Run: 2026-02-25-01KJBJMG3C0PNKG4ZZQH2HXREB

Run Details

Duration:
47.9s
Cost:
$0.018978
Provider:
Alibaba

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
Aurora wiped the condensation from the heavy glass mug. Her thumb traced the crescent scar on her left wrist. The rag moved in tight circles. The bar smelled of stale beer and lemon polish. Outside, the green neon sign buzzed against the Soho rain. Inside, the air hung still. The bell above the door jingled. Aurora did not look up. She placed the mug on the polished oak counter. A customer would come. Silas would come. The rhythm of the night dictated the flow. The footsteps were wrong. Heavy. Hesitant. She lifted her head. The woman standing in the doorway wore a coat too thin for the London chill. Dark hair hung in wet strands around a face that had lost its softness. Eyes darted from the maps on the wall to the empty stools. Rory. The name sat in the air between them. Aurora gripped the rag. Her knuckles turned white. Eva stepped inside. She shook the water from her coat. The fabric clung to her shoulders. She looked smaller than the girl who had dragged Aurora out of Cardiff five years ago. You found the place. Eva moved to the counter. Her boots left wet prints on the floorboards. She smelled of smoke and cheap perfume. I asked around. Aurora set the rag down. The cloth landed with a soft thud. You shouldn't be here. Eva smiled. It did not reach her eyes. The scar on her chin caught the dim light. A new addition. I needed to see you. Silence stretched. The hum of the fridge filled the gap. Aurora watched Eva's hands. They trembled. You left. I had to. Eva reached into her pocket. Her fingers fumbled with a small object. She placed a silver key on the counter. It spun on the wood. Where did you get this? My flat. The one you left. Aurora leaned forward. The wood of the counter pressed into her forearms. Why are you giving this to me? Because they know. Eva's voice dropped. The words fell like stones into deep water. Who? The people Evan worked for. Aurora felt the cold bite of the air. She had buried that name. She had buried the man. She had buried the life in Cardiff. Evan is dead. Eva laughed. A dry, brittle sound. He is not. She pulled a photograph from her coat. She slid it across the oak. The image showed a man in a grey suit. He stood outside a building Aurora recognised. The Golden Empress. He paid for the rent. He paid for the food. He paid for the silence. Aurora stared at the photo. The man's eyes looked out at her. Cold. Calculating. Silas appeared from the shadows. His limp slowed his stride. The silver signet ring on his right hand caught the light. We close in ten minutes. Eva turned. Her face went pale. I know who you are. Silas stopped. His hazel eyes narrowed. He looked at Aurora. Is this a problem? Aurora stood. The chair scraped against the floor. A sharp noise in the quiet room. No. She looked at Eva. You brought them here. I brought the truth. Eva reached for the photo. Aurora slapped her hand away. The metal key clattered to the floor. You don't understand. I understand enough. Silas moved between them. His height loomed over Eva. He smelled of tobacco and old leather. Get out. She can't. Eva backed away. Her heel caught the edge of the rug. She stumbled. They are coming. Who? The ones who own the debt. Aurora looked at the door. The green neon buzzed louder. The rain hammered the glass. I paid it off. Did you? Eva pointed at the scar on Aurora's wrist. He marked you. He marks everyone. Silas stepped forward. His hand rested on the bar. Leave. Now. Eva shook her head. She pulled a phone from her coat. The screen glowed blue. I have the evidence. Aurora lunged. She grabbed Eva's wrist. The skin felt hot. Give it to me. No. Eva twisted. She pulled free. She raised the phone. I am sending it. Silas moved fast. He slammed his hand down on the counter. The wood shook. Don't. The screen lit up. A progress bar filled. Aurora saw the name of the recipient. A number she knew. A number she had never called. The door handle turned. Silas looked at the door. His face went hard. Too late. The door swung open. Three men stood in the frame. They wore dark coats. They held no umbrellas. Water dripped from their collars. The leader stepped inside. He held a black umbrella. He clicked it shut. The sound echoed like a gunshot. Evening. He looked at Aurora. He looked at Eva. He looked at the key on the floor. We are here for the girl. Aurora picked up the heavy glass mug. Her hand did not shake. You are in the wrong place. The man smiled. He showed a gold tooth. We are never in the wrong place. He nodded to his men. They moved in. Boots hit the floor. Eva backed into the corner. She pressed her back against the wall. I told you. Aurora threw the mug. It smashed against the leader's head. Glass rained down. He roared. Silas drew a knife. The blade flashed silver. Run. Aurora did not run. She grabbed the key. She grabbed the photo. She grabbed the truth. The first man swung. She ducked. The punch hit the counter. Wood splintered. She saw the exit. The back door. The hidden room. Silas fought. He moved with the grace of a man who had killed before. Aurora sprinted for the bookshelf. The men shouted. Boots thundered. She pushed the shelf. It swung open. Darkness waited inside. She dove. The door slammed shut behind her. Silence. Then, a knock. She held her breath. The handle turned.
created_at"2026-02-25T23:37:34.58Z" 2/25/2026, 11:37:34 PM
model"qwen/qwen3.5-122b-a10b-20260224"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1030
moderation_latency(null)
generation_time47870
tokens_prompt4618
tokens_completion5581
native_tokens_prompt4477
native_tokens_completion5371
native_tokens_completion_images(null)
native_tokens_reasoning3967
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"
usage0.018978
router(null)
provider_responses
0
endpoint_id"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id"chatcmpl-dbc0a9aa-dd0e-964a-9adb-acd28b7a32d2"
is_byokfalse
latency1030
model_permaslug"qwen/qwen3.5-122b-a10b-20260224"
provider_name"Alibaba"
status200
api_type"completions"
id"gen-1772062654-4Fs6zSY0WztZx0PuKo1s"
upstream_id"chatcmpl-dbc0a9aa-dd0e-964a-9adb-acd28b7a32d2"
total_cost0.018978
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount980
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)
43.88% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount980
totalAiIsms11
found
0
word"traced"
count1
1
word"footsteps"
count1
2
word"chill"
count1
3
word"silence"
count3
4
word"trembled"
count1
5
word"calculating"
count1
6
word"loomed"
count1
7
word"echoed"
count1
8
word"thundered"
count1
highlights
0"traced"
1"footsteps"
2"chill"
3"silence"
4"trembled"
5"calculating"
6"loomed"
7"echoed"
8"thundered"
66.67% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches2
maxInWindow2
found
0
label"eyes widened/narrowed"
count1
1
label"knuckles turned white"
count1
highlights
0"eyes narrowed"
1"knuckles turned white"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences211
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount0
narrationSentences211
filterMatches
0"know"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences211
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen16
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords980
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions0
unquotedAttributions0
matches(empty)
16.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions63
wordCount980
uniqueNames10
maxNameDensity2.24
worstName"Aurora"
maxWindowNameDensity4.5
worstWindowName"Eva"
discoveredNames
Soho1
London1
Aurora22
Cardiff2
Eva18
Evan2
Golden1
Empress1
Silas9
You6
persons
0"Aurora"
1"Eva"
2"Evan"
3"Silas"
4"You"
places
0"Soho"
1"London"
2"Cardiff"
globalScore0.378
windowScore0.167
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences57
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount980
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences211
matches
0"buried that name"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs103
mean9.51
std8.91
cv0.936
sampleLengths
049
16
229
36
445
51
68
78
832
94
1020
113
1212
134
1420
155
1616
172
183
1925
205
216
2212
237
243
2511
261
275
2825
293
306
313
3232
3315
3414
3521
365
376
385
3910
404
4115
421
434
444
454
4617
473
483
4916
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences211
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs204
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences211
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount980
adjectiveStacks0
stackExamples(empty)
adverbCount8
adverbRatio0.00816326530612245
lyAdverbCount0
lyAdverbRatio0
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences211
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences211
mean4.64
std2.53
cv0.545
sampleLengths
09
110
26
39
410
55
66
75
89
94
103
118
124
131
141
154
1615
1714
1812
191
208
214
224
233
247
256
2616
274
285
298
307
313
325
337
344
352
366
379
383
395
402
418
424
432
442
453
465
477
488
495
41.47% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats18
diversityRatio0.22748815165876776
totalSentences211
uniqueOpeners48
19.16% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences174
matches
0"Then, a knock."
ratio0.006
38.39% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount79
totalSentences174
matches
0"Her thumb traced the crescent"
1"She placed the mug on"
2"She lifted her head."
3"Her knuckles turned white."
4"She shook the water from"
5"She looked smaller than the"
6"You found the place."
7"Her boots left wet prints"
8"She smelled of smoke and"
9"I asked around."
10"You shouldn't be here."
11"It did not reach her"
12"I needed to see you."
13"I had to."
14"Her fingers fumbled with a"
15"She placed a silver key"
16"It spun on the wood."
17"She had buried that name."
18"She had buried the man."
19"She had buried the life"
ratio0.454
0.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount164
totalSentences174
matches
0"Aurora wiped the condensation from"
1"Her thumb traced the crescent"
2"The rag moved in tight"
3"The bar smelled of stale"
4"The bell above the door"
5"Aurora did not look up."
6"She placed the mug on"
7"A customer would come."
8"Silas would come."
9"The rhythm of the night"
10"The footsteps were wrong."
11"She lifted her head."
12"The woman standing in the"
13"Eyes darted from the maps"
14"The name sat in the"
15"Aurora gripped the rag."
16"Her knuckles turned white."
17"Eva stepped inside."
18"She shook the water from"
19"The fabric clung to her"
ratio0.943
28.74% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences174
matches
0"Because they know."
ratio0.006
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences8
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags0
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
81.8321%