Run: 2026-04-27-01KQ6ZEX591WEQZJBBW5Q55SX0

Run Details

Duration:
1m 29s
Cost:
$0.015900
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
Glass kissed the floorboards. I dropped the crate of Yu Fei spring rolls. Steam hissed from the torn cardboard. My boots slid on the slick linoleum. I caught the heavy delivery bag before it struck my ankle. The bar went quiet. Too quiet for a Tuesday night in Soho. A hand caught my wrist. Silver flashed. Familiar weight. Familiar callous. I looked up. Grey streaked auburn hair. Hazel eyes set in a face carved by decades of bad decisions and worse compromises. Silas Blackwood. I had not seen him since Cardiff. Since before Evan. Since before I packed two suitcases and fled across the border. “Careful.” His voice carried the rasp of cheap tobacco and older secrets. “Those rolls cost more than your daily wage.” “And you still owe me for the damages in Swansea.” I yanked my arm back. The crescent scar on my left wrist pulled tight against his thumb. “You vanished. Like a bad debt.” “People vanish. They also return.” He stepped out from behind the polished mahogany. The left leg dragged a fraction. That knee never healed properly. “Soho suits you. You look leaner.” “London eats the soft. I just stopped feeding it.” He poured two measures of whiskey. The amber liquid caught the green neon bleeding through the front window. He slid one tumbler across the wood. I did not touch it. “Your father would hate this place.” He gestured to the map shaded walls. Black and white photographs of dockworkers and spymasters hung crooked. “Maps of borders that stopped existing forty years ago.” “Dad preferred courtrooms. I prefer corners. Cuts the waiting short.” “Still answers questions with questions.” He tapped his signet ring against the glass. A hollow click clack rhythm echoed in the quiet room. “Evan’s out of prison.” The glass felt suddenly heavy. I kept my face flat. Cool. “And?” “And you are delivering food to Soho addresses he used to run. Coincidences breed trouble.” I finally lifted the tumbler. The burn in my throat felt like penance. “You should have called. Sent a warning. Anything. Instead I found out from a court clerk I barely know.” “Calls get intercepted. Letters get burned. I chose silence over a bullet.” He leaned in. The smell of old leather and floor wax clung to his jacket. “I failed you once. I will not fail again. The Nest is yours now. Floor, ceiling, walls. You live above it. You eat downstairs. You stay out of the line of fire.” “You are offering me a prison wrapped in a bar tab.” “I am offering you a door that only opens when I say so.” His hazel eyes locked onto mine. “Take it.” I set the glass down. Hard. “I do not run cages. Not anymore.” The front bell chimed. Sharp. Too sharp for a late night stray. Boots hit the threshold. Three pairs. Heavy soles. Deliberate steps. The green neon flickered once, twice, then held. I counted the strides. Eight. Nine. Ten. They stopped at the doorframe. Shadows stretched across the warped floorboards. Silas did not look at them. He looked at me. His hand drifted beneath the bar. The silver ring caught the dim light. “Back room.” He murmured. “Now.” “I am not hiding from—” A voice cut through the smoke. Low. Familiar. “Rory. Laila. Aurora. Carter. Malphora. Five names for a girl who thinks she can outrun a debt.” My pulse hammered against my ribs. That voice had not changed. It only got worse. Silas moved. Fast for an old man. The stool scraped. The drawer clicked open. Steel met steel. “Run.” He said. “Or die. Choose.” The first boot crossed the threshold. Glass crunched under a heavy sole. I grabbed the sharp curved silver hunting blade from my delivery belt. Cold. Balanced. Real. “Right then.” I stepped forward. “Let us see who collects.” The leader stepped into the light. A broad black coat. A thick silver chain resting against a pale throat. His eyes tracked the scar on my wrist. His fingers loosened on the knuckles of his right glove. Silas shifted his weight. The limp vanished into a solid stance. He pulled a sleek wooden pistol from the drawer. The grip fit his right hand perfectly. “You brought friends to my quiet bar.” Silas said. “That costs extra.” The leader smiled. A thin crack in a stone wall. “We brought friends to collect what Evan left behind. The girl. The ledger. The keys to the flat above.” I gripped the blade tighter. The crescent scar itched. Memory flared. Evan’s grip. The taste of copper. The promise I made to myself in the dark. Silas tapped the barrel against the mahogany. A steady warning beat. “This girl works for me now. The ledger burns tonight. The keys stay in my pocket.” The leader tilted his head. “MI6 taught you to protect assets. It did not teach you to protect strays.” “Strays learn fast.” Silas said. “Strays remember who feeds them.” I moved. A slip past the bar edge. A shift to the left. My boots stayed flat. My weight stayed low. The leader’s hand dropped toward his coat. Fast. Predictable. I did not wait for the draw. I threw the steel tumbler. It sailed across the gap. Struck his wrist. Knocked the pistol wide. It clattered against the floorboards. Silas fired. Once. The shot rang against the ceiling plaster. Plaster dust rained down. The second man dove behind a wooden stool. The third man drew a compact revolver. I ducked under the bar top. Wood splintered above my head. Heat washed over my shoulders. “Door.” Silas shouted. “Take the door.” I rolled. My back hit the warped floor. I grabbed the fallen pistol. Heavy. Cold. Real. I aimed. I did not shake. I did not hesitate. I exhaled. I squeezed. The revolver slipped from the third man’s grip. He dropped to one knee. The second man scrambled backward. The leader raised his empty hands. A slow clap echoed off the map shaded walls. “Bravo.” The leader said. “Evan will love this.” Silas stepped over the threshold. The silver ring flashed under the buzzing neon. He racked the slide. A final warning. “Tell Evan the Nest has new management.” Silas said. “Tell him the girl keeps the blade. I keep the door. He keeps running.” The leader nodded. Slow. Calculating. He backed toward the street. The other two men followed. Limping. Dragging. The front bell chimed. Heavy boots faded into the Soho fog. I stood. My legs shook. I forced them straight. I placed the pistol on the bar. I reached for the whiskey. The glass felt steady now. Silas watched me. His hazel eyes narrowed. His chest rose and fell. The limp returned. He limped back to his stool. He poured a fresh measure. He slid it across the polished wood. “Back room.” He said. “We have work to do. He will return by dawn.” I lifted the glass. I met his gaze. I did not blink. “Let him come.” I said. “I have a ledger to burn.”
created_at"2026-04-27T08:03:59.8Z" 4/27/2026, 8:03:59 AM
model"qwen/qwen3.5-plus-20260420"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency865
moderation_latency(null)
generation_time89009
tokens_prompt4618
tokens_completion6187
native_tokens_prompt4477
native_tokens_completion5879
native_tokens_completion_images(null)
native_tokens_reasoning4248
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.0159004
router(null)
provider_responses
0
endpoint_id"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id"chatcmpl-8eb50dbd-8120-964f-8c34-a8703c4160e3"
is_byokfalse
latency865
model_permaslug"qwen/qwen3.5-plus-20260420"
provider_name"Alibaba"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777277039-mnSoWTBpH6P3u7zsBmK9"
session_id(null)
api_type"completions"
id"gen-1777277039-8vIm5rbI5xtu3QAe1PoG"
upstream_id"chatcmpl-8eb50dbd-8120-964f-8c34-a8703c4160e3"
total_cost0.0159004
cache_discount(null)
upstream_inference_cost0
provider_name"Alibaba"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags17
adverbTagCount0
adverbTags(empty)
dialogueSentences46
tagDensity0.37
leniency0.739
rawRatio0
effectiveRatio0
91.49% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1175
totalAiIsmAdverbs2
found
0
adverb"suddenly"
count1
1
adverb"perfectly"
count1
highlights
0"suddenly"
1"perfectly"
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)
44.68% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1175
totalAiIsms13
found
0
word"familiar"
count3
1
word"weight"
count3
2
word"echoed"
count2
3
word"silence"
count1
4
word"flickered"
count1
5
word"pulse"
count1
6
word"predictable"
count1
7
word"calculating"
count1
highlights
0"familiar"
1"weight"
2"echoed"
3"silence"
4"flickered"
5"pulse"
6"predictable"
7"calculating"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"eyes widened/narrowed"
count1
highlights
0"eyes narrowed"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences175
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences175
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences204
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen32
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1175
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions14
unquotedAttributions0
matches(empty)
66.67% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount830
uniqueNames11
maxNameDensity1.45
worstName"Silas"
maxWindowNameDensity3
worstWindowName"Silas"
discoveredNames
Yu1
Fei1
Tuesday1
Soho2
Blackwood1
Cardiff1
Evan2
Black1
Silas12
Familiar3
Heavy3
persons
0"Blackwood"
1"Evan"
2"Silas"
places
0"Soho"
1"Cardiff"
globalScore0.777
windowScore0.667
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences59
glossingSentenceCount1
matches
0"felt like penance"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1175
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences204
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs49
mean23.98
std13.97
cv0.582
sampleLengths
049
156
220
333
430
59
630
732
810
927
1012
1115
1232
1359
1411
1521
1613
1748
1823
195
205
2125
2215
2317
246
2527
2610
2737
2827
2912
3029
3126
3227
3319
3410
3559
3645
376
3830
3933
408
4120
4223
4328
4426
4533
4614
4712
4811
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences175
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs150
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences204
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount830
adjectiveStacks0
stackExamples(empty)
adverbCount14
adverbRatio0.016867469879518072
lyAdverbCount5
lyAdverbRatio0.006024096385542169
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences204
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences204
mean5.76
std4.22
cv0.732
sampleLengths
04
19
26
37
411
54
68
75
82
92
102
113
124
1315
142
157
163
1711
1812
198
2015
2112
226
2313
246
255
266
279
286
2912
307
315
3213
3310
349
3510
3613
3710
384
395
405
411
421
4315
445
458
4619
4715
4812
4932
49.84% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats25
diversityRatio0.37254901960784315
totalSentences204
uniqueOpeners76
51.68% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences129
matches
0"Too quiet for a Tuesday"
1"Too sharp for a late"
ratio0.016
46.36% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount56
totalSentences129
matches
0"I dropped the crate of"
1"My boots slid on the"
2"I caught the heavy delivery"
3"I looked up."
4"I had not seen him"
5"His voice carried the rasp"
6"I yanked my arm back"
7"He stepped out from behind"
8"He poured two measures of"
9"He slid one tumbler across"
10"I did not touch it."
11"He gestured to the map"
12"He tapped his signet ring"
13"I kept my face flat."
14"I finally lifted the tumbler."
15"He leaned in"
16"His hazel eyes locked onto"
17"I set the glass down."
18"I counted the strides."
19"They stopped at the doorframe."
ratio0.434
2.64% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount118
totalSentences129
matches
0"Glass kissed the floorboards."
1"I dropped the crate of"
2"Steam hissed from the torn"
3"My boots slid on the"
4"I caught the heavy delivery"
5"The bar went quiet."
6"A hand caught my wrist."
7"I looked up."
8"Hazel eyes set in a"
9"I had not seen him"
10"His voice carried the rasp"
11"I yanked my arm back"
12"The crescent scar on my"
13"He stepped out from behind"
14"The left leg dragged a"
15"That knee never healed properly."
16"He poured two measures of"
17"The amber liquid caught the"
18"He slid one tumbler across"
19"I did not touch it."
ratio0.915
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences129
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences10
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags17
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount2
fancyTags
0"He murmured (murmur)"
1"Silas shouted (shout)"
dialogueSentences46
tagDensity0.196
leniency0.391
rawRatio0.222
effectiveRatio0.087
85.1115%