Run: 2026-02-19-01KHTYXDX8CF2F8ZQ5D3C8M5YB

Run Details

Duration:
59.8s
Cost:
$0.001750
Provider:
AtlasCloud

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 suspect’s heel clipped the edge of a slick bin lid, sending it clattering into the alley wall. The sound echoed off wet brick like a gunshot. Detective Harlow Quinn didn’t flinch. Her own footfalls were a steady, economical beat against the glistening pavement. She’d had him for six blocks. From the moment he’d bolted from the dim glow of The Raven’s Nest, that distinctive green neon sign casting his shadow long and thin. He was younger, faster. But fear made people stupid. Fear made them run in straight lines. Quinn cut a diagonal across the mouth of an alley, her worn leather watchband tight against her wrist, military precision calculating the intercept. He vanished down a service stairwell. *Underground. Of course.* She paused at the top, the rain needling the shoulders of her coat. The steps descended into a pitch black that swallowed the sound of the downpour. Her hand went to her sidearm, a familiar, cold weight. She flicked on her torch. The beam cut a shaky path down concrete steps littered with wrappers and broken glass. The air changed halfway down. The damp chill of the London night was replaced by something else. Stale. Ozone and old incense. The faint, coppery tang of something that wasn’t blood but wanted to be. A low hum vibrated through the soles of her boots. The stairwell bottomed out into a disused ticket hall for an abandoned Tube station. Graffiti covered the old tiled maps. A single, flickering emergency light buzzed overhead. And there, disappearing through an arched doorway where a ticket barrier had once been, was the flapping edge of a dark coat. Quinn followed. The corridor beyond was narrow, pipes dripping rust-coloured water onto the floor. The hum grew louder. Became a murmur. Then a cacophony of voices, bartering, the clink of glass. She rounded a corner and stopped. The Veil Market sprawled before her in the cavernous belly of the old station. Stalls constructed from scrap wood and faded fabric lined the curved platforms. Lanterns hung from the arched ceiling, casting a sickly, greenish light that made shadows writhe. The air was thick with the smell of strange herbs, hot metal, and decay. People—if they were people—moved through the throng. A woman with eyes like polished jet hawked vials of swirling liquid. A hulking figure in a heavy cloak ground what looked like teeth in a mortar. Her suspect was twenty yards ahead, shouldering his way through the crowd towards a stall hung with dried, unrecognisable things. "Police! Stop!" The command, sharp and practised, died in the market’s noise. A few heads turned. Eyes, too many and too bright, fixed on her. The murmur didn’t cease, but it lowered. Became a watchful silence. The suspect glanced back. His face, pale in the weird light, was a mask of panic. He ducked behind a stall selling what appeared to be intricate clockwork birds. Quinn moved. The crowd didn’t part so much as it absorbed her, bodies shifting to let her through then closing behind her. She felt watched. Assessed. A man with fingers too long and jointed reached out as she passed, holding up a bone-white token. "Lost, detective?" His voice was a dry rustle. She ignored him, her focus on the dark coat. He was heading for a narrower tunnel at the far end of the platform, one marked by a curtain of stained beads. "Tommy! It’s me!" The shout cut through the market’s murmur. Her suspect had reached a stall at the tunnel’s mouth. A man stood behind it, arranging small glass bottles on a felt cloth. Tomás Herrera. Quinn recognised him from his file. The former paramedic. His Saint Christopher medallion glinted against his olive skin as he looked up, his warm brown eyes going from the panicked man to her, then back. "Mate, you’re steaming," Herrera said, his voice calm, carrying a faint Spanish lilt. He put a steadying hand on the suspect’s arm. The scar on his own forearm stood out, pale against his skin. "He’s with me, detective. Off the books." Herrera’s gaze met Quinn’s across the stall. No fear. A weary sort of resignation. "Whatever you think he did, it’s a misunderstanding." "This isn’t a social call, Herrera. Step aside." "Or what? You’ll arrest us both?" A humourless smile touched his lips. "You’ve no jurisdiction here. This place… it moves. You’ll never find it again. And the things that guard it don’t care about your warrant card." The suspect—Tommy—was trembling, his hands on the stall’s edge. Herrera kept a firm grip on him. Quinn’s fingers tightened on her torch. The greenish light gleamed off the bottles on Herrera’s stall. One held a thick, dark liquid that seemed to pulse. Another contained what looked like moth wings, iridescent and fragile. Medical supplies for a clientele the NHS wouldn’t touch. "Three years ago," Quinn said, the words leaving her mouth before she could stop them. The market’s noise seemed to fade further. "A detective sergeant. Ian Morris. His body was found in a place like this. Not a mark on him. Eyes wide open." Herrera’s expression didn’t change, but something shifted behind his eyes. A shutter closing. "I remember the case. Tragic." "You provided a statement. Said you’d never seen him before." "I hadn’t." "Your signature was on a requisition form for potassium chloride. The kind that stops a heart without leaving a trace. Found in an evidence lock-up that shouldn’t have existed." The air between them grew colder. The market’s sounds were a distant ocean now. Tommy was staring at Herrera, a new kind of fear dawning on his face. "I lost my licence for helping people," Herrera said quietly. "Not for hurting them." "Did Morris need help? Or was he in the way?" A figure detached itself from the shadows behind Herrera’s stall. Tall, thin, draped in grey rags. It made no sound as it moved to stand beside Tommy. No face was visible within the hood, just a deeper darkness. Herrera’s jaw tightened. "This conversation is over, detective. Leave. Take the stairs up. Forget the route." "Not without him." Quinn nodded at Tommy. "You’re not taking anyone." Herrera’s hand moved. Not towards a weapon. Towards a small, polished brass bell on his stall. He rang it once. A single, clear note hung in the damp air. All around them, the market fell utterly silent. The bartering stopped. The clinking ceased. Every head turned. Every unnatural eye fixed on Detective Harlow Quinn. The bead curtain behind the stall rustled. Another figure emerged from the tunnel. This one was solid, broad, wearing the remnants of a security uniform from a department store. Its skin had a grey, waxy sheen. It stared at Quinn with milky, unblinking eyes. "Last chance," Herrera whispered. The Saint Christopher medallion rose and fell with his breath. "Walk away. This isn’t your world." Quinn’s service pistol was in her hand. The weight was comforting. Real. The creature in the security uniform took a heavy step forward. Its boots scraped on the concrete. Tommy whimpered. Three years of unanswered questions. A partner gone without reason. A case file that smelled of a cover-up so deep it was buried in places like this. In stinking markets that moved with the moon. She saw Morris’s face. The sharp line of his jaw, gone slack. His own eyes, staring at nothing in a room that official reports said didn’t exist. The waxy-faced thing took another step. Its hand reached for her. Quinn made her decision.
created_at"2026-02-19T12:45:04.816Z" 2/19/2026, 12:45:04 PM
model"deepseek/deepseek-v3.2-20251201"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1828
moderation_latency(null)
generation_time59814
tokens_prompt4663
tokens_completion1957
native_tokens_prompt4220
native_tokens_completion1718
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
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"stop"
usage0.00175004
router(null)
provider_responses
0
endpoint_id"3570a950-b80f-4acd-bb92-8e1c1c51fafc"
id"75e982772a95400587bd34a778d793d2"
is_byokfalse
latency1828
model_permaslug"deepseek/deepseek-v3.2-20251201"
provider_name"AtlasCloud"
status200
api_type"completions"
id"gen-1771505104-5RVrMEfRbJw3EX4Jq66n"
upstream_id"75e982772a95400587bd34a778d793d2"
total_cost0.00175004
cache_discount(null)
upstream_inference_cost0
provider_name"AtlasCloud"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags7
adverbTagCount1
adverbTags
0"Herrera said quietly [quietly]"
dialogueSentences23
tagDensity0.304
leniency0.609
rawRatio0.143
effectiveRatio0.087
96.03% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1261
totalAiIsmAdverbs1
found
0
adverb"utterly"
count1
highlights
0"utterly"
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)
32.59% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1261
totalAiIsms17
found
0
word"echoed"
count1
1
word"glistening"
count1
2
word"calculating"
count1
3
word"familiar"
count1
4
word"weight"
count2
5
word"flicked"
count1
6
word"chill"
count1
7
word"vibrated"
count1
8
word"cacophony"
count1
9
word"constructed"
count1
10
word"hulking"
count1
11
word"silence"
count1
12
word"intricate"
count1
13
word"lilt"
count1
14
word"pulse"
count1
15
word"comforting"
count1
highlights
0"echoed"
1"glistening"
2"calculating"
3"familiar"
4"weight"
5"flicked"
6"chill"
7"vibrated"
8"cacophony"
9"constructed"
10"hulking"
11"silence"
12"intricate"
13"lilt"
14"pulse"
15"comforting"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"air was thick with"
count1
highlights
0"The air was thick with"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences126
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount3
narrationSentences126
filterMatches(empty)
hedgeMatches
0"appeared to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences140
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen30
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords3
totalWords1252
ratio0.002
matches
0"Underground. Of course."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions4
unquotedAttributions0
matches(empty)
16.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions46
wordCount1068
uniqueNames15
maxNameDensity1.22
worstName"Quinn"
maxWindowNameDensity4.5
worstWindowName"Herrera"
discoveredNames
Harlow2
Quinn13
Raven1
Nest1
London1
Tube1
Veil1
Market1
Herrera12
Saint2
Christopher2
Spanish1
Tommy5
Detective2
Morris1
persons
0"Harlow"
1"Quinn"
2"Raven"
3"Herrera"
4"Saint"
5"Christopher"
6"Tommy"
7"Morris"
places
0"London"
globalScore0.891
windowScore0.167
61.76% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences85
glossingSentenceCount3
matches
0"looked like teeth in a mortar"
1"liquid that seemed to pulse"
2"looked like moth wings, iridescent and fr"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1252
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences140
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs46
mean27.22
std20.61
cv0.757
sampleLengths
044
169
26
33
457
545
649
72
835
989
1020
112
1234
1329
1444
158
1631
173
1867
1934
2029
218
2237
2316
2445
2544
2618
2710
282
2929
3028
3114
3210
3338
3416
357
3624
379
3825
3944
4020
4129
422
4362
4411
454
96.91% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences126
matches
0"was replaced"
1"been, was"
2"was buried"
84.39% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs173
matches
0"was heading"
1"was trembling"
2"was staring"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences2
totalSentences140
ratio0.014
matches
0"People—if they were people—moved through the throng."
1"The suspect—Tommy—was trembling, his hands on the stall’s edge."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1076
adjectiveStacks0
stackExamples(empty)
adverbCount22
adverbRatio0.020446096654275093
lyAdverbCount4
lyAdverbRatio0.0037174721189591076
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences140
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences140
mean8.94
std5.68
cv0.635
sampleLengths
018
19
25
312
46
524
64
75
87
923
106
111
122
1313
1414
1510
165
1715
185
1912
201
214
2213
2310
2414
256
267
2722
282
2912
304
313
3210
336
3414
3512
3615
3714
387
3912
4015
4120
422
4310
444
459
467
474
484
4912
56.67% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.37857142857142856
totalSentences140
uniqueOpeners53
28.99% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences115
matches
0"Then a cacophony of voices,"
ratio0.009
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount26
totalSentences115
matches
0"Her own footfalls were a"
1"She’d had him for six"
2"He was younger, faster."
3"He vanished down a service"
4"She paused at the top,"
5"Her hand went to her"
6"She flicked on her torch."
7"She rounded a corner and"
8"Her suspect was twenty yards"
9"His face, pale in the"
10"He ducked behind a stall"
11"She felt watched."
12"His voice was a dry"
13"She ignored him, her focus"
14"He was heading for a"
15"Her suspect had reached a"
16"His Saint Christopher medallion glinted"
17"He put a steadying hand"
18"It made no sound as"
19"He rang it once."
ratio0.226
33.91% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount98
totalSentences115
matches
0"The suspect’s heel clipped the"
1"The sound echoed off wet"
2"Detective Harlow Quinn didn’t flinch."
3"Her own footfalls were a"
4"She’d had him for six"
5"He was younger, faster."
6"Fear made them run in"
7"Quinn cut a diagonal across"
8"He vanished down a service"
9"She paused at the top,"
10"The steps descended into a"
11"Her hand went to her"
12"She flicked on her torch."
13"The beam cut a shaky"
14"The air changed halfway down."
15"The damp chill of the"
16"Ozone and old incense."
17"The faint, coppery tang of"
18"A low hum vibrated through"
19"The stairwell bottomed out into"
ratio0.852
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences115
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences46
technicalSentenceCount1
matches
0"The crowd didn’t part so much as it absorbed her, bodies shifting to let her through then closing behind her."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags7
uselessAdditionCount2
matches
0"Herrera said, his voice calm, carrying a faint Spanish lilt"
1"Quinn said, the words leaving her mouth before she could stop them"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount1
fancyTags
0"Herrera whispered (whisper)"
dialogueSentences23
tagDensity0.174
leniency0.348
rawRatio0.25
effectiveRatio0.087
80.2642%