Run: 2026-02-19-01KHTQQSNT57VAEJ6XSHG30ETT

Run Details

Duration:
16.5s
Cost:
$0.003464
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
The door to The Raven’s Nest creaked open into a wet gust that carried the city’s grime into the dim haven. A pair of bright blue eyes scanned the room with the precision of someone picking through trouble before trouble picked through her. Aurora Carter froze by the bar, the weight of years clambering up her spine. "Rory?" The voice came, quiet but deliberate, cutting through the low hum like a shard of glass on stone. Silas Blackwood, the Spymaster himself, took a slow, measured step forward from his perch behind the bar. His hazel eyes flickered with something unreadable, the usual quiet authority deepened by the creaking of his old knee. Aurora’s breath hiccupped before she masked it with a cool tilt of her head. “Silas.” He scrutinised her—the sharp line of her jaw, the straight black hair that grazed her shoulders, the small crescent scar on her wrist peeking from the sleeve. Not the radiant girl he remembered, but no less formidable. Definitely not the girl who ran away. The bar’s green neon sign cast a sickly light on Silas’ grey-streaked auburn hair, and that crooked silver signet ring on his right hand caught a glint when he moved it from the glass. “I’ve been told you disappeared,” he said. Aurora shrugged, tracing the rim of her glass. “Changing a few things. London’s not that forgiving.” “You’ve kept well.” He nodded towards her wrist, shadowed beneath the folds. “Remember how you used to catch trouble before it caught you?” She allowed a brief, dry smile. “Trouble found its way in regardless.” The room felt smaller, the walls closing as they orbited years of silent distance. “So,” Silas said, voice dropping an octave, “how much of that old trouble is still out there?” “Evan’s ghosts don’t haunt London. Not anymore.” She lifted her eyes sharply. “You?” He drained his glass, his gaze steady. “Retired. Fronting this place now.” A pause. “Though the past doesn’t do retirement well.” The bar was littered with relics of another life: old maps curling in frames, black-and-white photographs of war zones. Aurora’s eyes flicked to the bookshelf hiding the secret room Silas once used for his clandestine dealings. Behind this facade, secrets thrived, but tonight they weren’t the point. A silence stretched, holding more than the distance between them. “Funny how time doesn’t erase much,” Silas murmured, “just layers it.” Aurora caught the glint that betrayed regret beneath his careful tone. “You don’t think I changed much?” “Outside, maybe.” He looked her over again. “Inside… that fire’s still there. Just buried, deeper.” Her fingers curled reflexively. “Maybe I wanted it that way.” “And the law degree?” “Paused. Not lost.” She tapped the scar on her wrist. “Some lessons run longer than degrees.” A spark flickered, years of shared history sizzling beneath the surface. Silas leaned closer, voice husky. “You ever wonder why you ran?” “Every day,” she admitted. “But some chains are quieter.” He nodded, the old pain flickering in his eyes. “You had reasons. I have ghosts too.” The bar’s door rattled as the wind pushed harder outside. Aurora’s gaze drifted to the neon sign, green like a warning light. “You ever regret not telling me?” Silence swelled. “Back then.” She exhaled slowly. “Regret’s a luxury for safer people. I couldn’t risk pulling you in.” He took a rag, polishing a glass with rough precision. “I could handle more than you thought.” A tension tightened, unspoken accusations wrapped in years of silence. “I left because I had to,” she said finally. “Not because you weren’t there.” “You walked into a storm without a word.” “Storms tend to prefer quiet exits,” she whispered, eyes distant. Silas let the counter thud as he slammed down the glass. “You were family.” “Some families bleed in silence,” she shot back, the old stubbornness sparking bright again. The moment cracked. For a heartbeat, the years of separation were tangible—thick and suffocating—before Aurora turned abruptly. “I don’t want pity.” Silas held his gaze, unflinching. “Never offered it.” Her jaw clenched. The Spymaster’s bar, a ground zero for debts and secrets, now bore witness to this fragile collision. The past and present coiled tight around the space between them. “Why now?” Silas asked. She hesitated, fingers brushing the crescent scar. “I need a friend who understands shadows.” The corners of Silas’ lips twitched. “That’s what I’m here for.” Thunder rumbled in the distance. The door swung open again, a sharp draft scattering papers. They both glanced up—an unexpected presence, unfamiliar, whose eyes flicked between them like a predator smelling weakness. Silas' hand fell to the silver signet ring, fingers curling around it. Aurora’s pulse quickened. “No more ghosts tonight,” she said, voice low. But the strangers at the doorway were already stepping in. The room shrank. Secrets threatened to explode. Silas fixed Aurora with a hard look. “Looks like the past isn’t done with us yet.”
created_at"2026-02-19T10:39:40.708Z" 2/19/2026, 10:39:40 AM
model"openai/gpt-4.1-mini-2025-04-14"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency531
moderation_latency(null)
generation_time15840
tokens_prompt4618
tokens_completion1413
native_tokens_prompt4132
native_tokens_completion1132
native_tokens_completion_images0
native_tokens_reasoning0
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"completed"
usage0.003464
router(null)
provider_responses
0
endpoint_id"872eccb7-9c85-45fc-974a-ff7c8e2407e6"
id"resp_0d7beabade785f1c016996e86cd92081959dbf58dc2d5b20ac"
is_byokfalse
latency104
model_permaslug"openai/gpt-4.1-mini-2025-04-14"
provider_name"OpenAI"
status200
api_type"completions"
id"gen-1771497580-6cZlRiSP0gCNMMB1ZuCF"
upstream_id"resp_0d7beabade785f1c016996e86cd92081959dbf58dc2d5b20ac"
total_cost0.003464
cache_discount(null)
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
totalTags15
adverbTagCount1
adverbTags
0"she said finally [finally]"
dialogueSentences41
tagDensity0.366
leniency0.732
rawRatio0.067
effectiveRatio0.049
87.85% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount823
totalAiIsmAdverbs2
found
0
adverb"sharply"
count1
1
adverb"slowly"
count1
highlights
0"sharply"
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)
wordCount823
totalAiIsms25
found
0
word"scanned"
count1
1
word"weight"
count1
2
word"measured"
count1
3
word"flickered"
count2
4
word"unreadable"
count1
5
word"radiant"
count1
6
word"glint"
count2
7
word"tracing"
count1
8
word"flicked"
count2
9
word"clandestine"
count1
10
word"facade"
count1
11
word"silence"
count4
12
word"tension"
count1
13
word"unspoken"
count1
14
word"tangible"
count1
15
word"jaw clenched"
count1
16
word"predator"
count1
17
word"pulse"
count1
18
word"quickened"
count1
highlights
0"scanned"
1"weight"
2"measured"
3"flickered"
4"unreadable"
5"radiant"
6"glint"
7"tracing"
8"flicked"
9"clandestine"
10"facade"
11"silence"
12"tension"
13"unspoken"
14"tangible"
15"jaw clenched"
16"predator"
17"pulse"
18"quickened"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"jaw/fists clenched"
count1
highlights
0"jaw clenched"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences61
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences61
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences88
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen35
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords816
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions9
unquotedAttributions0
matches(empty)
68.63% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions25
wordCount553
uniqueNames8
maxNameDensity1.63
worstName"Aurora"
maxWindowNameDensity2.5
worstWindowName"Silas"
discoveredNames
Raven1
Nest1
Carter1
Blackwood1
Spymaster2
Aurora9
Silas9
Thunder1
persons
0"Nest"
1"Carter"
2"Blackwood"
3"Spymaster"
4"Aurora"
5"Silas"
6"Thunder"
places
0"Raven"
globalScore0.686
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences39
glossingSentenceCount0
matches(empty)
77.45% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords1.225
wordCount816
matches
0"Not the radiant girl he remembered, but no less formidable"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences88
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs51
mean16
std12.15
cv0.759
sampleLengths
057
11
254
315
444
534
67
716
823
912
1014
1117
1213
1321
1447
1510
1611
1717
1815
1910
204
2116
2211
2311
249
2516
2622
2710
2815
2917
3010
3114
328
3310
3414
3514
3617
374
388
3931
404
4114
4211
4332
4412
453
468
4710
487
497
99.51% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences61
matches
0"was littered"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs97
matches(empty)
45.45% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount4
semicolonCount0
flaggedSentences3
totalSentences88
ratio0.034
matches
0"He scrutinised her—the sharp line of her jaw, the straight black hair that grazed her shoulders, the small crescent scar on her wrist peeking from the sleeve."
1"For a heartbeat, the years of separation were tangible—thick and suffocating—before Aurora turned abruptly."
2"They both glanced up—an unexpected presence, unfamiliar, whose eyes flicked between them like a predator smelling weakness."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount322
adjectiveStacks0
stackExamples(empty)
adverbCount6
adverbRatio0.018633540372670808
lyAdverbCount2
lyAdverbRatio0.006211180124223602
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences88
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences88
mean9.27
std5.76
cv0.621
sampleLengths
021
122
214
31
418
517
619
714
81
927
1010
117
1234
137
148
158
1612
1711
186
196
2014
2117
2212
231
247
257
267
2719
2817
2911
3010
3111
3211
336
347
358
364
376
384
3910
406
4111
425
436
444
455
469
477
4810
4912
78.41% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.4772727272727273
totalSentences88
uniqueOpeners42
60.61% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences55
matches
0"Definitely not the girl who"
ratio0.018
81.82% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount19
totalSentences55
matches
0"His hazel eyes flickered with"
1"He scrutinised her—the sharp line"
2"He nodded towards her wrist,"
3"She allowed a brief, dry"
4"She lifted her eyes sharply"
5"He drained his glass, his"
6"He looked her over again"
7"Her fingers curled reflexively."
8"She tapped the scar on"
9"He nodded, the old pain"
10"She exhaled slowly."
11"He took a rag, polishing"
12"she said finally"
13"she whispered, eyes distant"
14"she shot back, the old"
15"Her jaw clenched."
16"She hesitated, fingers brushing the"
17"They both glanced up—an unexpected"
18"she said, voice low"
ratio0.345
5.45% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount50
totalSentences55
matches
0"The door to The Raven’s"
1"A pair of bright blue"
2"Aurora Carter froze by the"
3"The voice came, quiet but"
4"Silas Blackwood, the Spymaster himself,"
5"His hazel eyes flickered with"
6"Aurora’s breath hiccupped before she"
7"He scrutinised her—the sharp line"
8"The bar’s green neon sign"
9"Aurora shrugged, tracing the rim"
10"He nodded towards her wrist,"
11"She allowed a brief, dry"
12"The room felt smaller, the"
13"Silas said, voice dropping an"
14"She lifted her eyes sharply"
15"He drained his glass, his"
16"The bar was littered with"
17"Aurora’s eyes flicked to the"
18"A silence stretched, holding more"
19"Aurora caught the glint that"
ratio0.909
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences55
matches(empty)
ratio0
89.95% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences27
technicalSentenceCount2
matches
0"He scrutinised her—the sharp line of her jaw, the straight black hair that grazed her shoulders, the small crescent scar on her wrist peeking from the sleeve."
1"Aurora caught the glint that betrayed regret beneath his careful tone."
0.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags15
uselessAdditionCount4
matches
0"Silas said, voice dropping an octave,"
1"she whispered, eyes distant"
2"she shot back, the old stubbornness sparking bright again"
3"she said, voice low"
76.83% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags8
fancyCount3
fancyTags
0"Silas murmured (murmur)"
1"she admitted (admit)"
2"she whispered (whisper)"
dialogueSentences41
tagDensity0.195
leniency0.39
rawRatio0.375
effectiveRatio0.146
79.0652%