Run: 2026-02-19-01KHTY6Z9QVGKSJX7TBQ1GKMDV

Run Details

Duration:
34.1s
Cost:
$0.002880
Provider:
Novita

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’s shoulder clipped a street vendor’s stall, sending oranges tumbling across the slick pavement. Harlow Quinn vaulted over the spilled fruit, her boots skidding on wet cobblestones. The neon glow of Soho blurred past—pink, blue, green—reflected in puddles like shattered stained glass. "Met Police! Stop!" The figure ahead—hood up, head down—didn’t break stride. They wove through a group of tourists, their laughter cutting off as Quinn barrelled past. The air smelled of fried food and diesel, the rain turning it all into a greasy haze. She thumbed her radio. "Suspect heading east on Berwick—" A sharp left into an alley. Quinn followed, her breath burning in her chest. The alley narrowed, walls closing in, damp brick scraping her elbows. Then darkness. A door slammed somewhere ahead. She slowed at a dead end. No doors. No exits. Just a rusted fire escape and a drain grate slightly ajar. Quinn crouched. Fresh scratches on the grate’s hinges. The radio crackled. "Detective? Status?" She hesitated. The drain led underground—abandoned tunnels, maybe. Or worse. Morris had vanished down a hole like this three years ago. They’d found his badge in the Thames a week later, polished clean. Her fingers brushed the worn leather of her watch. She yanked the grate open. The ladder descended into blackness. The air rising from below carried the scent of damp earth and something metallic. Blood? No—oil. Machinery. Distant voices echoed up, distorted by the tunnels. Quinn dropped in. Her boots hit concrete. The tunnel stretched left and right, pipes lining the ceiling, dripping condensation. A flickering bulb far to the right cast jagged shadows. Movement there—a figure slipping around a corner. She unholstered her torch. The beam cut through the gloom, revealing graffiti in languages she didn’t recognise. Symbols. Warnings. One phrase stood out, spray-painted in red: *Abandon hope, all who enter here.* "Charming," she muttered. The voices grew louder as she advanced. Laughter. Bargaining. The clink of glass. Then—light. A green glow spilling from an archway ahead. Quinn edged closer. The arch opened into a cavernous space—an abandoned Tube station, its tiled walls cracked but still bearing faded signs for Camden Town. Stalls lined the platform, their awnings patched together from tarps and old curtains. The crowd milling between them moved like shadows, faces obscured by hoods, scarves, the occasional grotesque mask. The Veil Market. She’d heard rumours. A black market for things that shouldn’t exist. Morris had been investigating it before he— A hand grabbed her arm. Quinn spun, elbow raised, but stopped short. The man holding her wore a paramedic’s jacket, the NHS logo half-torn off. His olive skin gleamed under the green lights, a scar running down his forearm like a pale seam. "You’re not supposed to be here," Tomás Herrera said, his Spanish accent thickening with urgency. "I’m following a suspect." "Not here, you’re not." His grip tightened. "This place eats cops." She jerked free. "Then it’s about to choke." Tomás blocked her path. "You don’t have a token." "What token?" He tapped the Saint Christopher medal at his throat. "Bone. Carved. Lets you in. Lets you out." His eyes flicked past her. "Without one, they’ll smell you before you take three steps." Quinn followed his gaze. The crowd had stilled. Heads turned. A vendor lowered his hood—too sharp teeth glinting in a smile. "Too late," Tomás muttered. The first figure stepped forward. Then another. The market’s chatter had died. Only the drip of water in the tunnels remained. Quinn’s hand went to her hip. Tomás caught her wrist. "Don’t. You’ll just piss them off." "Suggestions?" "Run." The crowd surged.
created_at"2026-02-19T12:32:48.958Z" 2/19/2026, 12:32:48 PM
model"deepseek/deepseek-chat-v3"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency1085
moderation_latency(null)
generation_time34082
tokens_prompt4663
tokens_completion1038
native_tokens_prompt4219
native_tokens_completion917
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"
usage0.0028797
router(null)
provider_responses
0
endpoint_id"cefb5a1e-9fea-4496-9a64-4e1b11a7cc8c"
id"e031d11c097e89f239c82e3fb2f8af34"
is_byokfalse
latency1085
model_permaslug"deepseek/deepseek-chat-v3"
provider_name"Novita"
status200
api_type"completions"
id"gen-1771504368-2DUj9RNCVlmtKNpmpv7k"
upstream_id"e031d11c097e89f239c82e3fb2f8af34"
total_cost0.0028797
cache_discount(null)
upstream_inference_cost0
provider_name"Novita"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags5
adverbTagCount0
adverbTags(empty)
dialogueSentences17
tagDensity0.294
leniency0.588
rawRatio0
effectiveRatio0
91.80% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount610
totalAiIsmAdverbs1
found
0
adverb"slightly"
count1
highlights
0"slightly"
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)
59.02% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount610
totalAiIsms5
found
0
word"shattered"
count1
1
word"echoed"
count1
2
word"gloom"
count1
3
word"flicked"
count1
4
word"glinting"
count1
highlights
0"shattered"
1"echoed"
2"gloom"
3"flicked"
4"glinting"
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
emotionTells1
narrationSentences79
matches
0"g with urgency"
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences79
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences91
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen23
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans1
markdownWords6
totalWords598
ratio0.01
matches
0"Abandon hope, all who enter here."
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions3
unquotedAttributions0
matches(empty)
64.93% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions24
wordCount529
uniqueNames13
maxNameDensity1.7
worstName"Quinn"
maxWindowNameDensity2
worstWindowName"Quinn"
discoveredNames
Quinn9
Soho1
Thames1
Tube1
Camden1
Town1
Veil1
Market1
Herrera1
Spanish1
Saint1
Christopher1
Tomás4
persons
0"Quinn"
1"Herrera"
2"Saint"
3"Christopher"
4"Tomás"
places
0"Soho"
1"Thames"
2"Camden"
3"Town"
globalScore0.649
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences38
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount598
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences91
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs37
mean16.16
std14.28
cv0.884
sampleLengths
043
13
240
39
432
521
68
75
833
99
105
1130
123
1333
1432
153
1622
1755
183
1918
205
2138
2215
234
2411
258
269
272
2832
2921
304
3121
326
3310
341
351
363
100.00% Passive voice overuse
Target: ≤2% passive sentences
passiveCount0
totalSentences79
matches(empty)
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs103
matches(empty)
0.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount11
semicolonCount0
flaggedSentences9
totalSentences91
ratio0.099
matches
0"The neon glow of Soho blurred past—pink, blue, green—reflected in puddles like shattered stained glass."
1"The figure ahead—hood up, head down—didn’t break stride."
2"The drain led underground—abandoned tunnels, maybe."
3"No—oil."
4"Movement there—a figure slipping around a corner."
5"Then—light."
6"The arch opened into a cavernous space—an abandoned Tube station, its tiled walls cracked but still bearing faded signs for Camden Town."
7"Morris had been investigating it before he—"
8"A vendor lowered his hood—too sharp teeth glinting in a smile."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount541
adjectiveStacks0
stackExamples(empty)
adverbCount12
adverbRatio0.022181146025878003
lyAdverbCount2
lyAdverbRatio0.0036968576709796672
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences91
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences91
mean6.57
std4.8
cv0.73
sampleLengths
015
113
215
33
48
515
617
74
85
96
108
1111
122
135
146
152
162
1711
182
196
203
212
222
236
242
2511
2612
279
285
295
3014
311
321
331
348
353
364
3712
3810
397
404
4113
421
431
4413
453
467
471
481
494
75.46% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats3
diversityRatio0.4725274725274725
totalSentences91
uniqueOpeners43
100.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences61
matches
0"Just a rusted fire escape"
1"Only the drip of water"
ratio0.033
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount14
totalSentences61
matches
0"They wove through a group"
1"She thumbed her radio."
2"She slowed at a dead"
3"They’d found his badge in"
4"Her fingers brushed the worn"
5"She yanked the grate open."
6"Her boots hit concrete."
7"She unholstered her torch."
8"She’d heard rumours."
9"His olive skin gleamed under"
10"His grip tightened"
11"She jerked free."
12"He tapped the Saint Christopher"
13"His eyes flicked past her"
ratio0.23
9.18% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount55
totalSentences61
matches
0"The suspect’s shoulder clipped a"
1"Harlow Quinn vaulted over the"
2"The neon glow of Soho"
3"The figure ahead—hood up, head"
4"They wove through a group"
5"The air smelled of fried"
6"She thumbed her radio."
7"A sharp left into an"
8"Quinn followed, her breath burning"
9"The alley narrowed, walls closing"
10"A door slammed somewhere ahead."
11"She slowed at a dead"
12"The radio crackled."
13"The drain led underground—abandoned tunnels,"
14"Morris had vanished down a"
15"They’d found his badge in"
16"Her fingers brushed the worn"
17"She yanked the grate open."
18"The ladder descended into blackness."
19"The air rising from below"
ratio0.902
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences61
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences21
technicalSentenceCount1
matches
0"The suspect’s shoulder clipped a street vendor’s stall, sending oranges tumbling across the slick pavement."
25.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags5
uselessAdditionCount1
matches
0"Tomás Herrera said, his Spanish accent thickening with urgency"
32.35% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags3
fancyCount2
fancyTags
0"she muttered (mutter)"
1"Tomás muttered (mutter)"
dialogueSentences17
tagDensity0.176
leniency0.353
rawRatio0.667
effectiveRatio0.235
81.9248%