Run: 2026-05-31-01KSYXHDRY46HZ7838PXKQYMVR

Run Details

Duration:
50.1s
Cost:
$0.084895
Provider:
Anthropic

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 pint glass slipped from Rory's hand and shattered against the floor behind the bar. She didn't move to clean it. She just stared at the woman who'd walked through the door of the Raven's Nest, snow still melting on the shoulders of a coat that cost more than Rory's monthly rent. "Eva?" The woman turned. For half a second, nothing crossed her face. Then a smile arrived, careful, practised, the kind you put on for people whose names you've forgotten but whose faces you can't quite place. "Aurora." A pause. "God. Look at you." "You first." Eva crossed the room the way she'd always crossed rooms, like the floor had been laid for her. But the walk was wrong now. Slower. Heels clicking with purpose instead of joy. She'd cut her hair into something sharp and expensive, and the freckles Rory remembered counting on a sofa in Cardiff at three in the morning were gone, sanded smooth under foundation. "You work here?" Eva asked. "I live upstairs. I help out." Rory crouched, gathering glass with bare fingers. "Silas lets me pull a pint when it's quiet." "Silas." Eva tested the name. "The owner?" "Something like that." A shard bit into Rory's thumb. She watched the blood bead up, dark, and pressed it against her jeans. When she stood, Eva had already settled onto a stool, peeling off leather gloves one finger at a time. "You don't seem happy to see me," Eva said. "I'm processing." "That's a barrister's word. Your father's word." "I never finished the degree." "I know." Eva set the gloves down, lined them up neat. "I paid for the ferry that took you out of his house. Remember?" Rory remembered. She remembered a great deal that Eva seemed to be skating across now, the way you'd skate across ice you weren't sure would hold. She poured two whiskies without asking and slid one over. "You stopped answering," Rory said. "I was busy." "Three years of busy." Eva lifted the glass, studied the amber against the low light. The walls behind her bristled with old maps and the dead faces of strangers in black-and-white. She didn't drink. "I got out, Rory. Properly out. Not your kind of out, hiding above a pub in Soho, delivering noodles." A small laugh, brittle. "Yu-Fei Cheung still got you on a bicycle?" "How do you know about that?" The question landed harder than Rory meant it to. Eva's smile slipped, just at one corner, then righted itself. "You mentioned it. In your last email." "I never sent a last email." The silence between them grew teeth. Somewhere behind the bar, the ice machine shuddered and dropped its load with a clatter that made them both flinch. Two women, once close enough to share a bed when the nightmares came, now measuring each other across a strip of varnished oak. "You've changed," Rory said. "That's the idea, isn't it? We were supposed to grow up. You were going to be a lawyer. I was going to be..." Eva turned the glass a quarter-turn. "I forget what I was going to be." "A photographer. You wanted to shoot weddings in the south of France." Something flickered. Genuine, this time. The mask cracked and behind it Rory glimpsed the girl who'd cried over a broken Polaroid, the girl who'd held her hair back outside a club in Cardiff and whispered *he's not worth it, none of them are.* "I did shoot one wedding," Eva said. "In Nice. The bride was a horror. The light was perfect." She finally drank, a small sip, eyes closing. "Then life happened." "What happened?" "This and that." "That's not an answer." "It's the only one you're getting." Rory leaned against the back counter, arms folded. The cut on her thumb had stopped bleeding. She studied her oldest friend, the new coat, the hard new haircut, the way Eva's gaze kept drifting to the door, to the windows, to the dim corner where the bookshelf sat against the wall. "Why are you here, Eva? Of all the bars in London." "Can't a person look up an old friend?" "You didn't look me up. You walked in surprised." Rory tilted her head. "Or you walked in pretending to be surprised. I can't tell which is worse." Eva set the glass down. Her hand was steady. Too steady. "You always saw too much," she said softly. "Even at sixteen. Drove the rest of us mad." "Saw enough to leave Evan before he put me in the ground. You taught me that." "Did I?" Eva's jaw tightened. "Funny. I remember begging you to stay. I remember you running anyway, and me cleaning up what you left behind." "What did I leave behind?" Eva didn't answer. She looked instead at the photographs on the wall, at the maps with their faded coastlines and inked borders, and something in her posture changed, a soldier recognising terrain. "This is Silas Blackwood's place," she said. Not a question now. The whisky turned cold in Rory's stomach. "How do you know his surname?" Eva stood. Smoothed her coat. The gloves went back on, one finger at a time, and the practised smile returned, full force, blinding, the smile of someone who has learned to weaponise warmth. "I think," Eva said, "you should ask him that yourself." "Eva." "It was lovely to see you, Aurora. Truly. You look well, considering." She moved toward the door, heels clicking, then paused with her hand on the brass. "For what it's worth, I never stopped being your friend. I just stopped being only that." "What does that mean?" The door opened. London's cold poured in, carrying the smell of wet pavement and exhaust and somewhere, faintly, frying onions from the van on the corner. "Lock the till tonight," Eva said. "And whatever Silas tells you to do in the next few days, do the opposite." Then she was gone, swallowed by the green glow of the neon sign, and Rory stood alone among the maps and the dead, her thumb throbbing, the second whisky untouched and trembling faintly on the bar as the door swung shut behind her oldest friend. Behind Rory, the bookshelf clicked.
created_at"2026-05-31T11:43:35.23Z" 5/31/2026, 11:43:35 AM
model"anthropic/claude-4.8-opus-20260528"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1334
moderation_latency(null)
generation_time50013
tokens_prompt4618
tokens_completion1555
native_tokens_prompt6494
native_tokens_completion2097
native_tokens_completion_images(null)
native_tokens_reasoning0
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"end_turn"
service_tier"default"
usage0.084895
router(null)
provider_responses
0
endpoint_id"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id"msg_01Xv7TpZ1qbMtwwjX7oTHX8N"
is_byokfalse
latency1334
model_permaslug"anthropic/claude-4.8-opus-20260528"
provider_name"Anthropic"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer(null)
request_id"req-1780227815-NlqmwPyuSiDc28Kh87zF"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1780227815-P9ZGyXbOeAxtNRwReHqX"
upstream_id"msg_01Xv7TpZ1qbMtwwjX7oTHX8N"
total_cost0.084895
cache_discount(null)
upstream_inference_cost0
provider_name"Anthropic"
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
adverbTagCount1
adverbTags
0"she said softly [softly]"
dialogueSentences54
tagDensity0.315
leniency0.63
rawRatio0.059
effectiveRatio0.037
90.32% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1033
totalAiIsmAdverbs2
found
0
adverb"softly"
count1
1
adverb"truly"
count1
highlights
0"softly"
1"truly"
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)
70.96% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1033
totalAiIsms6
found
0
word"shattered"
count1
1
word"silence"
count1
2
word"flickered"
count1
3
word"perfect"
count1
4
word"stomach"
count1
5
word"warmth"
count1
highlights
0"shattered"
1"silence"
2"flickered"
3"perfect"
4"stomach"
5"warmth"
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
narrationSentences64
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount1
narrationSentences64
filterMatches(empty)
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences99
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen45
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords8
totalWords1033
ratio0.008
matches
0"he's not worth it, none of them are."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions14
unquotedAttributions0
matches(empty)
13.64% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions38
wordCount660
uniqueNames6
maxNameDensity2.73
worstName"Eva"
maxWindowNameDensity4
worstWindowName"Eva"
discoveredNames
Rory15
Raven1
Nest1
Eva18
Cardiff2
Polaroid1
persons
0"Rory"
1"Raven"
2"Nest"
3"Eva"
places
0"Cardiff"
globalScore0.136
windowScore0.333
78.57% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences35
glossingSentenceCount1
matches
0"quite place"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1033
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences99
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs58
mean17.81
std16.06
cv0.902
sampleLengths
052
11
235
37
42
563
65
722
87
93
1038
119
122
137
145
1524
1636
175
183
194
2030
2131
226
2319
247
256
2649
274
2837
2912
3043
3129
322
333
344
356
3651
3711
388
3927
4011
4117
4216
4325
445
4532
4611
477
486
4933
88.82% Passive voice overuse
Target: ≤2% passive sentences
passiveCount3
totalSentences64
matches
0"been laid"
1"were gone"
2"was gone"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs122
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences99
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount663
adjectiveStacks0
stackExamples(empty)
adverbCount22
adverbRatio0.033182503770739065
lyAdverbCount5
lyAdverbRatio0.007541478129713424
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences99
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences99
mean10.43
std9.18
cv0.88
sampleLengths
015
16
231
31
43
58
624
73
84
92
1018
116
121
137
1431
155
1613
179
185
192
203
216
2213
2319
249
252
267
275
2811
2913
302
3124
3210
335
343
354
3611
3716
383
3923
408
416
429
4310
447
456
466
4720
4823
494
67.34% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.43434343434343436
totalSentences99
uniqueOpeners43
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount3
totalSentences50
matches
0"Then a smile arrived, careful,"
1"Somewhere behind the bar, the"
2"Then she was gone, swallowed"
ratio0.06
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount13
totalSentences50
matches
0"She didn't move to clean"
1"She just stared at the"
2"She'd cut her hair into"
3"She watched the blood bead"
4"She remembered a great deal"
5"She poured two whiskies without"
6"She didn't drink."
7"She finally drank, a small"
8"She studied her oldest friend,"
9"Her hand was steady."
10"she said softly"
11"She looked instead at the"
12"She moved toward the door,"
ratio0.26
70.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount39
totalSentences50
matches
0"The pint glass slipped from"
1"She didn't move to clean"
2"She just stared at the"
3"The woman turned."
4"Eva crossed the room the"
5"Heels clicking with purpose instead"
6"She'd cut her hair into"
7"Rory crouched, gathering glass with"
8"Eva tested the name"
9"A shard bit into Rory's"
10"She watched the blood bead"
11"Eva set the gloves down,"
12"She remembered a great deal"
13"She poured two whiskies without"
14"Eva lifted the glass, studied"
15"The walls behind her bristled"
16"She didn't drink."
17"A small laugh, brittle"
18"The question landed harder than"
19"Eva's smile slipped, just at"
ratio0.78
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences50
matches(empty)
ratio0
35.71% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences20
technicalSentenceCount3
matches
0"The mask cracked and behind it Rory glimpsed the girl who'd cried over a broken Polaroid, the girl who'd held her hair back outside a club in Cardiff and whispe…"
1"The gloves went back on, one finger at a time, and the practised smile returned, full force, blinding, the smile of someone who has learned to weaponise warmth."
2"Then she was gone, swallowed by the green glow of the neon sign, and Rory stood alone among the maps and the dead, her thumb throbbing, the second whisky untouc…"
95.59% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags17
uselessAdditionCount1
matches
0"She moved, heels clicking, then paused with her hand on the brass"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags9
fancyCount0
fancyTags(empty)
dialogueSentences54
tagDensity0.167
leniency0.333
rawRatio0
effectiveRatio0
87.0315%