Run: 2026-06-24-01KVX2WTWGARVH852EJAJEB9AD

Run Details

Duration:
39.5s
Cost:
$0.011927
Provider:
Z.AI

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
The bone token crumbled between Harlow Quinn's fingers. She stared at the pale dust coating her palm, then at the iron gate ahead. Rust had eaten through the hinges, but the padlock was new. Shiny. Completely wrong for an abandoned Tube station that hadn't seen a paying customer since 1932. "What've we got?" PC Yun jogged down the steps behind her, his hi-vis vest catching the sodium light from the street above. He held out a evidence bag. "Found this near the body. Well, what's left of it." Quinn took the bag. Inside sat a small brass compass with a face etched in protective sigils. Verdigris bloomed across the casing in green constellations. The needle spun, slow and deliberate, pointing not north but toward something deeper in the tunnel. "Who called it in?" "Homeless bloke. Regular in the area. Says the station started... humming." "Humming." "That's what he told dispatch. They thought he was off his meds." Yun shrugged. "Response team found the entrance open. Came down, found the body, called us." Quinn turned the compass over. No manufacturer's mark. No serial number. Just those sigils, intricate as Celtic knotwork, cut into the brass with surgical precision. The needle kept spinning, then stopped. Pointed down the tunnel. "Where's the body?" "Eastbound platform. I'll warn you, guv, it's not pretty." Quinn pocketed the compass and pushed through the gate. The padlock hung open, the key still inserted. Fresh oil glistened on the mechanism. Someone had wanted this door accessible tonight. The tunnel swallowed her. Torch beam cut through darkness that smelled of wet concrete and something else, something sweet and metallic that clung to the back of her throat. Not blood. She knew blood. This was older. Riper. Like copper left in rain. "PC Yun, you said the response team came down. How many?" "Two. Both took one look and called it in. One of them's outside being sick." The tunnel curved. Graffiti decorated the walls in layers, tags from decades of urban explorers and bored teenagers, all spray paint and profanity. But near the curve, the graffiti changed. Symbols. Not gang tags, not street art. Deliberate marks in what looked like chalk or bone dust, stretching in bands across the concrete. Quinn stopped. She knew these symbols. Not from the academy. Not from eighteen years on the force. From Morris's case files. The ones she'd memorised after they found his car empty on the M25, engine running, doors locked from the inside. "Similar markings were at three other scenes," she said. "Camden lockup, Bethnal Green storage unit, that warehouse in Deptford." Yun checked his notebook. "Those were all ruled accidental. Gas leaks, structural collapse-" "Three accidental deaths with identical pre-historic chalk markings. And now a fourth." The platform came into view. Quinn's torch found the body, and she understood why the response officer was outside being sick. The man had been arranged. That was the only word for it. Seated upright against the tiled wall, legs crossed, hands resting on his knees. His clothes were clean. His shoes were polished. But his chest was open, ribs spread like wings, and inside, where his heart should have been, sat a fist-sized stone the colour of dried blood. "Hell," Yun breathed. "No blood on the platform." Quinn swept her torch across the tiles. Pristine. "No drag marks. No spatter. His chest cavity's been cleaned out." "Could be a post-mortem staging. Serial killer signature." "With what tools? This is surgical. Precise." She crouched, keeping her distance from the body. "Look at the rib cuts. Smooth edges. No hesitation marks. Whoever did this knew exactly where to cut and how." "Could be medical training." "Could be." Quinn pulled out the compass again. The needle had stopped spinning. It pointed directly at the stone in the man's chest. "But a doctor wouldn't leave this." "What is it?" "That's what I need to find out." She stood and stepped back. "Who's our forensic lead?" "Dr. Cheng's en route. Twenty minutes." "Get her to bring a spectrometer. I want that stone analysed before it leaves this platform." Quinn photographed the body from multiple angles, her phone's flash harsh against the tableau. "And I want the homeless witness held. Don't arrest, just keep him comfortable. Tea, blankets, whatever he needs." She turned back toward the tunnel entrance, then stopped. The symbols on the wall. She hadn't noticed before, not in the dim light, but three of them were different. Newer. Drawn over the old ones in a darker shade. "Yun, those other three scenes. Did anyone photograph the wall markings?" "Some. Why?" "Because I think these symbols are instructions." She traced the air near the newest marking without touching it. "And someone's been updating them." Quinn's phone buzzed. She glanced at the screen. A text from an unknown number, just a string of digits and an emoji of an eye. "Everything alright, guv?" "Fine." She pocketed the phone. "Get CSU down here. Full sweep. And run the victim's face through missing persons. I want a name before Cheng finishes her coffee." She walked back up the tunnel, the compass heavy in her pocket. Its needle tugged at the fabric of her coat, straining toward something further down the line. Another platform. Another tunnel. Deeper. At the gate, she paused. The bone dust had blown away in the draft from the street above, but she could still feel its residue on her fingers. Greasy. Warm. Her watch read 11:47. Morris had disappeared at 11:52, three years ago. Five minutes. Quinn descended the steps again, following the compass needle deeper into the dark, and the tunnel behind her sealed shut with a sound like bone clicking against bone.
created_at"2026-06-24T15:10:06.768Z" 6/24/2026, 3:10:06 PM
model"z-ai/glm-5.2-20260616"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency3039
moderation_latency(null)
generation_time39313
tokens_prompt4671
tokens_completion1599
native_tokens_prompt4229
native_tokens_completion1365
native_tokens_completion_images(null)
native_tokens_reasoning80
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(null)
usage0.0119266
router(null)
provider_responses
0
endpoint_id"442ea97f-ad5e-40d5-b9a6-66e9e0417dce"
id"20260624231007bc61635f391744a0"
is_byokfalse
latency3039
model_permaslug"z-ai/glm-5.2-20260616"
provider_name"Z.AI"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer(null)
request_id"req-1782313806-5zsBpq65sufpJMFGRxCr"
session_id(null)
preset_id(null)
api_type"completions"
id"gen-1782313806-gkTrDXmw2s1l7NfJMNNi"
upstream_id"20260624231007bc61635f391744a0"
total_cost0.0119266
cache_discount(null)
upstream_inference_cost0
provider_name"Z.AI"
response_cache_source_id(null)
data_region"global"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags10
adverbTagCount0
adverbTags(empty)
dialogueSentences37
tagDensity0.27
leniency0.541
rawRatio0
effectiveRatio0
94.73% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount948
totalAiIsmAdverbs1
found
0
adverb"completely"
count1
highlights
0"completely"
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)
73.63% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount948
totalAiIsms5
found
0
word"etched"
count1
1
word"intricate"
count1
2
word"pristine"
count1
3
word"comfortable"
count1
4
word"traced"
count1
highlights
0"etched"
1"intricate"
2"pristine"
3"comfortable"
4"traced"
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
narrationSentences83
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences83
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences110
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen30
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords948
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions8
unquotedAttributions0
matches(empty)
65.12% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions21
wordCount648
uniqueNames7
maxNameDensity1.7
worstName"Quinn"
maxWindowNameDensity2.5
worstWindowName"Quinn"
discoveredNames
Harlow1
Quinn11
Tube1
Yun4
Celtic1
Morris2
Pristine1
persons
0"Harlow"
1"Quinn"
2"Yun"
3"Morris"
places(empty)
globalScore0.651
windowScore0.833
89.02% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences41
glossingSentenceCount1
matches
0"looked like chalk or bone dust, stretchin"
0.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches2
per1kWords2.11
wordCount948
matches
0"not north but toward something deeper in the tunnel"
1"not in the dim light, but three of them were different"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences110
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs45
mean21.07
std15.55
cv0.738
sampleLengths
08
142
23
335
441
54
611
71
827
935
103
119
1230
1343
1411
1515
1653
172
1839
1919
2013
2112
2221
2359
243
2524
268
2735
284
2929
303
3116
326
3348
3439
3511
362
3723
3825
393
4028
4133
4230
4314
4428
96.81% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences83
matches
0"been arranged"
1"been, sat"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount0
totalVerbs99
matches(empty)
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences110
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount650
adjectiveStacks0
stackExamples(empty)
adverbCount16
adverbRatio0.024615384615384615
lyAdverbCount3
lyAdverbRatio0.004615384615384616
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences110
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences110
mean8.62
std6.59
cv0.764
sampleLengths
08
115
211
31
415
53
619
76
810
94
1013
118
1216
134
1411
151
1614
1713
185
193
203
2114
226
234
243
259
269
278
286
297
304
3125
322
333
343
351
365
3711
3815
393
4020
417
421
436
4416
452
464
474
487
494
95.45% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats5
diversityRatio0.6090909090909091
totalSentences110
uniqueOpeners67
99.50% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount2
totalSentences67
matches
0"Completely wrong for an abandoned"
1"Just those sigils, intricate as"
ratio0.03
100.00% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount17
totalSentences67
matches
0"She stared at the pale"
1"He held out a evidence"
2"She knew blood."
3"She knew these symbols."
4"His clothes were clean."
5"His shoes were polished."
6"She crouched, keeping her distance"
7"It pointed directly at the"
8"She stood and stepped back"
9"She turned back toward the"
10"She hadn't noticed before, not"
11"She traced the air near"
12"She glanced at the screen."
13"She pocketed the phone"
14"She walked back up the"
15"Its needle tugged at the"
16"Her watch read 11:47."
ratio0.254
94.33% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount49
totalSentences67
matches
0"The bone token crumbled between"
1"She stared at the pale"
2"Rust had eaten through the"
3"PC Yun jogged down the"
4"He held out a evidence"
5"Quinn took the bag."
6"Verdigris bloomed across the casing"
7"The needle spun, slow and"
8"Quinn turned the compass over."
9"The needle kept spinning, then"
10"Quinn pocketed the compass and"
11"The padlock hung open, the"
12"Someone had wanted this door"
13"The tunnel swallowed her."
14"Torch beam cut through darkness"
15"She knew blood."
16"This was older."
17"The tunnel curved."
18"Graffiti decorated the walls in"
19"She knew these symbols."
ratio0.731
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences67
matches(empty)
ratio0
74.83% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences21
technicalSentenceCount2
matches
0"Completely wrong for an abandoned Tube station that hadn't seen a paying customer since 1932."
1"Torch beam cut through darkness that smelled of wet concrete and something else, something sweet and metallic that clung to the back of her throat."
75.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags10
uselessAdditionCount1
matches
0"Quinn photographed, her phone's flash harsh against the tableau"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags2
fancyCount1
fancyTags
0"Yun breathed (breathe)"
dialogueSentences37
tagDensity0.054
leniency0.108
rawRatio0.5
effectiveRatio0.054
88.6142%