemed to listen. “Who would risk opening a rift under Camden?” “Someone who wanted a body moved without a van, without CCTV, without a dock search. Someone who knew the market would swallow the blame.” Bell looked over his shoulder. “Or someone inside the market wanted the body found here.” Quinn’s gaze dropped to the dead man’s coat pocket, where something angular pressed against the wool. She slipped two fingers inside and drew out a folded scrap of paper. Not a receipt. A map fragment, old and stained, with one point marked in red ink. The mark sat on the abandoned lift corridor behind them. Under it, in sharp black strokes, someone had written one word. HERE. The compass needle gave a violent twitch. Quinn’s head came up. The seam in the wall groaned. A thin line of black slid through the mortar, then split the bricks with a crack like a knuckle snapping. Cold breathed out of it. The market lights flared and went dim. Bell stumbled back, one hand flying to his holster. “Quinn.” The crack widened. A pale hand pressed from the other side, fingers splayed against the brick from within.
created_at"2026-03-18T11:12:20.456Z" 3/18/2026, 11:12:20 AM
model"openai/gpt-5.4-mini-20260317"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency42647
moderation_latency(null)
generation_time45263
tokens_prompt4671
tokens_completion4084
native_tokens_prompt4157
native_tokens_completion6844
native_tokens_completion_images0
native_tokens_reasoning4973
native_tokens_cached3840
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"completed"
usage0.03132375
router(null)
provider_responses
0
endpoint_id"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id"resp_0984cdc2cf4b5db20169ba889482048194811ded5796f04348"
is_byokfalse
latency199
model_permaslug"openai/gpt-5.4-mini-20260317"
provider_name"OpenAI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773832340-wVfYtj9YuRJsL6jGOzKQ"
upstream_id"resp_0984cdc2cf4b5db20169ba889482048194811ded5796f04348"
total_cost0.03132375
cache_discount0.002592
upstream_inference_cost0
provider_name"OpenAI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences39
tagDensity0.026
leniency0.051
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1521
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)
80.28% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1521
totalAiIsms6
found
0
word"gloom"
count1
1
word"flicked"
count1
2
word"grave"
count1
3
word"weight"
count1
4
word"shattered"
count1
5
word"etched"
count1
highlights
0"gloom"
1"flicked"
2"grave"
3"weight"
4"shattered"
5"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
narrationSentences114
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences114
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences152
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen34
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1521
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
76.41% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions35
wordCount1155
uniqueNames7
maxNameDensity1.47
worstName"Bell"
maxWindowNameDensity2.5
worstWindowName"Bell"
discoveredNames
Camden1
Veil1
Market1
Tube1
Bell17
Quinn11
One3
persons
0"Market"
1"Tube"
2"Bell"
3"Quinn"
places
0"One"
globalScore0.764
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences76
glossingSentenceCount1
matches
0"looked like a bone token at a glance, the"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1521
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences152
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs82
mean18.55
std19.74
cv1.064
sampleLengths
032
17
287
342
47
516
623
713
85
921
1026
1162
1262
134
1419
152
166
1718
189
194
204
2116
2212
2313
2431
2534
2651
276
285
292
303
3115
3266
3348
344
355
3617
3710
384
3954
4013
4127
4275
433
444
454
461
475
4823
495
99.11% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences114
matches
0"been tipped"
1"been bolted"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs172
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences152
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1158
adjectiveStacks1
stackExamples
0"long bruise-black smear"
adverbCount37
adverbRatio0.03195164075993091
lyAdverbCount3
lyAdverbRatio0.0025906735751295338
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences152
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences152
mean10.01
std7.54
cv0.753
sampleLengths
011
121
27
332
427
59
619
721
821
97
1016
1123
129
134
145
1521
1620
176
1818
1912
209
211
221
232
2419
253
2613
2721
2825
294
3019
312
326
3318
349
354
364
3716
3812
3913
4031
417
427
436
442
452
4610
4724
482
492
53.29% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.35526315789473684
totalSentences152
uniqueOpeners54
66.01% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences101
matches
0"Then she looked at the"
1"Even the broken station seemed"
ratio0.02
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences101
matches
0"She looked up from the"
1"He had a broad face,"
2"His face had gone waxy,"
3"She leaned closer."
4"It ran round him in"
5"She hooked it free with"
6"It looked like a bone"
7"She held it under the"
8"She rose and crossed to"
9"She glanced at Bell."
10"She lifted the dead man’s"
11"He had not died in"
12"She slid her fingers behind"
13"He took the other side."
14"His voice lost its edge."
15"She tapped the wall."
16"He glanced at the dead"
17"She slipped two fingers inside"
ratio0.178
59.01% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount81
totalSentences101
matches
0"Quinn caught the brass compass"
1"The needle spun wild, then"
2"She looked up from the"
3"Police tape cut a bright"
4"DS Bell stood by the"
5"He had a broad face,"
6"Bell flicked his torch beam"
7"Quinn stepped over a chalk"
8"Bell gave a thin smile."
9"Quinn set the compass on"
10"The dead man wore a"
11"His face had gone waxy,"
12"A cut crossed his throat"
13"Blood dried into the fibres"
14"She leaned closer."
15"The ash ring Bell had"
16"It ran round him in"
17"Somebody had finished the circle"
18"Bell glanced towards the platform"
19"Bell shifted his weight."
ratio0.802
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences101
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences48
technicalSentenceCount2
matches
0"The smell hit next, sharp and mineral, with a thread of copper and something colder under it, something that made the teeth ache."
1"The mortar around it looked newer than the rest, pale and rough, as if someone had patched the wall in a hurry and then scrubbed it with a dirty rag."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
90.9365%