Run: 2026-02-19-01KHVP2BG3E9H0X8GB2M3X9XS3

Run Details

Duration:
2m 44s
Cost:
$0.153342
Provider:
Google AI Studio

Model input

System
You are an expert and award-winning novel writer in the dark Literary Fiction 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="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</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> </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 literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. 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
"You always did leave a trail of messes." The clipped Welsh accent sliced through the low murmur of the room. I froze. Hot garlic and ginger burned my nostrils. The paper delivery bag from Golden Empress slipped off my shoulder, hitting the sticky wooden floor with a heavy thud. "I ordered the crispy duck," Eva said. "I assume it got cold on the walk over." "I deliver to paying customers." My throat felt full of sand. "Not ghosts." Her heels went click-clack against the floorboards as she stepped fully inside. The Raven's Nest smelled of stale ale, spilled bourbon, and old rain. Silas paused his wiping of the mahogany counter, his hazel eyes darting from me to the woman standing beneath the distinctive green neon sign. The harsh emerald light painted sharp shadows across Eva's cheekbones. She wore a beautiful sharp modern black Italian silk suit. A far cry from the scuffed denim and band tees of our Cardiff days. She looked wealthy. She looked dangerous. "Eva." I kicked the delivery bag aside. "Rory." She claimed a stool. "You look well. The refugee aesthetic suits you." "Bourbon?" Silas asked. His silver signet ring clinked against a heavy crystal tumbler. "Neat." Eva did not look at him. Her gaze remained fixed on my left wrist. I pulled my sleeve down over the small crescent-shaped scar. "Five years." I leaned against the heavy wooden pillar near the booth. "You told me to run." "I told you to leave him." She took the tumbler from Silas. "I never told you to disappear." "Same concept." "Not to the people left behind." "Evan had a temper." "Evan had money." Eva traced the rim of her glass. "Money demands answers." Silas leaned against the back counter. His slight limp from an old knee injury barely showed, but he kept his weight on his good leg. A retired intelligence operative knew how to blend into the shadows of his own bar. The walls around him displayed old yellowed navigational maps and framed black-and-white photographs of forgotten cities. He picked up another glass, breathing quietly. He watched the entrance. He read the room. "I left my whole life behind." "You left your rent unpaid." Eva took a sip. "You left a furious man with a smashed ego. And you left me to pack up your flat." "You knew what he did to me." "We all knew his limits." Eva traced a water ring on the mahogany counter. "You pushed them." "He broke three of my ribs over a burnt dinner." "You poured boiling water on his lap." "He blocked the exit." I touched my sleeve. The old memory felt distant, replaced by much fresher wounds. "I defended myself." "And I stepped into the void you created." Her left hand moved to the counter. A massive diamond caught the dim light. The stone looked heavy enough to drown a person. "You married him." "Someone had to placate him." "You sold yourself, Eva." "We all endure things for security." She adjusted her clean collar. "You chose a dingy flat above a pub in Soho. I chose a massive Georgian estate in Monmouthshire." "You chose a monster." "I chose survival." The muscles in her jaw tightened. "And it worked. Until last month." "I haven't contacted anyone." "You paid for your mother's headstone repairs." Eva opened a sleek leather purse. "Cash up front to the mason, yes. But you paid the cemetery fees with the old routing number." "I closed that account years ago." "Evan kept it open. He deposited twenty pounds a month just to watch the ledger." She slid a folded piece of paper across the wood. A bank statement. "He woke up from a bender last week. He found the flag on the account. He knows you frequent this street." "We used to share a tiny room in halls," I said, staring at the paper. "We subsisted on cheap cider and toast. We were happy." "We were naive." Eva scoffed. "Happiness does not pay the heating bill. Happiness does not buy off the men Evan owes money to." "He owes money?" "He owes everyone." She tapped her manicured nails against the glass. "You broke his nose before you ran. You took his pride. His criminal associates saw weakness. They raised their interest rates." "Let them break his legs." "They target family, Rory." Eva smoothed out the wrinkles in her skirt. "They visited his mother in Swansea. They burned her car." "Karma." "They threatened to burn the house next." She looked straight into my eyes. "He needs capital to pay them off. High-value collateral." "I own nothing." "You are the collateral." "Human trafficking?" Silas asked. His voice rumbled low, a quiet mountain of authority. He dropped the rag. "Debt forgiveness," Eva corrected him. "A rich man in Surrey appreciates spirited women. Evan brokers the deal. The debt disappears." "Sickening." I felt my stomach twist. "You knew about this deal and you came anyway." "I drove the car." "Silas." I looked back at the older man. "Lock the door." "Already done, Laila." Silas used my alias. He reached under the counter. A heavy metallic click echoed through the quiet bar. He moved toward the front window, his gait uneven. Peering through the blinds, he scanned the dark street. "Who is your bodyguard?" Eva smirked. "Another stray?" "A friend." I stepped closer to her. "Why are you here, Eva? Point blank." "He promised to clear his debts if I bring you to him." Eva reached into her purse again. "He wants his favorite punchbag back." She placed a heavy object on the bar. A beautiful cold heavy black German steel pistol. I stared at the weapon. A dark crimson smear coated the grip. Copper stung my nostrils. Blood. Recent. "You shot someone." "I took it from his driver." Tears welled in her eyes, sharp and bitter. "He ruined my life, Rory. He isolates me." "By serving me up upon a silver platter." The harsh overhead light caught the edge of her jaw. The thick layer of foundation ended abruptly near her ear. A dark purple shadow lurked beneath the makeup. Deep and fresh. "He hit you today." Eva touched her cheek. "He made me understand the stakes." "And you chose him again." "I chose me." She leveled the gun at my chest. Silas flicked a switch on the wall. The distinctive green neon sign outside died. The bar plunged into near darkness. Only the amber glow of the streetlamps filtered through the large front windows. "Put the gun down, lass." Silas spoke from the shadows near the old maps. "You do not want to discharge a firearm in my establishment." "Stay back, old man." Eva kept her eyes on me. Her hand shook. A mix of fear and adrenaline. "Look at yourself." I kept my voice steady, channeling Silas' calm demeanor. "Eva Ellis. The girl who wanted to teach primary school children." "She died in Cardiff." Eva gripped the gun tighter. "Get your coat." "There are people you can call." "The system protects him. Evan bought the local inspector a holiday home in Spain." "This system protects me." I nodded to Silas. Silas stepped forward. His silver signet ring caught the amber light. "I run a quiet place here. I serve good drinks. I keep bad people out." "Step aside." Eva pointed the gun at him. "Your safety catch is still engaged." Silas crossed his arms. Eva glanced down at the pistol. A fatal error. I grabbed her wrist, twisting the joint outward. The pistol clattered onto the sticky wooden floor. Silas stepped forward, kicking the weapon into the dark corner of the room. Eva collapsed onto the stool and wept. "It was a trick," she sobbed into her hands. "He knew you would fight back." "Explain." I stepped away, breathing hard. My heart hammered against my ribs. "He sent me to confirm the address." Eva wiped the smeared makeup from her bruised face. "He followed my phone." "He gave you a head start." Silas deduced. "Ten minutes." She looked up, her eyes wide with terror. "To fetch you out the easy way." "And if you failed?" "He brought the loan sharks." Eva grabbed her glass and downed the rest of the bourbon. "He sold us both to clear his ledger." Heavy engines roared to life at the end of the street. Bright headlights flooded through the front windows, casting long, distorted shadows across the room. Tires screeched against the wet pavement. Heavy boots pounded the concrete outside in a rapid pitter-patter. "Into the back room." Silas pulled a heavy iron lever hidden behind the cash register. The large oak bookshelf against the back wall groaned, swinging inward to reveal a dark clandestine corridor. "Take her." I pushed Eva toward the hidden room. The heavy wooden front door splintered inward, ripping off its iron hinges. Metal groaned. Automatic gunfire shattered the silence, destroying the front windows and raining jagged glass over the bar.
created_at"2026-02-19T19:29:43.282Z" 2/19/2026, 7:29:43 PM
model"google/gemini-3.1-pro-preview-20260219"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency3318
moderation_latency(null)
generation_time163802
tokens_prompt4618
tokens_completion6486
native_tokens_prompt4497
native_tokens_completion12029
native_tokens_completion_images0
native_tokens_reasoning10001
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"
usage0.153342
router(null)
provider_responses
0
endpoint_id"2abf5677-0826-45d9-8470-3d62c31d54a1"
is_byokfalse
latency3318
model_permaslug"google/gemini-3.1-pro-preview-20260219"
provider_name"Google AI Studio"
status200
api_type"completions"
id"gen-1771529383-vsmB7bIMVIbhryX4kDF7"
upstream_id(null)
total_cost0.153342
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags48
adverbTagCount1
adverbTags
0"I stepped away [away]"
dialogueSentences108
tagDensity0.444
leniency0.889
rawRatio0.021
effectiveRatio0.019
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1497
totalAiIsmAdverbs0
found(empty)
highlights(empty)
100.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
59.92% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1497
totalAiIsms12
found
0
word"silk"
count1
1
word"crystal"
count1
2
word"traced"
count2
3
word"weight"
count1
4
word"stomach"
count1
5
word"echoed"
count1
6
word"scanned"
count1
7
word"flicked"
count1
8
word"clandestine"
count1
9
word"shattered"
count1
10
word"silence"
count1
highlights
0"silk"
1"crystal"
2"traced"
3"weight"
4"stomach"
5"echoed"
6"scanned"
7"flicked"
8"clandestine"
9"shattered"
10"silence"
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
emotionTells1
narrationSentences114
matches
0"e with terror"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences114
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences174
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen25
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1491
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions16
unquotedAttributions0
matches(empty)
25.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions45
wordCount840
uniqueNames11
maxNameDensity2.5
worstName"Eva"
maxWindowNameDensity4
worstWindowName"Eva"
discoveredNames
Welsh1
Golden1
Empress1
Raven1
Nest1
Eva21
Italian1
Cardiff1
Silas14
German1
Heavy2
persons
0"Empress"
1"Raven"
2"Nest"
3"Eva"
4"Silas"
places
0"Golden"
1"Cardiff"
globalScore0.25
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences77
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1491
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences174
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs91
mean16.38
std13.78
cv0.841
sampleLengths
020
129
216
313
488
57
613
713
815
910
1017
1118
122
136
144
1513
1671
176
1827
197
2017
2110
227
2321
2431
253
265
274
2829
294
3015
314
3231
336
3449
3525
3623
373
3832
395
4022
411
4222
433
444
4517
4620
4715
484
4911
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences114
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs138
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences174
ratio0
matches(empty)
76.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount699
adjectiveStacks4
stackExamples
0"beautiful sharp modern black Italian"
1"small crescent-shaped scar."
2"old yellowed navigational maps"
3"beautiful cold heavy black German"
adverbCount11
adverbRatio0.015736766809728183
lyAdverbCount5
lyAdverbRatio0.00715307582260372
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences174
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences174
mean8.57
std4.85
cv0.566
sampleLengths
020
12
27
320
47
59
611
72
812
912
1024
1110
1210
1314
143
153
167
175
188
193
2010
217
228
2310
2412
255
2612
276
282
296
304
3110
323
336
3419
3515
3616
377
384
394
406
419
4218
437
4414
453
4610
477
488
4910
47.89% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats20
diversityRatio0.3563218390804598
totalSentences174
uniqueOpeners62
32.05% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences104
matches
0"Only the amber glow of"
ratio0.01
54.62% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount43
totalSentences104
matches
0"My throat felt full of"
1"Her heels went click-clack against"
2"She wore a beautiful sharp"
3"She looked wealthy."
4"She looked dangerous."
5"I kicked the delivery bag"
6"She claimed a stool"
7"His silver signet ring clinked"
8"Her gaze remained fixed on"
9"I pulled my sleeve down"
10"I leaned against the heavy"
11"She took the tumbler from"
12"His slight limp from an"
13"He picked up another glass,"
14"He watched the entrance."
15"He read the room."
16"I touched my sleeve"
17"Her left hand moved to"
18"She adjusted her clean collar"
19"She slid a folded piece"
ratio0.413
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount96
totalSentences104
matches
0"The clipped Welsh accent sliced"
1"The paper delivery bag from"
2"My throat felt full of"
3"Her heels went click-clack against"
4"The Raven's Nest smelled of"
5"Silas paused his wiping of"
6"The harsh emerald light painted"
7"She wore a beautiful sharp"
8"A far cry from the"
9"She looked wealthy."
10"She looked dangerous."
11"I kicked the delivery bag"
12"She claimed a stool"
13"His silver signet ring clinked"
14"Eva did not look at"
15"Her gaze remained fixed on"
16"I pulled my sleeve down"
17"I leaned against the heavy"
18"She took the tumbler from"
19"Eva traced the rim of"
ratio0.923
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences104
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences23
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags48
uselessAdditionCount1
matches
0"She looked up, her eyes wide with terror"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount5
fancyTags
0"She claimed (claim)"
1"Eva corrected (correct)"
2"Silas spoke (speak)"
3"she sobbed (sob)"
4"Silas deduced (deduce)"
dialogueSentences108
tagDensity0.083
leniency0.167
rawRatio0.556
effectiveRatio0.093
83.1826%