agentleFS
4444J994444J99/a-i--skills/skills/creative/narratological-algorithms/SKILL.md

narratological-algorithms

Skill17 starsChanged 5 months agoApache-2.0Archived repositoryView on GitHub

Distill artist/theorist narrative principles into formal, implementable algorithmic frameworks. Use when asked to extract, formalize, or systematize narrative techniques from any storytelling source—filmmakers, writers, theorists, game designers, showrunners. Triggers on requests involving narrative principle extraction, story structure analysis, craft methodology formalization, or creating implementable storytelling protocols.

1 other project uses a version of this.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Always prioritize primary sources over secondary analysis:

    line 29
  2. Distinctive:

    When using secondary sources, validate principles against primary evidence.

    line 35
  3. Distinctive:

    When source material is medium-specific, include adaptation guidance for:

    line 107

≈ “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

Narratological Algorithm Distillation

Transform narrative principles from artists, theorists, and practitioners into formal, implementable algorithmic frameworks.

Workflow

1. Source Classification

Identify source type to calibrate extraction approach:

TypeCharacteristicsExtraction Focus
TheoristPrescriptive texts (McKee, Aristotle)Direct principle extraction
PractitionerInterviews, commentary, production docsReverse-engineering from stated methods
ClassicalAncient/foundational texts (Poetics, Natyasastra)Translation of archaic terminology
AnalystSecondary analysis of creator's workValidation against primary sources

2. Primary Source Prioritization

Always prioritize primary sources over secondary analysis:

  • Direct quotes from the creator
  • Production documents, interviews, lectures
  • The creator's own articulated methodology
  • Documented working processes

When using secondary sources, validate principles against primary evidence. Flag where principles are inferred vs. directly stated.

3. Principle Extraction Protocol

For each identified principle:

EXTRACT:
  1. Locate source statement (direct quote when available)
  2. Identify underlying mechanism (why it works)
  3. Formulate as rule or constraint
  4. Determine scope (universal vs. context-specific)
  5. Map to existing narrative theory where applicable

4. Document Structure

Generate output following the canonical structure. See references/output-template.md for the full template.

Required sections:

  1. Meta-Principles (Axioms)
  2. Structural Hierarchy
  3. Core Algorithms/Protocols
  4. Diagnostic Questions/Tests
  5. Quick Reference Card

Optional sections (as warranted):

  • Episode/Scene Templates
  • Theoretical Correspondence Tables
  • Source Cross-Reference Appendix

5. Formalization Patterns

Convert principles to implementable forms:

Source FormTarget Form
Conceptual statementConstraint rule
Process descriptionPseudocode function
Best practiceValidity test
ComparisonDecision table
TaxonomyClassification tree

See references/formalization-patterns.md for detailed examples.

6. Axiom Identification

Identify 3-7 meta-principles that underpin the creator's entire approach:

AXIOM_CRITERIA:
  - Foundational (other principles derive from it)
  - Non-negotiable in the creator's worldview
  - Distinguishes this approach from alternatives
  - Stated explicitly or demonstrated consistently

Format axioms with unique identifiers: [CREATOR_INITIALS]-A[N]

7. Validation Checks

Before finalizing, verify:

  • All principles traceable to source material
  • Pseudocode is syntactically coherent
  • Decision tables have complete coverage
  • Quick reference captures essential operations
  • Diagnostic questions are answerable yes/no
  • Theoretical correspondences are accurate

8. Cross-Medium Adaptation Notes

When source material is medium-specific, include adaptation guidance for:

  • Film → Television (serialization, episode structure)
  • Literature → Interactive (agency, branching)
  • Single creator → Collaborative (writers' room dynamics)
  • Western → Non-Western theoretical traditions

Reference Files

  • references/output-template.md — Full document structure template
  • references/formalization-patterns.md — Examples of converting prose to algorithms
  • references/theoretical-correspondences.md — Mapping table across narrative traditions

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.