Run: 2026-04-24-01KQ0GE8CPN0WTYECYH2M752WK

Run Details

Duration:
32.9s
Cost:
$0.091340
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 had been dumped on the platform like a bag of laundry, and that was the first thing that bothered Quinn. "Overdose," Sergeant Patel said, scrolling through photos on his tablet. "Needle's still in his arm. SOCO found three more in his pocket. Poor bastard wandered in to shoot up, picked the wrong place." "Wandered in." "Urban explorers. Couple of them posted a TikTok from down here last week, couldn't keep their mouths shut. Word spreads." Quinn crouched beside the corpse. Male, mid-thirties, cheap coat, expensive boots. His fingernails were clean. Scrubbed clean, in fact, the half-moons pale as bone against skin that had otherwise gone the colour of old putty. The syringe in his crooked elbow caught what little light the emergency lamps threw down the tunnel. She brushed her thumb along her leather watch strap. An old habit. Morris had bought her the watch. "Who called it in?" "Transport for London. Motion sensor at the surface hatch. Boys on shift went down for a look." "Motion sensor." "Standard kit. Camden's been a headache since the flood in '21." Quinn stood. The platform stretched in both directions, curving out of sight where the tiling gave way to brickwork. The tiles themselves were the wrong colour. Not the cream and oxblood of old Underground stock, but a dark, bruised green, as if somebody had painted over the originals and then painted over that again. She ran a gloved finger along the grout. It came away with a fine grey powder that smelled, faintly, of burnt sugar. "Patel. When did this station close?" "1907. Something about a tunnel collapse. Never reopened." "And the tiles?" "What about them?" "They're new." Patel looked up from his tablet. "New how?" "No dust accumulation at the base. No water staining. No graffiti." She turned a slow circle. "In a hundred and eighteen years, not one tagger found their way down here?" "Place is sealed off." "So is every abandoned station in London, and every one of them looks like a teenager's sketchbook." She crouched again, this time on the far side of the body, so that the emergency lamps threw her shadow across his face. "Who attended from the coroner's?" "Bellamy. She went back up half an hour ago. Said it was routine." "Did she now." She lifted the man's right hand by the sleeve. Rigor had set in and then, interestingly, set back out again. The fingers moved too easily. She pressed a gloved knuckle into the pad of his thumb and watched the flesh refuse to blanch. "How long's he been down here, according to Bellamy?" "Six hours. Maybe seven." "Seven hours, and no lividity on his back." Quinn tilted the body towards her. The skin beneath the coat was uniformly grey. Not a single purpling pool where gravity should have done its work. "He didn't die here, Patel." "Then somebody dragged him." "Down two flights, through a sealed hatch, past your motion sensor. To leave him on a platform nobody visits. With smack in his pocket they could've sold." Patel's mouth opened and closed. He was a good sergeant. He was used to things adding up. "Maybe he crawled." "Maybe." She didn't believe it. She suspected he didn't either. She moved down the platform, giving the body her back. The tiles on the far wall bore a pattern she had taken, at first, for a repeating geometric motif. A station decoration. Now, with her torch close, she saw the lines weren't repeating at all. They were characters of some kind, each one slightly different from the last, each one cut into the glaze rather than painted on. They ran the length of the platform in a neat band at shoulder height. Where her torch beam crossed them, the marks seemed to catch and hold the light a beat longer than the tile around them. "Quinn." Patel's voice had lost its certainty. "Uniforms are asking about a cordon. What do you want?" "I want this whole platform photographed. Every tile. Every inch of grout." "For an overdose." "For whatever this is." She kept walking. The band of marks continued around the curve and stopped, abruptly, at a section of wall where the tiles had been knocked through. Someone had hung a strip of dark cloth over the gap. She lifted it with the end of her pen. Beyond, the tunnel opened into a wider chamber. Her torch beam swept over crates. Folding trestles. A brass hand-bell on a nail. A smell of cold iron and something sweeter underneath, closer to orange peel than to rot. In the middle of the floor, a chalked circle, half scuffed away by footprints. Dozens of them. All sizes. All directions. She lowered the cloth. "Patel." "Yeah?" "Get Bellamy back." "She's on another shout." "Unshout her." She heard him mutter into his radio. She didn't look round. The tiles nearest the cloth bore a darker stain, low down, where something had leaked and then been wiped up in a hurry. Not blood. Blood didn't dry that colour, that blue-green, like oxidised copper. Her watch ticked against her wrist. Morris had gone into a basement in Whitechapel three years ago and come out, some hours later, wrong. She had not, at the time, known what wrong meant. She had written tunnel collapse in her own report, because what else was there to write, and the file had gone to a drawer, and she had carried on, and sometimes, on nights when she couldn't sleep, she had taken the watch off and turned it over and read the inscription on the back and put it on again. Burnt sugar. Orange peel. Copper. "Ma'am." One of the uniforms had come up behind her, breathing hard from the stairs. "Ma'am, there's a woman at the cordon. Says she needs to speak to whoever's in charge. Says it's urgent." "Name?" "Kowalski. Eva Kowalski. Says she's from the British Museum." Quinn turned, slowly, the torch beam dragging across the chalked circle and up the far wall. "Ma'am?" "Bring her down." "Down here?" "Down here. Now."
created_at"2026-04-24T19:46:03.293Z" 4/24/2026, 7:46:03 PM
model"anthropic/claude-4.7-opus-20260416"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency4025
moderation_latency(null)
generation_time32812
tokens_prompt4671
tokens_completion1629
native_tokens_prompt6543
native_tokens_completion2345
native_tokens_completion_images(null)
native_tokens_reasoning83
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"
usage0.09134
router(null)
provider_responses
0
endpoint_id"0fa65117-00d9-4835-808d-9b68041d9ce4"
id"cc8628a5-3c38-4aa1-8a61-7ead7008bd22"
is_byokfalse
latency1830
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-1777059963-Wds9CmBDyRHtILGdvsZN"
session_id(null)
api_type"completions"
id"gen-1777059963-U1LBSptQ5cAVykDAAvDM"
upstream_id"cc8628a5-3c38-4aa1-8a61-7ead7008bd22"
total_cost0.09134
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
totalTags7
adverbTagCount1
adverbTags
0"She crouched again [again]"
dialogueSentences47
tagDensity0.149
leniency0.298
rawRatio0.143
effectiveRatio0.043
90.12% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1012
totalAiIsmAdverbs2
found
0
adverb"slightly"
count1
1
adverb"slowly"
count1
highlights
0"slightly"
1"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)
95.06% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1012
totalAiIsms1
found
0
word"standard"
count1
highlights
0"standard"
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
narrationSentences67
matches(empty)
78.89% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount1
narrationSentences67
filterMatches
0"watch"
hedgeMatches
0"seemed to"
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences107
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
repeatedSegmentCount0
maxSentenceWordsSeen59
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1012
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions7
unquotedAttributions0
matches(empty)
100.00% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions11
wordCount700
uniqueNames4
maxNameDensity0.71
worstName"Quinn"
maxWindowNameDensity1.5
worstWindowName"Quinn"
discoveredNames
Quinn5
Patel4
Underground1
Whitechapel1
persons
0"Quinn"
1"Patel"
places
0"Whitechapel"
globalScore1
windowScore1
100.00% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences45
glossingSentenceCount0
matches(empty)
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches1
per1kWords0.988
wordCount1012
matches
0"Not the cream and oxblood of old Underground stock, but a dark, bruised green, as if somebody had painted over the o"
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount1
totalSentences107
matches
0"dry that colour"
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs55
mean18.4
std23.33
cv1.268
sampleLengths
022
133
22
320
452
518
64
717
82
911
1076
116
128
133
143
152
168
1730
184
1945
2013
213
2243
239
244
2539
264
2727
2817
293
3010
31105
3217
3312
343
354
3646
3759
384
391
401
413
424
432
4446
4593
465
4734
481
499
84.32% Passive voice overuse
Target: ≤2% passive sentences
passiveCount4
totalSentences67
matches
0"been dumped"
1"was used"
2"been knocked"
3"been wiped"
100.00% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount1
totalVerbs110
matches
0"weren't repeating"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences107
ratio0
matches(empty)
100.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount704
adjectiveStacks0
stackExamples(empty)
adverbCount21
adverbRatio0.029829545454545456
lyAdverbCount7
lyAdverbRatio0.009943181818181818
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences107
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences107
mean9.46
std8.79
cv0.929
sampleLengths
022
110
223
32
420
55
66
74
820
917
109
113
126
134
1417
152
1611
172
1817
197
2028
218
2214
236
248
253
263
272
286
292
3016
3114
324
3340
345
3513
363
379
3811
395
4018
419
424
4314
448
4512
465
474
4827
495
83.80% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats12
diversityRatio0.5700934579439252
totalSentences107
uniqueOpeners61
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences59
matches(empty)
ratio0
57.29% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount24
totalSentences59
matches
0"His fingernails were clean."
1"She brushed her thumb along"
2"She ran a gloved finger"
3"It came away with a"
4"She turned a slow circle"
5"She crouched again, this time"
6"She lifted the man's right"
7"She pressed a gloved knuckle"
8"He was a good sergeant."
9"He was used to things"
10"She didn't believe it"
11"She suspected he didn't either."
12"She moved down the platform,"
13"They were characters of some"
14"They ran the length of"
15"She kept walking."
16"She lifted it with the"
17"Her torch beam swept over"
18"She lowered the cloth."
19"She heard him mutter into"
ratio0.407
36.27% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount50
totalSentences59
matches
0"The body had been dumped"
1"Sergeant Patel said, scrolling through"
2"Quinn crouched beside the corpse."
3"His fingernails were clean."
4"The syringe in his crooked"
5"She brushed her thumb along"
6"An old habit."
7"Morris had bought her the"
8"The platform stretched in both"
9"The tiles themselves were the"
10"She ran a gloved finger"
11"It came away with a"
12"Patel looked up from his"
13"She turned a slow circle"
14"She crouched again, this time"
15"She lifted the man's right"
16"Rigor had set in and"
17"The fingers moved too easily."
18"She pressed a gloved knuckle"
19"Quinn tilted the body towards"
ratio0.847
84.75% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount1
totalSentences59
matches
0"Now, with her torch close,"
ratio0.017
85.71% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences25
technicalSentenceCount2
matches
0"Scrubbed clean, in fact, the half-moons pale as bone against skin that had otherwise gone the colour of old putty."
1"Not the cream and oxblood of old Underground stock, but a dark, bruised green, as if somebody had painted over the originals and then painted over that again."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags7
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags1
fancyCount0
fancyTags(empty)
dialogueSentences47
tagDensity0.021
leniency0.043
rawRatio0
effectiveRatio0
89.2068%