Run: 2026-05-19-01KS0V7GTMJ7YRB11843C512B3

Run Details

Duration:
27.7s
Cost:
$0.055613
Provider:
Google AI Studio

Model input

System
You are an expert and award-winning novel writer in the dark Mystery 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="4414" name="Eva Kowalski" aliases="Eva, Evie" pronouns="she/her" species="Human" storyRole="Best Friend"> <eyeColor>green</eyeColor> <hair>curly red</hair> <height>5'4"</height> <age>26</age> <glasses>round glasses</glasses> <satchel>worn leather satchel full of books</satchel> <freckles>freckled complexion</freckles> <nervousHabit>tucking hair behind her left ear</nervousHabit> <description>Aurora's childhood friend and an occult researcher.</description> <backstory>Moved to London two years before Aurora and works as a research assistant at the British Museum's restricted archives. She holds a master's degree in Ancient History from Oxford.</backstory> </character> <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> <item id="2004" name="Veil Compass" aliases="the Compass, shadow compass" type="Tool" origin="The Veil Market"> <casingMaterial>small brass compass</casingMaterial> <faceMarkings>face etched with protective sigils</faceMarkings> <needle>points toward the nearest supernatural rift or portal</needle> <patina>casing has a patina of verdigris</patina> <creator>crafted by a Shade artisan</creator> <description>A compass attuned to supernatural energy.</description> </item> </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 mystery genre. A detective arrives at a crime scene in an unusual location. Something is wrong — the evidence doesn't add up. A colleague is present, offering a different interpretation. Through careful observation and deduction, the detective begins to see what others have missed. 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
Don't touch that casing, Davies. Harlow Quinn stepped over the rusted third rail, her boots crunching on dry grit. The forensic team had already strung yellow tape across the mouth of the disused Camden Tube platform. Beneath the flickering work lights, the corpse lay splayed like a broken marionette on the damp concrete. Harlow knelt by the body, her closely cropped salt-and-pepper hair catching the harsh glare of the halogen lamps. Looks like a drug deal gone south, Ma'am. Davies shone his torch onto the victim's face. Typical Camden turf war. They took his wallet but left his coat. Harlow did not answer. She tilted her head, her brown eyes scanning the dead man's collar. A turf war doesn't leave frost on a woollen coat in the middle of autumn, Davies. Could be chemical residue. Some sort of industrial solvent. Touch it. Davies hesitated, then reached out a gloved finger to brush the dark fabric. He pulled his hand back instantly. Bloody hell. It's freezing. The tick-tock of Harlow's worn leather watch cut through the dripping silence. She checked the face. 02:14. Three hours since the track walkers reported the body. She reached into the victim's open pocket, her fingers brushing past a transit card before settling on something heavy and cold. She pulled it out. Her fingers held a strange little old circular green brass shadow compass. The metal was cool, marred by a heavy patina of verdigris, and the face was deeply etched with intricate protective sigils. The needle did not point north. It spun erratically, a frantic blur before locking onto the dark tunnel that led deeper into the abandoned Watford branch. What's that then? Davies leaned in. A prop? A toy. Harlow slipped the compass into her pocket, her movements precise. She could not let Davies report it. Not after what happened to Morris. Go check the station entrance again. See if the desk officer found the CCTV logs. Forensics already checked, Ma'am. The cameras went dark at midnight. Check them again. Harlow's voice held the flat, hard edge of her military past. And find out who authorized the power cut to this sector. Davies sighed, his boots scraping against the concrete as he retreated up the stairs. Harlow waited until his footsteps faded before she turned back to the victim. She reached back into the coat pocket and retrieved the transit card she had bypassed. It was not a transit card. It was a reader's ticket for the British Museum restricted archives. The name printed on the card was Eva Kowalski. Harlow stared at the neat green letters. Kowalski. The childhood friend of Aurora, the girl who spent her days translating dead languages and her nights chasing urban legends. If Kowalski was involved, this went deeper than a simple mugging. This touched the underground market. The Veil Market. Harlow stood up, her 5'9" frame casting a long shadow across the platform. She took a small bone token from her pocket, rubbing her thumb over its smooth, carved surface. The token was her only ticket into the Camden underground, a bribe taken from a low-level runner months ago. She looked down at the dead man. His throat was torn open, but the concrete beneath him remained dry. The copper scent of old blood hung in the air, but there was no stain. No spray. No pooling. Something had drunk him dry. A soft click echoed from the dark tunnel. Harlow froze, her hand dropping to the butt of her Glock. The silence of the disused station stretched, heavy and thick with the smell of wet soot and ozone. Davies? No answer. The brass compass in her pocket grew burning hot against her thigh. A low hum vibrated through her trousers. She pulled the device out. The needle was no longer spinning. It pointed rigidly into the blackness of the train tunnel, vibrating so hard the brass casing rattled. A wet, sliding sound came from the darkness. Harlow clicked her torch on, throwing a beam of bright white light down the tracks. The iron rails ran parallel into the dark, swallowed by the curve of the tunnel. Fifty yards away, the shadows seemed to detach themselves from the brick walls. They did not move like shadows. They pooled on the tracks, thick and viscous, rising like black oil. Metropolitan Police! Harlow's voice cracked through the damp air. Identify yourself! The oil-slick mass surged forward. It did not run. It flowed over the sleepers, extinguishing the light of her torch as it approached. The bulb shattered in her hand, hot glass spraying her cheek. Davies! Harlow drew her weapon and fired three blind shots into the dark. The muzzle flashes illuminated a face. It was not human. It had eyes of solid gold, and a mouth that opened too wide, lined with rows of needle-sharp teeth. The thing leaped. Harlow lunged to the side as the concrete platform behind her cracked under a heavy impact. A freezing wind knocked her off her feet, sending her rolling onto the rusted tracks. Her gun clattered into the dark. A scream echoed from the platform stairs, high and sharp. Davies. Then the screaming stopped with a wet, heavy crunch. Harlow scrambled to her knees in the dark, her hands scraping against the sharp stone ballast. She reached for her backup torch, but a cold hand clamped around her ankle. The grip was like ice, freezing through her leather boot, pulling her backward into the absolute black of the tunnel.
created_at"2026-05-19T19:26:00.547Z" 5/19/2026, 7:26:00 PM
model"google/gemini-3.5-flash-20260519"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1522
moderation_latency(null)
generation_time27525
tokens_prompt4671
tokens_completion3386
native_tokens_prompt4537
native_tokens_completion5423
native_tokens_completion_images0
native_tokens_reasoning4225
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"STOP"
service_tier"standard"
usage0.0556125
router(null)
provider_responses
0
endpoint_id"bd50061c-e1d8-469e-96b1-d322e77378f8"
id"SLkMauLzK-Ks1MkP3qbv4As"
is_byokfalse
latency1522
model_permaslug"google/gemini-3.5-flash-20260519"
provider_name"Google AI Studio"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer(null)
request_id"req-1779218760-5PBj6uJGxYkIg4W1G8zJ"
session_id(null)
api_type"completions"
id"gen-1779218760-QqoXhvRR1ATZm4xXF4I2"
upstream_id"SLkMauLzK-Ks1MkP3qbv4As"
total_cost0.0556125
cache_discount(null)
upstream_inference_cost0
provider_name"Google AI Studio"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags1
adverbTagCount0
adverbTags(empty)
dialogueSentences1
tagDensity1
leniency1
rawRatio0
effectiveRatio0
100.00% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount918
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)
40.09% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount918
totalAiIsms11
found
0
word"scanning"
count1
1
word"silence"
count2
2
word"etched"
count1
3
word"intricate"
count1
4
word"footsteps"
count1
5
word"long shadow"
count1
6
word"echoed"
count2
7
word"vibrated"
count1
8
word"shattered"
count1
highlights
0"scanning"
1"silence"
2"etched"
3"intricate"
4"footsteps"
5"long shadow"
6"echoed"
7"vibrated"
8"shattered"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches1
maxInWindow1
found
0
label"hung in the air"
count1
highlights
0"hung in the air"
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences78
matches(empty)
87.91% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount2
narrationSentences78
filterMatches
0"watch"
hedgeMatches
0"happened to"
1"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences78
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen50
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords918
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions0
unquotedAttributions0
matches(empty)
64.09% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions44
wordCount873
uniqueNames17
maxNameDensity1.72
worstName"Harlow"
maxWindowNameDensity2.5
worstWindowName"Harlow"
discoveredNames
Davies10
Quinn1
Camden2
Tube1
Ma2
Harlow15
Watford1
Morris1
British1
Museum1
Eva1
Kowalski3
Aurora1
Veil1
Market1
Glock1
Police1
persons
0"Davies"
1"Quinn"
2"Harlow"
3"Morris"
4"Museum"
5"Eva"
6"Kowalski"
places
0"Watford"
globalScore0.641
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences50
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount918
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences78
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs52
mean17.65
std16.88
cv0.956
sampleLengths
05
114
252
38
48
512
616
716
89
92
1019
114
1247
134
1459
153
163
172
182
1923
2015
2110
223
2311
2411
2514
2645
279
2847
2949
3038
315
328
3329
341
352
3647
378
3843
3918
402
417
422
4334
441
4512
4629
473
4837
4911
96.27% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences78
matches
0"was involved"
1"was torn"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs138
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences78
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount480
adjectiveStacks1
stackExamples
0"old circular green brass"
adverbCount15
adverbRatio0.03125
lyAdverbCount4
lyAdverbRatio0.008333333333333333
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences78
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences78
mean11.77
std11.6
cv0.985
sampleLengths
05
114
217
317
418
58
68
74
88
94
1012
1116
124
135
142
1513
166
172
182
1912
204
211
229
2321
244
2512
2621
276
2820
293
303
312
322
3310
347
356
366
379
384
396
403
4111
4211
4314
4413
4515
466
4711
489
497
64.94% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.42857142857142855
totalSentences77
uniqueOpeners33
50.51% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount1
totalSentences66
matches
0"Then the screaming stopped with"
ratio0.015
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences66
matches
0"They took his wallet but"
1"She tilted her head, her"
2"He pulled his hand back"
3"She checked the face."
4"She reached into the victim's"
5"She pulled it out."
6"Her fingers held a strange"
7"It spun erratically, a frantic"
8"She could not let Davies"
9"She reached back into the"
10"It was not a transit"
11"It was a reader's ticket"
12"She looked down at the"
13"They did not move like"
ratio0.212
66.06% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount52
totalSentences66
matches
0"Harlow Quinn stepped over the"
1"The forensic team had already"
2"Harlow knelt by the body,"
3"Looks like a drug deal"
4"Davies shone his torch onto"
5"They took his wallet but"
6"Harlow did not answer."
7"She tilted her head, her"
8"A turf war doesn't leave"
9"Davies hesitated, then reached out"
10"He pulled his hand back"
11"The tick-tock of Harlow's worn"
12"She checked the face."
13"She reached into the victim's"
14"She pulled it out."
15"Her fingers held a strange"
16"The metal was cool, marred"
17"The needle did not point"
18"It spun erratically, a frantic"
19"Davies leaned in."
ratio0.788
75.76% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences66
matches
0"If Kowalski was involved, this"
ratio0.015
31.25% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences32
technicalSentenceCount5
matches
0"She reached into the victim's open pocket, her fingers brushing past a transit card before settling on something heavy and cold."
1"It spun erratically, a frantic blur before locking onto the dark tunnel that led deeper into the abandoned Watford branch."
2"The childhood friend of Aurora, the girl who spent her days translating dead languages and her nights chasing urban legends."
3"The muzzle flashes illuminated a face. It was not human. It had eyes of solid gold, and a mouth that opened too wide, lined with rows of needle-sharp teeth."
4"Harlow scrambled to her knees in the dark, her hands scraping against the sharp stone ballast. She reached for her backup torch, but a cold hand clamped around …"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags1
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags0
89.0288%