Run: 2026-04-25-01KQ2EB510XFGYB0RW68A4KEK8

Run Details

Duration:
46.7s
Cost:
$0.001533
Provider:
DeepSeek

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
Detective Harlow Quinn's torch beam caught the bone token first, still clutched in the victim's left hand. "CID's been waiting twenty minutes." DS Raj Patel emerged from the maintenance door, breath misting in the cold. "Couldn't find the entrance. One of your lot tipped me off about the Camden station rumour." Harlow didn't answer. She swept the beam across the abandoned platform. The Veil Market had packed up three days ago, moved to wherever it crawled during the full moon, but the residue remained: chalked sigils on the tiles, scorch marks in circular patterns, the copper-sweet smell of old alchemy. The body lay face-down at the edge of the platform, one arm dangling into the track bed. Female. Late twenties. Curly red hair splayed across stained concrete. "Eva Kowalski," Patel said. "British Museum researcher. Reported missing forty-eight hours ago by her flatmate." That snapped Harlow's attention up. She knew the name. She knew it too well. Patel was watching her. "You want to tell me why we dragged our feet on this one?" "We didn't have jurisdiction. She worked in the restricted archives. Temple Church has its own-" "Don't." His voice was flat. "She's been dead at least twelve hours. Rigor's starting to fade. And your department stonewalled the missing persons report." Harlow crouched beside the body. The round glasses were intact, one lens reflecting her torchlight. Worn leather satchel still strapped across the chest, beneath an arm twisted at an angle that suggested falling, not placement. But the satchel was zipped shut. The books were still inside. No sign of a struggle to take them. "Robbery's not the motive," she murmured. "Brilliant observation. The occult researcher found dead in a supernatural black market. What gave it away?" "The books are still here." Patel paused. "Show me." She pointed. "Her satchel's got eight texts inside. I count spines. Rare editions, too. A Shade-crafted compass should fetch five hundred at minimum, but look." She lifted the chain gently. The brass casing had a patina of verdigris, the face etched with protective sigils. "Still around her neck." "So she wasn't shopping." "She was meeting someone. Or running from someone." Harlow moved her torch to the victim's right hand. Clean. No defensive wounds. "Check the track bed." "What am I looking for?" "Anything that shouldn't be there." Patel climbed down, his own torch sweeping discarded crisp packets and a single trainer. "Got a broken vial. Green glass. Smells like... ozone?" Harlow's jaw tightened. "Don't touch it. Mason jars only. Full hazmat protocol." "Since when does a detective inspector carry-" "Since the last time someone handed me a body outside a Veil Market." She stood, brushing dust from her knees. "What's your working theory, Raj?" "Wrong place, wrong time. She came down here looking for research material, stumbled into something she shouldn't have. Panicked, ran, fell." He gestured at the platform edge. "Head trauma's consistent with a fall." "Consistent?" Harlow walked the perimeter of the body. Five steps out, six steps back. "What do you see?" "I see a dead woman in an abandoned tube station, Quinn. What am I supposed to see?" "The tracks." He looked. "What about them?" "They're dry." She pointed at the rails. "We had rain yesterday. Heavy. King's Cross flooded two platforms. But these tracks are bone dry. No puddles. No damp. The drainage here should be worse than the operational stations." "Mechanical failure?" "Or someone dried them deliberately. Look at the ballast stones." She angled her torch. "See the pattern? Swept. Recently." Patel climbed back onto the platform. "Why would anyone sweep the tracks at a murder scene?" "Because something happened down there that they didn't want us to see." She returned to the body. "Help me turn her." They rolled Eva Kowalski onto her back. The face was peaceful, almost sleeping, freckled complexion undisturbed except for a small cut above the left eyebrow. The green eyes were half-open, staring at nothing. "Head wound's minor," Patel said. "Not enough blood for a fatal fall." "No." Harlow traced her finger above the body without touching. "Look at her hands. No scrapes. No bruises. She didn't try to catch herself." "You fall backwards, you don't catch yourself." "And she was running. You said it yourself." She pointed at the victim's shoes. Sturdy boots, good tread. "She's wearing walking shoes. Prepared. Knew where she was going. The satchel's packed for a research trip. The compass suggests she was navigating the Veil. But her hands are clean. Clothes are clean." "Meaning?" "Meaning she wasn't running through an abandoned station. She walked here calmly. Stood at the edge. Fell backward." Harlow stood. "Or was pushed. But either way, the fall didn't kill her." Patel was silent for a long moment. "Then what did?" "The body's been moved. She died somewhere else, on her back. Rigor set in while she was supine. Then someone transported her here, positioned her face-down, and staged the fall." Harlow pointed at the satchel strap. "See how it's twisted? It was put on after death. The books were packed by someone who wanted us to think she was researching." "You're saying she was killed elsewhere, posed here, and the tracks were swept to hide evidence." "I'm saying someone wanted us to find her exactly like this. In the Veil Market. With the bone token. With the compass. Everything screaming 'occult researcher went too deep.'" "When?" "The missing persons report clears Temple Church jurisdiction after forty-eight hours. That's when Metropolitan gets the case. That's when I get involved." She looked at him. "Who called you in, Raj?" "A tip. Anonymous. Landline from a call box in Holborn." "Timed perfectly for the forty-eight hour mark." Patel ran a hand through his hair. "You have a suspect already, don't you?" Harlow looked down at Eva Kowalski's peaceful face, the clean hands, the carefully arranged satchel. The freckles that still held warmth. The green eyes that had studied shadows and sigils. "My partner died three years ago," she said. "DS Morris. Case file said accident. Fell down stairs during a pursuit." Her voice was steady. "But I was there. He didn't fall. He was pushed by something that wasn't human. And the scene was staged exactly like this. Clean. Collected. A story ready-made for the paperwork." "The same person?" "Maybe. Or the same thing." She pulled out her mobile. "I need to make a call. Secure the scene. Nobody touches the body until I'm back." "Where are you going?" "To find out what Eva Kowalski was actually researching." She paused at the maintenance door. "And why someone needed me specifically to find her body." The worn leather watch on her wrist ticked steadily. Outside the station, London was waking up. Inside, the torch beams crossed and recrossed, and the dead woman's compass needle spun slowly, still pointing toward something unseen.
created_at"2026-04-25T13:47:53.256Z" 4/25/2026, 1:47:53 PM
model"deepseek/deepseek-v4-pro-20260423"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency977
moderation_latency(null)
generation_time46644
tokens_prompt4671
tokens_completion1835
native_tokens_prompt4249
native_tokens_completion1573
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached4224
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"
usage0.001532505
router(null)
provider_responses
0
endpoint_id"d084170b-dd99-4e53-9ae1-b63881f3cfbf"
id"5c3b1919-03a3-4d62-8946-21b7f597ed77"
is_byokfalse
latency376
model_permaslug"deepseek/deepseek-v4-pro-20260423"
provider_name"DeepSeek"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777124873-tgP3y3L0EcAq7JYpcnOe"
session_id(null)
api_type"completions"
id"gen-1777124873-aQjxVt31cQkbWetfykJC"
upstream_id"5c3b1919-03a3-4d62-8946-21b7f597ed77"
total_cost0.001532505
cache_discount0.00168432
upstream_inference_cost0
provider_name"DeepSeek"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags20
adverbTagCount0
adverbTags(empty)
dialogueSentences69
tagDensity0.29
leniency0.58
rawRatio0
effectiveRatio0
78.01% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1137
totalAiIsmAdverbs5
found
0
adverb"gently"
count1
1
adverb"deliberately"
count1
2
adverb"perfectly"
count1
3
adverb"carefully"
count1
4
adverb"slowly"
count1
highlights
0"gently"
1"deliberately"
2"perfectly"
3"carefully"
4"slowly"
80.00% AI-ism character names
Target: 0 AI-default names (17 tracked, −20% each)
codexExemptions(empty)
found
0"Patel"
100.00% AI-ism location names
Target: 0 AI-default location names (33 tracked, −20% each)
codexExemptions(empty)
found(empty)
69.22% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1137
totalAiIsms7
found
0
word"etched"
count1
1
word"mechanical"
count1
2
word"eyebrow"
count1
3
word"traced"
count1
4
word"sturdy"
count1
5
word"navigating"
count1
6
word"warmth"
count1
highlights
0"etched"
1"mechanical"
2"eyebrow"
3"traced"
4"sturdy"
5"navigating"
6"warmth"
100.00% Cliché density
Target: ≤1 cliche(s) per 800-word window
totalCliches0
maxInWindow0
found(empty)
highlights(empty)
100.00% Emotion telling (show vs. tell)
Target: ≤3% sentences with emotion telling
emotionTells0
narrationSentences62
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount0
narrationSentences62
filterMatches
0"watch"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences109
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen39
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1137
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions15
unquotedAttributions0
matches(empty)
27.78% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions32
wordCount450
uniqueNames12
maxNameDensity2.44
worstName"Harlow"
maxWindowNameDensity3.5
worstWindowName"Harlow"
discoveredNames
Harlow11
Quinn1
Raj1
Patel9
Veil1
Market1
Clean1
Five1
Eva2
Kowalski2
Sturdy1
London1
persons
0"Harlow"
1"Quinn"
2"Raj"
3"Patel"
4"Market"
5"Five"
6"Eva"
7"Kowalski"
8"Sturdy"
places
0"London"
globalScore0.278
windowScore0.5
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences33
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1137
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences109
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs58
mean19.6
std14.5
cv0.74
sampleLengths
017
134
249
327
415
55
69
717
815
924
1035
1119
126
1316
145
154
1648
174
1825
195
205
2123
2212
237
2425
2533
2618
2717
282
295
3037
312
3219
3316
3421
3533
3612
3724
387
3951
401
4131
4210
4360
4416
4529
461
4731
4810
497
99.60% Passive voice overuse
Target: ≤2% passive sentences
passiveCount1
totalSentences62
matches
0"was zipped"
41.27% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount2
totalVerbs84
matches
0"was watching"
1"was waking"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences109
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount453
adjectiveStacks0
stackExamples(empty)
adverbCount14
adverbRatio0.03090507726269316
lyAdverbCount5
lyAdverbRatio0.011037527593818985
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences109
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences109
mean10.43
std8.23
cv0.789
sampleLengths
017
118
216
33
48
538
617
71
82
97
104
1111
125
134
145
154
1613
1715
185
1919
205
2110
2220
236
245
258
266
2716
285
292
302
312
3228
3314
344
354
3617
371
383
394
405
415
4214
439
443
459
467
4720
485
4927
87.77% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats6
diversityRatio0.5596330275229358
totalSentences109
uniqueOpeners61
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences51
matches(empty)
ratio0
94.51% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount16
totalSentences51
matches
0"She swept the beam across"
1"She knew the name."
2"She knew it too well."
3"His voice was flat"
4"She lifted the chain gently"
5"She stood, brushing dust from"
6"He gestured at the platform"
7"She pointed at the rails"
8"She angled her torch"
9"She returned to the body"
10"They rolled Eva Kowalski onto"
11"She pointed at the victim's"
12"She looked at him"
13"Her voice was steady"
14"She pulled out her mobile"
15"She paused at the maintenance"
ratio0.314
48.24% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount42
totalSentences51
matches
0"Detective Harlow Quinn's torch beam"
1"DS Raj Patel emerged from"
2"Harlow didn't answer."
3"She swept the beam across"
4"The Veil Market had packed"
5"The body lay face-down at"
6"That snapped Harlow's attention up."
7"She knew the name."
8"She knew it too well."
9"Patel was watching her."
10"His voice was flat"
11"Harlow crouched beside the body."
12"The round glasses were intact,"
13"The books were still inside."
14"She lifted the chain gently"
15"The brass casing had a"
16"Harlow moved her torch to"
17"Patel climbed down, his own"
18"Harlow's jaw tightened."
19"She stood, brushing dust from"
ratio0.824
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences51
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences10
technicalSentenceCount0
matches(empty)
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags20
uselessAdditionCount1
matches
0"DS Raj Patel emerged, breath misting in the cold"
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags4
fancyCount1
fancyTags
0"she murmured (murmur)"
dialogueSentences69
tagDensity0.058
leniency0.116
rawRatio0.25
effectiveRatio0.029
84.2131%