Run: 2026-02-19-01KHT02EPCN28WB71KXMXM9TF7

Run Details

Duration:
41.8s
Cost:
$0.037575
Provider:
Anthropic

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 smell hit Quinn before she reached the bottom of the stairs. Old stone, standing water, and underneath it all, something burnt. Not wood or plastic. Something organic. The abandoned Tube station yawned open beneath Camden High Street, its tiled archways furred with decades of grime. Portable work lights had been strung along the platform, casting the whole scene in a flat, clinical white that made everything look like a photograph taken too close. Two uniformed officers stood near the mouth of the tunnel, keeping well back from whatever lay at the far end of the platform. Quinn noted that. Men who'd seen bodies before, keeping distance. She stepped under the cordon tape and approached. The victim was a man in his fifties, heavyset, dressed in the kind of nondescript clothing that suggested deliberate anonymity. Dark coat, dark trousers, no labels visible. He was sitting upright against the old station wall, beneath a defunct sign that still read CAMDEN ROAD in faded blue and white, back straight, hands folded in his lap. Not slumped. Not sprawled. Positioned. DS Carver was crouching nearby, notebook out, pen tapping against his knee. "Took your time." "Traffic," Quinn said, which was not true. She'd stood outside for three minutes, listening. "What've we got?" "Male, unidentified. No wallet, no phone, no keys. Station's been derelict since 2019, no official access points in use." Carver stood. He was a broad, sandy-haired man with the permanent expression of someone who'd just been told the meeting ran long. "Uniform says someone called it in anonymously. Payphone on Kentish Town Road, which is remarkable given there's about four working payphones left in London." "Cause of death?" "That's where it gets interesting." Carver moved aside to let her look properly. Quinn crouched. The man's hands in his lap, she'd noted those first, but now she looked at his palms, both turned upward, fingers curled slightly. The skin there was darkened. Scorched, but not blistered. Whatever had burned him had done it from the inside out. "Pathologist's working theory is cardiac event," Carver said. "The hands." "She thinks he gripped something. Whatever it was, he dropped it before he died. Or someone took it." Quinn looked at the floor around the body. Dust and old grit, thick enough to hold prints. She pulled her phone out and switched on the torch, angling the beam low across the platform surface. Footprints, several sets, circling the body at varying distances. And there, two feet to the left of the victim's right knee, a small circular impression in the dust. Something had rested there. Something small, round, with a flat base. "He didn't come here alone," she said. "Agreed. We've got at least three separate sets of tracks leading in from the service entrance on Greenland Road. Two sets walk out. His don't." "So two people left him here." "Or one person made two trips." Quinn straightened and turned in a slow circle, looking at the archways, the defunct ticket booths, the far end of the platform where the tunnel mouth swallowed the light. Something was wrong with the geometry of the footprints. She pulled out her worn leather notebook and sketched them quickly, marking the circular impression. "The prints leading in," she said, "which direction?" Carver pointed toward the service entrance corridor to the north. "All three sets come from that end. Two sets exit the same way." "And the victim's prints stop where?" Carver hesitated. He moved to the victim's feet, then traced the track backwards with his torch. The dead man's footprints walked in from the service corridor, yes, but they stopped and turned, mid-platform. He hadn't walked to the wall where he now sat. Carver's jaw tightened. "He was moved." "After death, or during." "Does it matter?" Quinn looked at the positioned hands again. The straight back. "Whoever left him made a decision about how he'd be found. That's not panic. That's intention." She pulled on a glove and crouched again, this time leaning close to the man's coat collar. There, on the dark wool, a faint residue. Pale, powdery, faintly iridescent under her torch beam. She photographed it with her phone before the forensics team could disturb it. "Carver. Run the name Veil Market." The pause stretched a beat too long. "Where'd you hear that?" She looked up at him. Carver was watching her with an expression she couldn't quite catalogue. Not quite surprise. Not quite guilt. Something in between, like a man deciding how much he already knew. "Three years ago," she said, "Morris and I pulled a DB from the canal near Regent's Park. Same positioning. Hands folded. No identification. Burns on the palms." She stood and faced him squarely. "Same white residue on his coat collar. The case was filed as unexplained cardiac event and buried so fast I didn't even get to finish my notes." "Quinn." "Morris died six weeks later. Case circumstances unexplained." "Quinn, I'm telling you as your colleague, leave that thread alone." "The circular impression in the dust," she said, over him. "Something sat there. Something small and round. A compass, perhaps. Brass, from the trace oxidation on the outer edge of the impression." She angled her torch so the green-tinged ring in the dust was unmistakable. Carver stared at it. "I want the full forensics sweep," Quinn said. "Every print, every residue sample, every inch of this platform." "We're already doing that." "I want it done again. And I want the anonymous call trace." "It'll come back to nothing." "Then nothing will take five minutes." She peeled her glove off and pocketed it. "This man didn't die of a cardiac event. He was holding something when he died, and the people who left him here took it with them and arranged him like a display. That's a message." She turned back to the body one last time, to the upturned palms with their burnt, blackened skin. "Someone is telling us exactly what they do to people who take what isn't theirs." Her phone buzzed. Unknown number. She answered it. "Detective Quinn." The voice was low, unhurried, a woman's. "You're at the station. I thought you'd want to know, the item you're looking for moved an hour ago. If you want to find it before it disappears, you'll need to leave Camden. Now." The line went dead.
created_at"2026-02-19T03:46:03.615Z" 2/19/2026, 3:46:03 AM
model"anthropic/claude-4.6-sonnet-20260217"
app_id182717
external_user(null)
streamedtrue
cancelledfalse
latency592
moderation_latency(null)
generation_time41696
tokens_prompt4671
tokens_completion1657
native_tokens_prompt4740
native_tokens_completion1557
native_tokens_completion_images(null)
native_tokens_reasoning0
native_tokens_cached0
num_media_prompt(null)
num_input_audio_prompt(null)
num_media_completion0
num_search_results(null)
origin"https://ncbench.com/"
is_byokfalse
finish_reason"stop"
native_finish_reason"stop"
usage0.037575
router(null)
provider_responses
0
endpoint_id"6d408764-7dd7-4626-bb87-a6cc1589bc86"
id"msg_01SrBrtzre6hLars1sjtcQoo"
is_byokfalse
latency592
model_permaslug"anthropic/claude-4.6-sonnet-20260217"
provider_name"Anthropic"
status200
api_type"completions"
id"gen-1771472763-FbQVWSi8i52vPkyVmmX1"
upstream_id"msg_01SrBrtzre6hLars1sjtcQoo"
total_cost0.037575
cache_discount(null)
upstream_inference_cost0
provider_name"Anthropic"

Evaluation details

Result Evaluator Details Meta Data
100.00% Adverbs in dialogue tags
Target: ≤10% dialogue tags with adverbs
totalTags12
adverbTagCount2
adverbTags
0"Carver moved aside [aside]"
1"She turned back [back]"
dialogueSentences40
tagDensity0.3
leniency0.6
rawRatio0.167
effectiveRatio0.1
90.55% AI-ism adverb frequency
Target: <2% AI-ism adverbs (58 tracked)
wordCount1058
totalAiIsmAdverbs2
found
0
adverb"slightly"
count1
1
adverb"quickly"
count1
highlights
0"slightly"
1"quickly"
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)
85.82% AI-ism word frequency
Target: <2% AI-ism words (290 tracked)
wordCount1058
totalAiIsms3
found
0
word"remarkable"
count1
1
word"traced"
count1
2
word"tinged"
count1
highlights
0"remarkable"
1"traced"
2"tinged"
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
narrationSentences70
matches(empty)
100.00% Filter word density
Target: ≤3% sentences with filter/hedge words
filterCount2
hedgeCount0
narrationSentences70
filterMatches
0"look"
hedgeMatches(empty)
100.00% Gibberish response detection
Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)
analyzedSentences97
gibberishSentences0
adjustedGibberishSentences0
longSentenceCount0
runOnParagraphCount0
giantParagraphCount0
wordSaladCount0
repetitionLoopCount0
controlTokenCount0
maxSentenceWordsSeen53
ratio0
matches(empty)
100.00% Markdown formatting overuse
Target: ≤5% words in markdown formatting
markdownSpans0
markdownWords0
totalWords1055
ratio0
matches(empty)
100.00% Missing dialogue indicators (quotation marks)
Target: ≤10% speech attributions without quotation marks
totalAttributions11
unquotedAttributions0
matches(empty)
79.58% Name drop frequency
Target: ≤1.0 per-name mentions per 100 words
totalMentions21
wordCount639
uniqueNames6
maxNameDensity1.41
worstName"Carver"
maxWindowNameDensity2.5
worstWindowName"Carver"
discoveredNames
Quinn8
Tube1
Camden1
High1
Street1
Carver9
persons
0"Quinn"
1"Carver"
places
0"Camden"
1"High"
2"Street"
globalScore0.796
windowScore0.833
91.86% Narrator intent-glossing
Target: ≤2% narration sentences with intent-glossing patterns
analyzedSentences43
glossingSentenceCount1
matches
0"quite catalogue"
100.00% "Not X but Y" pattern overuse
Target: ≤1 "not X but Y" per 1000 words
totalMatches0
per1kWords0
wordCount1055
matches(empty)
100.00% Overuse of "that" (subordinate clause padding)
Target: ≤2% sentences with "that" clauses
thatCount0
totalSentences97
matches(empty)
100.00% Paragraph length variance
Target: CV ≥0.5 for paragraph word counts
totalParagraphs48
mean21.98
std23.09
cv1.05
sampleLengths
028
179
28
362
412
53
617
765
83
913
1045
118
122
1318
1474
157
1625
176
186
1953
208
2123
226
2343
246
254
263
2726
2846
296
307
314
3234
3360
341
358
3611
3745
384
3918
404
4112
425
4382
445
453
4643
474
95.24% Passive voice overuse
Target: ≤2% passive sentences
passiveCount2
totalSentences70
matches
0"been told"
1"was darkened"
11.32% Past progressive (was/were + -ing) overuse
Target: ≤2% past progressive verbs
pastProgressiveCount3
totalVerbs106
matches
0"was sitting"
1"was crouching"
2"was watching"
100.00% Em-dash & semicolon overuse
Target: ≤2% sentences with em-dashes/semicolons
emDashCount0
semicolonCount0
flaggedSentences0
totalSentences97
ratio0
matches(empty)
94.00% Purple prose (modifier overload)
Target: <4% adverbs, <2% -ly adverbs, no adj stacking
wordCount642
adjectiveStacks1
stackExamples
0"broad, sandy-haired man"
adverbCount23
adverbRatio0.03582554517133956
lyAdverbCount5
lyAdverbRatio0.00778816199376947
100.00% Repeated phrase echo
Target: ≤20% sentences with echoes (window: 2)
totalSentences97
echoCount0
echoWords(empty)
100.00% Sentence length variance
Target: CV ≥0.4 for sentence word counts
totalSentences97
mean10.88
std9.21
cv0.847
sampleLengths
012
110
24
32
418
528
623
73
87
98
1020
117
1230
132
142
151
1612
173
187
197
203
2121
2220
2324
243
2513
262
2723
285
294
3011
318
322
3318
348
359
3618
379
3819
394
407
417
4225
436
446
4529
469
4715
488
4910
83.51% Sentence opener variety
Target: ≥60% unique sentence openers
consecutiveRepeats4
diversityRatio0.5257731958762887
totalSentences97
uniqueOpeners51
0.00% Adverb-first sentence starts
Target: ≥3% sentences starting with an adverb
adverbCount0
totalSentences58
matches(empty)
ratio0
95.86% Pronoun-first sentence starts
Target: ≤30% sentences starting with a pronoun
pronounCount18
totalSentences58
matches
0"She stepped under the cordon"
1"He was sitting upright against"
2"She'd stood outside for three"
3"He was a broad, sandy-haired"
4"She pulled her phone out"
5"She pulled out her worn"
6"He moved to the victim's"
7"He hadn't walked to the"
8"She pulled on a glove"
9"She photographed it with her"
10"She looked up at him."
11"she said, She stood and"
12"she said, over him"
13"She angled her torch so"
14"She peeled her glove off"
15"She turned back to the"
16"Her phone buzzed."
17"She answered it."
ratio0.31
46.21% Subject-first sentence starts
Target: ≤72% sentences starting with a subject
subjectCount48
totalSentences58
matches
0"The smell hit Quinn before"
1"The abandoned Tube station yawned"
2"Quinn noted that."
3"Men who'd seen bodies before,"
4"She stepped under the cordon"
5"The victim was a man"
6"He was sitting upright against"
7"DS Carver was crouching nearby,"
8"Quinn said, which was not"
9"She'd stood outside for three"
10"He was a broad, sandy-haired"
11"Carver moved aside to let"
12"The man's hands in his"
13"The skin there was darkened."
14"Whatever had burned him had"
15"Quinn looked at the floor"
16"Dust and old grit, thick"
17"She pulled her phone out"
18"Footprints, several sets, circling the"
19"Something had rested there."
ratio0.828
0.00% Subordinate conjunction sentence starts
Target: ≥2% sentences starting with a subordinating conjunction
subConjCount0
totalSentences58
matches(empty)
ratio0
100.00% Technical jargon density
Target: ≤6% sentences with technical-jargon patterns
analyzedSentences23
technicalSentenceCount1
matches
0"He was a broad, sandy-haired man with the permanent expression of someone who'd just been told the meeting ran long."
100.00% Useless dialogue additions
Target: ≤5% dialogue tags with trailing filler fragments
totalTags12
uselessAdditionCount0
matches(empty)
100.00% Dialogue tag variety (said vs. fancy)
Target: ≤10% fancy dialogue tags
totalTags7
fancyCount0
fancyTags(empty)
dialogueSentences40
tagDensity0.175
leniency0.35
rawRatio0
effectiveRatio0
85.7980%