Run: 2026-02-19-01KHTXDB4GAXMEDXHRJXY88TT0

Run Details

Duration:
48.7s
Cost:
$0.007594
Provider:
SiliconFlow

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
The whisky glass hit the bar hard enough to crack the ice inside. "Another." I glanced at the woman nursing her third drink in forty minutes. Dark roots showing beneath a bleached blonde that had long since faded to brass. Nails bitten to the quick. The kind of desperate that wore exhaustion like a second skin. "You're cut off after this one." Her head snapped toward me. Recognition flickered behind glassy eyes, then something harder settled in its place. "Rory?" The voice was wrong. Too thin. Too sharp. But I knew that face, even with the extra years carved into it. Even with the once-copper hair now dishwater blonde, the cheekbones more prominent than they'd been at nineteen. "Melissa." She laughed. The sound scraped like a broken drawer. "Seven years and that's all you've got? 'Melissa'?" I slid the whisky across the bar. Silas had stepped out for supplies, leaving me to watch the evening crowd. The Raven's Nest rarely got busy before nine, and tonight was no exception. Three regulars. Two tourists who'd wandered in looking for somewhere quieter. And now this. "What are you doing in London?" "Existing." She threw back the drink like it was water. "Same as everyone else." We'd shared a flat in second year. Melissa Chen, law student, top of our cohort. Her father was a QC, her mother a professor at LSE. She'd been destined for greatness. We'd all been destined for something, back then. "Last I heard, you'd landed a training contract at Clifford Chance." "Two years ago, I did." Her finger traced the rim of the empty glass. "Corporate law. Mergers and acquisitions. Seventy-hour weeks. Corner office by thirty, they said." "Sounds like success." "Sounds like." She caught the bartender's eye, then mine. "Vodka. Whatever's cheap." I didn't move. "Come on, Rory. We were friends once." "Were we?" The question hung between us. Melissa's jaw tightened. In the dim light of the bar, with its old maps and black-and-white photographs of a London that no longer existed, she looked like a ghost haunting her own life. "Fair point." She pulled out her phone, frowned at the cracked screen, and typed something with her thumb. "You always were the honest one. Brutally so, Eva used to say." Eva. My chest tightened at the name. My childhood friend. The one who'd pulled me out of Cardiff when staying became impossible. The one who'd found me this job, this flat, this life. "How is Eva?" "You'd have to ask her yourself." "When's the last time you spoke?" "Three weeks. Maybe four." I busied myself wiping down the bar. "She's been busy." "She's getting married." My hands stied. "What?" "Next spring. Some investment banker. She invited me to the engagement party last month, but I..." Melissa gestured vaguely at herself, at the bar, at whatever wreckage she'd brought in with her. "Didn't seem appropriate." I thought about the missed calls on my phone. The texts I'd let pile up. Eva reaching out, and me too caught up in my own survival to respond. "She didn't tell me." "Maybe she tried." Melissa's gaze held mine. "Maybe some of us aren't worth reaching for anymore." The words landed harder than they should have. I'd built walls since Cardiff. Good walls. Necessary walls. But every now and then, something slipped through. "What happened to you, Melissa?" She smiled, and it transformed her face into something almost beautiful. Almost like the girl I'd known. "What happened to any of us? Life. Choices. The slow grind of becoming someone you don't recognise in the mirror." "That's not an answer." "No." She pushed the empty glass away. "It isn't." Silence stretched between us. The tourists left, laughing about something on their phones. One of the regulars ordered another pint. I pulled it without thinking, muscle memory taking over. "Remember Evan?" My stomach dropped. "I remember him." "Of course you do." Melissa's voice softened. "I should have done something. We all should have. But we were young, and scared, and he was so..." She shook her head. "You disappeared, Rory. One day you were there, and the next you'd vanished. Eva told me later what happened. What he did." "I don't want to talk about Evan." "I know. But I need to say this." She met my eyes, and for the first time that evening, I saw clarity there. Sober clarity, the kind that comes from months of therapy or a lifetime of regret. "I saw him last year. At a legal conference. He's a partner now. Married. His wife is pregnant." The information hit me like a physical blow. I gripped the bar's edge. "He didn't recognise me," Melissa continued. "Or maybe he pretended not to. I watched him work the room, charming everyone, and I thought about you. About how we let you carry that alone." "We?" "The flatmates. The friends. The people who noticed the bruises and said nothing." Her voice cracked. "I was so worried about my training contract, my future, my precious career. And you were fighting for your life." I swallowed hard. The past pressed against my throat, choking off words I'd never learned to say. "Why are you telling me this?" "Because I'm dying." The bar seemed to contract around us. "What?" "Liver failure. Three years of drinking like this, it turns out, has consequences." She said it matter-of-factly, like discussing the weather. "I have maybe six months. The doctors were very precise about it. Very sympathetic. Very useless." "Melissa—" "I came to London to find you. To apologise. To..." She laughed, that broken sound again. "I don't know what. Make amends? Clear my conscience before the end?" "You came to find me?" "Eva gave me your address. After I told her. She cried for an hour, I think. Said you'd want to know." Melissa studied my face. "Do you? Want to know, I mean. About any of it?" I thought about the life I'd built here. The flat above the bar. The delivery runs for Yu-Fei. Silas teaching me to read people, to survive, to stay three steps ahead of the shadows that had chased me from Cardiff. The careful distance I kept from everyone and everything. "I don't know," I said honestly. Melissa nodded, as if she'd expected nothing less. "Fair enough." She stood, swaying only slightly. "For what it's worth, Rory, I'm glad you got out. I'm glad you built something here. Even if I can't be part of it." "You're not staying?" "What's the point?" She reached into her pocket and pulled out a card. Slid it across the bar with a hand that trembled. "My number. In case you want to... I don't know. Talk. Before." She turned toward the door, and I watched her go. Watched the way she carried herself, hunched against a weight that had nothing to do with the bag on her shoulder. The green neon sign outside cast her shadow long against the pavement. The door swung shut behind her. I looked down at the card. Simple white cardstock. Her name. Her number. Nothing else. She'd come all this way, knowing what she faced, to say the words she'd carried for seven years. The door to the bar swung open again, but it wasn't Melissa returning. Silas stepped through, a box of supplies under one arm. His eyes found mine across the empty room. "You all right?" "I don't know." He set the box down and moved to the bar, his limp more pronounced than usual. His hazel eyes studied my face, reading everything I couldn't say. "Someone you knew?" "Someone I used to know." I tucked the card into my pocket. "Someone from before." Silas nodded slowly. He'd been in intelligence long enough to understand that some doors, once opened, couldn't be closed again. That the past had teeth, and it bit when you least expected. "Need a minute?" "I need to make a call." He didn't ask who. Just took up position behind the bar, taking over, giving me space. I pulled out my phone. Eva's number glowed on the screen. Three weeks of silence. A lifetime of words unspoken. And somewhere out there, a woman I'd once called friend was dying with my forgiveness still caught in her throat. The phone rang once. Twice. "Rory?" Eva's voice was thick with sleep and worry. "Is everything okay? It's late." "It's about Melissa." A sharp intake of breath. "You saw her." "She found me." I closed my eyes. "Tell me everything."
created_at"2026-02-19T12:18:49.112Z" 2/19/2026, 12:18:49 PM
model"z-ai/glm-5-20260211"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency6821
moderation_latency(null)
generation_time48618
tokens_prompt4618
tokens_completion2889
native_tokens_prompt4200
native_tokens_completion2484
native_tokens_completion_images(null)
native_tokens_reasoning588
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"
usage0.0075942
router(null)
provider_responses
0
endpoint_id"c173ea30-3dc0-4957-850e-f2df8c031f10"
id"019c75d6c4504eaa59546891f0b8194d"
is_byokfalse
latency6812
model_permaslug"z-ai/glm-5-20260211"
provider_name"SiliconFlow"
status200
api_type"completions"
id"gen-1771503529-UDpxbectbduOgNH1MpFL"
upstream_id"019c75d6c4504eaa59546891f0b8194d"
total_cost0.0075942
cache_discount(null)
upstream_inference_cost0
provider_name"SiliconFlow"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags21
adverbTagCount2
adverbTags
0"Melissa gestured vaguely [vaguely]"
1"I said honestly [honestly]"
dialogueSentences78
tagDensity0.269
leniency0.538
rawRatio0.095
effectiveRatio0.051
82.44% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1424
totalAiIsmAdverbs5
found
0
adverb"very"
count3
1
adverb"slightly"
count1
2
adverb"slowly"
count1
highlights
0"very"
1"slightly"
2"slowly"
80.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found
0"Chen"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
71.91% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1424
totalAiIsms8
found
0
word"flickered"
count1
1
word"traced"
count1
2
word"silence"
count2
3
word"stomach"
count1
4
word"trembled"
count1
5
word"weight"
count1
6
word"unspoken"
count1
highlights
0"flickered"
1"traced"
2"silence"
3"stomach"
4"trembled"
5"weight"
6"unspoken"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"stomach dropped/sank"
count1
highlights
0"stomach dropped"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences113
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences113
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences169
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1417
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions20
unquotedAttributions0
matches(empty)
99.89% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount898
uniqueNames12
maxNameDensity1
worstName"Melissa"
maxWindowNameDensity2
worstWindowName"Melissa"
discoveredNames
Raven1
Nest1
Chen1
London1
Eva4
Cardiff3
Silence1
Sober1
Melissa9
Yu-Fei1
Slid1
Silas4
persons
0"Raven"
1"Nest"
2"Chen"
3"Eva"
4"Silence"
5"Melissa"
6"Silas"
places
0"London"
1"Cardiff"
globalScore0.999
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences68
glossingSentenceCount1
matches
0"looked like a ghost haunting her own life"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1417
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount2
totalSentences169
matches
0"knew that face"
1"understand that some"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs81
mean17.49
std15.33
cv0.877
sampleLengths
013
11
242
36
417
51
638
71
817
947
106
1114
1239
1311
1427
153
1612
173
187
192
2038
2130
2233
233
246
256
2614
273
284
2935
3029
314
3216
3325
345
3537
364
379
3829
392
406
4152
427
4356
4413
4533
461
4736
4817
496
99.05% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences113
matches
0"been destined"
1"been destined"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs163
matches
0"was dying"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences169
ratio0
matches(empty)
94.35% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount904
adjectiveStacks0
stackExamples(empty)
adverbCount42
adverbRatio0.046460176991150445
lyAdverbCount7
lyAdverbRatio0.007743362831858407
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences169
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences169
mean8.38
std6.32
cv0.753
sampleLengths
013
11
212
314
45
511
66
75
812
91
104
112
122
1313
1417
151
162
177
188
197
2013
2113
222
239
243
256
2610
274
287
298
3011
315
328
3311
3414
3513
363
379
383
393
407
412
425
433
4430
4518
4612
471
486
493
58.78% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats14
diversityRatio0.40236686390532544
totalSentences169
uniqueOpeners68
66.01% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences101
matches
0"Almost like the girl I'd"
1"Just took up position behind"
ratio0.02
45.74% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount44
totalSentences101
matches
0"I glanced at the woman"
1"Her head snapped toward me."
2"I slid the whisky across"
3"She threw back the drink"
4"We'd shared a flat in"
5"Her father was a QC,"
6"She'd been destined for greatness."
7"We'd all been destined for"
8"Her finger traced the rim"
9"She caught the bartender's eye,"
10"I didn't move."
11"She pulled out her phone,"
12"My chest tightened at the"
13"My childhood friend."
14"I busied myself wiping down"
15"My hands stied."
16"I thought about the missed"
17"I'd built walls since Cardiff."
18"She smiled, and it transformed"
19"She pushed the empty glass"
ratio0.436
44.16% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount84
totalSentences101
matches
0"The whisky glass hit the"
1"I glanced at the woman"
2"The kind of desperate that"
3"Her head snapped toward me."
4"Recognition flickered behind glassy eyes,"
5"The voice was wrong."
6"The sound scraped like a"
7"I slid the whisky across"
8"Silas had stepped out for"
9"The Raven's Nest rarely got"
10"She threw back the drink"
11"We'd shared a flat in"
12"Melissa Chen, law student, top"
13"Her father was a QC,"
14"She'd been destined for greatness."
15"We'd all been destined for"
16"Her finger traced the rim"
17"She caught the bartender's eye,"
18"I didn't move."
19"The question hung between us."
ratio0.832
49.50% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences101
matches
0"Even with the once-copper hair"
ratio0.01
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences31
technicalSentenceCount1
matches
0"Sober clarity, the kind that comes from months of therapy or a lifetime of regret."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags21
uselessAdditionCount1
matches
0"She laughed, that broken sound again"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount2
fancyTags
0"Melissa continued (continue)"
1"She laughed (laugh)"
dialogueSentences78
tagDensity0.051
leniency0.103
rawRatio0.5
effectiveRatio0.051
89.7278%