Run: 2026-07-08-01KX1MK94R65KDQBX2FT9TD6WW

Run Details

Duration:
56.8s
Cost:
$0.018078
Provider:
xAI

Model input

System
You are an expert and award-winning novel writer in the dark Thriller 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="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> <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> </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 thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
The man vaulted the iron railing and hit the pavement running, coat flaring behind him like torn shadow. Quinn's boots pounded after him, every stride jarring her knees. She closed the gap by half a block before he cut hard into Delancey Street, water from the gutters spraying up in dirty fans under his heels. A late bus hissed its brakes at the corner. The driver cursed as the figure darted across the beams. Quinn followed without breaking stride, shoulder glancing a parked taxi that blared its horn too late. The rain needled her face, cold enough to cut. It flattened her salt-and-pepper crop to her scalp and soaked the collar of her jacket until leather clung like a second skin. He glanced back once. Dark eyes, sharp under a hoodie sodden black. No panic. That made her push harder. Three years since Morris went down and still these runners thought they could vanish into the night like the rest of London's ghosts. She would teach this one otherwise. Camden High Street loomed, neon from closed shops bleeding colour across no-man's-land of wet tarmac. Music thumped from a basement doorway somewhere, bass and laughter. The suspect veered right, past the shuttered magazine stalls and the metal skeletons of empty bikes. Quinn's worn leather watch caught the light as she reached for her radio. Static spat back. Dead zone. Typical. He took the side road by the lock. Too narrow for cars. She knew the bottleneck well enough from other nights that ended with knives or worse. Her palm still burned from the scrape against brick two streets back. She wiped the blood on her trousers without slowing. Rain mixed it to thin pink trails. He ducked left again, through a rusted gate half off its hinges. She cursed under her breath and followed into the service yard behind the old railway arches. Puddles catched the last streetlamps and threw broken light up the greasy walls. The air smelt of diesel and rot. His footsteps splashed ahead, then stopped. Silence pressed in, thick as the rain itself. Quinn slowed. She drew her torch. The beam cut a dirty cone through the downpour, landing first on stacked pallets, then a corrugated door ajar with a gap wide enough for a body. No sound from inside. She thumbed the switch off and listened. Only the rain drumming metal roofs and her own pulse in her ears. She approached the door the same way she had approached every ambush since the night Morris vanished: low, eyes up, weight distributed for a sudden shift. Boot against the frame, she pushed. It swung with a soft scrape. Darkness waited, air colder, drier, laced with something sharp like ozone and old bone. A stone stairwell twisted down. Emergency strip lighting flickered in places, painting the walls jaundice yellow. The suspect's wet print trailed clear on dusty concrete. Deeper. She should call it in. Protocol demanded backup before entering unknown sublevels, especially under Camden where heaven knew what sunk its roots. The Yard still listed half these tunnels as sealed. They were wrong about so many seals. Her hand hovered near the radio again. Then she saw it on the fourth step down: a small pale disc, bone yellow in the stuttering light. Circles etched into one face, a crude snout of a beast she half-recognised from old statements that never made the official files. A token. He had dropped his entry chip. Or thrown it to buy seconds. Quinn pocketed it without ceremony. The edges bit her cut palm. She started down. Each step swallowed more of the rain noise until the storm became a distant rumour. The stairwell opened onto a wide platform that belonged to some forgotten line, tiles cracked and black with decades of soot. Further along, where the tunnels should have ended in collapsible brick, the mouth gaped alive with light and motion. She kept to the wall, torch low and dark. Voices reached her first: sharp bargains in half a dozen tongues, the clink of glass on metal, laughter that skittered too high. Then the shapes resolved under hanging oil lamps and glowing runes scratched into rusted supports. Tables. Stalls. Merchants draped in oilcloth and stranger hides. Patrons drifted between them with yellow eyes catching the light or skin mottled like wet stone. A woman sold vials that smoked without fire. A rotund man measured out powder that glittered and whispered. Someone paid with a lock of hair still pink at the roots. The Veil Market. She had only ever seen grainy CCTV stubs of it, and those vanished by morning. Moved every full moon, word had it. Tonight it nestled under Camden like a rotten tooth. The suspect cut straight through the middle, shoving past a trader with scaled wrists. Heads turned. Conversation dipped. Quinn hesitated at the threshold of the platform floor. Unfamiliar ground. Potentially hostile every shadow. She held no warrant that stretched this deep, no authority these buyers would recognise. The token in her pocket bought entry; it bought nothing about walking out again. She followed him anyway. The crowd parted for her in uneven ripples. A man with too many joints sniffed as she passed. Another, face masked by the lower jaw of something feline, faded backward into hanging cloth. She kept eyes on the black coat ahead. He quickened. A merchant shouted after him, accusatory. He ignored it and angled for a gap between two overloaded tables of tools that hummed under their own power. Quinn closed distance. Ten metres. Five. He plunged into a narrower spur off the main platform, where light thinned and boxes labileled in scripts she refused to learn blocked both walls. Wet coat range. She lunged, fingers snatching fabric. He twisted, the move fluid, and her grip slid on soaked cloth. Momentum carried her down the spur. She recovered quick, shoulder knocking a crate that clattered open to spill small dark bones across the floor. He spun to face her then. No more flight. The hoodie fell back and she saw him fully under the single hanging bulb: hollow cheeks, a scar prize across the nose, eyes the colour of cheap tea. In his hand he held a thin blade, the edge dark and irregular as if forged from frozen oil. "Detective Quinn," he said. The accent rolled unwelcome, South London over something older. "You never know when to fuck off." She drew her baton in one snap. "Put it down." He smiled with too many teeth and dropped something that was not the knife: another of those bone tokens, this one larger, etched with a different spiral. It hit the floor and cracked. The crack ran like a fracture through glass. Around them the hum of the market cut off, every conversation, every chew of air. Even the lamps dimmed. Figures melted out of the boxes to either side. Not stallholders. Too tall, too silent. One peeled itself free of the brick wall as if it had been painted there all along, features unfinished, limbs too long for the jacket it wore. Another crouched on the ceiling tiles above her head, upside-down and dripping. The man with the blade stepped closer. Rain still dripped from his hem onto the dust. "Took you long enough to walk down," he said. "We were starting to think old Harlow lost her nerve." The ceiling endless thing dropped.
created_at"2026-07-08T19:52:07.589Z" 7/8/2026, 7:52:07 PM
model"x-ai/grok-4.5-20260708"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency670
moderation_latency(null)
generation_time56721
tokens_prompt4663
tokens_completion2135
native_tokens_prompt4395
native_tokens_completion2636
native_tokens_completion_images(null)
native_tokens_reasoning1116
native_tokens_cached4352
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"
usage0.018078
router(null)
provider_responses
0
endpoint_id"0e927811-b1a8-4604-8b86-db5ce6eaa87c"
id"4ff03fc9-6d03-93fe-914f-c7d4b8b15917"
is_byokfalse
latency325
model_permaslug"x-ai/grok-4.5-20260708"
provider_name"xAI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer(null)
request_id"req-1783540327-zI1z6MLGrO6G2SjvqZN1"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1783540327-NMRmEmX7mhozk3z96jLD"
upstream_id"4ff03fc9-6d03-93fe-914f-c7d4b8b15917"
total_cost0.018078
cache_discount0.006528
upstream_inference_cost0
provider_name"xAI"
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
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences5
tagDensity0.4
leniency0.8
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1234
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)
55.43% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1234
totalAiIsms11
found
0
word"loomed"
count1
1
word"footsteps"
count1
2
word"silence"
count1
3
word"pulse"
count1
4
word"weight"
count1
5
word"flickered"
count1
6
word"etched"
count2
7
word"resolved"
count1
8
word"measured"
count1
9
word"quickened"
count1
highlights
0"loomed"
1"footsteps"
2"silence"
3"pulse"
4"weight"
5"flickered"
6"etched"
7"resolved"
8"measured"
9"quickened"
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
narrationSentences123
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences123
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences126
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen28
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1234
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions22
wordCount1205
uniqueNames11
maxNameDensity0.58
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Delancey1
Street2
Morris2
London2
High1
Camden3
Yard1
Veil1
Market1
South1
Quinn7
persons
0"Morris"
1"Market"
2"Quinn"
places
0"Delancey"
1"Street"
2"London"
3"High"
4"Camden"
5"South"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences86
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1234
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences126
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs26
mean47.46
std24.53
cv0.517
sampleLengths
055
166
248
360
455
554
68
757
852
964
1062
1169
12101
1334
1461
154
1669
1775
1856
1920
2010
2160
2254
2316
2419
255
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences123
matches
0"been painted"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs202
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount1
flaggedSentences1
totalSentences126
ratio0.008
matches
0"The token in her pocket bought entry; it bought nothing about walking out again."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1211
adjectiveStacks0
stackExamples(empty)
adverbCount44
adverbRatio0.03633360858794385
lyAdverbCount5
lyAdverbRatio0.004128819157720892
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences126
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences126
mean9.79
std6.78
cv0.693
sampleLengths
018
110
227
39
410
516
69
722
84
98
102
115
1223
136
1415
1510
1616
1713
183
192
201
218
224
2315
2412
259
267
2712
2816
2913
307
316
328
332
344
3527
364
377
3813
3926
406
416
4214
435
4411
459
461
475
4817
499
79.89% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.48412698412698413
totalSentences126
uniqueOpeners61
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount8
totalSentences106
matches
0"Too narrow for cars."
1"Only the rain drumming metal"
2"Then she saw it on"
3"Further along, where the tunnels"
4"Then the shapes resolved under"
5"Potentially hostile every shadow."
6"Even the lamps dimmed."
7"Too tall, too silent."
ratio0.075
91.70% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount34
totalSentences106
matches
0"She closed the gap by"
1"It flattened her salt-and-pepper crop"
2"He glanced back once."
3"She would teach this one"
4"He took the side road"
5"She knew the bottleneck well"
6"Her palm still burned from"
7"She wiped the blood on"
8"He ducked left again, through"
9"She cursed under her breath"
10"His footsteps splashed ahead, then"
11"She drew her torch."
12"She thumbed the switch off"
13"She approached the door the"
14"It swung with a soft"
15"She should call it in."
16"They were wrong about so"
17"Her hand hovered near the"
18"He had dropped his entry"
19"She started down."
ratio0.321
63.77% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount84
totalSentences106
matches
0"The man vaulted the iron"
1"Quinn's boots pounded after him,"
2"She closed the gap by"
3"A late bus hissed its"
4"The driver cursed as the"
5"Quinn followed without breaking stride,"
6"The rain needled her face,"
7"It flattened her salt-and-pepper crop"
8"He glanced back once."
9"That made her push harder."
10"She would teach this one"
11"Camden High Street loomed, neon"
12"Music thumped from a basement"
13"The suspect veered right, past"
14"Quinn's worn leather watch caught"
15"Static spat back."
16"He took the side road"
17"She knew the bottleneck well"
18"Her palm still burned from"
19"She wiped the blood on"
ratio0.792
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences106
matches(empty)
ratio0
23.81% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences48
technicalSentenceCount8
matches
0"Quinn followed without breaking stride, shoulder glancing a parked taxi that blared its horn too late."
1"She knew the bottleneck well enough from other nights that ended with knives or worse."
2"The stairwell opened onto a wide platform that belonged to some forgotten line, tiles cracked and black with decades of soot."
3"She held no warrant that stretched this deep, no authority these buyers would recognise."
4"He ignored it and angled for a gap between two overloaded tables of tools that hummed under their own power."
5"She recovered quick, shoulder knocking a crate that clattered open to spill small dark bones across the floor."
6"In his hand he held a thin blade, the edge dark and irregular as if forged from frozen oil."
7"He smiled with too many teeth and dropped something that was not the knife: another of those bone tokens, this one larger, etched with a different spiral."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount0
fancyTags(empty)
dialogueSentences5
tagDensity0.4
leniency0.8
rawRatio0
effectiveRatio0
90.4868%