Run: 2026-03-15-01KKS2RRKMHQMD64A1ZNPW0AZS

Run Details

Duration:
19.1s
Cost:
$0.006554
Provider:
Z.AI

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 vaulted a bike rack like it was a garden gate. Quinn's boots hammered wet pavement, each footfall splashing filthy water up her calves. Thirty metres. Closing. He tore left down a narrow alley between a closed kebab shop and a boarded-up charity store. She followed, shoulder clipping the damp brickwork. The smell of bins and stale grease filled her nostrils. "Stop! Metropolitan Police!" He didn't even glance back. Just ran harder. Younger legs. She'd clocked him at maybe early twenties, dark hair plastered to his skull, wearing a leather jacket that had seen better decades. He'd been watching the flat on Brewer Street for three hours before she'd made her approach. Then he'd bolted like a rabbit. The alley spat them out onto a side street. More rain. Headlights swept across the wet tarmac. He dodged a parked taxi and scrambled over the bonnet. Quinn went around, knee screaming in protest. Eighteen years on the force and she still chased suspects on foot like a rookie. DS Morris would have laughed at her. Called her old before her time. The familiar ache of that thought settled in her chest. She shoved it down and ran harder. The suspect was slowing. His breathing ragged, visible in puffs of white when the streetlights caught it. Quinn's lungs burned but she'd run marathons in worse condition. The leather watch on her left wrist caught the glow of a passing bus shelter advertisement. Twenty-three minutes since the chase began. He glanced back. First time. His eyes widened when he saw how close she'd gotten. "Running out of road, mate." He made a decision. Veered sharp right toward a familiar green neon sign. The Raven's Nest. The bar's entrance yawned open, spilling amber light and jazz onto the wet pavement. Quinn followed him in. The bar hit her senses like a wall. Smoke. Whiskey. Old wood. Black-and-white photographs lined the walls alongside yellowed maps that looked centuries old. A handful of patrons scattered across mismatched tables. None of them looked up. None of them looked normal. The suspect was already at the back wall, pulling a bookshelf aside like it weighed nothing. Behind it, a door. He slipped through. "Did you see that?" The bartender, a thick man with a shaved head, shrugged. Polished a glass that didn't need polishing. "See what?" Quinn was already moving. She reached the bookshelf and found the mechanism, a simple latch hidden behind a leather-bound tome. The door opened onto a steep staircase descending into darkness. The smell hit her first. Wet stone. Something coppery. Something else she couldn't name, sweet and rotten at once. She pulled her torch from her jacket pocket and clicked it on. The beam cut through the gloom, illuminating rough brick walls that gave way to older stonework the deeper the stairs went. This wasn't part of the bar's original structure. This was older. Much older. Her radio crackled. "Quinn here." Static. Then silence. The signal couldn't penetrate this far underground. She descended anyway. The stairs spiralled. Seventeen steps. Twenty-three. Thirty-one. She counted automatically, a habit drilled into her during training. The temperature dropped with each step. Her breath misted in the torch beam. The staircase ended at a threshold. Beyond it, a space that shouldn't exist. An abandoned Tube station stretched before her, platforms intact, old advertising posters peeling from the walls. But that's where normality ended. Stalls had been erected on the platforms, covered in faded awnings. Glass jars lined wooden tables, their contents glowing faintly. Other objects caught her torch beam: feathers that shimmered with iridescent light, bones carved with symbols, vials of liquid that seemed to move on their own. The Veil Market. She'd heard whispers. Fragmented intelligence reports that got filed in the drawer marked "unsubstantiated." The same drawer where her partner's case had ended up. Her suspect stood at one of the stalls, arguing with something behind it. Not someone. Something. The figure was short, hunched, wrapped in layers of grey fabric that might have been cloth or might have been skin. Quinn couldn't tell in the dim light. She stepped onto the platform. Her footsteps echoed. Every head in the market turned toward her. Dozens of eyes. Some human. Most not. A woman with silver hair and black sclera tilted her head at Quinn like a bird examining a worm. A man whose face kept shifting, features sliding like wet clay, watched her from beside a pillar. Something large moved in the shadows beyond the stalls, something with too many limbs. And every single one of them stopped what they were doing to stare at the woman standing on the platform in her wet police jacket, holding a torch like it was a weapon. "Police." She held up her warrant card. It felt absurd. "I'm pursuing a suspect. The man in the leather jacket." Silence. Then laughter. It came from everywhere and nowhere, rippling through the market like wind through an empty building. The bartender appeared at her elbow. She hadn't heard him follow. "You shouldn't be here, Detective." "Where's the suspect?" "Somewhere you can't follow." His voice was flat. Clinical. "This isn't your world." "Last time I checked, this was still London." "This is the part of London that doesn't exist on your maps." He gestured at the market. "Bone token gets you in. Nothing gets you out without permission." Quinn's jaw tightened. She spotted her suspect pushing through the crowd on the far platform. He was heading for a tunnel mouth that swallowed the light whole. She moved. Hands grabbed her arms. Cold. Strong. She twisted, training kicking in, and broke free of one grip. Another took its place. The silver-haired woman had crossed the platform in the space of a heartbeat. "Let go of me." "You don't understand." The woman's voice was layered, like two people speaking at once. "He's not yours to take." "He's a suspect in a murder investigation. A woman is dead." "Many women are dead." The woman smiled. Too many teeth. "Some of them by his hand, yes. But that's not why you're really here, is it, Harlow Quinn?" The use of her full name stopped her cold. "You want to know what happened to DS Morris. What really happened." The woman leaned closer. Her breath smelled of roses and rot. "The answer isn't on this platform. It's down that tunnel. With him." The suspect had paused at the tunnel mouth. He turned back. Even at this distance, Quinn could see his expression. Not fear. Pity. Then he mouthed a single word. *Don't.* But the bartender was already speaking, his hand closing around her wrist. "She wants to go after him. Let her." "Silas, the agreement-" "Applies to those who wander in by accident." His grip tightened. "She chased a suspect through our door. That makes this official business." He released her. "The Market owes a favour to the Metropolitan Police. An old debt. Consider it called in." The silver-haired woman's smile vanished. She stepped back. "Your funeral." Quinn didn't wait for permission twice. She crossed the platform, shoving past a creature made entirely of smoke and mirrors, ducking under something that might have been a chandelier or might have been a cocoon. The tunnel mouth grew larger. Darker. Behind her, the market sounds faded to nothing. Ahead, footsteps. Her suspect. Waiting. She stepped into the tunnel. The darkness swallowed her torch beam whole.
created_at"2026-03-15T15:45:21.034Z" 3/15/2026, 3:45:21 PM
model"z-ai/glm-5-turbo-20260315"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1897
moderation_latency(null)
generation_time18933
tokens_prompt4663
tokens_completion2164
native_tokens_prompt4193
native_tokens_completion1796
native_tokens_completion_images(null)
native_tokens_reasoning175
native_tokens_cached4191
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"
usage0.006553792
router(null)
provider_responses
0
endpoint_id"9ce3b132-3a17-4fea-8092-0e8e519ed32b"
id"202603152345218fffee403e0f4d82"
is_byokfalse
latency1897
model_permaslug"z-ai/glm-5-turbo-20260315"
provider_name"Z.AI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer(null)
api_type"completions"
id"gen-1773589521-nv583BwetjHSpc8TZeGm"
upstream_id"202603152345218fffee403e0f4d82"
total_cost0.006553792
cache_discount0.00402336
upstream_inference_cost0
provider_name"Z.AI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags8
adverbTagCount0
adverbTags(empty)
dialogueSentences29
tagDensity0.276
leniency0.552
rawRatio0
effectiveRatio0
91.91% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1236
totalAiIsmAdverbs2
found
0
adverb"really"
count2
highlights
0"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)
51.46% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1236
totalAiIsms12
found
0
word"footfall"
count1
1
word"familiar"
count2
2
word"gloom"
count1
3
word"structure"
count1
4
word"silence"
count2
5
word"shimmered"
count1
6
word"fragmented"
count1
7
word"footsteps"
count2
8
word"echoed"
count1
highlights
0"footfall"
1"familiar"
2"gloom"
3"structure"
4"silence"
5"shimmered"
6"fragmented"
7"footsteps"
8"echoed"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"eyes widened/narrowed"
count1
highlights
0"eyes widened"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences146
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences146
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)
analyzedSentences166
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen33
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords1
totalWords1236
ratio0.001
matches
0"Don't."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions19
wordCount1043
uniqueNames10
maxNameDensity0.96
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Brewer1
Street1
Morris1
Raven1
Nest1
Tube1
Veil1
Market1
Quinn10
Clinical1
persons
0"Morris"
1"Raven"
2"Quinn"
places
0"Brewer"
1"Street"
2"Market"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences73
glossingSentenceCount1
matches
0"liquid that seemed to move on their own"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1236
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences166
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs62
mean19.94
std16.18
cv0.812
sampleLengths
028
134
23
354
434
545
649
715
85
930
104
1142
1223
134
1417
152
1630
1719
1846
193
202
2110
2233
2313
2467
2527
2644
2716
287
2950
3033
3120
3219
3311
345
353
3613
378
3828
3927
402
4134
424
4319
4411
4528
469
4735
4823
496
98.05% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences146
matches
0"been erected"
1"got filed"
2"was layered"
20.79% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount5
totalVerbs186
matches
0"was slowing"
1"was already moving"
2"were doing"
3"was heading"
4"was already speaking"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences166
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1052
adjectiveStacks0
stackExamples(empty)
adverbCount35
adverbRatio0.03326996197718631
lyAdverbCount4
lyAdverbRatio0.0038022813688212928
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences166
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences166
mean7.45
std5.93
cv0.797
sampleLengths
012
113
22
31
417
57
610
73
85
93
102
1122
1216
136
149
152
166
1710
187
1915
207
216
2210
237
244
2513
2610
2716
286
293
302
3110
325
334
349
353
3614
374
388
391
401
412
4212
438
445
455
4616
474
483
494
70.88% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats9
diversityRatio0.4578313253012048
totalSentences166
uniqueOpeners76
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount4
totalSentences113
matches
0"Just ran harder."
1"Then he'd bolted like a"
2"Too many teeth."
3"Then he mouthed a single"
ratio0.035
85.49% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount38
totalSentences113
matches
0"He tore left down a"
1"She followed, shoulder clipping the"
2"He didn't even glance back."
3"She'd clocked him at maybe"
4"He'd been watching the flat"
5"He dodged a parked taxi"
6"She shoved it down and"
7"His breathing ragged, visible in"
8"He glanced back."
9"His eyes widened when he"
10"He made a decision."
11"He slipped through."
12"She reached the bookshelf and"
13"She pulled her torch from"
14"Her radio crackled."
15"She descended anyway."
16"She counted automatically, a habit"
17"Her breath misted in the"
18"She'd heard whispers."
19"Her suspect stood at one"
ratio0.336
44.07% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount94
totalSentences113
matches
0"The suspect vaulted a bike"
1"Quinn's boots hammered wet pavement,"
2"He tore left down a"
3"She followed, shoulder clipping the"
4"The smell of bins and"
5"He didn't even glance back."
6"She'd clocked him at maybe"
7"He'd been watching the flat"
8"The alley spat them out"
9"Headlights swept across the wet"
10"He dodged a parked taxi"
11"Quinn went around, knee screaming"
12"DS Morris would have laughed"
13"The familiar ache of that"
14"She shoved it down and"
15"The suspect was slowing."
16"His breathing ragged, visible in"
17"Quinn's lungs burned but she'd"
18"The leather watch on her"
19"He glanced back."
ratio0.832
44.25% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences113
matches
0"Even at this distance, Quinn"
ratio0.009
51.28% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences39
technicalSentenceCount5
matches
0"She'd clocked him at maybe early twenties, dark hair plastered to his skull, wearing a leather jacket that had seen better decades."
1"Black-and-white photographs lined the walls alongside yellowed maps that looked centuries old."
2"Other objects caught her torch beam: feathers that shimmered with iridescent light, bones carved with symbols, vials of liquid that seemed to move on their own."
3"But the bartender was already speaking, his hand closing around her wrist."
4"She crossed the platform, shoving past a creature made entirely of smoke and mirrors, ducking under something that might have been a chandelier or might have be…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags8
uselessAdditionCount0
matches(empty)
81.03% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount2
fancyTags
0"Fragmented intelligence reports (fragmented intelligence report)"
1"people speaking (speak)"
dialogueSentences29
tagDensity0.069
leniency0.138
rawRatio1
effectiveRatio0.138
87.9738%