Sensitivity and Representation Review
Reviews a manuscript for problematic representation, stereotypes, cultural insensitivity, and harmful tropes across multiple dimensions including gender, race, disability, sexuality, and cultural accuracy. This skill is advisory — it flags concerns for human review rather than prescribing changes. Use when the user wants a representation check before publication.
A structured review process for identifying representation concerns in fiction manuscripts. This skill surfaces potential issues for the author's consideration — it does not dictate creative choices. The author retains full authority over their work. ## Key Points - User says "sensitivity read", "check for stereotypes", "representation review" - User wants to identify potentially harmful tropes before publication - User is writing outside their own experience and wants a flag-pass - User wants to ensure diverse characters are portrayed with depth and respect - **Inspiration porn**: Is a disabled character's primary narrative function to inspire able-bodied - **Cure narratives**: Is disability treated as a problem to be fixed rather than an aspect of - **Accuracy**: Do depicted disabilities match real-world experience, or are they based on - **Agency**: Do disabled characters make their own choices and drive their own arcs? - **Language**: Is person-first or identity-first language used consistently with community - **Magical disability**: Is a disability paired with a compensating superpower (blind - **Bury your gays**: Do LGBTQ+ characters die at disproportionate rates compared to straight - **Coming out as entire arc**: Is a character's queerness their only defining trait, or are
skilldb get novel-audit-skills/sensitivity-and-representation-reviewFull skill: 173 linesSensitivity and Representation Review Skill
A structured review process for identifying representation concerns in fiction manuscripts. This skill surfaces potential issues for the author's consideration — it does not dictate creative choices. The author retains full authority over their work.
When to Use This Skill
- User says "sensitivity read", "check for stereotypes", "representation review"
- User wants to identify potentially harmful tropes before publication
- User is writing outside their own experience and wants a flag-pass
- User wants to ensure diverse characters are portrayed with depth and respect
Core Principle
This skill identifies patterns and flags concerns. It does not label text as "wrong" or demand changes. Every flag is a question for the author to consider, not a verdict. Fiction can and should explore difficult, uncomfortable, and morally complex territory. The goal is to help authors make informed choices, not safe ones.
Review Dimensions
1 — Gender Representation
Examine agency distribution, description patterns (appearance vs. action), role diversity, the Bechdel baseline, power dynamics, and treatment of non-binary characters. Flag when female characters only react to male actions, or when gender roles are uniformly stereotypical.
2 — Racial and Ethnic Portrayal
Examine descriptor patterns (unmarked whiteness), dialect rendering, role limitations (stereotypical casting), cultural accuracy, white savior dynamics, and whether cultural practices are depicted as normal or exoticized.
3 — Disability Depiction
Examine:
- Inspiration porn: Is a disabled character's primary narrative function to inspire able-bodied characters?
- Cure narratives: Is disability treated as a problem to be fixed rather than an aspect of a full human life?
- Accuracy: Do depicted disabilities match real-world experience, or are they based on misconceptions?
- Agency: Do disabled characters make their own choices and drive their own arcs?
- Language: Is person-first or identity-first language used consistently with community preferences? Is outdated or slur-adjacent terminology present?
- Magical disability: Is a disability paired with a compensating superpower (blind characters who "see" better than sighted ones)?
4 — LGBTQ+ Representation
Examine:
- Bury your gays: Do LGBTQ+ characters die at disproportionate rates compared to straight characters? Is their suffering the primary narrative purpose?
- Coming out as entire arc: Is a character's queerness their only defining trait, or are they a full person who also happens to be queer?
- Villainous coding: Are antagonists coded as queer through stereotyped traits while protagonists are straight?
- Relationship parity: Are queer relationships given the same depth, tenderness, and screen time as straight ones?
- Historical accuracy vs. erasure: In historical settings, is queerness acknowledged as having always existed, rather than treated as modern invention?
- Terminology: Is language current and respectful? Are slurs used only with clear narrative purpose and appropriate consequences?
5 — Cultural Accuracy and Sensitivity
Examine:
- Setting research: If the story is set in a real culture, are customs, geography, food, religion, and social norms accurately depicted?
- Language use: Are non-English words used correctly, with proper diacritical marks? Are they used for flavor or for function?
- Religious depiction: Are religious practices and beliefs depicted accurately and with appropriate nuance?
- Historical sensitivity: For stories involving historical atrocities (slavery, genocide, colonialism), is the depiction respectful to survivors and descendants?
- Naming conventions: Do character names match their stated cultural background?
6 — Power Dynamics and Structural Patterns
Track by demographic: who speaks, who acts, who suffers, who gets complexity. Does the narrative perspective center dominant groups even when telling marginalized characters' stories?
7 — Age-Appropriate Content
For the stated target audience, check violence level, sexual content, profanity, and thematic weight against genre and age-category expectations.
Output Format
# Sensitivity and Representation Review
**Title**: [Novel title]
**Date**: [Today]
**Reviewer note**: This review flags concerns for the author's consideration. It does not
prescribe changes. The author retains full creative authority.
## Summary
[2-3 sentence overview of the manuscript's representation landscape]
## Findings by Dimension
### Gender Representation
**Overall**: [brief assessment]
**Flags**:
- [flag]: [description] — Ch. X (p. Y)
- *Context*: [why this might be a concern]
- *Consider*: [question for the author, not a directive]
### Racial and Ethnic Portrayal
[same structure]
### Disability Depiction
[same structure]
### LGBTQ+ Representation
[same structure]
### Cultural Accuracy
[same structure]
### Power Dynamics
[same structure]
### Age-Appropriate Content
[same structure]
## Pattern Summary
[Are there systemic patterns across dimensions, or isolated instances?]
## Strengths
[What the manuscript does well in terms of representation — always include this section]
## Recommended Resources
[Relevant sensitivity reading resources, #ownvoices perspectives, or research materials
the author might consult for flagged areas]
Anti-Patterns
Prescribing creative decisions. This skill flags and questions. It does not command. "You must change this" is never appropriate. "You may want to consider whether this reads as..." is the correct framing.
Flattening nuance into checklists. Representation quality is not about counting demographics. A story with one deeply rendered character from a marginalized group is better than a story with a diverse cast of cardboard cutouts.
Ignoring genre context. A grimdark fantasy will depict cruelty. A historical novel set during Jim Crow will contain racism. The question is not whether these things appear but how the narrative frames them — does it endorse, challenge, or merely depict?
Projecting a single cultural lens. Different cultures have different norms and values. A behavior that reads as problematic in one cultural context may be perfectly normal in another. Flag with humility and acknowledge when you lack expertise.
Forgetting to note strengths. Always include what the manuscript does well. A review that only lists problems is demoralizing and incomplete. Good representation deserves recognition.
Treating this as a substitute for human sensitivity readers. This skill is a first pass. For manuscripts dealing substantially with experiences outside the author's own, recommend that the author also consult human sensitivity readers from the relevant communities.
Install this skill directly: skilldb add novel-audit-skills
Related Skills
show-dont-tell-enforcer
Detects and fixes AI over-telling — when the narration states emotions, motivations, themes, and subtext directly instead of conveying them through action, dialogue, sensory detail, and implication. Catalogs: stated emotions ("she felt sad"), explained motivations ("he did this because"), narrated subtext ("the tension between them was palpable"), theme announcements ("she realized that love was about sacrifice"), redundant interiority (showing AND telling the same thing), and the AI tendency to explain every metaphor after deploying it. Produces a show/tell ratio and specific rewrite guidance. Use when the prose feels over-explained, hand-holdy, or like the narrator doesn't trust the reader.
Subplot Tracker
Identifies and tracks every subplot in a manuscript from introduction through development to resolution or abandonment. Maps subplot touchpoints across chapters and flags dropped threads, abrupt resolutions, and subplots that disappear for too long. Use when the user wants to verify all their narrative threads are properly managed.
Timeline Continuity Checker
Builds a chronological timeline from a manuscript by tracking every stated time reference, then identifies temporal impossibilities, travel time violations, aging inconsistencies, and contradictory event ordering. Use when the user needs to verify their story's internal chronology or suspects timeline errors in an AI-generated manuscript.
voice-drift-detector
Detects narrator voice drift in AI-generated novels — when the narrative voice shifts inconsistently between chapters, POV bleeds across characters in multi-POV novels, tonal register changes randomly, and the prose style oscillates between literary, casual, and generic depending on which AI session generated it. Produces a voice consistency map, identifies drift zones, and provides recalibration guidance. Use when the novel's narration feels inconsistent, or when different chapters feel like they were written by different people.
worldbuilding-consistency-auditor
Audits worldbuilding consistency across a novel — detects contradictions in setting rules, magic systems, technology, geography, culture, economics, politics, and physical laws that AI introduces when generating across multiple sessions. Scans for: rule contradictions, geography errors, anachronisms, economic impossibilities, cultural inconsistencies, magic/tech system violations, and generic/default world elements that lack specificity. Produces a world bible discrepancy report. Use when the novel's world has been built incrementally by AI and needs consistency verification.
AI Tell Detector
Specialized in detecting AI-generated prose patterns in fiction manuscripts. Catalogs 30+ specific AI writing tells, provides per-chapter density scoring, suggests human-sounding replacements, and maintains a phrase blacklist. Use when the user wants to scrub their manuscript of robotic or formulaic AI language, or when AI-generated text needs to read as authentically human-written.