Run: 2026-04-24-01KPZTTSG5YDK1SPH0PKV2F8N2

Run Details

Duration:
40.5s
Cost:
$0.100490
Provider:
Amazon Bedrock

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 body lay in the orchestra pit, and nobody could tell Quinn how it got there. "Cleaner found him at five." DS Bashir handed her the log, pages already curling from the damp. "Stage door was locked. Alarm set. Watchman swears no one came through." "Watchman swears a lot of things." "Tox'll be back Tuesday. Pathologist puts death between midnight and two." Quinn ducked under the tape and took the three worn steps down into the pit. The Lyceum had closed for refurbishment in March. Dust-sheets draped the stalls like a congregation of ghosts, and the chandelier overhead had been lowered to head height, its crystals wrapped in brown paper. She skirted a music stand and crouched beside the corpse. Male. Late forties. Dinner suit, but not a fresh one. The lapels shone with the sort of wear a man gets from leaning on too many bars. No blood that she could see. No obvious wound. His left hand rested on his chest like a tenor about to hit a high note, and his right was flung wide, fingers curled around nothing. "Heart, probably," Bashir said behind her. "He's the age for it. Found a glyceryl trinitrate spray in the jacket." "Mm." "Guv?" "Mm." She'd learned the sound from her first DI, a man who'd used it to mean anything from *go on* to *you're an idiot*. Bashir read it correctly and shut up. Quinn didn't touch the body. She looked at it the way she'd been taught to look at rooms, at exits, at men across interview tables: as a set of facts refusing to agree with one another. The dust on the floor of the pit had been disturbed in one continuous smear from the steps to the body. One set of prints in. None out. Which fit Bashir's theory fine, until you noticed the dead man's shoes. Patent leather. Polished. Clean. She leaned closer. The soles, where she could see them, carried a fine pale grey film. Not the grit of a London pavement. Not the grime of the Lyceum's corridors, which she'd just walked herself and which had left a streak on her own boot the colour of wet tea. This grey was lighter. Drier. Almost chalky. "Harlow." The voice came from the wings above. Detective Mayberry, in the sort of overcoat that suggested he'd been pulled from dinner. "They told me Serious Crime wasn't sending anyone till morning." "They weren't. I was passing." "At five?" "I don't sleep much." He came down into the pit with the careful gait of a man who didn't enjoy stairs. Mayberry was a good detective; he was also a tidy one, which Quinn had always distrusted. Tidy detectives closed cases. They didn't always solve them. "Cardiac event," he said. "Wanders in during the afternoon, hides when they lock up, has a turn in the pit. Sad little end for some sad little man." "Wanders in how?" "Group tour. Two o'clock. Twenty-eight people, twenty-seven came out. We've got him on the CCTV going in." "Going in where?" "Foyer camera. Bashir's got the still." Bashir produced his phone and held it out. The image was grainy, but the man in the grainy image was undeniably the man at her feet. Same suit. Same loose knot in the bow-tie. She looked at the timestamp. 14:07. "And between two and midnight?" "Nothing. He went to ground somewhere. Green room, probably. Plenty of cupboards in a place like this." "Mm." She stood up and walked the length of the pit, then back. Mayberry waited, hands in his overcoat pockets, the picture of patience. He'd always been patient with her. It was one of his better qualities, and one of his worst. "The tour," she said. "Where did it go?" "Usual route. Stalls, dress circle, backstage, out through the scenic dock." "Not the pit." "Insurance doesn't allow it." "Then how," she said, "did our man get down here without leaving a footprint before he died?" Mayberry's patience flickered. She saw it: a twitch at the corner of the mouth. "He came down the steps. Like you did." "The dust on those steps is undisturbed under mine." She pointed. Her own prints went down in a neat, if heavy, line. Beneath them, nothing. "No one walked down these before me tonight. Not him. Not the cleaner." "The cleaner said she didn't come into the pit." "Then who made the smear?" Mayberry looked. She watched him look. He was a good enough detective to see it, and she saw the moment he did, the small sag of the shoulders that meant *damn*. "He was moved," he said. "From where?" "Stage? Dock?" "By whom, through where, leaving what trace?" She crouched again. Lifted the dead man's right hand with the end of her pen. The fingertips were grey with the same chalky film as the soles. "And what's he been handling?" Bashir leaned over the rail. "Plaster?" "Plaster's wetter. It clumps." She sniffed, careful, at a distance. Nothing. Or almost nothing: a faint, cold mineral note, like the inside of a church. "Bone dust, maybe. Or something sold as it." Mayberry laughed, a short, tired bark. "Bone dust. Harlow." "You asked." "I didn't." "You were about to." He rubbed his eye with the heel of his hand. "The man had a heart condition. He had a spray in his pocket. He's forty-nine and fat and he came into a cold theatre on an empty stomach-" "He was moved." "-and he had a turn, and someone who shouldn't have been here panicked and dragged him somewhere tidier. That's all. You want a murder because you always want a murder." She didn't answer. She was looking at the dead man's left wrist, where the cuff had ridden up. A narrow band of skin, paler than the rest, ringed the wrist like the ghost of a watch. No watch on him now. No watch in the jacket pocket Bashir had inventoried. And on the pale band of skin, faint, almost apologetic, a smudge of the same chalky grey. "He was wearing something here," she said. "Until recently." "A watch." "Something." She straightened. The pit felt colder than the stalls above, which was wrong; heat rose, pits should have been warmer than open air. She'd noticed it walking in and dismissed it, because one dismissed such things or one went mad. Her leather strap creaked as she flexed her wrist. "Bashir. The cleaner. Where is she?" "Green room. Medic's with her." "Did she touch him?" "Says not." "Ask her again. Ask her what she heard before she found him. Not saw. Heard." Bashir was already moving. Mayberry watched him go with the expression of a man whose dinner was cooling in a restaurant he would not now return to. "Harlow. You're chasing ghosts." "I'm chasing a man who isn't where he should be, wearing clothes that are too clean, missing an item he was wearing an hour ago, in a room with one set of footprints that aren't his." She met his eyes. "If that's a ghost, it's a sloppy one." Above them, in the dress circle, something shifted. A dust-sheet, perhaps, settling. Perhaps not. Quinn didn't look up, because looking up was what they wanted, whoever they were, and she'd learned three years ago, in a basement in Deptford with DS Morris bleeding out beside her and the lights failing one by one, that the thing you were meant to look at was never the thing you needed to see. She looked, instead, at the dead man's shoes. And then she saw it, tucked against the instep of the left one, half-hidden by the trouser cuff: a small, dull disc of something that was not metal and not plastic and not, when she bent very close, any material she had a name for. It was the colour of old teeth. It had a hole drilled through it. "Mayberry." "What now." "Don't move." From the wings above, very softly, someone began to laugh.
created_at"2026-04-24T13:28:25.361Z" 4/24/2026, 1:28:25 PM
model"anthropic/claude-4.7-opus-20260416"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency853
moderation_latency(null)
generation_time40377
tokens_prompt4671
tokens_completion1976
native_tokens_prompt6543
native_tokens_completion2711
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)
num_fetches(null)
web_search_engine(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"end_turn"
usage0.10049
router(null)
provider_responses
0
endpoint_id"0fa65117-00d9-4835-808d-9b68041d9ce4"
id"1f79226c-2934-4fb6-8c23-7d8662bc1bb1"
is_byokfalse
latency853
model_permaslug"anthropic/claude-4.7-opus-20260416"
provider_name"Amazon Bedrock"
status200
user_agent"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer(null)
request_id"req-1777037305-7V1MzwbToXjWmrMVsitq"
session_id(null)
api_type"completions"
id"gen-1777037305-evHeJTjxcNHdbJPPyOHF"
upstream_id"1f79226c-2934-4fb6-8c23-7d8662bc1bb1"
total_cost0.10049
cache_discount(null)
upstream_inference_cost0
provider_name"Amazon Bedrock"
response_cache_source_id(null)

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags14
adverbTagCount1
adverbTags
0"She crouched again [again]"
dialogueSentences64
tagDensity0.219
leniency0.438
rawRatio0.071
effectiveRatio0.031
88.74% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1332
totalAiIsmAdverbs3
found
0
adverb"very"
count2
1
adverb"softly"
count1
highlights
0"very"
1"softly"
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)
92.49% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1332
totalAiIsms2
found
0
word"flickered"
count1
1
word"stomach"
count1
highlights
0"flickered"
1"stomach"
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
narrationSentences93
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount1
hedgeCount1
narrationSentences93
filterMatches
0"look"
hedgeMatches
0"began to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences143
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen56
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans3
markdownWords6
totalWords1331
ratio0.005
matches
0"go on"
1"you're an idiot"
2"damn"
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions16
unquotedAttributions0
matches(empty)
83.33% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions28
wordCount926
uniqueNames10
maxNameDensity0.86
worstName"Bashir"
maxWindowNameDensity2.5
worstWindowName"Mayberry"
discoveredNames
Quinn5
Bashir8
Lyceum2
March1
London1
Detective1
Mayberry7
Lifted1
Deptford1
Morris1
persons
0"Quinn"
1"Bashir"
2"Lyceum"
3"Mayberry"
4"Morris"
places
0"March"
1"London"
2"Deptford"
globalScore1
windowScore0.833
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences54
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1331
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences143
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs70
mean19.01
std20.43
cv1.075
sampleLengths
016
129
26
311
458
562
619
71
81
91
1030
1176
124
1357
1432
155
162
174
1842
1928
203
2117
223
236
2440
255
2617
271
2841
298
3011
313
324
3317
3422
3538
369
375
3831
395
402
412
4239
436
4433
459
462
472
484
4938
82.63% Passive voice overuse
Target: ≤2% passive sentences
passiveCount6
totalSentences93
matches
0"been lowered"
1"was flung"
2"been taught"
3"been disturbed"
4"been pulled"
5"were meant"
70.97% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs155
matches
0"was looking"
1"was already moving"
2"was cooling"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount2
flaggedSentences2
totalSentences143
ratio0.014
matches
0"Mayberry was a good detective; he was also a tidy one, which Quinn had always distrusted."
1"The pit felt colder than the stalls above, which was wrong; heat rose, pits should have been warmer than open air."
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount700
adjectiveStacks0
stackExamples(empty)
adverbCount25
adverbRatio0.03571428571428571
lyAdverbCount2
lyAdverbRatio0.002857142857142857
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences143
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences143
mean9.31
std8.95
cv0.961
sampleLengths
016
117
212
36
411
515
68
725
810
91
102
117
1217
136
143
1526
166
1713
181
191
201
2123
227
235
2431
2521
265
272
2812
292
301
311
323
3313
347
3527
364
371
382
398
4014
4110
425
432
444
4517
4616
474
485
494
73.94% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats10
diversityRatio0.4859154929577465
totalSentences142
uniqueOpeners69
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences73
matches(empty)
ratio0
77.53% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount26
totalSentences73
matches
0"She skirted a music stand"
1"His left hand rested on"
2"She'd learned the sound from"
3"She looked at it the"
4"She leaned closer."
5"He came down into the"
6"They didn't always solve them."
7"She looked at the timestamp."
8"She stood up and walked"
9"He'd always been patient with"
10"It was one of his"
11"She saw it: a twitch"
12"Her own prints went down"
13"She watched him look."
14"He was a good enough"
15"She crouched again"
16"She sniffed, careful, at a"
17"He rubbed his eye with"
18"She didn't answer."
19"She was looking at the"
ratio0.356
76.44% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount56
totalSentences73
matches
0"The body lay in the"
1"DS Bashir handed her the"
2"Quinn ducked under the tape"
3"The Lyceum had closed for"
4"Dust-sheets draped the stalls like"
5"She skirted a music stand"
6"Dinner suit, but not a"
7"The lapels shone with the"
8"His left hand rested on"
9"Bashir said behind her"
10"She'd learned the sound from"
11"Bashir read it correctly and"
12"Quinn didn't touch the body."
13"She looked at it the"
14"The dust on the floor"
15"She leaned closer."
16"The soles, where she could"
17"This grey was lighter."
18"The voice came from the"
19"Detective Mayberry, in the sort"
ratio0.767
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences73
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences35
technicalSentenceCount1
matches
0"And then she saw it, tucked against the instep of the left one, half-hidden by the trouser cuff: a small, dull disc of something that was not metal and not plas…"
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags14
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags7
fancyCount1
fancyTags
0"She sniffed (sniff)"
dialogueSentences64
tagDensity0.109
leniency0.219
rawRatio0.143
effectiveRatio0.031
88.2025%