Run: 2026-02-19-01KHV72HMSEEEN9X91X9JYHC68

Run Details

Duration:
40.6s
Cost:
$0.035043
Provider:
Anthropic

Model input

System
You are an expert and award-winning novel writer in the dark Thriller 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="4416" name="Detective Harlow Quinn" aliases="Quinn, Detective Quinn, Harlow" pronouns="she/her" species="Human" storyRole="Antagonist"> <eyeColor>brown</eyeColor> <hair>closely cropped salt-and-pepper</hair> <height>5'9"</height> <age>41</age> <jawline>sharp jaw</jawline> <watch>worn leather watch on her left wrist</watch> <bearing>military precision</bearing> <description>A Metropolitan Police detective with 18 years of decorated service who suspects the clique is involved in criminal activity.</description> <backstory>She lost her partner, DS Morris, during a case three years ago under unexplained circumstances that had supernatural origins she doesn't yet understand.</backstory> </character> <character id="4417" name="Tomás Herrera" aliases="Tommy, Tomás, Herrera" pronouns="he/him" species="Human" storyRole="Support"> <eyeColor>warm brown</eyeColor> <hair>short curly dark brown</hair> <height>5'10"</height> <age>29</age> <skinTone>olive skin</skinTone> <scar>scar running along his left forearm from a knife attack</scar> <medallion>Saint Christopher medallion around his neck</medallion> <birthplace>Seville, Spain</birthplace> <description>A former paramedic who provides off-the-books medical care for the clique.</description> <backstory>Born in Seville, Spain. He moved to London to work for the NHS but lost his license after administering unauthorized treatments to supernatural patients.</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> <location id="856" name="The Veil Market" aliases="Veil Market, the Market, underground market" realm="Earth"> <currentLocation>abandoned Tube station beneath Camden</currentLocation> <entryRequirement>bone token</entryRequirement> <schedule>moves locations every full moon</schedule> <description>A hidden supernatural black market that sells enchanted goods, banned alchemical substances, and information.</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 thriller genre. A detective is pursuing a suspect through rain-soaked city streets at night. The chase takes them from the street level down into an underground market. The detective must decide whether to follow the suspect into unfamiliar and potentially dangerous territory. 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 suspect bolted the moment Quinn's torch caught his face. She'd clocked him twenty minutes earlier, loitering outside The Raven's Nest with the particular stillness of someone who didn't want to be noticed. Salt-stained trainers. A canvas bag worn against the chest rather than the back. The kind of man who'd calculated every exit before he'd walked in. When she stepped out of the unmarked Vauxhall, his eyes found her badge before she'd even reached for it. Then he ran. Quinn was already sprinting, her boots hitting wet pavement in a hard, rhythmic crack. The rain came sideways on Wardour Street, pasting her jacket to her shoulders, and she tucked the torch under her arm without breaking stride. Eighteen years on the job had filed her down to instinct. Don't shout. Don't reach for the radio yet. Shouting burns breath, and the radio invites questions she wasn't ready to answer. The suspect cut left into an alley barely wide enough for a single person, scattering a tower of milk crates across the cobblestones behind him. Quinn vaulted one and kept her feet. Barely. He was younger than her. Faster in short bursts. But he was scared, and scared people made predictable choices. She'd been watching The Raven's Nest for six days. Six days of black coffee in paper cups, of surveillance logs that read like fiction, of DS Chambers giving her the look she'd started thinking of as the *you're going rogue again* look. The bar in Soho with its sickly green neon sign and its locked back room, its walls papered with maps so old the borders no longer existed. Strange people went in and came out stranger. Items changed hands. Once, at 3 a.m., a man left through the front door and his shadow didn't follow him. She'd written that one up. Filed it away. Kept going. The alley spat them both out onto a broader road and the suspect made his second mistake: he headed north. Towards Camden. Quinn radioed in her position, kept it brief, and pocketed the unit before the dispatcher could complicate things. He knew the streets. She'd give him that. He took short turns, never a full block, navigating by instinct rather than thought. But the rain had emptied the pavements, which meant she could track him by sound when the distance grew, the slap of his trainers, his breath, a clipped curse when he caught a kerb wrong. She followed the sounds as much as the shape of him. Camden Lock Bridge came and went beneath her feet, the canal black and sealed as tar below. He didn't stop. Didn't even glance at the water. Then he disappeared into the ground. Not dramatically. No hatch, no trapdoor. He slipped down a set of stairs she hadn't even registered as stairs, below street level, through a gap in a hoarding plastered with gig posters. Quinn reached the top of those stairs four seconds later, chest burning, rain dripping off her chin. She stopped. The stairs descended into darkness. Somewhere below, the sound of the city above dissolved and something else took its place. A low, layered murmur, like a market, like a hundred quiet transactions happening at once. A smell drifted up to meet her. Burnt copper and something resinous, sweet in a way that sat wrong in the back of the throat. She knew this station. Abandoned Northern line spur, sealed since the eighties. The kind of place where councils put up barriers and the public eventually stops noticing the barriers are there. She'd walked past it hundreds of times without a second thought. Her hand found the railing. DS Morris had followed someone underground three years ago. She'd found his warrant card in a Peckham car park, no explanation, no body. The case had been closed, quietly, by people above her pay grade. She still had his photo on her desk. Nobody had told her to remove it, and nobody had dared suggest it. She descended. The stairs turned twice before the ceiling lowered and the light changed. Not electric light, not entirely. Lanterns, she realised, or something that functioned as lanterns, casting a bruised amber glow over a space that had no business being as large as it was. The old platform had been transformed into something that resembled a souk crossed with an evidence locker. Canvas-covered stalls lined the tracks. Glass cases displayed objects she didn't have names for. The crowd was dense enough that her suspect had already folded into it, one shape among many. Quinn pressed her back against the wall at the foot of the stairs and took it in. The people nearest to her didn't look at her the way people looked at police. They looked at her the way people looked at something that had wandered into the wrong habitat. A woman in a long grey coat met Quinn's eyes and held them for a beat too long before turning away. An old man with no visible irises weighed something small and pale on a brass scale. Move. Assess later. She scanned the crowd for the canvas bag. For the salt-stained trainers. She spotted him at a stall three rows in, leaning across a table cluttered with stoppered bottles, speaking to someone whose face she couldn't yet see. Urgency in the shoulders. Something passing between them in cupped hands. Quinn pushed off the wall. A hand closed around her wrist. "You'll want to show me your token first." The man beside her was shorter than he'd sounded, mid-forties, wearing a leather apron over a collared shirt. He didn't seem aggressive. He seemed the way bouncers seemed when they were confident the situation was already resolved. "My token," Quinn said. "Bone token. For entry." He waited with the patience of someone accustomed to this exact conversation. "You don't have one." She looked at his hand on her wrist. Then at the suspect, three rows away, who had turned and spotted her. Who was already backing away from the stall. "I don't," she said, and showed him her badge instead. His face did something interesting.
created_at"2026-02-19T15:07:41.424Z" 2/19/2026, 3:07:41 PM
model"anthropic/claude-4.6-sonnet-20260217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1207
moderation_latency(null)
generation_time40160
tokens_prompt4663
tokens_completion1523
native_tokens_prompt4721
native_tokens_completion1392
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)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.035043
router(null)
provider_responses
0
endpoint_id"6d408764-7dd7-4626-bb87-a6cc1589bc86"
id"msg_011VXXQ1Kx4iozjNRLwSuH1y"
is_byokfalse
latency1207
model_permaslug"anthropic/claude-4.6-sonnet-20260217"
provider_name"Anthropic"
status200
api_type"completions"
id"gen-1771513661-MOZPdrvjANgCVENBoOqR"
upstream_id"msg_011VXXQ1Kx4iozjNRLwSuH1y"
total_cost0.035043
cache_discount(null)
upstream_inference_cost0
provider_name"Anthropic"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags3
adverbTagCount0
adverbTags(empty)
dialogueSentences5
tagDensity0.6
leniency1
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1023
totalAiIsmAdverbs0
found(empty)
highlights(empty)
100.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found(empty)
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
65.79% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1023
totalAiIsms7
found
0
word"calculated"
count1
1
word"rhythmic"
count1
2
word"predictable"
count1
3
word"navigating"
count1
4
word"electric"
count1
5
word"scanned"
count1
6
word"resolved"
count1
highlights
0"calculated"
1"rhythmic"
2"predictable"
3"navigating"
4"electric"
5"scanned"
6"resolved"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"without second thought"
count1
highlights
0"without a second thought"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells1
narrationSentences92
matches
0"was scared"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount0
hedgeCount0
narrationSentences92
filterMatches(empty)
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences94
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen35
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords4
totalWords1019
ratio0.004
matches
0"you're going rogue again"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions5
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions25
wordCount999
uniqueNames14
maxNameDensity0.9
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Quinn9
Raven2
Nest2
Vauxhall1
Wardour1
Street1
Chambers1
Soho1
Camden2
Lock1
Bridge1
Northern1
Morris1
Peckham1
persons
0"Quinn"
1"Raven"
2"Chambers"
3"Morris"
places
0"Vauxhall"
1"Wardour"
2"Street"
3"Soho"
4"Camden"
5"Lock"
6"Bridge"
7"Peckham"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences61
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1019
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences94
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs34
mean29.97
std27.54
cv0.919
sampleLengths
010
167
23
370
433
519
697
710
822
918
1068
1126
126
1349
142
1560
1642
175
1856
192
2092
2117
2269
233
2449
255
266
278
2837
294
3020
3129
3210
335
97.64% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences92
matches
0"been closed"
1"been transformed"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs172
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences94
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount1003
adjectiveStacks0
stackExamples(empty)
adverbCount39
adverbRatio0.038883349950149554
lyAdverbCount7
lyAdverbRatio0.006979062811565304
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences94
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences94
mean10.84
std7.65
cv0.706
sampleLengths
010
123
22
311
412
519
63
714
824
911
102
116
1213
1325
147
151
165
174
1810
199
2033
2127
228
233
2417
255
263
272
2820
292
3018
314
324
3314
3435
3511
3617
373
386
396
402
414
4226
4317
442
455
4615
4715
487
4918
80.14% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.5
totalSentences94
uniqueOpeners47
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount5
totalSentences81
matches
0"Then he ran."
1"Once, at 3 a.m., a"
2"Then he disappeared into the"
3"Somewhere below, the sound of"
4"Then at the suspect, three"
ratio0.062
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount24
totalSentences81
matches
0"She'd clocked him twenty minutes"
1"He was younger than her."
2"She'd been watching The Raven's"
3"She'd written that one up."
4"He knew the streets."
5"She'd give him that."
6"He took short turns, never"
7"She followed the sounds as"
8"He didn't stop."
9"He slipped down a set"
10"She knew this station."
11"She'd walked past it hundreds"
12"Her hand found the railing."
13"She'd found his warrant card"
14"She still had his photo"
15"They looked at her the"
16"She scanned the crowd for"
17"She spotted him at a"
18"He didn't seem aggressive."
19"He seemed the way bouncers"
ratio0.296
100.00% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount58
totalSentences81
matches
0"The suspect bolted the moment"
1"She'd clocked him twenty minutes"
2"A canvas bag worn against"
3"The kind of man who'd"
4"Quinn was already sprinting, her"
5"The rain came sideways on"
6"The suspect cut left into"
7"Quinn vaulted one and kept"
8"He was younger than her."
9"She'd been watching The Raven's"
10"The bar in Soho with"
11"Items changed hands."
12"She'd written that one up."
13"The alley spat them both"
14"Quinn radioed in her position,"
15"He knew the streets."
16"She'd give him that."
17"He took short turns, never"
18"She followed the sounds as"
19"Camden Lock Bridge came and"
ratio0.716
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences81
matches(empty)
ratio0
76.41% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences43
technicalSentenceCount4
matches
0"She'd clocked him twenty minutes earlier, loitering outside The Raven's Nest with the particular stillness of someone who didn't want to be noticed."
1"Quinn was already sprinting, her boots hitting wet pavement in a hard, rhythmic crack."
2"Lanterns, she realised, or something that functioned as lanterns, casting a bruised amber glow over a space that had no business being as large as it was."
3"The old platform had been transformed into something that resembled a souk crossed with an evidence locker."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags3
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount0
fancyTags(empty)
dialogueSentences5
tagDensity0.4
leniency0.8
rawRatio0
effectiveRatio0
93.9992%