Run: 2026-02-19-01KHTQVZPE9J9TDSA0DXMWX696

Run Details

Duration:
2m 43s
Cost:
$0.088311
Provider:
OpenAI

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
“Rory?” The word scraped down her spine. She set her chopsticks aside with a clatter that sounded far too loud for a nearly empty bar. Green neon from the sign above splintered into jagged shapes across the polished oak counter. Her pulse thundered in her ears. Shadows pooled in corners where patrons once whispered secrets. Every surface in The Raven’s Nest felt slick with untold stories. She forced herself to breathe. She perched on a high stool, resting one elbow on the counter while the other held a porcelain bowl of dumplings, steam curling around her fingers. Silas Blackwood moved behind the bar with effortless grace—limp tapping softly on worn floorboards as he arranged glassware in neat ranks. The walls wore old maps and black-and-white photographs like war medals, each image something unwritten, something lost. She inhaled wood polish and stale beer, the two smells mingling until she couldn’t tell one from the other. Somewhere a dart struck a board with a muffled thunk. The jukebox buzzed between tracks. Aurora’s gaze flicked to the faint crescent scar on her wrist, a souvenir from a childhood fall. The scar pulsed with memory. She could taste five-spice on her tongue and regret in her throat. Through the mirror behind the bar she glimpsed movement at the far end—an angular silhouette of a woman she thought she’d left behind. A woman sat seven stools down, chin tipped upward, shoulders squared. Auburn hair fell in sharp lines, framing cheekbones too defined for casual conversation. She wore a tailored wool coat that whispered of boardrooms and late nights drafting briefs. Aurora’s stomach knotted. The flicker of recognition that crawled up her spine thrummed through every nerve. “Rory?” “Greta Morgan?” Greta’s glass trembled in her hand. She stared at Aurora as if seeing her for the first time, lips parting in disbelief. Aurora stood slowly, stool scraping wood in protest. Her sleeve rode up, revealing that small scar. Every memory she’d tried to bury surged forward—damp Cardiff nights, whispered study sessions, that last morning she’d fled. “It’s been years.” “Five, to be exact.” Silence folded around them. Aurora’s fingers drummed on the counter. The bar’s distant hum dimmed until only her own heartbeat echoed in her skull. She lifted her bowl, studying the cold dumplings as if they held the answer to everything. “You ghosted me.” “I was running.” Greta’s voice cracked like old paint. Aurora swallowed, mouth dry. She recalled running from Evan, the bruises, the threats in the dark. From the moment she’d slipped out to London, she’d carried a suitcase full of fear. Now it lay between them, weighty as lead. “From what?” “My mistakes.” Air seemed to stop. The dartboard’s soft thud punctuated the tension. Silas appeared beside Aurora, polishing a tumbler. His hazel eyes caught the neon light as he measured the silent storm between two women. He offered a slight nod, as if lending them permission to speak truths long buried. “Greta.” Aurora’s voice trembled. She pressed a fingertip to the scar, willing herself to steady. “We could have helped each other.” Greta’s shoulders fell. For a heartbeat, the years dissolved and they stood side by side in some forgotten library. Aurora felt Silas’s presence anchor her, the ghost of his old life as an MI6 operative lending calm. She dared to meet Greta’s gaze, saw regret flicker beneath the surface. “I know.” A fragile stillness settled. Aurora rose, boots clicking against the worn floor. She slipped her jacket on, warming to the idea of escape—until the magnetism of shared history tugged her feet back in place. “So what now?” Greta’s voice was low, edged with unspent tears. Aurora closed her eyes. Rain rattled against the window in staccato rhythms, a drumbeat of inevitability. “Before I go—” Her words died as the door flew open. Wind and rain stormed in, coiling around tables and chairs, sweeping the bar into sudden chaos. Everyone turned as a tall man paused in the threshold, hat dripping, coat clinging to broad shoulders. His gaze cut across the room until it locked on Aurora’s wrist. Recognition curled on his lips. “Evening, Laila.”
created_at"2026-02-19T10:41:57.462Z" 2/19/2026, 10:41:57 AM
model"openai/o4-mini-high-2025-04-16"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency2618
moderation_latency(null)
generation_time163170
tokens_prompt4618
tokens_completion1658
native_tokens_prompt4131
native_tokens_completion19758
native_tokens_completion_images0
native_tokens_reasoning18816
native_tokens_cached3840
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"completed"
usage0.0883113
router(null)
provider_responses
0
endpoint_id"60020533-2fb2-4aa1-9454-181029fd52de"
id"resp_01351db82681e6b4016996e8f5d8688197a033a1061d4b730b"
is_byokfalse
latency164
model_permaslug"openai/o4-mini-high-2025-04-16"
provider_name"OpenAI"
status200
api_type"completions"
id"gen-1771497717-1RyR5zSMvuSsOinw7qwQ"
upstream_id"resp_01351db82681e6b4016996e8f5d8688197a033a1061d4b730b"
total_cost0.0883113
cache_discount0.003168
upstream_inference_cost0
provider_name"OpenAI"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags2
adverbTagCount0
adverbTags(empty)
dialogueSentences15
tagDensity0.133
leniency0.267
rawRatio0
effectiveRatio0
85.59% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount694
totalAiIsmAdverbs2
found
0
adverb"softly"
count1
1
adverb"slowly"
count1
highlights
0"softly"
1"slowly"
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)
0.00% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount694
totalAiIsms16
found
0
word"down her spine"
count1
1
word"pulse"
count1
2
word"thundered"
count1
3
word"porcelain"
count1
4
word"effortless"
count1
5
word"flicked"
count1
6
word"pulsed"
count1
7
word"stomach"
count1
8
word"flicker"
count2
9
word"trembled"
count2
10
word"silence"
count1
11
word"echoed"
count1
12
word"tension"
count1
13
word"measured"
count1
highlights
0"down her spine"
1"pulse"
2"thundered"
3"porcelain"
4"effortless"
5"flicked"
6"pulsed"
7"stomach"
8"flicker"
9"trembled"
10"silence"
11"echoed"
12"tension"
13"measured"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"stomach dropped/sank"
count1
highlights
0"stomach knotted"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences58
matches
0"g in disbelief"
93.60% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount2
narrationSentences58
filterMatches(empty)
hedgeMatches
0"tried to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences71
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen26
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords687
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions2
unquotedAttributions0
matches(empty)
57.55% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions26
wordCount649
uniqueNames9
maxNameDensity1.85
worstName"Aurora"
maxWindowNameDensity3
worstWindowName"Aurora"
discoveredNames
Raven1
Nest1
Blackwood1
Aurora12
Cardiff1
Evan1
London1
Silas3
Greta5
persons
0"Nest"
1"Blackwood"
2"Aurora"
3"Evan"
4"Silas"
5"Greta"
places
0"Raven"
1"Cardiff"
2"London"
globalScore0.576
windowScore0.667
0.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences46
glossingSentenceCount3
matches
0"as if seeing her for the first time, lips parting in disbelief"
1"appeared beside Aurora, polishing a tumbler"
2"as if lending them permission to speak truths long buried"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount687
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences71
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs25
mean27.48
std27.16
cv0.988
sampleLengths
071
183
272
355
41
52
656
73
84
940
103
113
1245
132
142
1549
1621
1749
182
1934
203
2124
223
2358
242
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences58
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs116
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences4
totalSentences71
ratio0.056
matches
0"Silas Blackwood moved behind the bar with effortless grace—limp tapping softly on worn floorboards as he arranged glassware in neat ranks."
1"Through the mirror behind the bar she glimpsed movement at the far end—an angular silhouette of a woman she thought she’d left behind."
2"Every memory she’d tried to bury surged forward—damp Cardiff nights, whispered study sessions, that last morning she’d fled."
3"She slipped her jacket on, warming to the idea of escape—until the magnetism of shared history tugged her feet back in place."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount656
adjectiveStacks0
stackExamples(empty)
adverbCount13
adverbRatio0.019817073170731708
lyAdverbCount4
lyAdverbRatio0.006097560975609756
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences71
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences71
mean9.68
std6.13
cv0.633
sampleLengths
07
118
215
36
49
511
65
726
821
917
1019
1110
125
1317
145
1512
1623
1711
1813
1915
203
2113
221
232
246
2516
268
278
2818
293
304
314
326
3314
3416
353
363
376
384
3912
4015
418
422
432
444
457
467
4716
4815
494
77.00% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats2
diversityRatio0.4788732394366197
totalSentences71
uniqueOpeners34
57.47% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences58
matches
0"Somewhere a dart struck a"
ratio0.017
95.86% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences58
matches
0"She set her chopsticks aside"
1"Her pulse thundered in her"
2"She forced herself to breathe."
3"She perched on a high"
4"She inhaled wood polish and"
5"She could taste five-spice on"
6"She wore a tailored wool"
7"She stared at Aurora as"
8"Her sleeve rode up, revealing"
9"She lifted her bowl, studying"
10"She recalled running from Evan,"
11"His hazel eyes caught the"
12"He offered a slight nod,"
13"She pressed a fingertip to"
14"She dared to meet Greta’s"
15"She slipped her jacket on,"
16"Her words died as the"
17"His gaze cut across the"
ratio0.31
11.72% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount52
totalSentences58
matches
0"The word scraped down her"
1"She set her chopsticks aside"
2"Her pulse thundered in her"
3"Shadows pooled in corners where"
4"Every surface in The Raven’s"
5"She forced herself to breathe."
6"She perched on a high"
7"Silas Blackwood moved behind the"
8"The walls wore old maps"
9"She inhaled wood polish and"
10"The jukebox buzzed between tracks."
11"Aurora’s gaze flicked to the"
12"The scar pulsed with memory."
13"She could taste five-spice on"
14"A woman sat seven stools"
15"Auburn hair fell in sharp"
16"She wore a tailored wool"
17"Aurora’s stomach knotted."
18"The flicker of recognition that"
19"Greta’s glass trembled in her"
ratio0.897
86.21% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences58
matches
0"Now it lay between them,"
ratio0.017
53.57% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences32
technicalSentenceCount4
matches
0"She set her chopsticks aside with a clatter that sounded far too loud for a nearly empty bar."
1"She wore a tailored wool coat that whispered of boardrooms and late nights drafting briefs."
2"She lifted her bowl, studying the cold dumplings as if they held the answer to everything."
3"He offered a slight nod, as if lending them permission to speak truths long buried."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags2
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
80.6189%