emotional-monotone-detector
Detects AI emotional monotone — when a novel operates in a narrow emotional register, defaulting to wistful, bittersweet, melancholy, or gently hopeful tones instead of the full spectrum of human emotion. Scans for: missing ugly emotions (pettiness, spite, boredom, disgust, glee, shame), emotional words overused vs. absent, scenes that should be funny/terrifying/infuriating but land as merely "poignant," and the AI tendency to aestheticize all suffering. Produces an emotional spectrum analysis with coverage gaps. Use when the novel feels emotionally samey or "everything is bittersweet."
Identifies when AI locks a novel into a narrow emotional bandwidth, producing prose that feels perpetually wistful regardless of what's actually happening in the story. ## Key Points - Every scene feels the same emotionally despite different events - Reader describes the novel as "beautiful but I didn't feel anything" - The default mood is melancholy, bittersweet, or gently sad - Nothing is genuinely funny, terrifying, disgusting, or enraging - Suffering is always poetic and meaningful, never ugly or pointless - The novel has no emotional peaks because it has no emotional valleys - Bittersweet - Quietly devastating - Achingly beautiful - Heavy with unspoken meaning - Tinged with loss - Every negative experience is described with poetic metaphors
skilldb get novel-audit-skills/emotional-monotone-detectorFull skill: 228 linesEmotional Monotone Detector
Identifies when AI locks a novel into a narrow emotional bandwidth, producing prose that feels perpetually wistful regardless of what's actually happening in the story.
When to Use This Skill
- Every scene feels the same emotionally despite different events
- Reader describes the novel as "beautiful but I didn't feel anything"
- The default mood is melancholy, bittersweet, or gently sad
- Nothing is genuinely funny, terrifying, disgusting, or enraging
- Suffering is always poetic and meaningful, never ugly or pointless
- The novel has no emotional peaks because it has no emotional valleys
The AI Emotional Default
AI language models have a strong attractor toward a specific emotional register that might be called "prestige melancholy" — the tone of literary fiction award acceptance speeches. Everything is:
- Wistful
- Bittersweet
- Quietly devastating
- Achingly beautiful
- Heavy with unspoken meaning
- Tinged with loss
This register is pleasant and inoffensive. It sounds "literary." And it is emotional death for a novel because it flattens everything to the same frequency.
A character stubs their toe: "a small pain that somehow held the weight of all the larger ones." A character's mother dies: "something shifted, a quiet rearranging of the world." A character eats a good sandwich: "for a moment, the simple pleasure was almost enough."
All three scenes feel identical. That's the problem.
The Full Emotional Spectrum
A novel needs access to the full range. Here's what AI typically includes and what it avoids:
AI's Comfort Zone (overrepresented)
| Emotion | AI's Version |
|---|---|
| Sadness | Quiet, dignified, aesthetically pleasing |
| Love | Tender, overwhelming, described through nature metaphors |
| Hope | Fragile, tentative, "a small light in the darkness" |
| Loss | Aching, poetic, meaningful |
| Nostalgia | Warm, sepia-toned, bittersweet |
| Loneliness | Contemplative, existential, paired with rain |
| Anxiety | A weight, a tightness, a heaviness |
| Determination | Quiet, internal, dignified |
AI's Avoidance Zone (underrepresented or absent)
| Emotion | What It Actually Looks Like |
|---|---|
| Pettiness | Counting who paid last time. Noticing your friend's success and feeling sick about it. Being glad someone failed. |
| Spite | Doing something specifically to hurt someone, and enjoying it. Cutting remarks designed to find the wound. |
| Boredom | Mind-numbing, fidgeting, clock-watching tedium that makes characters do stupid things just for stimulation. |
| Disgust | Physical revulsion. The smell of a nursing home. Finding something repulsive about someone you're supposed to love. |
| Glee | Uncontained, undignified joy. Cackling. Doing a dance when no one's watching. Joy that's embarrassing in its intensity. |
| Shame | Not guilt (AI does guilt). Shame — the full-body certainty that you are fundamentally defective as a person. Wanting to disappear. |
| Contempt | Looking at someone and finding them beneath you. Not anger — cold dismissal. The death of respect. |
| Mania | Racing thoughts, grand plans at 3 AM, spending money you don't have, feeling invincible and making terrible decisions. |
| Pity | Condescending compassion. Feeling sorry for someone in a way that has more to do with your own superiority than their suffering. |
| Lust | Actual physical desire, not "connection." Wanting someone's body specifically, not their soul. Base, animal, sometimes inappropriate. |
| Rage | Not controlled anger. Seeing red. Breaking things. Saying the unforgivable thing. Physical violence of emotion. |
| Apathy | Not caring. Not beautifully numb — just... not caring. The absence of feeling that's more frightening than any feeling. |
| Jealousy | Possessive, irrational, consuming. Not "I worry about losing you" — "I checked your phone while you were asleep." |
| Cruelty | Deliberate unkindness. Not because you're hurt — because you can. Because it feels powerful. |
| Humiliation | Public exposure. The laughter of others. Wanting to die, not poetically, but because the shame is unbearable. |
| Elation | Explosive, physical, unreasonable happiness. The kind that makes you yell in your car. |
| Awkwardness | Excruciating social discomfort. Saying the wrong thing. The silence that follows. Wanting to crawl out of your skin. |
Scanning Process
Step 1 — Emotional Word Inventory
Extract all emotion-bearing words and phrases from the manuscript. Categorize each into the emotion it conveys. Count frequencies.
EMOTIONAL WORD FREQUENCY:
Sadness family (ache, loss, weight, heavy, tears, grief): 847 occurrences
Love family (warm, tender, heart, gentle, soft): 623 occurrences
Hope family (light, maybe, someday, small smile): 412 occurrences
Fear family (cold, tight, racing, dark): 298 occurrences
Anger family (clench, sharp, burn, snap): 156 occurrences
Joy family (laugh, grin, bright, alive): 134 occurrences
Disgust family: 12 occurrences
Shame family: 8 occurrences
Spite/pettiness family: 3 occurrences
Boredom family: 0 occurrences
DIAGNOSIS: Emotional range is 85% melancholy-love-hope.
The ugly emotions are virtually absent.
Step 2 — Scene-Emotion Mismatch Analysis
For each scene, ask: what emotion SHOULD this scene primarily evoke?
Then ask: what emotion does it ACTUALLY evoke as written?
| Scene | Should Feel | Actually Feels | Mismatch? |
|---|---|---|---|
| Character gets fired | Humiliating, enraging | Bittersweet, reflective | YES |
| First kiss | Exciting, nervous, giddy | Tender, aching, profound | YES — wrong register |
| Discovering betrayal | Gut-punch, rage, disbelief | Quietly devastating | YES — aestheticized |
| Comedy scene at dinner | Funny, chaotic, warm | Gently amusing, wistful | YES — muted |
| Child being born | Overwhelming, raw, messy | Beautiful, miraculous | PARTIAL — sanitized |
| Bar fight | Ugly, scary, adrenaline | Tense, controlled | YES — too composed |
Mismatches above 40% indicate emotional monotone.
Step 3 — The Aestheticization Audit
AI has a specific failure mode: it makes everything beautiful. Even suffering, failure, and ugliness get the literary treatment.
Signs of aestheticization:
- Every negative experience is described with poetic metaphors
- Crying is always described as beautiful ("tears traced silver lines down her cheeks")
- Violence is choreographed rather than chaotic and ugly
- Poverty/hardship is described with dignity rather than humiliation
- Mental illness is treated as depth rather than dysfunction
- Death is always meaningful
- Pain always "teaches something"
The ugliness test: Find the five most negative scenes in the manuscript. Are any of them genuinely unpleasant to read? Not sad-beautiful — actually unpleasant? Uncomfortable? Ugly?
If none are: the emotional range is sanitized.
Step 4 — Tonal Shift Detection
A novel needs tonal shifts — moments where the emotional register changes abruptly because life does that.
Scan for:
- Does the novel ever shift from serious to genuinely funny? (Not wry — funny.)
- Does the novel ever shift from tender to ugly?
- Does the novel ever shift from controlled to chaotic?
- Is there a scene that's in a completely different emotional key from everything around it?
- Can you identify the single funniest moment? The most disgusting? The most embarrassing? If you can't, those registers don't exist in the novel.
Emotional Range Score
EMOTIONAL COVERAGE REPORT:
Core emotions present:
✓ Sadness (well-covered)
✓ Love (well-covered)
✓ Fear (present but narrow — mostly anxiety, no terror)
✓ Hope (well-covered)
✗ Anger (mentioned but never fully expressed)
✗ Joy (present only as quiet contentment)
✗ Disgust (absent)
✗ Surprise (absent as genuine shock)
Complex emotions present:
✓ Nostalgia
✓ Guilt
✓ Loneliness
✗ Shame
✗ Jealousy
✗ Contempt
✗ Pettiness
✗ Humiliation
✗ Glee
✗ Awkwardness
✗ Boredom
✗ Spite
COVERAGE: 7/20 emotional registers (35%)
DOMINANT REGISTER: Prestige melancholy (72% of emotional content)
VERDICT: Severe emotional monotone. Novel operates in one octave.
Revision Guidance
For each missing or underrepresented emotion, identify the 2-3 scenes where it should naturally appear and describe how to rewrite the emotional core:
MISSING: Pettiness
SCENE: Ch. 8 — Sarah learns her ex is engaged
CURRENT: "Something shifted inside her. She wished them well, even as the ache settled in."
REWRITE DIRECTION: Sarah stalks the fiancée's Instagram. Finds a bad photo.
Screenshots it and sends it to her group chat with "lol." Feels a hot spike of
satisfaction. Then hates herself. Then looks at the photo again.
MISSING: Genuine humor
SCENE: Ch. 14 — the dinner party
CURRENT: "Warm laughter filled the room as old stories were shared."
REWRITE DIRECTION: Someone tells a specific, actually funny story. Another
person laughs so hard wine comes out their nose. Someone else tries to one-up
it and bombs. The failed joke is funnier than the successful one. Write the
jokes. If the reader doesn't smile, the scene doesn't work.
Anti-Patterns
- Demanding every scene contain ugly emotions. A novel can have tender moments. The problem is when EVERY moment is tender.
- Mistaking darkness for emotional range. Grimdark isn't the fix for prestige melancholy. The fix is the full spectrum — including joy, humor, and silliness.
- Telling the author to "add more anger." Emotion must arise from character and situation. The recommendation should be about which scenes are suppressing natural emotions, not about injecting emotions artificially.
- Ignoring genre. A cozy mystery and a literary thriller have different emotional spectrums. Calibrate expectations to what the story is trying to do.
- Assuming the author wants ugly emotions. Some authors intentionally write in a gentle register. This audit informs — the author decides whether to change.
Install this skill directly: skilldb add novel-audit-skills
Related Skills
Novel Audit
Comprehensive AI-generated novel auditor. Use this skill whenever the user wants to audit, review, proofread, or quality-check an AI-generated novel, book, or long-form fiction. Triggers include: "audit my novel", "check my book for errors", "review my manuscript", "check character names", "find plot inconsistencies", "check for duplicate text", "verify my story follows the outline", "review my AI-written novel", "novel QA", "book consistency check". Use even if the user only mentions one specific concern (names, duplicates, etc.) — always run the full audit unless explicitly told otherwise. This skill handles novels of any genre, length, or structure.
originality-cliche-scanner
Deep cliché and originality scanner operating beyond phrase-level — detects clichéd plot structures, stock character archetypes, predictable story beats, borrowed world elements, and AI's tendency to reproduce the most common version of every story element. Scans for: chosen one narratives, love triangles that resolve predictably, mentor deaths, training montages, villain monologues, deus ex machina, and 50+ cataloged plot/character/setting clichés. Produces an originality score and specific subversion suggestions. Use when the novel feels derivative or "like something I've read before."
Outline Compliance Checker
Deep-dives into verifying a manuscript follows its outline beat-by-beat. Maps every outline item to its manuscript location, identifies missing scenes, added scenes, reordered events, underdeveloped beats, and over-developed tangents. Use when the user wants to confirm their manuscript matches their plan, or when drift between outline and draft is suspected.
pacing-structure-collapse
Detects AI-generated pacing and structural failures in novels: uniform tension curves, premature conflict resolution, missing rising action, false climaxes, saggy middles, identical chapter structures, scene-to-sequel ratio imbalance, absent rest beats, escalation failure (every scene at the same emotional pitch), and the AI tendency to resolve everything too neatly. Produces a tension map, pacing graph, and structural diagnosis. Use when the novel feels flat, predictable, or like nothing is building.
Prose Polish Pass
A line-editing pass focused on improving prose quality at the sentence and paragraph level. Unlike the audit skills, this skill actively rewrites — targeting weak verbs, redundant adverbs, filter words, cliche metaphors, awkward rhythms, and paragraph-level pacing issues. Use when the user wants their manuscript's prose tightened and polished chapter by chapter.
Publication Readiness Checklist
A final pre-publication checklist covering everything beyond the story itself: front matter, back matter, formatting, metadata, and platform-specific requirements for KDP, IngramSpark, and other distributors. Use when the user's manuscript is content-complete and they need to prepare it for actual publication.