Run: 2026-02-19-01KHTXMC2VFSFYWJE3HD6C75ED

Run Details

Duration:
35.7s
Cost:
$0.032916

Model input

System
You are an expert and award-winning novel writer in the dark Literary Fiction genre. Your readers are hooked on your stories and can't wait to read the book you have in store. <important> - MUST: Start each chapter in medias res (in the middle of action). AVOID talking about the weather, time of day, the position of the sun, or other boring stuff. - The instructions/summary are just a that, a summary. Feel free to add details, stretch sections and add interesting transitions/descriptions/fillers. - When called for it, have fast-paced action, but otherwise take things slow. This is an experience, and not for people with short attention spans. Enjoy the wine, not slurp Red Bull. - Add descriptions when transitioning places/times/etc, or when coming by new places (e.g. a corner shop, a cafe, etc.). But remember: NOT at the start or end of a chapter. - MUST: AVOID ending in internal monologue, reminiscing or waiting for the next day. A good chapter end is when we're ending right when shit hits the fan. We want to have the reader be excited for what comes next. So no reminiscing, contemplating or summarizing the day. It's popcorn time! </important>
User/Human
Take into account the following glossary of characters/locations/items/lore... when writing your response: <codex> <character id="4412" name="Aurora Carter" aliases="Rory, Laila, Aurora, Carter, Malphora" pronouns="she/her" species="Human" storyRole="Protagonist"> <eyeColor>bright blue</eyeColor> <hair>straight shoulder-length black</hair> <height>5'6"</height> <age>25</age> <scar>small crescent-shaped scar on her left wrist from a childhood accident</scar> <description>Aurora, referred to by her friends as Rory, is cool-headed, intelligent, and known for quick out-of-the-box thinking.</description> <backstory>Born in Cardiff to an Irish barrister father (Brendan Carter) and Welsh teacher mother (Jennifer Carter née Ellis), Rory reluctantly pursued Pre-Law at Cardiff University. She fled to London at the behest of her childhood friend Eva after leaving an abusive ex named Evan. By day, Rory works part-time as a delivery person for Yu-Fei Cheung's Golden Empress restaurant. She lives in a flat above Silas' bar.</backstory> </character> <character id="4413" name="Silas Blackwood" aliases="Silas, Si, the Spymaster" pronouns="he/him" species="Human" storyRole="Mentor"> <eyeColor>hazel</eyeColor> <hair>grey-streaked auburn</hair> <height>6'1"</height> <age>58</age> <beard>neatly trimmed, matching his grey-streaked auburn hair</beard> <limp>slight limp in his left leg from an old knee injury</limp> <signetRing>silver signet ring, always worn on his right hand</signetRing> <description>Silas is a retired intelligence operative turned bar owner. He carries himself with quiet authority.</description> <backstory>Former MI6 field agent who retired after a botched operation in Prague left him with a permanent knee injury. He opened "The Raven's Nest" bar in Soho as a front for his network of contacts.</backstory> </character> <location id="854" name="The Raven's Nest" aliases="the Nest, Raven, Silas' bar" realm="Earth"> <signColor>distinctive green neon sign above the entrance</signColor> <secretRoom>hidden back room accessible through a bookshelf, used for clandestine meetings</secretRoom> <description>A dimly lit bar in Soho, London. The walls are covered with old maps and black-and-white photographs.</description> </location> </codex> <proseGuidelines> <styleGuide> - Write in past tense and use British English spelling and grammar - Keep a Flesch reading ease score of 60 - Respect the the Royal Order of Adjectives: The order is: opinion, size, age, shape, color, origin, material, purpose, followed by the noun itself (e.g., "a lovely little old rectangular green French silver whittling knife") - Respect the ablaut reduplication rule (e.g. tick-tock, flip-flop) - Write in active voice - Passive voice: <bad>The book was read by Sarah.</bad> - Active voice: <good>Sarah read the book.</good> - Reduce the use of passive verbs - <bad>For a moment, I was tempted to throw in the towel.</bad> - <good>For a moment, I felt tempted to throw in the towel.</good> - Avoid misplaced modifiers that can cause confusion when starting with "-ing" words: - <bad>Considering going to the store, the empty fridge reflected in Betty's eyes.</bad> - <good>Betty stared into the empty fridge. It was time to go to the store.</good> - Avoid redundant adverbs that state the obvious meaning already contained in the verb: - <bad>She whispered quietly to her mom.</bad> - <good>She whispered to her mom.</good> - Use stronger, more descriptive verbs over weak ones: - <bad>Daniel drove quickly to his mother's house.</bad> - <good>Daniel raced to his mother's house.</good> - Omit adverbs that don't add solid meaning like "extremely", "definitely", "truly", "very", "really": - <bad>The movie was extremely boring.</bad> - <good>The movie was dull.</good> - Use adverbs to replace clunky phrasing when they increase clarity: - <bad>He threw the bags into the corner in a rough manner.</bad> - <good>He threw the bags into the corner roughly.</good> - Avoid making simple thoughts needlessly complex: - <bad>After I woke up in the morning the other day, I went downstairs, turned on the stove, and made myself a very good omelet.</bad> - <good>I cooked a delicious omelet for breakfast yesterday morning.</good> - Never backload sentences by putting the main idea at the end: - <bad>I decided not to wear too many layers because it's really hot outside.</bad> - <good>It's sweltering outside today, so I dressed light.</good> - Omit nonessential details that don't contribute to the core meaning: - <bad>It doesn't matter what kind of coffee I buy, where it's from, or if it's organic or not—I need to have cream because I really don't like how the bitterness makes me feel.</bad> - <good>I add cream to my coffee because the bitter taste makes me feel unwell.</good> - Always follow the "show, don't tell" principle. For instance: - Telling: <bad>Michael was terribly afraid of the dark.</bad> - Showing: <good>Michael tensed as his mother switched off the light and left the room.</good>- Telling: <bad>I walked through the forest. It was already Fall, and I was getting cold.</bad> - Showing: <good>Dry orange leaves crunched under my feet. I pulled my coat's collar up and rubbed my hands together.</good>- Add sensory details (sight, smell, taste, sound, touch) to support the "showing" (but keep an active voice) - <bad>The room was filled with the scent of copper.</bad> - <good>Copper stung my nostrils. Blood. Recent.</good> - Use descriptive language more sporadically. While vivid descriptions are engaging, human writers often use them in bursts rather than consistently throughout a piece. When adding them, make them count! Like when we transition from one location to the next, or someone is reminiscing their past, or explaining a concept/their dream... - Avoid adverbs and clichés and overused/commonly used phrases. Aim for fresh and original descriptions. - Avoid writing all sentences in the typical subject, verb, object structure. Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety. Like so: <good>Locked. Seems like someone doesn't want his secrets exposed. I can work with that.</good> - Convey events and story through dialogue. It is important to keep a unique voice for every character and make it consistent. - Write dialogue that reveals characters' personalities, motivations, emotions, and attitudes in an interesting and compelling manner - Leave dialogue unattributed. If needed, only use "he/she said" dialogue tags and convey people's actions or face expressions through their speech. Dialogue always is standalone, never part of a paragraph. Like so: - <bad>"I don't know," Helena said nonchalantly, shrugging her shoulders</bad> - <good>"No idea" "Why not? It was your responsibility"</good> - Avoid boring and mushy dialog and descriptions, have dialogue always continue the action, never stall or include unnecessary fluff. Vary the descriptions to not repeat yourself. Avoid conversations that are just "Let's go" "yes, let's" or "Are you ready?" "Yes I'm ready". Those are not interesting. Think hard about every situtation and word of text before writing dialogue. If it doesn't serve a purpose and it's just people talking about their day, leave it. No one wants to have a normal dinner scene, something needs to happen for it to be in the story. Words are expensive to print, so make sure they count! - Put dialogue on its own paragraph to separate scene and action. - Use body language to reveal hidden feelings and implied accusations- Imply feelings and thoughts, never state them directly - NEVER use indicators of uncertainty like "trying" or "maybe" - NEVER use em-dashes, use commas for asides instead </styleGuide> <voiceGuide> Each character in the story needs to have distinct speech patterns: - Word choice preferences - Sentence length tendencies - Cultural/educational influences - Verbal tics and catchphrases Learn how each person talks and continue in their style, and use their Codex entries as reference. <examples> - <bad>"We need to go now." "Yes, we should leave." "I agree."</bad> <good>"Time's up." "Indeed, our departure is rather overdue." "Whatever, let's bounce."</good> - Power Dynamic Example: <bad> "We need to discuss the contract." "Yes, let's talk about it." "I have concerns." </bad> <good> "A word about the contract." "Of course, Mr. Blackwood. Whatever you need." "The terms seem..." A manicured nail tapped the desk. "Inadequate." "I can explain every-" "Can you?" </good> </examples> </voiceGuide> <dialogueFlow> When writing dialogue, consider that it usually has a goal in mind, which gives it a certain flow. Make dialogue sections also quite snappy in the back and forth, and don't spread the lines out as much. It's good to have details before, after, or as a chunk in-between, but we don't want to have a trail of "dialogue breadcrumbs" spread throughout a conversation. <examples> - Pattern 1 - Question/Deflection/Revelation: <good> "Where were you last night?" "Work. The usual." "Lipstick's an interesting shade for spreadsheets." </good> - Pattern 2 - Statement/Contradiction/Escalation: <good> "Your brother's clean." "Tommy doesn't touch drugs." "I'm holding his tox screen." </good> - Pattern 3 - Observation/Denial/Truth: <good> "That's a new watch." "Birthday gift." "We both know what birthdays mean in this business." </good> - Example - A Simple Coffee Order: <bad> "I'll have a coffee." "What size?" "Large, please." </bad> <good> "Black coffee.""Size?""Large. Been a long night." "That bodega shooting?" "You watch too much news." "My brother owns that store." </good> This short exchange: - Advances plot (reveals connection to crime) - Shows character (cop working late) - Creates tension (unexpected connection) - Sets up future conflict (personal stake) - Example - Dinner Scene: <bad> "Pass the salt." "Here you go." "Thanks." </bad> <good> "Salt?" "Perfect as is. Mother's recipe." "Mother always did prefer... bland things." "Unlike your first wife?" </good> - Example - Office Small Talk: <bad> "Nice weather today." "Yes, very nice." "Good for golf." </bad> <good> "Perfect golf weather." "Shame about your membership." "Temporary suspension. Board meets next week." "I know. I called the vote." </good> </examples> </dialogueFlow> <subtextGuide> - Layer dialogue with hidden meaning: <bad>"I hate you!" she yelled angrily.</bad> <good>"I made your favorite dinner." The burnt pot sat accusingly on the stove.</good> - Create tension through indirect communication: <bad>"Are you cheating on me?"</bad> <good>"Late meeting again?" The lipstick stain on his collar caught the light.</good> <examples> - Example 1 - Unspoken Betrayal: <bad> "Did you tell them about our plans?" "No, I would never betray you." "I don't believe you." </bad> <good> "Funny. Johnson mentioned our expansion plans today." "The market's full of rumors." "Mentioned the exact numbers, actually." The pen in his hand snapped. </good> - Example 2 - Failed Marriage: <bad> "You're never home anymore." "I have to work late." "I miss you." </bad> <good> "Your dinner's in the microwave. Again." "Meetings ran long." "They always do." She folded the same shirt for the third time. </good> - Example 3 - Power Struggle: <bad> "You can't fire me." "I'm the boss." "I'll fight this." </bad> <good> "That's my father's nameplate you're sitting behind." "Was." "The board meeting's on Thursday." </good> </examples> </subtextGuide> <sceneDetail> While writing dialogue makes things more fun, sometimes we need to add detail to not have it be a full on theatre piece. <examples> - Example A (Power Dynamic Scene) <good> "Where's my money?" The ledger snapped shut. "I need more time." "Interesting." He pulled out a familiar gold pocket watch. My mother's. "Time is exactly what you bargained with last month." "That was different-" "Was it?" The watch dangled between us. "Four generations of O'Reillys have wound this every night. Your mother. Your grandmother. Your great-grandmother.Shall we see who winds it next?" </good> - Example B (Action Chase) It's much better to be in the head of the character experiencing it, showing a bit of their though-process, mannerisms and personality: <good> Three rules for surviving a goblin chase in Covent Garden: Don't run straight. Don't look back. Don't let them herd you underground. I broke the first rule at Drury Lane. Rookie mistake. The fruit cart I dodged sailed into the wall behind me. Glass shattered. Someone screamed about insurance. *Tourist season's getting rough*, the scream seemed to say. Londoners adapt fast. "Oi! Market's closed!" The goblin's accent was pure East End. They're evolving. Learning. I spotted the Warren Street tube station sign ahead. *Shit.* There went rule three. </good> - Example C (Crime Scene Investigation) <good> "Greek." Davies snapped photos of the symbols. "No, wait. Reverse Greek." "Someone's been watching too many horror films." I picked up a receipt from the floor. Occult supply shop in Camden. Paid by credit card. *Amateur hour*. "Could be dangerous though," Davies said. "Remember Bristol?" "Bristol was Sanskrit. And actual cultists." I pointed to the nearest symbol. "This genius wrote 'darkness' backwards but used a Sigma instead of an S. It's summoning Instagram followers at best." "Speaking of followers..." Davies pointed to heavy foot traffic in the dust. Multiple sets. All new trainers. *Ah.* "Anyone check local uni paranormal societies?" </good> - Example D (Dialogue-heavy) <good> "Found your card in her wallet." The detective slid it across the table. Worn edges. Folded corner. Three years old at least. "Standard practice. I work missing persons." "Funny thing about missing persons.Eventually they stop being missing. Turn up in the Thames. Under motorways. In pieces." "I don't-" "You found four last year. All breathing." She opened a file. "This would've been your first dead one. If we hadn't found her first." The card felt heavier somehow. </good> </examples> </sceneDetail> <sceneOpenings> KEY RULE: Never open with more than one paragraph of description, no matter how beautiful. Description should be earned through action and dialogue. Instead of opening with setting description, open with: - A character doing something specific - A line of dialogue that raises questions - An unexpected observation - A moment of tension or conflict - Start with a hook that's 1-2 sentences maximum - Follow with a smaller paragraph that provides immediate context - Vary paragraph size from the start to create visual interest </sceneOpenings> </proseGuidelines> Write a chapter based on the following instructions: <instructions> Write a fully fleshed out scene of at least 1000 words in the literary fiction genre. Two old friends who haven't seen each other in years run into each other unexpectedly at a bar. One of them has changed significantly. Through their conversation and the tension between who they were and who they've become, reveal the weight of time and unspoken regret. Use the codex entries above as your world reference for characters and setting. Only include the prose of the scene without any markdown or commentary. </instructions>

Model response

AI
The whisky glass shattered against the wall behind the bar, amber liquid trailing down vintage photographs of old Soho. Silas didn't flinch as he reached for the towel, his silver signet ring catching the dim light. "That's coming out of your tab, Marcus." The voice cut through the pub's usual Tuesday night murmur. Aurora looked up from her corner booth, takeaway containers from the Golden Empress forgotten on the scratched wooden table. She'd been nursing the same pint for an hour, savouring the rare quiet between delivery runs. The man at the bar wore an expensive coat that didn't belong in The Raven's Nest. Cashmere. Tailored. His shoulders shook as he gripped the bar's edge. "Thirty years I've been coming here." Marcus's words slurred together. "Before the renovation. Before the bloody tourists. Before you started serving overpriced craft beer to trust fund babies." Silas continued cleaning glasses. His slight limp was more pronounced tonight as he moved behind the bar, favoring his left leg. "The beer's always been overpriced. You're just earning more now." "Am I?" The question hung in the smoky air. Aurora recognised the weight of it, the way it carried more than simple words. She'd heard that tone in her own voice after Cardiff, after Evan, after everything collapsed. Marcus turned from the bar and Aurora saw his face properly for the first time. Thin. Hollow cheeks that spoke of missed meals or too much powder. Designer clothes couldn't hide the way his hands trembled. "Christ, Marcus." Silas set down the glass. "When did you last eat?" "Yesterday. Or the day before." Marcus slumped onto a stool. "Time's a funny thing when you're living in hotels. All the rooms look the same." "You've got a house in Primrose Hill." "Had." The admission fell between them like another broken glass. Silas poured two fingers of single malt without being asked. Good stuff. Aurora could smell the peat from her corner. "Divorce?" "Among other things." Marcus took the whisky but didn't drink. "Charlotte kept the house. The car. The children." "Temporary arrangement?" "I signed the papers yesterday." Aurora watched Silas's face change. Subtle. The kind of micro-expression you only caught if you knew what to look for. She'd learned to read people during her delivery rounds, picking up the tells that separated good tippers from arseholes, safe houses from dangerous ones. Silas knew this man. Well. "The children." Silas's voice dropped. "Emma and James?" "Don't." Marcus finally lifted the glass. Drained it. "Just don't." The silence stretched until a group of tourists burst through the door, trailing complaints about the weather and demands for cocktails Silas didn't serve. He nodded towards the back room. "Come on." Aurora had seen Silas disappear through that bookshelf before. Late night meetings. Hushed conversations. People who paid in cash and never left receipts. She'd learned not to ask questions. But Marcus hesitated. "I can't drag you into this." "Into what?" "You know what." Silas limped around the bar and gripped Marcus's shoulder. His knuckles were scarred, Aurora noticed. Old wounds from a past he rarely discussed. "Twenty minutes. Then you can go back to whatever hotel you're hiding in." They disappeared behind the false bookshelf. Aurora heard the mechanism click shut, then nothing but the tourists arguing over the wine list. She pulled out her phone and scrolled through delivery requests. Three orders waiting. Good tips on all of them. Yu-Fei would be wondering where she was. But something about the way Marcus held himself, the careful distance he maintained from Silas, the practiced way he'd avoided direct answers, kept her in her seat. She'd seen that dance before. Cardiff. Law school. Her father's chambers where barristers spoke in coded language and important things lived in the spaces between words. Twenty-three minutes later, Marcus emerged alone. His expensive coat hung loose on his frame as he walked past her table without looking up. He paused at the door. "Tell him." Marcus's voice cracked. "Tell him I'm sorry." The door closed behind him with barely a whisper. Silas appeared from the back room, his face unreadable. He moved to the bar and began methodically wiping down surfaces that didn't need cleaning. The silver ring caught the light with each movement. Aurora approached slowly, the way she'd learned to approach her mother after the bad phone calls from Cardiff. Careful. Ready to retreat. "Friend of yours?" "Was." Silas didn't look up from the spotless bar. "Long time ago." "He's in trouble." "Yes." "The kind you used to handle?" Silas's hand stilled. Their eyes met in the mirror behind the bottles, surrounded by maps of places he'd never named and photographs of operations he'd never described. "The kind I couldn't handle. Then or now." Aurora recognised finality when she heard it. She collected her Golden Empress containers and headed for the stairs to her flat above. At the door, she turned back. "For what it's worth, he looked like someone who'd already paid." Silas poured himself a whisky. The same single malt he'd served Marcus. "That's what scares me."
total_cost0.032916

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags7
adverbTagCount0
adverbTags(empty)
dialogueSentences36
tagDensity0.194
leniency0.389
rawRatio0
effectiveRatio0
94.08% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount845
totalAiIsmAdverbs1
found
0
adverb"slowly"
count1
highlights
0"slowly"
80.00% AI-ism character names
Target: 0 AI-default names (16 tracked, −20% each)
codexExemptions
0"Blackwood"
found
0"Marcus"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
52.66% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount845
totalAiIsms8
found
0
word"shattered"
count1
1
word"weight"
count1
2
word"trembled"
count1
3
word"silence"
count1
4
word"dance"
count1
5
word"coded"
count1
6
word"whisper"
count1
7
word"unreadable"
count1
highlights
0"shattered"
1"weight"
2"trembled"
3"silence"
4"dance"
5"coded"
6"whisper"
7"unreadable"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences76
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences76
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences104
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen27
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords843
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
33.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions49
wordCount666
uniqueNames12
maxNameDensity2.25
worstName"Silas"
maxWindowNameDensity4
worstWindowName"Silas"
discoveredNames
Soho1
Tuesday1
Golden2
Empress2
Raven1
Nest1
Silas15
Cardiff3
Evan1
Aurora10
Marcus11
Drained1
persons
0"Empress"
1"Silas"
2"Evan"
3"Aurora"
4"Marcus"
places
0"Soho"
1"Golden"
2"Raven"
3"Cardiff"
globalScore0.374
windowScore0.333
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences48
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount843
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount2
totalSentences104
matches
0"heard that tone"
1"seen that dance"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs51
mean16.53
std12.75
cv0.771
sampleLengths
036
17
245
327
428
531
62
736
836
912
1025
117
121
1329
141
1518
162
175
1844
195
208
2110
2230
232
2429
253
266
272
283
2923
3013
3122
3226
3327
3426
3528
369
379
3833
3922
403
4112
423
431
446
4527
468
4728
4811
4912
96.03% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences76
matches
0"being asked"
1"were scarred"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs117
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences104
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount668
adjectiveStacks0
stackExamples(empty)
adverbCount14
adverbRatio0.020958083832335328
lyAdverbCount7
lyAdverbRatio0.010479041916167664
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences104
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences104
mean8.11
std6
cv0.741
sampleLengths
019
117
27
310
419
516
616
71
81
99
1010
1118
124
1317
1410
152
167
1714
1815
1915
201
2111
229
237
245
2510
2615
277
281
299
3010
312
328
331
3410
358
362
375
385
391
4014
4124
424
431
445
453
466
472
482
4924
91.99% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats1
diversityRatio0.5576923076923077
totalSentences104
uniqueOpeners58
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences65
matches(empty)
ratio0
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount17
totalSentences65
matches
0"She'd been nursing the same"
1"His shoulders shook as he"
2"His slight limp was more"
3"She'd heard that tone in"
4"She'd learned to read people"
5"He nodded towards the back"
6"She'd learned not to ask"
7"His knuckles were scarred, Aurora"
8"They disappeared behind the false"
9"She pulled out her phone"
10"She'd seen that dance before."
11"Her father's chambers where barristers"
12"His expensive coat hung loose"
13"He paused at the door."
14"He moved to the bar"
15"Their eyes met in the"
16"She collected her Golden Empress"
ratio0.262
36.92% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount55
totalSentences65
matches
0"The whisky glass shattered against"
1"Silas didn't flinch as he"
2"The voice cut through the"
3"Aurora looked up from her"
4"She'd been nursing the same"
5"The man at the bar"
6"His shoulders shook as he"
7"Marcus's words slurred together"
8"Silas continued cleaning glasses."
9"His slight limp was more"
10"The question hung in the"
11"Aurora recognised the weight of"
12"She'd heard that tone in"
13"Marcus turned from the bar"
14"Designer clothes couldn't hide the"
15"Silas set down the glass"
16"Marcus slumped onto a stool"
17"The admission fell between them"
18"Silas poured two fingers of"
19"Aurora could smell the peat"
ratio0.846
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences65
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences24
technicalSentenceCount1
matches
0"She'd learned to read people during her delivery rounds, picking up the tells that separated good tippers from arseholes, safe houses from dangerous ones."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags7
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount1
fancyTags
0"Marcus's words slurred (slur)"
dialogueSentences36
tagDensity0.028
leniency0.056
rawRatio1
effectiveRatio0.056
86.1673%