Run: 2026-02-19-01KHT0T8F5VBXVDC5HVFHZE63E

Run Details

Model:: Arcee AI: Trinity Large (Preview)
Test:: Bad Writing Habits
Scenario:: Mystery: examining a crime scene
Duration:: 31.3s
Cost:: $0.000000
Provider:: Arcee AI

Evaluation summary

Score	Evaluator	Details Link
100.00%	Adverbs in dialogue tags	(details)
68.65%	AI-ism adverb frequency	(details)
100.00%	AI-ism character names	(details)
100.00%	AI-ism location names	(details)
0.00%	AI-ism word frequency	(details)
100.00%	Cliché density	(details)
100.00%	Emotion telling (show vs. tell)	(details)
6.80%	Filter word density	(details)
100.00%	Gibberish response detection	(details)
100.00%	Markdown formatting overuse	(details)
100.00%	Missing dialogue indicators (quotation marks)	(details)
59.64%	Name drop frequency	(details)
0.00%	Narrator intent-glossing	(details)
100.00%	"Not X but Y" pattern overuse	(details)
100.00%	Overuse of "that" (subordinate clause padding)	(details)
100.00%	Paragraph length variance	(details)
88.55%	Passive voice overuse	(details)
100.00%	Past progressive (was/were + -ing) overuse	(details)
32.97%	Em-dash & semicolon overuse	(details)
100.00%	Purple prose (modifier overload)	(details)
100.00%	Repeated phrase echo	(details)
100.00%	Sentence length variance	(details)
75.00%	Sentence opener variety	(details)
83.33%	Adverb-first sentence starts	(details)
90.00%	Pronoun-first sentence starts	(details)
85.00%	Subject-first sentence starts	(details)
0.00%	Subordinate conjunction sentence starts	(details)
80.75%	Technical jargon density	(details)
100.00%	Useless dialogue additions	(details)
87.50%	Dialogue tag variety (said vs. fancy)	(details)
78.6065%	Overall

Model input

System

You are an expert fiction writer.

Always keep the following rules in mind:
- Write in past tense and use General English spelling, grammar, and colloquialisms/slang.
- Write in active voice
- Always follow the "show, don't tell" principle.
- Avoid adverbs and cliches and overused/commonly used phrases. Aim for fresh and original descriptions.
- Convey events and story through dialogue.
- Mix short, punchy sentences with long, descriptive ones. Drop fill words to add variety.
- Skip "he/she said said" dialogue tags and convey people's actions or face expressions through their speech
- Avoid mushy dialog and descriptions, have dialogue always continue the action, never stall or add unnecessary fluff. Vary the descriptions to not repeat yourself.
- Put dialogue on its own paragraph to separate scene and action.
- Reduce indicators of uncertainty like "trying" or "maybe"

When writing text:
- NEVER conclude the scene on your own, follow the beat instructions very closely.
- NEVER end with foreshadowing.
- NEVER write further than what I prompt you with.
- AVOID imagining possible endings, NEVER deviate from the instructions.
- STOP EARLY if the continuation contains what was required in the instructions. You do not need to fill out the full amount of words possible.

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>

Continue the story using 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

The damp air clung to Detective Quinn's skin as she descended the metal staircase into the abandoned Tube station. Her worn leather watch caught the dim emergency lighting as she checked the time - 2:47 AM. The station had been decommissioned in the 70s, its platforms now coated in a layer of grime and graffiti that spoke of decades of neglect.

"Quinn," called her partner, DS Morris, from the far end of the platform. "Over here."

She followed the sound of his voice, her footsteps echoing in the cavernous space. The crime scene was marked by yellow tape stretched across the tracks, a single pool of light illuminating the area. As she approached, Quinn noted the unusual details - the lack of blood, the pristine condition of the victim's clothing, the absence of any visible weapon.

"What have we got?" she asked, crouching beside the body.

"John Doe, early 30s," Morris replied, consulting his notes. "No ID on him. The uniform found him about an hour ago during a routine patrol of the station."

Quinn studied the victim's face, noting the peaceful expression, the lack of any defensive wounds. "No signs of struggle," she murmured. "And no blood. If this was a murder, where's the blood?"

Morris shrugged. "Maybe he was killed elsewhere and dumped here?"

Quinn shook her head. "No lividity. If he'd been moved, we'd see discoloration in the lower extremities." She stood, scanning the platform. "And there's no sign of a struggle. No scuff marks, no disturbed dust. It's like he just... appeared here."

She walked to the edge of the platform, peering down at the tracks. "Anything on the CCTV?"

Morris shook his head. "Cameras were disabled. Looks like someone knew what they were doing."

Quinn frowned, her mind racing. This wasn't adding up. A body appearing in a sealed-off station with no signs of entry or exit, no evidence of foul play, yet clearly dead. It was as if the man had simply... vanished from existence.

She turned back to Morris. "I want a full sweep of the station. Check for any hidden entrances, any signs of recent activity. And get forensics in here. I want every inch of this place examined."

As Morris moved to relay her orders, Quinn's gaze fell on a glint of metal near the victim's hand. She crouched again, carefully extracting a small brass object from beneath the body. It was a compass, its casing etched with intricate sigils that seemed to shift and writhe in the dim light.

Quinn's pulse quickened. She'd seen symbols like these before, in the case files of her missing partner. The same case that had driven her to the edge of sanity, that had cost her everything.

She pocketed the compass, a sense of foreboding settling over her. This was no ordinary murder. This was something else entirely, something that reached into the shadows of London's underworld and touched on forces beyond human understanding.

As she stood, Quinn caught a flicker of movement in her peripheral vision. She turned sharply, but there was nothing there. Just the oppressive darkness of the abandoned station, pressing in on all sides.

"Quinn?" Morris called from across the platform. "You okay?"

She nodded, forcing a smile. "Fine. Just... let's wrap this up quickly."

As she watched the forensics team move in, Quinn's mind was already racing ahead. This case was going to take her down a path she'd hoped never to walk again. But she had no choice. Not if she wanted to find out what had really happened to her partner, and what dark secrets lurked beneath the streets of London.

The compass in her pocket seemed to pulse with an otherworldly energy, a silent promise of answers to come. And with it, the knowledge that nothing in her world would ever be the same again.

Evaluation details

Result

Evaluator

Details

Meta Data

100.00%

Adverbs in dialogue tags

Target: ≤10% dialogue tags with adverbs

totalTags	6
adverbTagCount	0
adverbTags	(empty)
dialogueSentences	16
tagDensity	0.375
leniency	0.75
rawRatio	0
effectiveRatio	0

68.65%

AI-ism adverb frequency

Target: <2% AI-ism adverbs (58 tracked)

wordCount

638

totalAiIsmAdverbs

found

adverb	"carefully"
count	1

adverb	"sharply"
count	1

adverb	"quickly"
count	1

adverb	"really"
count	1

highlights

0	"carefully"
1	"sharply"
2	"quickly"
3	"really"

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)

0.00%

AI-ism word frequency

Target: <2% AI-ism words (290 tracked)

wordCount

638

totalAiIsms

found

word	"footsteps"
count	1

word	"echoing"
count	1

word	"pristine"
count	1

word	"scanning"
count	1

word	"racing"
count	2

word	"glint"
count	1

word	"etched"
count	1

word	"intricate"
count	1

word	"pulse"
count	2

word	"quickened"
count	1

word	"sense of"
count	1

word	"foreboding"
count	1

word	"flicker"
count	1

word	"oppressive"
count	1

word	"otherworldly"
count	1

highlights

0	"footsteps"
1	"echoing"
2	"pristine"
3	"scanning"
4	"racing"
5	"glint"
6	"etched"
7	"intricate"
8	"pulse"
9	"quickened"
10	"sense of"
11	"foreboding"
12	"flicker"
13	"oppressive"
14	"otherworldly"

100.00%

Cliché density

Target: ≤1 cliche(s) per 800-word window

totalCliches

maxInWindow

found

label	"sense of foreboding"
count	1

highlights

0	"a sense of foreboding"

100.00%

Emotion telling (show vs. tell)

Target: ≤3% sentences with emotion telling

emotionTells

narrationSentences

matches

0	"a sense of foreboding"

6.80%

Filter word density

Target: ≤3% sentences with filter/hedge words

filterCount

hedgeCount

narrationSentences

filterMatches

"watch"

hedgeMatches

0	"seemed to"
1	"happened to"

100.00%

Gibberish response detection

Target: ≤1% gibberish-like sentences (hard fail if a sentence exceeds 800 words)

analyzedSentences	52
gibberishSentences	0
adjustedGibberishSentences	0
longSentenceCount	0
runOnParagraphCount	0
giantParagraphCount	0
wordSaladCount	0
repetitionLoopCount	0
controlTokenCount	0
maxSentenceWordsSeen	31
ratio	0
matches	(empty)

100.00%

Markdown formatting overuse

Target: ≤5% words in markdown formatting

markdownSpans	0
markdownWords	0
totalWords	639
ratio	0
matches	(empty)

100.00%

Missing dialogue indicators (quotation marks)

Target: ≤10% speech attributions without quotation marks

totalAttributions	7
unquotedAttributions	0
matches	(empty)

59.64%

Name drop frequency

Target: ≤1.0 per-name mentions per 100 words

totalMentions

wordCount

498

uniqueNames

maxNameDensity

1.81

worstName

"Quinn"

maxWindowNameDensity

worstWindowName

"Quinn"

discoveredNames

Detective	1
Quinn	9
Tube	1
Morris	7
London	2

persons

0	"Detective"
1	"Quinn"
2	"Morris"

places

"London"

globalScore

0.596

windowScore

0.667

0.00%

Narrator intent-glossing

Target: ≤2% narration sentences with intent-glossing patterns

analyzedSentences

glossingSentenceCount

matches

0	"It was as if the man had simply"
1	"sigils that seemed to shift and writhe in the dim light"

100.00%

"Not X but Y" pattern overuse

Target: ≤1 "not X but Y" per 1000 words

totalMatches	0
per1kWords	0
wordCount	639
matches	(empty)

100.00%

Overuse of "that" (subordinate clause padding)

Target: ≤2% sentences with "that" clauses

thatCount	0
totalSentences	52
matches	(empty)

100.00%

Paragraph length variance

Target: CV ≥0.5 for paragraph word counts

totalParagraphs

mean

31.95

std

16.9

0.529

sampleLengths

0	61
1	15
2	60
3	10
4	28
5	32
6	10
7	41
8	17
9	15
10	42
11	36
12	52
13	34
14	37
15	34
16	9
17	12
18	59
19	35

88.55%

Passive voice overuse

Target: ≤2% passive sentences

passiveCount

totalSentences

matches

0	"been decommissioned"
1	"was marked"

100.00%

Past progressive (was/were + -ing) overuse

Target: ≤2% past progressive verbs

pastProgressiveCount

totalVerbs

matches

0	"wasn't adding"

32.97%

Em-dash & semicolon overuse

Target: ≤2% sentences with em-dashes/semicolons

emDashCount

semicolonCount

flaggedSentences

totalSentences

ratio

0.038

matches

0	"Her worn leather watch caught the dim emergency lighting as she checked the time - 2:47 AM."
1	"As she approached, Quinn noted the unusual details - the lack of blood, the pristine condition of the victim's clothing, the absence of any visible weapon."

100.00%

Purple prose (modifier overload)

Target: <4% adverbs, <2% -ly adverbs, no adj stacking

wordCount	497
adjectiveStacks	0
stackExamples	(empty)
adverbCount	15
adverbRatio	0.030181086519114688
lyAdverbCount	7
lyAdverbRatio	0.014084507042253521

100.00%

Repeated phrase echo

Target: ≤20% sentences with echoes (window: 2)

totalSentences	52
echoCount	0
echoWords	(empty)

100.00%

Sentence length variance

Target: CV ≥0.4 for sentence word counts

totalSentences

mean

12.29

std

7.17

0.584

sampleLengths

0	19
1	17
2	25
3	13
4	2
5	14
6	20
7	26
8	10
9	9
10	19
11	15
12	6
13	11
14	2
15	8
16	4
17	18
18	19
19	13
20	4
21	4
22	11
23	5
24	4
25	22
26	8
27	3
28	5
29	31
30	19
31	13
32	20
33	3
34	14
35	17
36	11
37	5
38	21
39	13
40	8
41	13
42	7
43	2
44	5
45	7
46	14
47	16
48	5
49	24

75.00%

Sentence opener variety

Target: ≥60% unique sentence openers

consecutiveRepeats	1
diversityRatio	0.46153846153846156
totalSentences	52
uniqueOpeners	24

83.33%

Adverb-first sentence starts

Target: ≥3% sentences starting with an adverb

adverbCount

totalSentences

matches

0	"Just the oppressive darkness of"

ratio

0.025

90.00%

Pronoun-first sentence starts

Target: ≤30% sentences starting with a pronoun

pronounCount

totalSentences

matches

0	"Her worn leather watch caught"
1	"She followed the sound of"
2	"she asked, crouching beside the"
3	"She stood, scanning the platform"
4	"She walked to the edge"
5	"It was as if the"
6	"She turned back to Morris."
7	"She crouched again, carefully extracting"
8	"It was a compass, its"
9	"She'd seen symbols like these"
10	"She pocketed the compass, a"
11	"She turned sharply, but there"
12	"She nodded, forcing a smile."

ratio

0.325

85.00%

Subject-first sentence starts

Target: ≤72% sentences starting with a subject

subjectCount

totalSentences

matches

0	"The damp air clung to"
1	"Her worn leather watch caught"
2	"The station had been decommissioned"
3	"She followed the sound of"
4	"The crime scene was marked"
5	"she asked, crouching beside the"
6	"Morris replied, consulting his notes"
7	"Quinn studied the victim's face,"
8	"Quinn shook her head."
9	"She stood, scanning the platform"
10	"She walked to the edge"
11	"Morris shook his head."
12	"Quinn frowned, her mind racing."
13	"This wasn't adding up."
14	"A body appearing in a"
15	"It was as if the"
16	"She turned back to Morris."
17	"She crouched again, carefully extracting"
18	"It was a compass, its"
19	"Quinn's pulse quickened."

ratio

0.75

0.00%

Subordinate conjunction sentence starts

Target: ≥2% sentences starting with a subordinating conjunction

subConjCount	0
totalSentences	40
matches	(empty)
ratio	0

80.75%

Technical jargon density

Target: ≤6% sentences with technical-jargon patterns

analyzedSentences

technicalSentenceCount

matches

0	"The station had been decommissioned in the 70s, its platforms now coated in a layer of grime and graffiti that spoke of decades of neglect."
1	"This was something else entirely, something that reached into the shadows of London's underworld and touched on forces beyond human understanding."

100.00%

Useless dialogue additions

Target: ≤5% dialogue tags with trailing filler fragments

totalTags	6
uselessAdditionCount	0
matches	(empty)

87.50%

Dialogue tag variety (said vs. fancy)

Target: ≤10% fancy dialogue tags

totalTags

fancyCount

fancyTags

0	"she murmured (murmur)"

dialogueSentences

tagDensity

0.313

leniency

0.625

rawRatio

0.2

effectiveRatio

0.125

78.6065%