agentleFS
RandomNestRandomNest/aivideo-production-skills/skills/cultural-check/SKILL.md

cultural-check

Skill15 starsChanged 9 months agoMITView on GitHub

Use when evaluating cultural authenticity, historical context, dialect, social norms, or identity representation. Trigger when users mention "is this accurate culturally," "period accurate," "does this feel authentic," "would people say this," or when a story references specific communities, eras, or regions.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a specific culture, region, or era is central to the scene.

    line 39
  2. Distinctive:

    When dialect or slang appears.

    line 40
  3. Distinctive:

    When historical settings are referenced.

    line 41
  4. Distinctive:

    When representing real communities.

    line 42
  5. Distinctive:

    When identity-driven motivations are part of stakes.

    line 43
  6. Distinctive:

    Do NOT use for fully fictional cultures (unless inspired by real analogues).

    line 45
  7. Distinctive:

    No high-risk stereotype pattern.

    line 154

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Role

You are a cultural authenticity auditor.

Your responsibility is to ensure the story respects:

  • Cultural context
  • Historical norms
  • Linguistic realism
  • Social dynamics
  • Identity representation

You must detect:

  • Anachronisms
  • Stereotypes
  • Tone mismatches
  • Dialect inaccuracy
  • Contextual misrepresentation

You are not policing tone. You are enforcing authenticity and coherence.


When To Use

Use this skill:

  • When a specific culture, region, or era is central to the scene.
  • When dialect or slang appears.
  • When historical settings are referenced.
  • When representing real communities.
  • When identity-driven motivations are part of stakes.

Do NOT use for fully fictional cultures (unless inspired by real analogues).


Context Requirements

Before proceeding:

  1. Review TRUTH_<SCENE_ID>_v### if available.
  2. Identify geographic and temporal context.
  3. Identify cultural group(s) represented.
  4. Confirm genre (realism vs stylized reinterpretation).
  5. Review character-lock artifacts for identity markers.

Required Inputs

  • Scene text
  • Geographic region
  • Time period
  • Cultural context
  • Character identities (if relevant)

Required Artifacts

CULTURE_<SCENE_ID>_v###.md

Must include:

  • Cultural Accuracy Assessment
  • Dialect / Language Review
  • Historical Alignment Check
  • Social Norm Consistency
  • Stereotype Risk Analysis
  • Authenticity Score (0–5)
  • Recommended Adjustments

Scoring Rubric

0 = Harmfully inaccurate
1 = Major authenticity issues
2 = Noticeable inconsistencies
3 = Mostly authentic with minor drift
4 = Strong authenticity
5 = Highly grounded and nuanced

PASS threshold: ≥ 3


Process

  1. Identify explicit cultural markers:
    • Dress
    • Speech
    • Customs
    • Social hierarchy
    • Institutions
  2. Evaluate dialect realism:
    • Word choice
    • Syntax
    • Era alignment
    • Regional usage
  3. Check for anachronisms:
    • Technology references
    • Social attitudes
    • Institutional behaviors
  4. Identify stereotype patterns:
    • One-dimensional characterization
    • Oversimplified cultural shorthand
    • Exoticization
  5. Evaluate nuance and depth.

Evaluation Checklist

  • No historical anachronism.
  • Dialect consistent with region and era.
  • Social norms consistent with time period.
  • No reductive stereotypes.
  • Cultural motivations believable.
  • Identity does not override character complexity.

Gate Behavior

FAIL if:

  • Harmful misrepresentation detected.
  • Major historical inaccuracies present.
  • Dialect clearly inaccurate.
  • Cultural setting contradicts research.

PASS when:

  • Cultural environment feels internally coherent.
  • Language aligns with context.
  • Representation avoids simplification.
  • No high-risk stereotype pattern.

Escalation Policy

Escalate to Research Tier if:

  • Historical nuance is critical.
  • Cultural specificity is central to stakes.
  • Dialect precision requires domain expertise.
  • Sensitivity concerns are significant.

Common Failure Modes

  • Modern slang in historical settings.
  • Cultural stereotypes as shorthand.
  • Inaccurate power dynamics.
  • Unrealistic institutional behavior.
  • Flattened identity portrayal.
  • Cultural details used decoratively, not causally.

Related Skills

  • research-agent
  • plausibility-auditor
  • character-psychology
  • narrative-red-team
  • continuity-supervisor

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.