Run: 2026-06-01-01KT1GFB5T7MS2XYX0XRRPRR2K

Run Details

Duration:
1m 59s
Cost:
$0.003345
Provider:
Minimax

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 was fast. Faster than the file suggested. Quinn's boots struck wet cobblestone as she cut through the alley off Brewer Street, her shoulder slamming into a stack of brewery crates as she rounded the corner. The crash echoed off the narrow walls. Somewhere above, a cat yowled from a fire escape. Rain hammered the metal awnings, turning the alley into a clattering drum. She'd clocked the woman three blocks back, leaving the address Quinn had been surveilling for six days. A known associate of the Northbridge lot. Not the target herself, but close enough to follow. Close enough to matter. The woman ran like someone who'd run before. Low centre of gravity, smooth footwork, never breaking stride on the slicked granite. She wore a dark coat, collar up, and her hair was plastered to her skull. She'd glanced back twice. Both times, Quinn saw the calculation in her eyes. Not panic. Problem-solving. Quinn reached the end of the alley and stopped. Breathing hard. Her leather watch was soaked through, the face fogged. She wiped it with her thumb, read the time. Three minutes since Brewer Street. The woman had at least a thirty-second lead. The street ahead split three ways. A main road, a service lane, and a set of iron steps descending into what looked like a disused Tube entrance. Old signage, scratched and half-rotted. The kind of place tourists avoided and locals forgot. Quinn listened. The main road carried the usual Soho noise, late taxis, a kebab shop radio, someone laughing. The service lane was quiet. The iron steps were silent except for water dripping down them. She took the steps. The descent was steep, the railings cold through her gloves. The walls were tiled, the old London Underground pattern, cream and oxblood, the colours bled out by years of grime. A single bulb buzzed at the bottom, swaying slightly in a draft Quinn couldn't feel. The platform stretched into darkness both directions. No train. No benches. No graffiti. That was the wrong detail. Graffiti covered every abandoned station in London. Someone had cleaned this one. Recently. Quinn's hand moved to her service weapon by instinct. She didn't draw. Not yet. A sound. A soft click, like a lock tumbler. She moved along the platform, following the sound, her feet careful on the wet tile. The light ended. She let her eyes adjust. The darkness ahead wasn't empty. There was a shape. A door, set into the tiled wall where no door had any right to be. Old wood. Brass handle. It was closing. Quinn lunged. Her fingers caught the edge. Wood ground against wood. A gap of three inches, then two, then one. She wedged her boot against the frame and pulled, every muscle in her back screaming, and the door shuddered to a stop. Beyond it, the air changed. Warmer. Drier. Carrying a smell she couldn't place, like sandalwood and something older, something that made the back of her throat tighten. Light came from below, amber and unsteady, and with it the murmur of voices, many voices, talking in low tones like market traders. She pulled the door open another inch and peered through. Stone steps descended into a vault. Long, arched, lit by hanging lanterns that gave off no smoke. Stalls lined both sides of a central walkway, draped in heavy cloth, laden with goods she couldn't name at this distance. Jars. Bundles of dried things. Books bound in materials she chose not to examine. People moved between the stalls, hooded, masked, ordinary, the lot of them, and none of them looked up. The suspect was halfway down the steps, fifteen feet below. She'd stopped. She'd turned. And she was watching Quinn with an expression that wasn't fear. It was pity. "You shouldn't be here." The voice came from behind Quinn. She spun, hand finally drawing the weapon, and found a man standing in the doorway of a small office cut into the platform wall. Mid-thirties. Olive skin, dark curly hair plastered to his forehead by the rain. A scar ran along his left forearm, visible because his sleeve was rolled back. He wore a worn leather satchel and a medallion around his neck that caught the amber light from below. "Step away from the door," Quinn said. "You're Detective Quinn." His tone was calm. The calm of someone who'd made peace with something a long time ago. "Harlow. Eighteen years. Currently suspended pending investigation into the death of your partner. DS Morris. Three years ago this November." Quinn's grip on the weapon didn't waver, but something behind her ribs tightened. "Who the hell are you?" "Tommy. I'm a friend." He raised both hands, palms out. Slowly. "Or the closest thing to one you're going to find down here. I keep people alive. That's what I do." "People." "And others." He nodded toward the steps. "You saw her run. You chased her. Good instincts, wrong target. She's a courier. She runs messages between the Market and the surface. Whatever you think she's involved in, she isn't your suspect." "And you know my suspect." Silence. The lanterns below flickered. Voices murmured, indifferent, like a heartbeat beneath a conversation. "No," Tommy said. "I know the people who know your suspect. And I know what happens to coppers who walk into that market without a token." "Token." He reached into his satchel and produced a small object. Bone, perhaps. Carved into a shape that hurt to look at directly. He held it out, not toward Quinn, but toward the threshold of the door. It caught the light and seemed to drink it. "You don't have one. If you go down there, you're not a detective anymore. You're not a cop. You're just a woman in a place where the rules aren't the ones you were trained for. And there are people down there who've been waiting a long time to meet someone like you." "Someone like me." "Someone who asks questions about the things that don't make sense. DS Morris. The Northbridge fires. The Holloway disappearances." He let the names land. "You ever get an answer that satisfied you, Detective?" Quinn didn't answer. Her jaw tightened. Her pulse thudded against the worn leather of her watch strap. Below, the courier had stopped descending. She stood on a step, half-turned, waiting. The pity in her eyes had shifted into something more dangerous. Anticipation. "She's not going to wait all night," Tommy said. "The Market closes when the bell rings. And once it closes, the entrance moves. Somewhere else. You won't find it again for a month." "And if I go down?" "Then you find out what really happened to your partner. And you don't come back the same. Those are the only two options." Quinn looked past him. The steps. The vault. The amber light. The murmur of voices that had no business existing beneath a London street. Three years of cold cases. Three years of closed files and unhelpful coroners and witnesses who forgot what they'd seen overnight. Three years of watching the world not add up and being told, professionally, to stop asking. She thought of DS Morris. The way he'd laughed. The way he hadn't laughed for the last three months of his life. The way he'd told her, the night before, that something was watching him. Something that wasn't human. She'd told him he was overworked. She'd never told him she was sorry. The bell rang somewhere below. A single clear note that shouldn't have been audible through stone and distance, but was. The courier turned and walked down into the light. The market stirred. Voices rose. Tommy held out the bone token. "Last chance, Detective." Quinn took it.
created_at"2026-06-01T11:52:58.823Z" 6/1/2026, 11:52:58 AM
model"minimax/minimax-m3-20260531"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1230
moderation_latency(null)
generation_time119066
tokens_prompt4663
tokens_completion3074
native_tokens_prompt4254
native_tokens_completion2572
native_tokens_completion_images(null)
native_tokens_reasoning1123
native_tokens_cached4240
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"stop"
service_tier(null)
usage0.003345
router(null)
provider_responses
0
endpoint_id"6851b352-a7e2-45ad-a69e-67ed1208a416"
id"066ca59a7857a5bdb46a2a531ebc118f"
is_byokfalse
latency1229
model_permaslug"minimax/minimax-m3-20260531"
provider_name"Minimax"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer(null)
request_id"req-1780314778-TTtnslOsOjf0DHh2JiUS"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1780314778-eWBPfT39fNLWEXVFhjrq"
upstream_id"066ca59a7857a5bdb46a2a531ebc118f"
total_cost0.003345
cache_discount0.0020352
upstream_inference_cost0
provider_name"Minimax"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags6
adverbTagCount0
adverbTags(empty)
dialogueSentences23
tagDensity0.261
leniency0.522
rawRatio0
effectiveRatio0
88.34% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1286
totalAiIsmAdverbs3
found
0
adverb"slightly"
count1
1
adverb"slowly"
count1
2
adverb"really"
count1
highlights
0"slightly"
1"slowly"
2"really"
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)
80.56% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1286
totalAiIsms5
found
0
word"echoed"
count1
1
word"silence"
count1
2
word"flickered"
count1
3
word"pulse"
count1
4
word"anticipation"
count1
highlights
0"echoed"
1"silence"
2"flickered"
3"pulse"
4"anticipation"
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
narrationSentences133
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount1
narrationSentences133
filterMatches
0"watch"
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences149
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen52
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1286
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions10
unquotedAttributions0
matches(empty)
66.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions37
wordCount1014
uniqueNames13
maxNameDensity1.58
worstName"Quinn"
maxWindowNameDensity3
worstWindowName"Quinn"
discoveredNames
Brewer2
Street2
Quinn16
Northbridge1
Tube1
Soho1
London3
Underground1
Slowly1
Silence1
Morris1
Three4
Tommy3
persons
0"Quinn"
1"Morris"
2"Tommy"
places
0"Brewer"
1"Street"
2"Soho"
3"London"
globalScore0.711
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences68
glossingSentenceCount1
matches
0"looked like a disused Tube entrance"
44.48% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches2
per1kWords1.555
wordCount1286
matches
0"Not the target herself, but close enough to follow"
1"not toward Quinn, but toward the threshold of the door"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences149
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs48
mean26.79
std21.62
cv0.807
sampleLengths
09
156
237
352
442
541
634
74
876
914
1063
112
1240
1350
1410
1570
1625
173
184
196
2070
217
2240
2318
2431
251
2640
275
2814
2926
301
3145
3252
333
3433
3517
3625
3733
385
3923
4061
4139
426
437
4434
456
463
473
92.07% Passive voice overuse
Target: ≤2% passive sentences
passiveCount5
totalSentences133
matches
0"was plastered"
1"were tiled"
2"was rolled"
3"being told"
4"was overworked"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs175
matches
0"was watching"
1"was watching"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences149
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1019
adjectiveStacks0
stackExamples(empty)
adverbCount24
adverbRatio0.023552502453385672
lyAdverbCount7
lyAdverbRatio0.0068694798822374874
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences149
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences149
mean8.63
std7.49
cv0.867
sampleLengths
04
15
228
37
49
512
617
77
89
94
108
1113
1215
134
149
152
161
179
182
199
209
215
228
236
2421
255
269
272
2816
295
3011
314
3210
3320
3415
357
362
372
382
395
407
415
421
439
443
452
462
477
4815
493
52.57% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats20
diversityRatio0.3959731543624161
totalSentences149
uniqueOpeners59
32.05% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences104
matches
0"Somewhere above, a cat yowled"
ratio0.01
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount29
totalSentences104
matches
0"She'd clocked the woman three"
1"She wore a dark coat,"
2"She'd glanced back twice."
3"Her leather watch was soaked"
4"She wiped it with her"
5"She took the steps."
6"She didn't draw."
7"She moved along the platform,"
8"She let her eyes adjust."
9"It was closing."
10"Her fingers caught the edge."
11"She wedged her boot against"
12"She pulled the door open"
13"It was pity."
14"She spun, hand finally drawing"
15"He wore a worn leather"
16"His tone was calm"
17"He raised both hands, palms"
18"He nodded toward the steps"
19"He reached into his satchel"
ratio0.279
51.35% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount85
totalSentences104
matches
0"The suspect was fast."
1"Quinn's boots struck wet cobblestone"
2"The crash echoed off the"
3"She'd clocked the woman three"
4"A known associate of the"
5"The woman ran like someone"
6"She wore a dark coat,"
7"She'd glanced back twice."
8"Both times, Quinn saw the"
9"Quinn reached the end of"
10"Her leather watch was soaked"
11"She wiped it with her"
12"The woman had at least"
13"The street ahead split three"
14"A main road, a service"
15"The kind of place tourists"
16"The main road carried the"
17"The service lane was quiet."
18"The iron steps were silent"
19"She took the steps."
ratio0.817
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences104
matches(empty)
ratio0
69.60% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences39
technicalSentenceCount4
matches
0"Carrying a smell she couldn't place, like sandalwood and something older, something that made the back of her throat tighten."
1"He wore a worn leather satchel and a medallion around his neck that caught the amber light from below."
2"Three years of closed files and unhelpful coroners and witnesses who forgot what they'd seen overnight."
3"A single clear note that shouldn't have been audible through stone and distance, but was."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags6
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount0
fancyTags(empty)
dialogueSentences23
tagDensity0.13
leniency0.261
rawRatio0
effectiveRatio0
85.9227%